Prof. Xiaofeng Yang Profile

Prof. Xiaofeng Yang

at The Winship Cancer Institute of Emory Univ

SPIE Involvement:

Conference Program Committee | Author

Websites:

Personal Website

Publications (195)

Proceedings Article | 4 October 2024 Presentation

Deep learning in medical imaging and its clinical applications

Xiaofeng Yang

Proceedings Volume PC13118, PC131180G (2024) https://doi.org/10.1117/12.3027390

KEYWORDS: Deep learning, Medical imaging, Biomedical applications, Medicine, Image segmentation, Image registration, Diseases and disorders, Clinical research, Cancer detection, X-rays

Read Abstract +

Proceedings Article | 6 May 2024 Presentation + Paper

Unsupervised-learning material decomposition for dual-energy CT with image-domain data fidelity

Junbo Peng, Huiqiao Xie, Chih-Wei Chang, Justin Roper, Richard L. Qiu, Tonghe Wang, Xiangyang Tang, Xiaofeng Yang

Proceedings Volume 12925, 1292513 (2024) https://doi.org/10.1117/12.3006936

KEYWORDS: Signal to noise ratio, Computed tomography, Matrices, Tissues, Bone, Biomedical applications, Education and training, Clinical practice, Machine learning, Interference (communication)

Read Abstract +

Proceedings Article | 3 April 2024 Poster + Paper

Polyp-SAM: transfer SAM for polyp segmentation

Yuheng Li, Mingzhe Hu, Xiaofeng Yang

Proceedings Volume 12927, 1292735 (2024) https://doi.org/10.1117/12.3006809

KEYWORDS: Image segmentation, Polyps, Visual process modeling, Performance modeling, Medical imaging, Education and training, Error control coding, Data modeling, Video, Image resolution

Read Abstract +

Proceedings Article | 3 April 2024 Poster + Paper

Explainable AI for lung nodule detection and classification in CT images

Chih-Wei Chang, Qilong Zhao, Liang Zhao, Xiaofeng Yang

Proceedings Volume 12927, 129272U (2024) https://doi.org/10.1117/12.3008472

KEYWORDS: Lung, Computed tomography, Lung cancer, Visualization, Education and training, Artificial intelligence, Cancer, Magnesium, Machine learning, Visual process modeling

Read Abstract +

Lung cancer is the second most prevalent and deadliest cancer in the United States, primarily due to its elusive early symptoms that hinder timely diagnosis. Lung nodules, minute anomalous areas, hold potential significance in lung cancer occurrence. Swift identification of these nodules can significantly enhance patient survival rates. Thoracic thin-sliced Computed Tomography (CT) scanning has emerged as a widely adopted approach for radiologists' diagnosing and prognosticating lung abnormalities. However, human factors can be prone to errors stemming from the multifarious causes underlying nodule formation, including factors like pollutants and infections. The domain of deep learning algorithms has recently showcased remarkable prowess in classifying and segmenting medical images. This study is geared towards the creation of a comprehensive framework that seamlessly integrates explainable AI techniques to achieve precise pulmonary nodule detection for computer-aided detection and diagnosis (CAD) systems. The framework's execution is underpinned by an explanation supervision approach, employing radiologists' nodule contours as guiding signals to imbue the model with an understanding of nodule morphologies. The nodule detection is achieved by augmentation of the model's learning capabilities, particularly on smaller datasets. Furthermore, two imputation techniques are deployed to refine the nodule region annotations, thereby attenuating noise inherent in human annotations. These techniques empower the model with steadfast attributions that align with human expectations. Our approach consistently elevates ResNet18's classification performance and explanation quality regarding accuracy and specificity by 22% and 23% using training datasets with 100 samples. For small dataset learning using 50 samples, the proposed framework still outperforms ResNet18 by 16% regarding accuracy and specificity. This framework seamlessly integrates a robust explanation supervision technique, guaranteeing nodule classification and morphology assessment accuracy. Reducing the burden on radiologists allows them to focus on diagnosing and prognosticating potentially cancerous pulmonary nodules at an early stage, consequently augmenting survival rates in lung cancer.

Proceedings Article | 3 April 2024 Presentation + Paper

David vs. Goliath: large foundation models are not outperforming small models in multi-view mammogram breast cancer prediction

Xuxin Chen, Mingzhe Hu, Ke Zhang, Neman Abdoli, Youkabed Sadri, Patrik Gilley, Omkar Saiswaroop Varma Chekuri, Farid Omoumi, Yuchen Qiu, Bin Zheng, Xiaofeng Yang

Proceedings Volume 12927, 129270X (2024) https://doi.org/10.1117/12.3007054

KEYWORDS: Mammography, Transformers, Breast cancer, Medical image processing, Deep learning, Computer aided detection

Read Abstract +

Proceedings Article | 3 April 2024 Poster + Paper

MRI-based prostate cancer detection using cross-shaped windows transformer

Yuheng Li, Jacob Wynne, Jing Wang, Richard L. Qiu, Justin Roper, Shaoyan Pan, Ashesh Jani, Tian Liu, Pretesh Patel, Hui Mao, Xiaofeng Yang

Proceedings Volume 12927, 129271T (2024) https://doi.org/10.1117/12.3006812

KEYWORDS: Transformers, Cancer detection, Windows, Prostate cancer, Prostate, Magnetic resonance imaging, Education and training, Principal component analysis, Object detection, Deep learning

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Synthetic CT generation from MRI using 3D diffusion model

Shaoyan Pan, Elham Abouei, Jacob Wynne, Tonghe Wang, Richard L. Qiu, Yuheng Li, Chih-Wei Chang, Junbo Peng, Shihan Qiu, Justin Roper, Pretesh Patel, David Yu, Hui Mao, Xiaofeng Yang

Proceedings Volume 12926, 129262L (2024) https://doi.org/10.1117/12.3006578

KEYWORDS: Computed tomography, Magnetic resonance imaging, Diffusion, 3D modeling, Denoising, Brain, Prostate, Education and training, Radiotherapy, Lithium

Read Abstract +

Proceedings Article | 2 April 2024 Presentation + Paper

Mobile-friendly skin lesion detection using an attention-driven lightweight model

Mingzhe Hu, Xiaofeng Yang

Proceedings Volume 12931, 129310T (2024) https://doi.org/10.1117/12.3006822

KEYWORDS: Skin, Performance modeling, Tumor growth modeling, Tunable filters, Machine learning, Statistical modeling, Skin cancer, Education and training, Diagnostics, Cancer detection

Read Abstract +

Proceedings Article | 2 April 2024 Presentation + Paper

Patient-specific 3D volumetric CBCT image reconstruction with single x-ray projection using denoising diffusion probabilistic model

Shaoyan Pan, Shao-Yuan Lo, Chih-Wei Chang, Ellahheh Salari, Tonghe Wang, Justin Roper, Aparna Kesarwala, Xiaofeng Yang

Proceedings Volume 12931, 129310P (2024) https://doi.org/10.1117/12.3006561

KEYWORDS: Cone beam computed tomography, Diffusion, 3D modeling, X-rays, 3D projection, Denoising, Image processing, Education and training, CT reconstruction, Image restoration

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Cardiac MRI segmentation using block-partitioned transformer with global-local information integration

Elham Abouei, Shaoyan Pan, Mingzhe Hu, Aparna Kesarwala, Jun Zhou, Justin Roper, Tian Liu, Xiaofeng Yang

Proceedings Volume 12930, 1293021 (2024) https://doi.org/10.1117/12.3006929

KEYWORDS: Image segmentation, Cardiovascular magnetic resonance imaging, Windows, Transformers, Magnetic resonance imaging, Deep learning, Information fusion, Visualization, Network architectures

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Image-domain material decomposition for dual-energy CT using a conditional diffusion model

Junbo Peng, Chih-Wei Chang, Mingdong Fan, Huiqiao Xie, Justin Roper, Richard L. Qiu, Tonghe Wang, Xiangyang Tang, Xiaofeng Yang

Proceedings Volume 12930, 1293022 (2024) https://doi.org/10.1117/12.3006941

KEYWORDS: Diffusion, Signal to noise ratio, Computed tomography, Tissues, Matrices, Education and training, Bone, Performance modeling, Image processing, Biomedical applications

Read Abstract +

Proceedings Article | 2 April 2024 Paper

Contrast-enhanced dual-energy CT synthesis from single energy CT using diffusion model

Yuan Gao, Huiqiao Xie, Chih-wei Chang, Junbo Peng, Jing Wang, Richard Qiu, Tonghe Wang, Beth Ghavidel, Justin Roper, Jun Zhou, Xiaofeng Yang

Proceedings Volume 12930, 129302B (2024) https://doi.org/10.1117/12.3008507

KEYWORDS: Diffusion, Education and training, Iodine, Scanners, Computed tomography, Tissues, X-ray computed tomography, Radiotherapy, Image processing, Data modeling

Read Abstract +

Proceedings Article | 2 April 2024 Presentation + Paper

MRI data consistency guided conditional diffusion probabilistic model for MR imaging acceleration

Mojtaba Safari, Xiaofeng Yang, Ali Fatemi

Proceedings Volume 12930, 129300R (2024) https://doi.org/10.1117/12.3002863

KEYWORDS: Magnetic resonance imaging, Data modeling, Diffusion, Sampling rates, Tumors, Medical image reconstruction, Image restoration, Education and training, Visualization, Motion models

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Using diffusion model to generate high-resolution MRI

Chih-Wei Chang, Shaoyan Pan, Junbo Peng, Elahheh Salari, Justin Roper, Richard Qiu, Yuan Gao, Tian Liu, Hui-Kuo Shu, Hui Mao, Xiaofeng Yang

Proceedings Volume 12930, 129301S (2024) https://doi.org/10.1117/12.3006586

KEYWORDS: Magnetic resonance imaging, Diffusion, Lawrencium, Image processing, Deep learning, Brain, Image quality, Denoising, Data modeling, Neuroimaging

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Dose-weighted proton linear energy transfer map generation using a deep learning framework

Yuan Gao, Chih-Wei Chang, Shaoyan Pan, Junbo Peng, Chaoqiong Ma, Pretesh Patel, Justin Roper, Jun Zhou, Xiaofeng Yang

Proceedings Volume 12930, 1293023 (2024) https://doi.org/10.1117/12.3006962

KEYWORDS: Proton therapy, Deep learning, Education and training, Monte Carlo methods, Gallium nitride, Tissues, Energy transfer, Radiotherapy, Prostate cancer, Performance modeling

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Full-dose PET synthesis from low-dose PET using 2D high efficiency denoising diffusion probabilistic model

Shaoyan Pan, Elham Abouei, Junbo Peng, Joshua Qian, Jacob Wynne, Tonghe Wang, Chih-Wei Chang, Justin Roper, Jonathon Nye, Hui Mao, Xiaofeng Yang

Proceedings Volume 12930, 129301Q (2024) https://doi.org/10.1117/12.3006565

KEYWORDS: Positron emission tomography, Diffusion, Denoising, Computed tomography, Medical imaging, 3D modeling, Image segmentation, Deep learning, Magnetic resonance imaging, Machine learning

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

MLP-UNEXT for brain metastasis detection and segmentation in multiparametric MRI

Yuheng Li, Chih-Wei Chang, Xiaofeng Yang

Proceedings Volume 12930, 129301W (2024) https://doi.org/10.1117/12.3006802

KEYWORDS: Brain, Transformers, Cancer detection, Education and training, Tumors, Magnetic resonance imaging, Image segmentation, Convolution, Machine learning, Design

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Information maximized U-Nets for vestibular schwannoma segmentation using MRI with missing modality

Mojtaba Safari, Xiaofeng Yang, Ali Fatemi

Proceedings Volume 12930, 129301H (2024) https://doi.org/10.1117/12.3000647

KEYWORDS: Education and training, Magnetic resonance imaging, Cochlea, Tumors, Image segmentation, Data modeling, Deep learning, Cancer, Performance modeling, Tumor growth modeling

Read Abstract +

Proceedings Article | 1 April 2024 Poster + Paper

Diffusion model-based single-scan dual-energy cone-beam CT using primary beam splitting

Junbo Peng, Chih-Wei Chang, Richard L. Qiu, Justin Roper, Tonghe Wang, Pretesh Patel, David Yu, Xiangyang Tang, Xiaofeng Yang

Proceedings Volume 12925, 129253A (2024) https://doi.org/10.1117/12.3005046

KEYWORDS: Data modeling, Diffusion, Cone beam computed tomography, Beam splitters, Tunable filters, Data acquisition, X-rays, X-ray computed tomography, Radiotherapy, Optical filters

Read Abstract +

Proceedings Article | 1 April 2024 Poster + Paper

Iodine map synthesis from non-contrast CT using diffusion model

Yuan Gao, Huiqiao Xie, Chih-Wei Chang, Junbo Peng, Richard Qiu, Tonghe Wang, Justin Roper, Beth Ghavidel, Jun Zhou, Xiaofeng Yang

Proceedings Volume 12925, 129254P (2024) https://doi.org/10.1117/12.3006952

KEYWORDS: Iodine, Diffusion, Computed tomography, Education and training, Tissues, Visual process modeling, Denoising, Deep learning, Data modeling, Systems modeling

Read Abstract +

Proceedings Article | 1 April 2024 Poster + Paper

Metal artifact reduction in CT using unsupervised sinogram manifold learning

Junbo Peng, Chih-Wei Chang, Huiqiao Xie, Mingdong Fan, Tonghe Wang, Justin Roper, Richard L. Qiu, Xiangyang Tang, Xiaofeng Yang

Proceedings Volume 12925, 129252G (2024) https://doi.org/10.1117/12.3006947

KEYWORDS: Metals, Computed tomography, Data acquisition, Image restoration, Machine learning, CT reconstruction, Data modeling, X-ray computed tomography, Matrices, Photons

Read Abstract +

Proceedings Article | 1 April 2024 Presentation + Paper

BreastSAM: adapting the segmentation anything model for breast tumor segmentation in ultrasound imaging

Mingzhe Hu, Yuheng Li, Xiaofeng Yang

Proceedings Volume 12932, 129320V (2024) https://doi.org/10.1117/12.3006773

KEYWORDS: Tumors, Image segmentation, Breast, Performance modeling, Tumor growth modeling, Ultrasonography, Medical imaging, Breast cancer, Visual process modeling, Data modeling

Read Abstract +

Proceedings Article | 29 March 2024 Presentation + Paper

SkinSAM: adapting the segmentation anything model for skin cancer segmentation

Mingzhe Hu, Yuheng Li, Xiaofeng Yang

Proceedings Volume 12929, 129290U (2024) https://doi.org/10.1117/12.3006837

KEYWORDS: Image segmentation, Skin cancer, Tumor growth modeling, Performance modeling, Visual process modeling, Skin, Machine learning, Education and training, Medical imaging, Cancer

Read Abstract +

Proceedings Article | 29 March 2024 Presentation + Paper

GhostMorph: a computationally efficient model for deformable inter-subject registration

Mingzhe Hu, Shaoyan Pan, Xiaofeng Yang

Proceedings Volume 12928, 129280W (2024) https://doi.org/10.1117/12.3006851

KEYWORDS: Image registration, Deformation, Medical imaging, Convolution, Performance modeling, Image processing, Anatomy, 3D modeling, Liver, Tumors

Read Abstract +

Proceedings Article | 29 March 2024 Poster + Paper

Surface-based volumetric image reconstruction for image-guided procedures using a data-driven framework

Chih-Wei Chang, Shaoyan Pan, Zhen Tian, Tonghe Wang, Marian Axente, Joseph Shelton, Tian Liu, Justin Roper, Xiaofeng Yang

Proceedings Volume 12928, 1292822 (2024) https://doi.org/10.1117/12.3006510

KEYWORDS: Radiotherapy, Computed tomography, 3D image processing, Image restoration, Anatomy, 3D modeling, 3D image reconstruction, Deep learning, Image quality, Machine learning

Read Abstract +

SPIE Journal Paper | 16 February 2024

MGMT promoter methylation prediction based on multiparametric MRI via vision graph neural network

Mingzhe Hu, Kailin Yang, Jing Wang, Richard L. J. Qiu, Justin Roper, Shannon Kahn, Hui-Kuo Shu, Xiaofeng Yang

JMI, Vol. 11, Issue 01, 014503, (February 2024) https://doi.org/10.1117/12.10.1117/1.JMI.11.1.014503

KEYWORDS: Magnetic resonance imaging, Education and training, Tumors, Performance modeling, RGB color model, 3D modeling, Machine learning, Medical imaging, Image segmentation, Visualization

Read Abstract +

Proceedings Article | 10 April 2023 Poster + Paper

Evaluating imaging reproducibility of portable ultrasound devices with histogram analysis: a phantom study

Jing Wang, Boran Zhou, Deborah Marshall, Mylin Torres, Xiaofeng Yang, Tian Liu

Proceedings Volume 12470, 124700X (2023) https://doi.org/10.1117/12.2654085

KEYWORDS: Histograms, Reproducibility, Portability, Transducers, Head, Ultrasound transducers, Ultrasonography, Scanners, Radiomics, Feature extraction

Read Abstract +

Proceedings Article | 10 April 2023 Poster + Paper

Ultrasound breast tumor detection based on vision graph neural network

Mingzhe Hu, Jing Wang, Chih-wei Chang, Tian Liu, Xiaofeng Yang

Proceedings Volume 12470, 124700W (2023) https://doi.org/10.1117/12.2654077

KEYWORDS: Breast, Tumors, Ultrasonography, Data modeling, Cancer detection, Neural networks, Breast cancer, Tumor growth modeling, Deep learning, Medical imaging

Read Abstract +

Proceedings Article | 10 April 2023 Poster + Paper

Radiomic feature robustness evaluations in ultrasound imaging

Jing Wang, Boran Zhou, Xiaofeng Yang, Tian Liu

Proceedings Volume 12470, 124700V (2023) https://doi.org/10.1117/12.2654072

KEYWORDS: Radiomics, Cooccurrence matrices, Muscles, Breast, Ultrasonography, Feature extraction, Visualization, Visual analytics, Visibility, Radiation oncology

Read Abstract +

Proceedings Article | 10 April 2023 Poster + Paper

Ultrasound-based dominant intraprostatic lesion classification with swin transformer

Yuheng Li, Boran Zhou, Jing Wang, Shaoyan Pan, Ashesh Jani, Tian Liu, Pretsh Patel, Xiaofeng Yang

Proceedings Volume 12470, 124700T (2023) https://doi.org/10.1117/12.2653634

KEYWORDS: Transformers, Image classification, Prostate, Deep learning, Ultrasonography, Modeling, Medical imaging

Read Abstract +

Proceedings Article | 10 April 2023 Poster + Paper

Quantification of radiation damage for proton craniospinal irradiation using magnetic resonance imaging

Chih-Wei Chang, Matt Goette, Nadja Kadom, Yinan Wang, Jacob Wynne, Tonghe Wang, Tian Liu, Natia Esiashvili, Jun Zhou, Bree Eaton, Xiaofeng Yang

Proceedings Volume 12468, 124681A (2023) https://doi.org/10.1117/12.2653665

KEYWORDS: Radiotherapy, Magnetic resonance imaging, Bone, Proton therapy, Computed tomography, Spine, Cancer, Oncology, In vivo imaging, Physics

Read Abstract +

Proceedings Article | 10 April 2023 Presentation + Paper

Multi-structure segmentation on cardiac MRI using multilayer perceptron mixer network

Shaoyan Pan, Chaoqiong Ma, Chih-Wei Chang, Jacob Wynne, Justin Roper, Tian Liu, Xiaofeng Yang

Proceedings Volume 12468, 124680D (2023) https://doi.org/10.1117/12.2653944

KEYWORDS: Image segmentation, Magnetic resonance imaging, Education and training, Transformers, Medical imaging, Cardiovascular magnetic resonance imaging, Image processing, Semantics, Visualization, Myocardium

Read Abstract +

In this work, we propose MLP-Vnet, a token-based U-shaped multilayer linear perceptron-mixer (MLP-Mixer) network, incorporating a convolutional neural network for multi-structure segmentation on cardiac magnetic resonance imaging (MRI). The proposed MLP-Vnet is composed of an encoder and decoder. Taking an MRI scan as input, the semantic features are extracted by the encoder with one early convolutional block followed by four consecutive MLP-Mixer blocks. Then, the extracted features are passed to the decoder with mirrored architecture of the encoder to form a N-classes segmentation map. We evaluated our proposed network on the Automated Cardiac Diagnosis Challenge (ACDC) dataset. The performance of the network was assessed in terms of the volume- and surface-based similarities between the predicted contours and the manually delineated ground-truth contours, and computational efficiency. The volume-based similarities were measured by the Dice score coefficient (DSC), sensitivity, and precision. The surface-based similarities were measured by Hausdorff distance (HD), mean surface distance (MSD), and residual mean square distance (RMSD). The performance of the MLP-Vnet was compared with four state-of-the-art networks. The proposed network demonstrated statistically superior DSC and superior sensitivity or precision on all the three structures to the competing networks (p-value < 0.05): average DSC of 0.904, sensitivity of 0.908 and precision of 0.902 among all structures. The best surfaceased similarities were also demonstrated by the MLP-Vnet: average HD = 3.266 mm, MSD = 0.684 mm, and RMSD = 1.487 mm. Compared to the competing networks, the MLP-Vnet showed the shortest training time (7.32 hours) inference time per patient (3.12 seconds). The proposed MLP-Vnet is capable of using reasonable number of trainable parameters to solve the segmentation task on the cardiac MRI scans more quickly and accurately than the state-ofthe- art networks. This novel network could be a promising tool for accurate and efficient cardiac MRI segmentation to assist cardiac diagnosis and treatment decision making.

Proceedings Article | 10 April 2023 Poster + Paper

End-to-end brain tumor detection using a graph-feature-based classifier

Mingzhe Hu, Jing Wang, Chih-Wei Chang, Tian Liu, Xiaofeng Yang

Proceedings Volume 12468, 124681C (2023) https://doi.org/10.1117/12.2654020

KEYWORDS: Brain, Tumors, Magnetic resonance imaging, Deep learning, Neuroimaging, Cancer detection, Neural networks, Medicine, Medical imaging, Physics

Read Abstract +

Proceedings Article | 10 April 2023 Presentation + Paper

Multi-parametric MRI radiomics analysis with ensemble learning for prostate lesion classification

Yuheng Li, Jing Wang, Chih-Wei Chang, Pretsh Patel, Ashesh Jani, Hui Mao, Tian Liu, Xiaofeng Yang

Proceedings Volume 12468, 124680B (2023) https://doi.org/10.1117/12.2653637

KEYWORDS: Magnetic resonance imaging, Radiomics, Machine learning, Prostate, Feature selection, Feature extraction, Random forests

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

In vivo proton range validation using pseudo proton radiography

Chih-Wei Chang, Shuang Zhou, Yuan Gao, Liyong Lin, Tian Liu, Jeffrey Bradley, Tiezhi Zhang, Jun Zhou, Xiaofeng Yang

Proceedings Volume 12463, 124632K (2023) https://doi.org/10.1117/12.2653669

KEYWORDS: Proton radiography, Computed tomography, Physics, In vivo imaging, Machine learning, Proton therapy, Biology, Monte Carlo methods, Medicine, Material characterization

Read Abstract +

The current clinical practice for Monte Carlo (MC) treatment planning reserves a 3.5% margin to compensate for proton range uncertainty. Additionally, patient positional uncertainty is typically 3-5 mm for proton craniospinal irradiation (CSI) treatment planning. These two uncertainties compromise the sparing of spine vertebrae in proton CSI patients. Computer tomography (CT) material characterization contributes approximately 2.5% proton range uncertainty. Multiple CT-tomaterial conversion methods have been investigated using dual-energy CT or magnetic resonance imaging to improve the range uncertainty. However, there is a lack of experimental data to validate the credibility of those material characterization models. We aim to develop an in vivo proton range method using pseudo proton radiography to validate imaging-based material characterization models consistently. Proton radiography techniques, such as proton water equivalent thickness (WET) and dose maps, were used to evaluate the in vivo proton range accuracy. Anteroposterior proton beams were penetrated through an anthropomorphic phantom. Then the exit doses were measured from proton radiography imaging. The validation experiment applied a newly designed multi-layer strip ionization chamber (MLSIC) for the first time to perform four-dimensional (4D) measurement for depth doses from 625 proton spots in two minutes. The depth doses of each spot were post-processed into WET imaging. A MatriXX PT was applied for 2D measurement from 19x19 cm2 proton fields. We compared the performance of the empirical DECT model and physics-informed machine learning (PIML) models for material conversion. The results indicated that the PIML-based material characteristic method generated more accurate WET and dose imaging using DECT compared to conventional machine learning and empirical material inference methods. The proposed in vivo proton range validation method can be used to quantify the credibility of DECT-based material conversion models for proton range enhancement. The method can potentially provide in-room patient anatomy changes to accomplish online adaption for modification. This technique will significantly benefit proton flash therapy, which demands high accuracy.

Proceedings Article | 7 April 2023 Poster + Paper

Sparse constraint-based iterative estimation of effective atomic number and electron density for dual energy CT

Qian Wang, Huiqiao Xie, Tonghe Wang, Justin Roper, Xiangyang Tang, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12463, 124633G (2023) https://doi.org/10.1117/12.2654232

KEYWORDS: X-ray computed tomography, Tissues, Dual energy imaging, Bone, X-rays, Proton therapy, Mathematical optimization, Computed tomography, Compton scattering, Attenuation

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Multi-constrained multi-material decomposition for dual energy CBCT

Qian Wang, Huiqiao Xie, Tonghe Wang, Justin Roper, Xiangyang Tang, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12463, 1246317 (2023) https://doi.org/10.1117/12.2654354

KEYWORDS: Cone beam computed tomography, Computed tomography, Image quality, Chemical composition, Tissues, Radiotherapy, Bone, Solids, Matrices, Dual energy imaging

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Mass density estimation based on single-energy computed tomography via deep learning

Yuan Gao, Chih-Wei Chang, Shaoyan Pan, Yang Lei, Tonghe Wang, Jun Zhou, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12463, 124632X (2023) https://doi.org/10.1117/12.2654016

KEYWORDS: Artificial neural networks, Tissues, Proton therapy, Computed tomography, Performance modeling, Education and training, Deep learning, Data modeling, Lung, Calibration

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Physics-informed multi-modal imaging-based material characterization for proton therapy

Chih-Wei Chang, Raanan Marants, Yuan Gao, Matthew Goette, Jessica Scholey, Jeffrey Bradley, Tian Liu, Jun Zhou, Atchar Sudhyadhom, Xiaofeng Yang

Proceedings Volume 12463, 124632J (2023) https://doi.org/10.1117/12.2653667

KEYWORDS: Computed tomography, Magnetic resonance imaging, Proton therapy, Physics, Data modeling, Education and training, Biology, Tissues, Medicine, Machine learning

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Quantitative ultrasound radiomics for monitoring radiation-induced toxicity following breast radiotherapy

Jing Wang, Boran Zhou, Mylin Torres, Xiaofeng Yang, Tian Liu

Proceedings Volume 12465, 124650L (2023) https://doi.org/10.1117/12.2654081

KEYWORDS: Breast, Radiomics, Toxicity, Ultrasonography, Skin, Radiotherapy, Breast cancer, Feature extraction, Tissues, Natural surfaces

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Prostate Gleason score prediction via MRI using capsule network

Yuheng Li, Jing Wang, Mingzhe Hu, Pretesh Patel, Hui Mao, Tian Liu, Xiaofeng Yang

Proceedings Volume 12465, 1246523 (2023) https://doi.org/10.1117/12.2653621

KEYWORDS: Magnetic resonance imaging, Education and training, Prostate, Convolution, 3D modeling, Cancer, Prostate cancer, Deep learning

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

A vision-GNN framework for retinopathy classification using optical coherence tomography

Mingzhe Hu, Jing Wang, Jacob Wynne, Tian Liu, Xiaofeng Yang

Proceedings Volume 12465, 124650Z (2023) https://doi.org/10.1117/12.2653615

KEYWORDS: Optical coherence tomography, Deep learning, Medical imaging, Education and training, Image classification, Data modeling, Retina, Feature extraction, Convolutional neural networks

Read Abstract +

Proceedings Article | 3 April 2023 Poster + Paper

Multi-organ CT segmentation using shifted-window multilayer perceptron mixer

Shaoyan Pan, Jacob Wynne, Mingzhe Hu, Tonghe Wang, Justin Roper, Pretesh Patel, Tian Liu, Xiaofeng Yang

Proceedings Volume 12466, 124661U (2023) https://doi.org/10.1117/12.2653956

KEYWORDS: Image segmentation, Windows, Computed tomography, Kidney, Head, Radiotherapy, Abdomen, Rectum, Medical imaging, Gallbladder

Read Abstract +

Proceedings Article | 3 April 2023 Poster + Paper

Deformable image registration of chest CT using deep cycle network

Luke Matkovic, Yang Lei, Yabo Fu, Tonghe Wang, Aparna Kesarwala, Marian Axente, Justin Roper, Kristin Higgins, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12466, 124661W (2023) https://doi.org/10.1117/12.2654112

KEYWORDS: Image registration, Deformation, Lung, Image fusion, Image quality, Computed tomography, Chest, Tumors, Transformers

Read Abstract +

Proceedings Article | 3 April 2023 Poster + Paper

Deep learning-based multi-organ CT segmentation with adversarial data augmentation

Shaoyan Pan, Shao-Yuan Lo, Min Huang, Chaoqiong Ma, Jacob Wynne, Tonghe Wang, Tian Liu, Xiaofeng Yang

Proceedings Volume 12464, 124642D (2023) https://doi.org/10.1117/12.2653970

KEYWORDS: Image segmentation, Kidney, Liver, Stomach, Gallbladder, Education and training, Deep learning, Aorta, Adversarial training, Computed tomography

Read Abstract +

In this work, we propose an adversarial attack-based data augmentation method to improve the deep-learning-based segmentation algorithm for the delineation of Organs-At-Risk (OAR) in abdominal Computed Tomography (CT) to facilitate radiation therapy. We introduce Adversarial Feature Attack for Medical Image (AFA-MI) augmentation, which forces the segmentation network to learn out-of-distribution statistics and improve generalization and robustness to noises. AFA-MI augmentation consists of three steps: 1) generate adversarial noises by Fast Gradient Sign Method (FGSM) on the intermediate features of the segmentation network’s encoder; 2) inject the generated adversarial noises into the network, intentionally compromising performance; 3) optimize the network with both clean and adversarial features. The effectiveness of the AFA-MI augmentation was validated on nnUnet. Experiments are conducted segmenting the heart, left and right kidney, liver, left and right lung, spinal cord, and stomach in an institutional dataset collected from 60 patients. We firstly evaluate the AFA-MI augmentation using nnUnet and Token-based Transformer Vnet (TT-Vnet) on the test data from a public abdominal dataset and an institutional dataset. In addition, we validate how AFA-MI affects the networks’ robustness to the noisy data by evaluating the networks with added Gaussian noises of varying magnitudes to the institutional dataset. Network performance is quantitatively evaluated using Dice Similarity Coefficient (DSC) for volume-based accuracy. Also, Hausdorff Distance (HD) is applied for surface-based accuracy. On the public dataset, nnUnet with AFA-MI achieves DSC = 0.85 and HD = 6.16 millimeters (mm); and TT-Vnet achieves DSC = 0.86 and HD = 5.62 mm. On the robustness experiment with the institutional data, AFA-MI is observed to improve the segmentation DSC score ranging from 0.055 to 0.010 across all organs relative to clean inputs. AFA-MI augmentation further improves all contour accuracies up to 0.527 as measured by the DSC score when tested on images with Gaussian noises. AFA-MI augmentation is therefore demonstrated to improve segmentation performance and robustness in CT multi-organ segmentation.

Proceedings Article | 4 April 2022 Poster + Paper

Using a neural network to enhance dual-energy computed tomography parametric mapping for proton therapy

Chih-Wei Chang, Yuan Gao, Qian Wang, Yang Lei, Tonghe Wang, Jun Zhou, Liyong Lin, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12031, 120312H (2022) https://doi.org/10.1117/12.2611891

KEYWORDS: Tissues, Lung, Data modeling, Brain mapping, Bone, Computed tomography, Neural networks, Brain, Associative arrays, Imaging systems

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

CT guided material decomposition of spectral CBCT

Qian Wang, Huiqiao Xie, Tonghe Wang, Justin Roper, Xiangyang Tang, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12031, 1203128 (2022) https://doi.org/10.1117/12.2611162

KEYWORDS: Image quality, Computed tomography, Radiotherapy, Optimization (mathematics), Tissues, Image processing, Cancer, Bone, Switching

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

Deformable histopathology-MRI image registration using deep learning

Yabo Fu, Yang Lei, David Schuster, Sagar Patel, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12039, 1203915 (2022) https://doi.org/10.1117/12.2611895

KEYWORDS: Magnetic resonance imaging, Image registration, Prostate, Image fusion, Tissues, Image segmentation, Cancer, Image processing, Motion models, Diffusion weighted imaging

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Liver motion tracking in ultrasound images using attention guided mask R-CNN with long-short-term-memory network

Yupei Zhang, Xianjin Dai, Zhen Tian, Yang Lei, Yue Chen, Pretesh Patel, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12038, 120380O (2022) https://doi.org/10.1117/12.2613013

KEYWORDS: Liver, Ultrasonography, Radiotherapy, Video, Temporal resolution, Network architectures, Cancer, Real time imaging, Radiation oncology, Liver cancer

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

CBCT lung multi-OAR segmentation via hierarchical network

Richard L. Qiu, Yang Lei, Joseph Shelton, Kristin Higgins, Jeffrey Bradley, Tian Liu, Aparna Kesarwala, Xiaofeng Yang

Proceedings Volume 12036, 120361L (2022) https://doi.org/10.1117/12.2612862

KEYWORDS: Lung, Image segmentation, Sensors, Spinal cord, Esophagus, Image quality, Heart, Distance measurement, Chlorine, Cancer

Read Abstract +

Lung SBRT patients could have daily setup variations that lead to suboptimal treatment delivery. While currently a cone- beam CT (CBCT) is captured prior to each fraction for patient alignment, no organ contours or dosimetric calculations are routinely done to verify radiation therapy (RT) treatment delivery quality. Organ contours on CBCT are challenging because of the inferior image quality and low image contrast of CBCT. Besides, manual contouring is labor-intensive that prohibits clinical implementation. Therefore, if organ contours could be obtained automatically on fractional CBCT with limited human interventions, it would pave the way to obtain dosimetry for coverage evaluation and toxicity assessment. In this study, we developed a deep learning-based method for automated segmentation of multiple organs on CBCT images which simultaneously performs detection, classification, and segmentation of multi-organ. Our proposed hierarchical network method consists of four subnetworks: feature extractor, detector, hierarchical block, and mask module. The feature extractor subnetwork is used to extract informative features from CBCT. The detector subnetwork is used to locate the volume-of-interest (VOIs) of multiple organs. The hierarchical block network is used to enhance the feature contrast around organ boundaries and improve the organ classification. The mask module subnetwork then segments organ from the refined feature map within the VOIs. We conducted a five-fold cross-validation on 30 CBCTs. Five organs (esophagus, heart, spinal cord, left lung, and right lung) were segmented and compared with manual contours using several evaluation metrics. The Dice similarity coefficient (DSC) is 0.68, 0.87, 0.80, 0.91 and 0.93 for esophagus, heart, spinal cord, left lung, and right lung, respectively. These results demonstrate the feasibility and efficacy of our proposed hierarchical network method for CBCT lung segmentation, which could be used for fractional delivery dose evaluations in the future.

Proceedings Article | 4 April 2022 Poster + Paper

Male pelvic multi-organ segmentation using V-transformer network

Shaoyan Pan, Yang Lei, Tonghe Wang, Jacob Wynne, Justin Roper, Ashesh Jani, Pretesh Patel, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12036, 120362A (2022) https://doi.org/10.1117/12.2628064

KEYWORDS: Transformers, Computer programming, Head, Image segmentation, Prostate, Computed tomography, Rectum, Bladder, Radiotherapy, Data modeling

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

Deep learning-based longitudinal CT registration for anatomy variation assessment during radiotherapy

Yabo Fu, Yang Lei, Zhen Tian, Tonghe Wang, Xianjin Dai, Jun Zhou, Mark McDonald, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12033, 1203321 (2022) https://doi.org/10.1117/12.2611901

KEYWORDS: Computed tomography, Image registration, Radiotherapy, Cancer, Oncology, Image processing, Tumors, Optimization (mathematics), Transformers, Target acquisition

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Deep-learning-based extraprostatic nodal lesion segmentation on 18F-fluciclovine PET

Tonghe Wang, Lei Yang, Eduard Schreibmann, Justin Roper, David Schuster, Jeffrey Bradley, Tian Liu, Ashesh Jani, Xiaofeng Yang

Proceedings Volume 12036, 120360P (2022) https://doi.org/10.1117/12.2611759

KEYWORDS: Positron emission tomography, Image segmentation, Radiotherapy, Prostate cancer, Distance measurement, Chlorine, Cancer, Binary data, Oncology, Convolutional neural networks

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

CVT-Vnet: a convolutional-transformer model for head and neck multi-organ segmentation

Shaoyan Pan, Zhen Tian, Yang Lei, Tonghe Wang, Jun Zhou, Mark McDonald, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12033, 120333L (2022) https://doi.org/10.1117/12.2611540

KEYWORDS: Head, Image segmentation, Neck, Optic nerve, Transformers, Computer programming, Visual process modeling, Radiotherapy, Computed tomography, Cancer

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

Neurovascular bundles segmentation on MRI via hierarchical object activation network

Yang Lei, Tonghe Wang, Justin Roper, Sibo Tian, Pretesh Patel, Jeffrey Bradley, Ashesh Jani, Tian Liu, Xiaofeng Yang

Proceedings Volume 12033, 120332O (2022) https://doi.org/10.1117/12.2611825

KEYWORDS: Magnetic resonance imaging, Image segmentation, Radiotherapy, Prostate cancer, Distance measurement, Head, Chlorine, Binary data, Tissues, Prostate

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

CT-based volumetric strain imaging via a deep learning registration framework

Yabo Fu, Yang Lei, Tonghe Wang, Justin Roper, Marian Axente, Jeffrey Bradley, Tian Liu, Kristin Higgins, Xiaofeng Yang

Proceedings Volume 12036, 1203620 (2022) https://doi.org/10.1117/12.2611905

KEYWORDS: Lung, Computed tomography, Tumors, Image registration, Tissues, Positron emission tomography, Radiotherapy, Image segmentation, Image enhancement, Lung cancer

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

Deep-learning-based markerless tumor localization using 2D KV/MV image

Yang Lei, Zhen Tian, Richard Qiu, Tonghe Wang, Justin Roper, Kristin Higgins, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12032, 120323J (2022) https://doi.org/10.1117/12.2611823

KEYWORDS: Tumors, 3D acquisition, Lung, Computed tomography, 3D image processing, Feature extraction, Cancer, 4D CT imaging, Stereoscopy, Radiotherapy

Read Abstract +

Deep inspiration breath-hold (DIBH) is a motion management technique that is commonly used in lung radiotherapy (RT) for patients with large tumor motion. Cone beam CT (CBCT) scan with DIBH is commonly used for treatment setup, and the acquisition of a CBCT scan (typically ~1 minute) requires multiple DIBHs. If a large shift of treatment couch is needed, a second CBCT scan is often acquired after the shift for verification purpose. However, the more DIBH occurred during treatment setup, the higher probability that patient may become tired and hence less able to reproduce consistent DIBH during treatment delivery, which would degrade the target coverage and deliver more dose to critical organs and normal tissues. To reduce the number of DIBHs required for treatment setup, we propose a deep learning method to locate tumor 3D location from two orthogonal and simultaneously acquired 2D projections (one is kV and the other is MV) for fast verification, which will eliminate the need for the second CBCT scan. Our proposed method, named center-ness matching network, is capable of collecting feature map that represent the probability distribution of tumor, called center-ness map, from 2D projections and re-aligning them to their projections’ angle in the Cartesian coordinate system. The tumor depth information is also collected. The center-ness matching network then re-transforms the 2D center-ness maps to the 3D center-ness map via depth learning. Finally, the 3D location of tumor is estimated from the 3D center-ness map. We conducted a retrospective study on 10 patient cases, who had undergone 4D-CT scans for motion evaluation at CT simulation and received lung RT treatments in our institution. For each 3D CT image set of a breathing phase, we simulated its 2D kV projection at gantry angle 0° and 2D MV projection at 90°. Patient specific 3D CT images of 9 phases and the corresponding 2D projections data were used for training, with the remaining phase used for testing. The target error (TE), which is of the difference in distance between the center-of-mass of ground truth tumor of 3D CT and the predicted tumor 3D location, achieved by our method was 2.6±0.7 mm. These results demonstrated the feasibility and efficacy of our proposed method, which provides a potential solution for fast verification of treatment setup of DIBH lung RT.

Proceedings Article | 4 April 2022 Presentation + Paper

Automatic breast ultrasound tumor segmentation via one-stage hierarchical target activation network

Tonghe Wang, Yang Lei, Marian Axente, Jincao Yao, Jolinta Lin, Jeffrey Bradley, Tian Liu, Dong Xu, Xiaofeng Yang

Proceedings Volume 12038, 120380L (2022) https://doi.org/10.1117/12.2611129

KEYWORDS: Tumors, Image segmentation, Breast, Breast cancer, Ultrasonography, Distance measurement, Computer aided diagnosis and therapy, Cancer, Binary data, Stereoscopy

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

High-resolution MR imaging using self-supervised parallel network

Huiqiao Xie, Yang Lei, Tonghe Wang, Justin Roper, Jeffrey Bradley, Tian Liu, Hui Mao, Xiaofeng Yang

Proceedings Volume 12033, 120332V (2022) https://doi.org/10.1117/12.2611614

KEYWORDS: Magnetic resonance imaging, Image segmentation, Lawrencium, Radiotherapy, Image resolution, Brain, Tumors, Signal to noise ratio, Neuroimaging, Cancer

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Deep learning-based contrast-enhanced MRI using cascade networks with local supervision

Huiqiao Xie, Yang Lei, Tonghe Wang, Marian Axente, Justin Roper, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12036, 1203619 (2022) https://doi.org/10.1117/12.2611622

KEYWORDS: Magnetic resonance imaging, Tumors, Brain, Image contrast enhancement, Retina, Image segmentation, Neuroimaging, Network architectures, Deconvolution, Cancer

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Echocardiographic image segmentation using mutual boosting network

Yang Lei, Yabo Fu, Marian Axente, Justin Roper, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12038, 120380J (2022) https://doi.org/10.1117/12.2611797

KEYWORDS: Image segmentation, Computer programming, Ultrasonography, Retina, Distance measurement, Cancer, Visualization, Single photon emission computed tomography, Positron emission tomography, Magnetic resonance imaging

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Brain multi-parametric MRI tumor subregion segmentation via hierarchical substructural activation network

Yang Lei, Shadab Momin, Zhen Tian, Justin Roper, Jolinta Lin, Shannon Kahn, Hui-Kuo Shu, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12036, 120360Q (2022) https://doi.org/10.1117/12.2611809

KEYWORDS: Tumors, Image segmentation, Brain, Magnetic resonance imaging, Neuroimaging, Brain mapping, Radiotherapy, Distance measurement, Cancer, Tissues

Read Abstract +

Multiparameter magnetic resonance imaging (mp-MRI) commonly used modality for segmentation of glioma and its subregions, whereas RT therapy is a commonly used treatment modality. Current workflow includes manual segmentation of brain tumor sub-regions, which is a very lengthy and laborious process given that different sets of MR images have to be analyzed for an appropriate diagnosis. This work focuses on implementing and testing feasibility of a new deep learning model for an automatic segmentation of brain tumor sub-regions. Our proposed method, named hierarchical substructural activation network, consists of three main parts: a detection and segmentation module, and a hierarchical convolutional block. While the detection module is employed to detect the view-of-interests (VOIs) of brain tumor, which include all tumor sub-structures, the hierarchical convolutional block is used to derive structural activation map (SAM) to boost the classification accuracy between different structures. This is followed by the semantic segmentation of each substructure within the detected VOI by segmentation module. Brain tumor segmentation challenge (BraTS) 2020 dataset was used for evaluating our proposed framework. We performed five-fold cross validation experiments on 100 BraTS datasets. Three substructures, i.e., necrosis and non-enhancing, edema, enhancing tumor (ET), tumor core (TC), were segmented and compared with manual contours using the Dice similarity coefficient (DSC) and mean surface distance (MSD). In terms of segmentation of necrosis and non-enhancing subregions, edema, ET and TC, our method yielded DSC of 0.69±0.24, 0.89±0.09, 0.80±0.14, and 0.88±0.11, respectively, and MSD of 2.01±2.75, 0.63±0.58, 0.98±1.10 and 1.74±1.06 mm, respectively. Preliminary results of this work show promise to both accurately and automatically segment brain tumor subregions by our proposed method, providing motivation for its clinical implementation to improve clinical workflow.

Proceedings Article | 4 April 2022 Poster + Paper

Longitudinal deformable MRI registration via dual-feasible deep learning-based framework

Yang Lei, Yabo Fu, Justin Roper, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12036, 120361O (2022) https://doi.org/10.1117/12.2611826

KEYWORDS: Magnetic resonance imaging, Image registration, Visualization, Neck, Head, Image fusion, Cancer, Transformers, Tissues, Data modeling

Read Abstract +

Magnetic resonance imaging (MRI) is a widely used modality for visualizing patient anatomy due to its non-invasiveness and superior soft tissue contrast. MRI can be used to quantify anatomical changes before and after therapy to assess treatment outcome and efficacy. However, longitudinal tracking depends on the accurate alignment of multiple image sets, which is challenged by rigid and deformable displacements. Deformable image registration is a promising tool to account for these changes and enable accurate longitudinal assessments. In this study, we aim to develop a deep learning-based method for automatic deformable registration to align post-treatment and pre-treatment head and neck (HN) MRIs. Our proposed method, named dual-feasible framework, is implemented by a mutual network that consists of a forward module and a backward module. The two modules alternate in generating a deformation vector field (DVF) for image registration. First the pre-treatment MRI is registered to the post-treatment MRI and then the post-treatment MRI is registered to the pre-treatment MRI, and the process repeats under a mutual enhancing strategy. Dual feasible loss is used to optimize the mutual network. We conducted longitudinal experiments on 4 public patient datasets (40 MRI scans), each with 2 head and neck (HN) MRI sequences (T1-weighted and T2-weighted) across 5 timepoints: one pre-treatment MRI and four posttreatment MRIs. To evaluate the proposed method, the pre-treatment MRIs were used as the target, and we calculated the peak-signal-to-noise ratio (PSNR), structural similarity index (SSIM) and mean absolute error (MAE) between the deformed post-treatment MRI and the pre-treatment MRI. The PSNR, SSIM and MAE are 29.3±0.3 dB, 0.89±0.02 and 52.4±2.7 for the T1-weighted MRI, and are 27.0±0.8 dB, 0.87±0.03 and 97.5±14.1 for the T2-weighted MRI. These results demonstrate the feasibility and efficacy of our proposed method for MRI deformable image registration.

Proceedings Article | 4 April 2022 Presentation + Paper

A deep learning approach to transform two orthogonal X-ray images to volumetric images for image-guided proton therapy

Chih-Wei Chang, Yang Lei, Tonghe Wang, Jun Zhou, Liyong Lin, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12032, 120321S (2022) https://doi.org/10.1117/12.2611893

KEYWORDS: 3D image processing, Computed tomography, 3D acquisition, X-ray computed tomography, Tumors, X-rays, X-ray imaging, 4D CT imaging, Imaging systems, Signal to noise ratio

Read Abstract +

Due to potential patient anatomy variation during the treatment, proton therapy requires image-guidance systems to minimize treatment uncertainty and ensure conformal doses are precisely delivered to tumor target. This study proposes a feature matching network to generate volumetric images through two orthogonal 2D X-ray images to detect target location during the treatment. The method leverages the kV image system of proton treatment machines to simultaneously acquire two orthogonal 2D images to consistently predict 3D real-time patient anatomy without biasing by motion. The proposed feature mapping network includes four components: a n° kV feature extractor, a n°+90° kV feature extractor, a feature re-alignment, and a depth estimation. The two feature extractors are constructed by two independent convolutional neural networks (CNN) to capture the details of 2D image structures. The re-aliment component ensures that the two orthogonal 2D images are aligned in the same coordinate system. The last part is built by a fully convolutional network (FCN) to inversely transform 2D information to volumetric images. 10 patient cases with 4D CT (100 3D CT images) were used to demonstrate the proposed method. Each 4DCT includes 10 respiratory phases, and the 2D orthogonal images are generated by forward projecting the 3D CT from each phase to planes. Leave-phase-out experiments were performed to ensure that each phase amount of the 10 phases will be used for testing once. Among all 10 patients, the mean absolute error, peak signal-to-noise ratio, and structural similarity index are 83.29 ± 2.83 HU, 16.86 ± 0.16 dB, and 0.83 ± 0.01. The results indicate that the feature matching network can successfully reconstruct the 3D tumor location using 2D projections, which can support treatment decision-making. The proposed method potentially can benefit proton FLASH therapy by offering real-time target localization and patient dose verification to ensure treatment quality.

Proceedings Article | 4 April 2022 Poster + Paper

Iterative material decomposition with gradient L0-norm minimization for dual-energy CT

Qian Wang, Huiqiao Xie, Tonghe Wang, Justin Roper, Xiangyang Tang, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12032, 1203220 (2022) https://doi.org/10.1117/12.2611171

KEYWORDS: X-rays, Spatial resolution, Signal attenuation, Optimization (mathematics), X-ray imaging, X-ray computed tomography, Parallel computing, Inverse problems, Computed tomography, Cancer

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Automated CT segmentation for rapid assessment of anatomical variations in head-and-neck radiation therapy

Xianjin Dai, Yang Lei, Tonghe Wang, Zhen Tian, Jun Zhou, Mark McDonald, David Yu, Beth Ghavidel, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12034, 120341E (2022) https://doi.org/10.1117/12.2613060

KEYWORDS: Computed tomography, Radiotherapy, Image segmentation, Cancer, Head, Tumors, Sensors, Oncology, Neck, Data modeling

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

Fast 3D imaging via deep learning for deep inspiration breath-hold lung radiotherapy

Yang Lei, Zhen Tian, Tonghe Wang, Marian Axente, Justin Roper, Kristin Higgins, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12034, 120342N (2022) https://doi.org/10.1117/12.2611813

KEYWORDS: 3D image processing, Computed tomography, Tumors, Lung, Stereoscopy, 4D CT imaging, Radiotherapy, Signal to noise ratio, Feature extraction, Cancer

Read Abstract +

Deep inspiration breath hold (DIBH) is a common method for managing respiratory motion in lung radiotherapy (RT) and has shown benefit for significant reduction of cardiovascular and pulmonary toxicity. Cone beam CT (CBCT) is used to capture 3D images of the patient in position for daily treatment, and multiple CBCT scans may be needed to fine tune the patient setup. Furthermore, multiple breath holds are often needed for a single CBCT acquisition (typically ~1 min). Because of differences in the tumor and healthy tissue positions between consecutive DIBHs, the inconsistent anatomy in the 2D projection images degrades the quality of the reconstructed CBCT. Moreover, multiple breath holds during the initial setup will increase the probability that a patient will become tired and less able to reproduce consistent DIBH during treatment delivery when it matters most. To address this important clinical issue, a proof-of-concept study was designed using a novel deep learning-based method to derive a 3D volumetric image from two perpendicular 2D projection images (kV-MV pair), thereby reducing the number of DIBHs needed for imaging. The proposed method – implemented with a feature matching network – derives feature maps from the 2D projections and re-aligns them to their projection angle in a Cartesian coordinate system. The 2D feature maps are rendered in 3D space via depth learning by the feature matching network. Finally, the 3D volume is derived from the 3D feature map. We conducted a simulation study using 10 patient cases (110 CT images). Each patient had a 4D CT scan that was split into 10 phase bins for motion evaluation and a DIBH CT scan during simulation and later received DIBH lung RT at our institution. Ray tracing through each phase-binned CT was used to simulate a 2D kV projection at gantry angle 0° and a MV projection at gantry angle 90°. Orthogonal 2D projections (200 projections) from 10 phases were used to train the network to be patient specific while the DIBH CT was held out for testing. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and structural similarity index metric (SSIM) achieved by our method are 93.1 HU and 92.5 HU, 21.7 dB and 15.6 dB, and 0.87 and 0.74 within body and tumor ROI, respectively. These results demonstrate the feasibility and efficacy of our proposed method for 3D imaging from two orthogonal kV and MV 2D projections, which provides a potential solution of fast 3D imaging for daily treatment setup of breath-hold lung RT to ensure treatment accuracy and effectiveness.

Proceedings Article | 4 April 2022 Presentation + Paper

Deep learning based volume-to-slice MRI registration via intentional overfitting

Yabo Fu, Yang Lei, Tonghe Wang, Marian Axente, Justin Roper, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12034, 1203412 (2022) https://doi.org/10.1117/12.2611898

KEYWORDS: Magnetic resonance imaging, Image registration, 3D image processing, 3D magnetic resonance imaging, Radiotherapy, Ultrasonography, Tumors, 3D modeling, 3D acquisition, X-rays

Read Abstract +

Proceedings Article | 4 April 2022 Paper

Using orthogonal 2D kV images for target localization via central matching networks

Chih-Wei Chang, Yang Lei, Tonghe Wang, Liyong Lin, Jun Zhou, Jeffrey Bradley, Tian Liu, Xiaofeng Yang

Proceedings Volume 12034, 120341Y (2022) https://doi.org/10.1117/12.2611899

KEYWORDS: Tumors, 3D acquisition, 3D image processing, Computed tomography, Radiotherapy, Data modeling, 3D modeling, Radiation oncology, Monte Carlo methods, Lung

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Deep-learning-based modulated radiotherapy dose plan prediction with integration of non-modulated dose distribution

Shadab Momin, Yang Lei, Jiahan Zhang, Tonghe Wang, Justin Roper, Jeffrey Bradley, Pretesh Patel, Tian Liu, Xiaofeng Yang

Proceedings Volume 12034, 1203418 (2022) https://doi.org/10.1117/12.2612230

KEYWORDS: Modulation, Radiotherapy, Pancreatic cancer, Computed tomography, Statistical analysis, Pancreas, Liver, Kidney, Feature extraction, Convolutional neural networks

Read Abstract +

Recently, various deep learning (DL)-based frameworks have been proposed for predicting dose distributions for radiotherapy treatment, which serve as initial dose maps and provide treatment planners with optimization starting points. This can be advantageous for dynamic treatment sites such as pancreatic cancer due to large patient to patient anatomic variations. DL-based methods thus far have used CT and contour maps to train DL networks for predictions of dose distributions. While these inputs provide important information such as density variations within a CT slice as well as spatial locations of various structures within the CT slice, these inputs do not provide radiation dose deposition information, which is typically used in inverse optimization algorithms during treatment planning to reach the desired dose distribution. In this work, we propose a new deep learning-based correction method for generating modulated dose map from non-modulated dose map, which is the dose distribution achieved from uniform beamlet intensities. Our method is consisted of two subnetworks: fusion module and correction module. Fusion module extracts features from CT and contours, including GTV contour and multi-OAR contours. Through hierarchical layers, the extracted feature map is represented as a target activation map, which can well represent the distribution of modulated dose map. To include the geometric information, the target activation map together with non-modulated dose map are then transferred into the correction module to obtain the estimated modulated dose map. Histogram matching loss with traditional losses are used. The goal of histogram matching loss is used to match the distribution of estimated modulated dose to that of ground truth modulated dose map. We performed 3-fold cross-validation on a dataset consisted of 30 patients. Our proposed method generated comparable predictions, compared to the ground truth, for 20/23 clinically relevant dose volume parameters. Overall results demonstrate the feasibility and efficacy of our proposed DL-based method for pancreas SBRT dose prediction.

Proceedings Article | 4 April 2022 Paper

An unsupervised patient-specific metal artifact reduction framework for proton therapy

Chih-Wei Chang, Yang Lei, Serdar Charyyev, Shuai Leng, Tim Yoon, Jun Zhou, Xiaofeng Yang, Liyong Lin

Proceedings Volume 12034, 120340X (2022) https://doi.org/10.1117/12.2612345

KEYWORDS: Computed tomography, Metals, Tissues, Reconstruction algorithms, Data modeling, Tumors, Spine, Scanners, Monte Carlo methods, Machine learning

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Mask R-CNN-based tumor localization and segmentation in 4D Lung CT

Yang Lei, Zhen Tian, Tonghe Wang, Justin Roper, Kristin Higgins, Jeffrey Bradley, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11600, 116000M (2021) https://doi.org/10.1117/12.2580795

KEYWORDS: Tumors, Lung, Computed tomography, 4D CT imaging, Image segmentation, Radiotherapy, Motion measurement, 3D image processing, Stereoscopy, Real time imaging

Read Abstract +

Motion management is of utmost importance to ensure the effectiveness of radiation treatment for lung cancer patients. The emerging 4D radiotherapy technique aims to actively manage lung tumor motion by providing a time-dependent treatment. This requires the delineation of tumors on all the 3D phase CT images in 4D CT, which is labor intensive and time consuming. In this study, we propose a novel deep learning-based method to automatically localize and segment lung tumor on 4D CT to facilitate the clinical workflow of 4D radiotherapy. The proposed network, named motion Regionbased Convolutional Neural Networks (R-CNN), consists of four stages, i.e., feature extraction, rough tumor location, fine tumor location, and segmentation within tumor region-of-interest (ROI). To aid the network to get rid of unreasonable detected ROIs, different from traditional mask R-CNN, our proposed method first fed 4D CT with consecutive phases into the backbone to extract tumor motion information and then utilized these motion information to estimate global and local deformation vector fields (DVFs), which is useful for measuring the movement of the tumor ROI between each two phases. Our method was tested on 20 patients’ lung 4D CT images in this study. Five metrics were used for quantitative evaluation, i.e., center-of-mass distance (COMD), Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD₉₅), mean surface distance (MSD), and volume difference (VD) calculated between the manual tumor contour and the contour obtained by our method. Averaged over the 20 cases, our method yielded 1.14±0.95 mm on COMD, 0.76±0.25 on DSC, 2.29±1.31 mm on HD95, 0.75±0.44 mm on MSD, and 0.51±0.51 cc on VD. These results have demonstrated the feasibility and efficacy of our motion R-CNN method for automatic localization and segmentation of lung tumors on 4D CT images. Our method is also expected to be applicable to in-treatment real-time volumetric imaging to provide 3D markerless tumor tracking during treatment delivery.

Proceedings Article | 15 February 2021 Poster + Paper

Deep learning-based 3D image generation using a single 2D projection image

Yang Lei, Zhen Tian, Tonghe Wang, Justin Roper, Kristin Higgins, Jeffrey Bradley, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11596, 115961V (2021) https://doi.org/10.1117/12.2580796

KEYWORDS: 3D image processing, Lung, Computed tomography, Signal to noise ratio, Real time imaging, Radiotherapy, Integration, Computer programming, 4D CT imaging

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Synthetic CT-based multi-organ segmentation in cone beam CT for adaptive pancreatic radiotherapy

Xianjin Dai, Yang Lei, James Janopaul-Naylor, Tonghe Wang, Justin Roper, Jun Zhou, Walter Curran, Tian Liu, Pretesh Patel, Xiaofeng Yang

Proceedings Volume 11596, 1159623 (2021) https://doi.org/10.1117/12.2581132

KEYWORDS: Radiotherapy, Tumors, Neural networks, Image segmentation, Image quality, Computed tomography

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Deep attention mask regional convolutional neural network for head-and-neck MRI multi-organ auto-delineation

Xianjin Dai, Yang Lei, Tonghe Wang, Jun Zhou, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11597, 115971B (2021) https://doi.org/10.1117/12.2581131

KEYWORDS: Magnetic resonance imaging, Convolutional neural networks, Radiotherapy, Cancer, Optic nerve, Spinal cord, Process modeling, Image segmentation, Feature extraction, Esophagus

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Multi-needle detection in ultrasound image using max-margin mask R-CNN

Yupei Zhang, Zhen Tian, Yang Lei, Tonghe Wang, Pretesh Patel, Ashesh Jani, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11602, 1160216 (2021) https://doi.org/10.1117/12.2580803

KEYWORDS: Ultrasonography, Prostate, High dynamic range imaging, Process modeling, Neural networks, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Ultrasound multi-needle detection using deep attention U-Net with TV regularizations

Yupei Zhang, Yang Lei, Xiuxiu He, Zhen Tian, Jiwoong Jeong, Tonghe Wang, Qiulan Zeng, Ashesh Jani, Walter Curran, Pretesh Patel, Tian Liu, Xiaofeng Yang

Proceedings Volume 11598, 1159829 (2021) https://doi.org/10.1117/12.2580802

KEYWORDS: Ultrasonography, High dynamic range imaging, Prostate cancer, Prostate, Image segmentation, 3D modeling, 3D image processing, Silver, Binary data

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Prostate dose prediction in HDR Brachytherapy using unsupervised multi-atlas fusion

Yang Lei, Yabo Fu, Tonghe Wang, Walter Curran, Tian Liu, Pretesh Patel, Xiaofeng Yang

Proceedings Volume 11596, 115962C (2021) https://doi.org/10.1117/12.2580979

KEYWORDS: High dynamic range imaging, Prostate, Prostate cancer, Natural surfaces, Binary data

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Ultrasound GLCM texture analysis of radiation-induced acute toxicity following breast cancer radiotherapy

Boran Zhou, Mingquan Lin, Xiaofeng Yang, Simone Henry, Jolinta Lin, Karen Godette, Shannon Kahn, Walter Curran, Mylin Torres, Tian Liu

Proceedings Volume 11602, 1160205 (2021) https://doi.org/10.1117/12.2581139

KEYWORDS: Ultrasonography, Toxicity, Radiotherapy, Breast cancer, Breast, Statistical analysis, Statistical methods, Reliability

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

A learning-based nonrigid MRI-CBCT image registration method for MRI-guided prostate cancer radiotherapy

Yabo Fu, Yang Lei, Tonghe Wang, Pretesh Patel, Ashesh Jani, Hui Mao, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11600, 116001J (2021) https://doi.org/10.1117/12.2580786

KEYWORDS: Prostate cancer, Image registration, Prostate, Radiotherapy, Magnetic resonance imaging, Tissues, Tumors, Visualization, Rectum, Image segmentation

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Fully automated segmentation of brain tumor from multiparametric MRI using 3D context U-Net with deep supervision

Mingquan Lin, Shadab Momin, Boran Zhou, Katherine Tang, Yang Lei, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11597, 115971I (2021) https://doi.org/10.1117/12.2581118

KEYWORDS: Tumors, Brain, Magnetic resonance imaging, Radiotherapy, Algorithm development, Computer programming

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Synthesizing high-resolution CT from low-resolution CT using self-learning

Tonghe Wang, Yang Lei, Zhen Tian, Xiangyang Tang, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11595, 115952N (2021) https://doi.org/10.1117/12.2581080

KEYWORDS: Computed tomography, Lawrencium, Image fusion, Image resolution, Super resolution, Brain, Associative arrays, 3D image reconstruction, 3D image processing

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Deformable MRI-CT liver image registration using convolutional neural network with modality independent neighborhood descriptors

Yabo Fu, Yang Lei, Tonghe Wang, Jun Zhou, Walter Curran, Pretesh Patel, Tian Liu, Xiaofeng Yang

Proceedings Volume 11597, 115970G (2021) https://doi.org/10.1117/12.2581082

KEYWORDS: Image registration, Liver, Computed tomography, Magnetic resonance imaging, Convolutional neural networks, Radiotherapy, Tumors, Error analysis, Tissues, Radio propagation

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Deep learning-based deformable image registration of inter-fraction CBCT images for adaptive radiation therapy

Huiqiao Xie, Yang Lei, Tonghe Wang, Yabo Fu, Xiangyang Tang, Walter Curran, Pretesh Patel, Tian Liu, Xiaofeng Yang

Proceedings Volume 11596, 115962I (2021) https://doi.org/10.1117/12.2581083

KEYWORDS: Image registration, Radiotherapy, Image quality, Computed tomography

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Abdominal CT-CBCT deformable image registration using Deep Neural Network with directional local structural similarity

Yabo Fu, Yang Lei, Tonghe Wang, Jun Zhou, Pretesh Patel, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11598, 115981A (2021) https://doi.org/10.1117/12.2581091

KEYWORDS: X-ray computed tomography, Image registration, Neural networks, Image quality, Radiotherapy, Optical simulations, Error analysis, X-rays, X-ray imaging, Tissues

Read Abstract +

Proceedings Article | 15 February 2021 Paper

Chest CBCT-based synthetic CT using cycle-consistent adversarial network with histogram matching

Richard L. Qiu, Yang Lei, Aparna Kesarwala, Kristin Higgins, Jeffrey Bradley, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11596, 115961Z (2021) https://doi.org/10.1117/12.2581094

KEYWORDS: Chest, Image quality, Computed tomography, Signal to noise ratio, Radiotherapy, Tissues, Standards development, Radiation oncology, Image quality standards

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Deep learning-based deformable MRI-CBCT registration of male pelvic region

Shadab Momin, Yang Lei, Tonghe Wang, Yabo Fu, Pretesh Patel, Ashesh Jani, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11597, 115970H (2021) https://doi.org/10.1117/12.2581096

KEYWORDS: Magnetic resonance imaging, Image registration, Neural networks, Radiotherapy, Prostate cancer

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Deep learning-based multi-catheter reconstruction for MRI-guided HDR prostate brachytherapy

Xianjin Dai, Yang Lei, Yupei Zhang, Tonghe Wang, Walter Curran, Pretesh Patel, Tian Liu, Xiaofeng Yang

Proceedings Volume 11598, 115981S (2021) https://doi.org/10.1117/12.2581123

KEYWORDS: Prostate, High dynamic range imaging, Magnetic resonance imaging, Prostate cancer, Visualization, Tissues, Rectum, Medical imaging, Convolutional neural networks, Blood vessels

Read Abstract +

Reconstructing catheters on medical images is a crucial step in high-dose-rate (HDR) brachytherapy for treating prostate cancer. However, manually identify the catheters is labor intensive. With its superior soft-tissue contrast, magnetic resonance imaging (MRI) can provide superior anatomic visualization of prostate gland and its surrounding tissues such as the rectum and the bladder. There is a considerable increase of using MRI-guided HDR prostate brachytherapy over the past decades. By incorporating MRI into prostate brachytherapy procedure, the therapeutic ratio could be improved attribute to MRI's capability of differentiating dominant prostatic lesions. However, it has been realized that challenge remains in recognition of multiple catheters in MRI because catheters used in routine HDR prostate brachytherapy appear dark, thus can be easily confused with blood vessels. In this study, we developed a deep learningbased catheter reconstruction method to tackle the challenge. Particularly, a 3D mask scoring regional convolutional neural network has been implemented to automatically identify all the catheters in MRI that are acquired after catheters insertion during HDR prostate brachytherapy. The network was trained using the paired MR images and binary catheter annotation images offered by experienced medical physicists as ground truth. After the network was trained, the locations, sizes and shapes of all the catheters can be predicted given MR images of a new prostate cancer patient receiving HDR brachytherapy. Quantities including catheter tip and shaft errors were computed to assess our proposed method. Our method detected 164 catheters from 11 patients receiving HDR prostate brachytherapy with a catheter tip error of 0.62±1.83 mm and a catheter shaft error of 0.94±0.52 mm. The proposed multi-catheter reconstruction method has the capability of precisely localizing the tips and shafts of catheters in 3D MRI images of HDR prostate brachytherapy. It paves the way for elevating the quality and treatment outcome of MRI-guided HDR prostate brachytherapy.

Proceedings Article | 15 February 2021 Presentation + Paper

CT-MRI pelvic deformable registration via deep learning

Shadab Momin, Yang Lei, Tonghe Wang, Yabo Fu, Pretesh Patel, Ashesh Jani, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11598, 1159818 (2021) https://doi.org/10.1117/12.2581069

KEYWORDS: Magnetic resonance imaging, Neural networks, Image registration, Computed tomography, Radiotherapy, Prostate cancer

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Residual mask scoring regional convolutional neural network for multi-organ segmentation in head-and-neck CT

Xianjin Dai, Yang Lei, Tonghe Wang, Jun Zhou, Justin Roper, Mark McDonald, Jonathan Beitler, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11600, 116001M (2021) https://doi.org/10.1117/12.2581126

KEYWORDS: Convolutional neural networks, Computed tomography, Image segmentation, Radiotherapy, Magnetic resonance imaging, Tumors, Cancer

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Synthetic MRI-aided multi-organ segmentation in head-and-neck cone beam CT

Xianjin Dai, Yang Lei, Tonghe Wang, Jun Zhou, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11598, 115981M (2021) https://doi.org/10.1117/12.2581128

KEYWORDS: Radiotherapy, Computed tomography, Optic nerve, Magnetic resonance imaging, Tumors, Spinal cord, Neural networks, Neck, Image segmentation, Head

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Region of interest discovery using discriminative concrete autoencoder for COVID-19 lung CT images

Yupei Zhang, Yang Lei, Mingquan Lin, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11597, 115970U (2021) https://doi.org/10.1117/12.2581143

KEYWORDS: Lung, Computed tomography, Image classification, Head, Feature selection, Quantitative analysis, Neural networks, Feature extraction, Chest

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Automatic tumor segmentation in 3D automated breast ultrasound using convolutional neural network

Yang Lei, Xiuxiu He, Tonghe Wang, Jincao Yao, Lijing Wang, Wei Li, Walter Curran, Tian Liu, Dong Xu, Xiaofeng Yang

Proceedings Volume 11602, 1160219 (2021) https://doi.org/10.1117/12.2581144

KEYWORDS: Tumors, Breast, Ultrasonography, Image segmentation, Convolutional neural networks, 3D acquisition, Mammography, Visualization

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Accurate characterization of metal implants and human materials using novel proton counting detector for Monte Carlo dose calculation in proton therapy

Serdar Charyyev, Chih-Wei Chang, Joseph Harms, Cristina Oancea, S. Tim Yoon, Xiaofeng Yang, Tiezhi Zhang, Jun Zhou, Shuai Leng, Liyong Lin

Proceedings Volume 11595, 115950B (2021) https://doi.org/10.1117/12.2581751

KEYWORDS: Metals, Sensors, Monte Carlo methods, Spine, Tissues, Spectral imaging cameras, Particles, Aluminum

Read Abstract +

Owing to poor characterization of implant and adjacent human tissues, the presence of metal implants has been shown to be a risk factor for clinical results for proton therapy. In this project we have developed a way of characterizing implant and human materials in terms of water-equivalent thicknesses (WET) and relative stopping power (RSP) using a novel proton counting detector. We tracked each proton using a fast spectral imaging camera AdvaPIX-TPX3 which operated in energy mode measures collected energy per-voxel to derive the deposited energy along the particle track across the voxelated sensor. We considered three scenarios: sampling of WET of a CIRS M701 Adult Phantom (CMAP) at different locations; measurements of energy perturbations in the CMAP implanted with metal rods; sampling of WET of a more complex spine phantom. WET and RSP information were extracted from energy spectra at position along the central axis by using the shift in the most probable energy (MPE) from the reference energy (either initial incident energy or energy without a metal implant). Measurements were compared to TOPAS simulation results. Measured WET of the CMAP ranged from 18.63 to 25.23 cm depending on the location of the sampling which agreed with TOPAS simulation results within 1.6%. The RSPs of metals from CMAP perturbation measurements were determined as 1.97, 2.98, and 5.44 for Al, Ti and CoCr, respectively, which agreed with TOPAS within 2.3%. RSPs for material composition of a more complex spine phantom yielded 1.096, 1.309 and 1.001 for Acrylic, PEEK and PVC, respectively. In summary, this work has shown a method to accurately characterize RSPs of metal and human materials of CMAP implanted with metals and a complex spine phantom. Using the data obtained by the proposed method, it may be possible to validate RSP maps provided by conventional photon computed tomography techniques. Owing to poor characterization of implant and adjacent human tissues, the presence of metal implants has been shown to be a risk factor for clinical results for proton therapy. In this project we have developed a way of characterizing implant and human materials in terms of water-equivalent thicknesses (WET) and relative stopping power (RSP) using a novel proton counting detector. We tracked each proton using a fast spectral imaging camera AdvaPIX-TPX3 which operated in energy mode measures collected energy per-voxel to derive the deposited energy along the particle track across the voxelated sensor. We considered three scenarios: sampling of WET of a CIRS M701 Adult Phantom (CMAP) at different locations; measurements of energy perturbations in the CMAP implanted with metal rods; sampling of WET of a more complex spine phantom. WET and RSP information were extracted from energy spectra at position along the central axis by using the shift in the most probable energy (MPE) from the reference energy (either initial incident energy or energy without a metal implant). Measurements were compared to TOPAS simulation results. Measured WET of the CMAP ranged from 18.63 to 25.23 cm depending on the location of the sampling which agreed with TOPAS simulation results within 1.6%. The RSPs of metals from CMAP perturbation measurements were determined as 1.97, 2.98, and 5.44 for Al, Ti and CoCr, respectively, which agreed with TOPAS within 2.3%. RSPs for material composition of a more complex spine phantom yielded 1.096, 1.309 and 1.001 for Acrylic, PEEK and PVC, respectively. In summary, this work has shown a method to accurately characterize RSPs of metal and human materials of CMAP implanted with metals and a complex spine phantom. Using the data obtained by the proposed method, it may be possible to validate RSP maps provided by conventional photon computed tomography techniques.

Proceedings Article | 15 February 2021 Presentation + Paper

Deformable MRI-US image registration using biomechanically constrained shape matching network for image-guided prostate intervention

Yabo Fu, Yang Lei, Tonghe Wang, Pretesh Patel, Ashesh Jani, Hui Mao, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11602, 116020K (2021) https://doi.org/10.1117/12.2580789

KEYWORDS: Prostate, Image registration, Magnetic resonance imaging, Image segmentation, Clouds, Tumors, Prostate cancer, Image fusion, Biopsy, Ultrasonography

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Deep learning-based self-high-resolution for 3D ultrasound imaging

Yang Lei, Tonghe Wang, Xiuxiu He, Ge Cui, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11602, 1160218 (2021) https://doi.org/10.1117/12.2581072

KEYWORDS: Ultrasonography, 3D image processing, Image resolution, Signal to noise ratio, Image quality, Image analysis, Breast

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Region proposal network for multi-organ segmentation in CT for pancreatic radiotherapy

Xianjin Dai, Yang Lei, James Janopaul-Naylor, Tonghe Wang, Justin Roper, Tian Liu, Walter Curran, Pretesh Patel, Xiaofeng Yang

Proceedings Volume 11598, 115981T (2021) https://doi.org/10.1117/12.2581147

KEYWORDS: Computed tomography, Radiotherapy, Image segmentation, Kidney, Stomach, Spinal cord, Liver, Feature extraction, Convolutional neural networks

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Contrast-enhanced MRI synthesis from non-contrast MRI using attention CycleGAN

Tonghe Wang, Yang Lei, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11600, 116001L (2021) https://doi.org/10.1117/12.2581064

KEYWORDS: Magnetic resonance imaging, Tissues, Brain mapping, Brain

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Multi-organ segmentation on head and neck dual-energy CT using Deep Neural Networks

Tonghe Wang, Yang Lei, Mark McDonald, Jonathan Beitler, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11596, 115961Y (2021) https://doi.org/10.1117/12.2580964

KEYWORDS: Image segmentation, Neural networks, Neck, Head, Computed tomography, Tumor growth modeling, Radiotherapy, Feature extraction, Dual energy imaging, Convolutional neural networks

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

MRI-based prostate and dominant lesion segmentation using deep neural network

Tonghe Wang, Yang Lei, Olayinka Abiodun Ojo, Oladunni Akin-Akintayo, Akinyemi Akintayo, Walter Curran, Tian Liu, David Schuster, Xiaofeng Yang

Proceedings Volume 11597, 115971L (2021) https://doi.org/10.1117/12.2581061

KEYWORDS: Image segmentation, Prostate, Neural networks, Magnetic resonance imaging, Radiotherapy, Magnetism, Binary data

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Post-op brain tumor bed detection and segmentation using 3D Mask R-CNN for dynamic magnetic resonance perfusion imaging

Jiwoong Jeong, Yang Lei, Karen Xu, Tian Liu, Hyunsuk Shim, Walter Curran, Hui-Kuo Shu, Xiaofeng Yang

Proceedings Volume 11600, 116001R (2021) https://doi.org/10.1117/12.2580792

KEYWORDS: Magnetic resonance imaging, Image segmentation, Brain, Neuroimaging, Tumors, Magnetism, Radiotherapy, Functional magnetic resonance imaging, 3D image processing

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Daily cone-beam CT multi-organ segmentation for prostate adaptive radiotherapy

Yabo Fu, Yang Lei, Tonghe Wang, Sibo Tian, Pretesh Patel, Ashesh Jani, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11596, 1159620 (2021) https://doi.org/10.1117/12.2580791

KEYWORDS: Image segmentation, Prostate, Radiotherapy, Magnetic resonance imaging, Rectum, Feature extraction, Bladder, Tissues, Computed tomography, Head

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Motion tracking in 3D ultrasound imaging based on Markov-like deep-learning-based deformable registration

Yang Lei, Shadab Momin, Justin Roper, Pretesh Patel, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11602, 1160215 (2021) https://doi.org/10.1117/12.2580794

KEYWORDS: 3D image processing, Ultrasonography, Liver, Gallium nitride, Error analysis

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Assessing the condition of spectral channelization (energy binning) in photon-counting CT: a singular value decomposition based approach

Yan Ren, Huiqiao Xie, Wenting Long, Xiaofeng Yang, Xiangyang Tang

Proceedings Volume 11595, 115952T (2021) https://doi.org/10.1117/12.2580933

KEYWORDS: X-ray computed tomography, Imaging spectroscopy, Sensors, Condition numbers, X-ray imaging, Tissues, Radiography, Head, Distortion

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Radiation dose prediction for pancreatic stereotactic body radiotherapy via convention neural networks

Shadab Momin, Yang Lei, Tonghe Wang, Yabo Fu, Pretesh Patel, Asesh Jani, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11598, 1159823 (2021) https://doi.org/10.1117/12.2580961

KEYWORDS: Radiotherapy, Pancreas, Tissues, Stomach, Scanning probe lithography, Liver

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Synthetic dual energy CT imaging from single energy CT using deep attention neural network

Tonghe Wang, Serdar Charyyev, Yang Lei, Beth Ghavidel, Jonathan Beitler, Mark McDonald, Walter Curran, Jun Zhou, Tian Liu, Xiaofeng Yang

Proceedings Volume 11595, 1159547 (2021) https://doi.org/10.1117/12.2580966

KEYWORDS: Computed tomography, Dual energy imaging, Neural networks, Target acquisition, Image processing, Cancer

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Prostate and tumor segmentation on PET/CT using Dual Mask R-CNN

Tonghe Wang, Yang Lei, Oladunni Akin-Akintayo, Olayinka Abiodun Ojo, Akinyemi Akintayo, Walter Curran, Tian Liu, David Schuster, Xiaofeng Yang

Proceedings Volume 11600, 116000S (2021) https://doi.org/10.1117/12.2580970

KEYWORDS: Tumors, Prostate, Image segmentation, Positron emission tomography, Computed tomography, Tomography, Radiotherapy, Binary data

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

4D cone-beam CT deformable registration using unsupervised spatial transformation network

Tonghe Wang, Yang Lei, Zhen Tian, Matt Giles, Jeffrey Bradley, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11600, 116001K (2021) https://doi.org/10.1117/12.2580971

KEYWORDS: Image registration, Lung, Tumors, Radiotherapy, Image resolution

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Lung tumor segmentation of PET/CT using dual pyramid mask R-CNN

Tonghe Wang, Yang Lei, Sibo Tian, Tian Liu, Walter Curran, Kristin Higgins, Xiaofeng Yang

Proceedings Volume 11596, 1159632 (2021) https://doi.org/10.1117/12.2580987

KEYWORDS: Tumors, Lung, Image segmentation, Positron emission tomography, Computed tomography, Tomography, Lung cancer, Convolutional neural networks, Binary data

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Deep learning-based denoising for magnetic resonance spectroscopy signals

Yang Lei, Bing Ji, Tian Liu, Walter Curran, Hui Mao, Xiaofeng Yang

Proceedings Volume 11600, 1160006 (2021) https://doi.org/10.1117/12.2580988

KEYWORDS: Magnetic resonance imaging, Signal to noise ratio, Denoising, In vivo imaging, Data acquisition

Read Abstract +

Magnetic resonance spectroscopy (MRS) is a non-invasive imaging tool for detecting and quantifying metabolites in vivo. However, the spectral data often suffer from poor signal-to-noise ratio (SNR) due to low concentrations of metabolites and limited acquisition time. In this work, we introduce a deep learning-based method for denoising MRS spectra. By identifying and characterizing the sparse representations in the feature vector domain of the noise in MRS data using the deep learning network, the non-signal components can be removed to improve the SNR of spectral data. We used a stack auto-encoder (SAE) network to train the deep learning-based model based on high SNR data collected from a brain phantom using a high number of signal average (NSA=192). To overcome overfitting, the SAE network is trained in a patch-based manner. The network and denoising method were then tested using the noisy data collected in the same sample volume but using low NSA (NSA=8) with much shorter acquisition time. The denoising performance of the reported method was then evaluated using statistical comparison analysis of spectra before and after being denoised and the paired “ground truth” high NSA spectra based on the measurements of SNR, and mean squared error (MSE) and known metabolite levels. for the results of testing and evaluating the reported method showed that the SNR improved by 40% and the MSE reduced by 72% in the data collected from the brain phantom, while, the SNR improved by 47% and the MSE reduced by 27% in the data collected from the human subjects. In summary, the reported deep-learning method demonstrated a model-free approach to enhance SNR of noisy MRS data that otherwise cannot be used for quantitative analysis. The potential applications of include using low NSA or short data collection time to accelerate MRS exams while maintaining adequate spectroscopic information for detection and quantification of the metabolites of interest when a little time is available for an MRS exam in the clinical setting.

Proceedings Article | 15 February 2021 Poster + Paper

Deep learning-based volumetric image generation from projection imaging for prostate radiotherapy

Xianjin Dai, Yang Lei, Zhen Tian, Tonghe Wang, Tian Liu, Walter Curran, Xiaofeng Yang

Proceedings Volume 11598, 115981R (2021) https://doi.org/10.1117/12.2581053

KEYWORDS: Prostate, Computed tomography, Radiotherapy, 3D image processing, Real time imaging, Signal to noise ratio, Safety, Prostate cancer, Computer programming

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Paper

Multi-organ segmentation of male pelvic CT using dual attention networks

Yang Lei, Tonghe Wang, Sibo Tian, Yabo Fu, Pretesh Patel, Ashesh Jani, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11598, 115981L (2021) https://doi.org/10.1117/12.2581055

KEYWORDS: Computed tomography, Prostate, Radiotherapy, Rectum, Prostate cancer, Head, Bladder, Magnetic resonance imaging, Image segmentation, Feature extraction

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Generation of contrast-enhanced CT with residual cycle-consistent generative adversarial network (Res-CycleGAN)

Huiqiao Xie, Yang Lei, Tonghe Wang, Pretesh Patel, Walter Curran, Tian Liu, Xiangyang Tang, Xiaofeng Yang

Proceedings Volume 11595, 1159540 (2021) https://doi.org/10.1117/12.2581056

KEYWORDS: Computed tomography, Tissues, Visualization, Optical inspection, Signal to noise ratio, Radiotherapy, Inspection, Image registration, Detection and tracking algorithms, Computer simulations

Read Abstract +

Proceedings Article | 16 March 2020 Paper

PET attenuation correction using non-AC PET-based synthetic CT

Yang Lei, Tonghe Wang, Xue Dong, Kristin Higgins, Tian Liu, Walter Curran, Hui Mao, Jonathon Nye, Xiaofeng Yang

Proceedings Volume 11312, 1131249 (2020) https://doi.org/10.1117/12.2548468

KEYWORDS: Positron emission tomography, Computed tomography, Signal attenuation, Tissues, Lung, Magnetic resonance imaging, Computer programming, Kidney, Cancer, Image registration

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Classification of lesion specific myocardial ischemia using cardiac computed tomography radiomics

Xiuxiu He, Bang Jun Guo, Tonghe Wang, Yang Lei, Tian Liu, Long Jiang Zhang, Xiaofeng Yang

Proceedings Volume 11314, 113143P (2020) https://doi.org/10.1117/12.2548471

KEYWORDS: Ischemia, Computed tomography, Heart, Feature extraction, Machine learning, Computer aided diagnosis and therapy, Medical imaging, Image segmentation, Cancer, Angiography

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Multi-needle detection in 3D ultrasound images with sparse dictionary learning

Yupei Zhang, Xiuxiu He, Zhen Tian, Jiwoong Jeong, Yang Lei, Tonghe Wang, Qiulan Zeng, Ashesh Jani, Walter Curran, Pretesh Patel, Tian Liu, Xiaofeng Yang

Proceedings Volume 11319, 113190I (2020) https://doi.org/10.1117/12.2549005

KEYWORDS: Associative arrays, 3D image processing, Prostate, Ultrasonography, Cancer, Visualization, 3D acquisition, Detection and tracking algorithms, Reconstruction algorithms, Prostate cancer

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Attenuation correction for PET/MRI using MRI-based pseudo CT

Tonghe Wang, Yang Lei, Xue Dong, Kristin Higgins, Tian Liu, Walter Curran, Hui Mao, Jonathon Nye, Xiaofeng Yang

Proceedings Volume 11312, 1131248 (2020) https://doi.org/10.1117/12.2548158

KEYWORDS: Computed tomography, Magnetic resonance imaging, Signal attenuation, Positron emission tomography, Image segmentation, Brain, Radiotherapy, Biology, Physics, Machine learning

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Deep learning-based low dose CT imaging

Tonghe Wang, Yang Lei, Xue Dong, Zhen Tian, Xiangyang Tang, Yingzi Liu, Xiaojun Jiang, Walter Curran, Tian Liu, Hui-Kuo Shu, Xiaofeng Yang

Proceedings Volume 11312, 113124P (2020) https://doi.org/10.1117/12.2548142

KEYWORDS: Computed tomography, X-ray computed tomography, Medical physics, CT reconstruction, Image segmentation, Medicine, Physics, Biology, Image quality, Radiotherapy

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Stopping power map estimation from dual-energy CT using deep convolutional neural network

Tonghe Wang, Yang Lei, Joseph Harms, Yingzi Liu, Beth Ghavidel, Liyong Lin, Jonathan Beilter, Walter Curran, Tian Liu, Jun Zhou, Xiaofeng Yang

Proceedings Volume 11312, 113124M (2020) https://doi.org/10.1117/12.2549357

KEYWORDS: Computed tomography, Radiotherapy, Image segmentation, Tissues, X-ray computed tomography, Medical physics, Dual energy imaging, Physics, Biology, Image fusion

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Low dose PET imaging with CT-aided cycle-consistent adversarial networks

Yang Lei, Tonghe Wang, Xue Dong, Kristin Higgins, Tian Liu, Walter Curran, Hui Mao, Jonathon Nye, Xiaofeng Yang

Proceedings Volume 11312, 1131247 (2020) https://doi.org/10.1117/12.2549386

KEYWORDS: Positron emission tomography, Computed tomography, Diagnostics, Computer programming, Image quality, Network architectures, Image enhancement, Cancer, 3D image processing, Image analysis

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Deep learning-based breast tumor detection and segmentation in 3D ultrasound image

Yang Lei, Jincao Yao, Xiuxiu He, Dong Xu, Lijing Wang, Wei Li, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11319, 113190Y (2020) https://doi.org/10.1117/12.2549157

KEYWORDS: Tumors, Image segmentation, Breast, Ultrasonography, Breast cancer, 3D image processing, Cancer, Computing systems, Visualization, 3D modeling

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Deep learning-based relative stopping power mapping generation with cone-beam CT in proton radiation therapy

Tonghe Wang, Joseph Harms, Yang Lei, Beth Ghavidel, William Stokes, Tian Liu, Walter Curran, Mark McDonald, Jun Zhou, Xiaofeng Yang

Proceedings Volume 11312, 113124L (2020) https://doi.org/10.1117/12.2549275

KEYWORDS: Computed tomography, Radiotherapy, Therapeutics, Cancer, Tissues, Calibration, Medical physics, Monte Carlo methods, Image quality, Image fusion

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Weakly supervised multi-needle detection in 3D ultrasound images with bidirectional convolutional sparse coding

Yupei Zhang, Joseph Harms, Yang Lei, Tonghe Wang, Tian Liu, Ashesh Jani, Walter Curran, Pretesh Patel, Xiaofeng Yang

Proceedings Volume 11319, 1131914 (2020) https://doi.org/10.1117/12.2549283

KEYWORDS: Computed tomography, Associative arrays, 3D image processing, Prostate, 3D modeling, Process modeling, Reconstruction algorithms, Ultrasonography, High dynamic range imaging, Visualization

Read Abstract +

Proceedings Article | 16 March 2020 Paper

3D thyroid segmentation in CT using self-attention convolutional neural network

Xiuxiu He, Bang Jun Guo, Yang Lei, Yingzi Liu, Tonghe Wang, Walter Curran, Long Jiang Zhang, Tian Liu, Xiaofeng Yang

Proceedings Volume 11314, 1131445 (2020) https://doi.org/10.1117/12.2549786

KEYWORDS: Image segmentation, Computed tomography, Medical imaging, Cancer, Prostate, Magnetic resonance imaging, 3D image processing, Convolutional neural networks, Ultrasonography, Tissues

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Automatic brain arteriovenous malformations segmentation on contrast CT images using combined region proposal network and V-Net

Yabo Fu, Yang Lei, Tonghe Wang, Xiaojun Jiang, Walter Curran, Tian Liu, Hui-kuo Shu, Xiaofeng Yang

Proceedings Volume 11314, 113142Y (2020) https://doi.org/10.1117/12.2550385

KEYWORDS: Image segmentation, Brain, Computed tomography, Convolution, Image processing, Cancer, Neuroimaging, Veins, Angiography, Target detection

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Wavelet-based protoacoustic signal denoising for proton range verification

James Sohn, Wei Nie, Stephen Avery, Xiuxiu He, Jun Zhou, Xiaofeng Yang, Tian Liu

Proceedings Volume 11319, 1131904 (2020) https://doi.org/10.1117/12.2550768

KEYWORDS: Denoising, Wavelets, Acoustics, Interference (communication), Sensors, Signal detection, Radiation oncology, Cancer, Wavelet transforms, Signal to noise ratio

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Deep attentional GAN-based high-resolution ultrasound imaging

Xiuxiu He, Yang Lei, Yingzi Liu, Zhen Tian, Tonghe Wang, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11319, 113190B (2020) https://doi.org/10.1117/12.2549556

KEYWORDS: Ultrasonography, 3D image processing, Image resolution, Prostate, Computer programming, Prostate cancer, Cancer, Gallium nitride, 3D modeling, Biopsy

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Optimization of basis material selection and energy binning in three material decomposition for spectral imaging without contrast agents in photon-counting CT

Yan Ren, Wenting Long, Huiqiao Xie, Xiaofeng Yang, Xiangyang Tang

Proceedings Volume 11312, 113124X (2020) https://doi.org/10.1117/12.2549678

KEYWORDS: X-ray computed tomography, X-rays, Sensors, X-ray detectors

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Organ-at-Risk (OAR) segmentation in head and neck CT using U-RCNN

Yang Lei, Joseph Harms, Xue Dong, Tonghe Wang, Xiangyang Tang, David Yu, Jonathan Beitler, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11314, 1131444 (2020) https://doi.org/10.1117/12.2549782

KEYWORDS: Image segmentation, Computed tomography, Cancer, Head, Neck, Radiotherapy, Tissues, Oncology, Tumors, 3D modeling

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Automatic detection of brain metastases using 3D mask R-CNN for stereotactic radiosurgery

Yang Lei, Zhen Tian, Shannon Kahn, Walter Curran, Tian Liu, Xiaofeng Yang

Proceedings Volume 11314, 113142X (2020) https://doi.org/10.1117/12.2549860

KEYWORDS: Brain, Magnetic resonance imaging, Image segmentation, Brain mapping, Tumors, Cancer, 3D image processing, Neuroimaging, 3D modeling, Data modeling

Read Abstract +

Brain metastases are one of the most common neurologic complications of cancers, occurring in about 30% of all patients with cancer. Moreover, about 40% of brain metastases patients have more than three metastases. Stereotactic radiosurgery (SRS) is a well-established treatment for brain metastases, which requires accurate detection and delineation of the brain metastases. However, manually detecting and locating all the brain metastases can be very time-consuming and laborintensive, which is a big efficiency bottleneck in this typical one-day outpatient SRS procedure. Developing a fast automatic detection tool of brain metastases is highly desirable, but is very challenging given the large number of brain metastases that a patient can have and the small size that a brain metastasis can be. In this work, we propose to use a 3D Mask R-CNN method to automatically and quickly detect the brain metastases on magnetic resonance (MR) images for SRS. At the training stage, coarse feature maps were extracted from 3D MR image patches using pretrained ResNet. Then, a region proposal network (RPN) was used to predict the locations and sizes of the rough candidate tumor ROIs from the coarse feature maps. By using a uniformed fully convolution network (FCN), the metastases within ROI was segmented. The segmentation loss, classification loss (metastases or non-metastases), as well as ROI location and size regression loss were used to supervise the proposed networks. For a new query patient, candidate ROIs and predicted probability maps within ROIs were obtained from our trained model. By aggregating ROIs and the tumor probability maps and performing a consolidation via weighted cluster scoring, the final ROIs of the brain metastases was obtained. We have tested our method on 20 patients’ brain contrast T1-weighted MR images, and achieved 86.5%±3.2% sensitivity and 89.7%±4.8% specificity. For each patient, it took our trained model a few seconds to detect the brain metastases on the 3D MR images. The results of our preliminary study have demonstrated its efficacy and clinical feasibility. This auto-detection method could be a useful tool to significantly improve the efficiency of SRS treatment planning and hence ultimately improve the clinical outcome.

Proceedings Article | 16 March 2020 Paper

Benign and malignant thyroid classification using computed tomography radiomics

Bang Jun Guo, Xiuxiu He, Tonghe Wang, Yang Lei, Walter Curran, Tian Liu, Long Jiang Zhang, Xiaofeng Yang