Dr. Shaojie Chang Profile

Dr. Shaojie Chang

PhD at Mayo Clinic

SPIE Involvement:

Author

Publications (17)

SPIE Journal Paper | 24 May 2024

Improved noise reduction in photon-counting detector CT using prior knowledge-aware iterative denoising neural network

Shaojie Chang, Jeffrey F. Marsh, Emily K. Koons, Hao Gong, Cynthia H. McCollough, Shuai Leng

JMI, Vol. 11, Issue S1, S12804, (May 2024) https://doi.org/10.1117/12.10.1117/1.JMI.11.S1.S12804

KEYWORDS: Denoising, Education and training, Infrared imaging, Computed tomography, Sensors, Photodetectors, Neural networks, Image quality, Image sharpness, Image processing

Read Abstract +

Proceedings Article | 1 April 2024 Poster + Paper

Improving stenosis assessment in energy integrating detector CT via learned monoenergetic imaging capability

Shaojie Chang, Emily Koons, Hao Gong, Jamison Thorne, Cynthia McCollough, Shuai Leng

Proceedings Volume 12925, 129252R (2024) https://doi.org/10.1117/12.3006468

KEYWORDS: Computed tomography, Sensors, Education and training, Visualization, Temporal resolution, Arteries, Visibility, Scanners, Photon counting, Computer aided detection

Read Abstract +

Coronary CT angiography (cCTA) is a fast non-invasive imaging exam for coronary artery disease (CAD) but struggles with dense calcifications and stents due to blooming artifacts, potentially causing stenosis overestimation. Virtual monoenergetic images (VMIs) at higher keV (e.g., 100 keV) from photon counting detector (PCD) CT have shown promise in reducing blooming artifacts and improving lumen visibility through its simultaneous high-resolution and multi-energy imaging capability. However, most cCTA exams are performed with single-energy CT (SECT) using conventional energy-integrating detectors (EID). Generating VMIs through EID-CT requires advanced multi-energy CT (MECT) scanners and potentially sacrifices temporal resolution. Given these limitations, MECT cCTA exams are not commonly performed on EID-CT and VMIs are not routinely generated. To tackle this, we aim to enhance the multi-energy imaging capability of EIDCT through the utilization of a convolutional neural network to LEarn MONoenergetic imAging from VMIs at Different Energies (LEMONADE). The neural network was trained using ten patient cCTA exams acquired on a clinical PCD-CT (NAEOTOM Alpha, Siemens Healthineers), with 70 keV VMIs as input (which is nominally equivalent to the SECT from EID-CT scanned at 120 kV) and 100 keV VMIs as the target. Subsequently, we evaluated the performance of EID-CT equipped with LEMONADE on both phantom and patient cases (n=10) for stenosis assessment. Results indicated that LEMONADE accurately quantified stenosis in three phantoms, aligning closely wi th ground truth and demonstrating stenosis percentage area reductions of 13%, 8%, and 9%. In patient cases, it led to a 12.9% reduction in average diameter luminal stenosis when compared to the original SECT without LEMONADE. These outcomes highlight LEMONADE's capacity to enable multi-energy CT imaging, mitigate blooming artifacts, and improve stenosis assessment for the widely available EID-CT. This has a high potential impact as most cCTA exams are performed on EID-CT.

Proceedings Article | 1 April 2024 Poster + Paper

Learned high-resolution cardiac CT imaging from ultra-high-resolution PCD-CT

Emily Koons, Hao Gong, Andrew Missert, Shaojie Chang, Tim Winfree, Zhongxing Zhou, Cynthia McCollough, Shuai Leng

Proceedings Volume 12925, 129252Q (2024) https://doi.org/10.1117/12.3006463

KEYWORDS: Arteries, Computed tomography, Image resolution, Image restoration, Computer aided detection, Medical image reconstruction, Spatial resolution, Image sharpness

Read Abstract +

Coronary computed tomography angiography (cCTA) is a widely used non-invasive diagnostic exam for patients with coronary artery disease (CAD). However, most clinical CT scanners are limited in spatial resolution from use of energy-integrating detectors (EIDs). Radiological evaluation of CAD is challenging, as coronary arteries are small (3-4 mm diameter) and calcifications within them are highly attenuating, leading to blooming artifacts. As such, this is a task well suited for high spatial resolution. Recently, photon-counting-detector (PCD) CT became commercially available, allowing for ultrahigh resolution (UHR) data acquisition. However, PCD-CTs are costly, restricting widespread accessibility. To address this problem, we propose a super resolution convolutional neural network (CNN): ILUMENATE (Improved LUMEN visualization through Artificial super-resoluTion imagEs), creating a high resolution (HR) image simulating UHR PCD-CT. The network was trained and validated using patches extracted from 8 patients with a modified U-Net architecture. Training input and labels consisted of UHR PCD-CT images reconstructed with a smooth kernel degrading resolution (LR input) and sharp kernel (HR label). The network learned the resolution difference and was tested on 5 unseen LR patients. We evaluated network performance quantitatively and qualitatively through visual inspection, line profiles to assess spatial resolution improvements, ROIs for CT number stability and noise assessment, structural similarity index (SSIM), and percent diameter luminal stenosis. Overall, ILUMENATE improved images quantitatively and qualitatively, creating sharper edges more closely resembling reconstructed HR reference images, maintained stable CT numbers with less than 4% difference, reduced noise by 28%, maintained structural similarity (average SSIM = 0.70), and reduced percent diameter stenosis with respect to input images. ILUMENATE demonstrates potential impact for CAD patient management, improving the quality of LR CT images bringing them closer to UHR PCD-CT images.

Proceedings Article | 7 April 2023 Poster + Paper

PKAID-Net: prior knowledge aware iterative denoising neural network for photon counting detector CT

Shaojie Chang, Jeffrey Marsh, Emily Koons, Hao Gong, Cynthia McCollough, Shuai Leng

Proceedings Volume 12463, 124632Q (2023) https://doi.org/10.1117/12.2653904

KEYWORDS: Denoising, Education and training, Neural networks, Computed tomography, Infrared imaging, Prior knowledge, Photon counting, Interference (communication), Image processing, Image quality

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Simulation study of a novel ZnO nanowire cold cathode flat-panel x-ray source using EGSnrc for Talbot-Lau type grating interferometry

Wangjiang Wu, Jiancong Dai, Mengke Qi, Song Kang, Zengxiang Pan, Xiaoying Zhang, Shaojie Chang, Linghong Zhou, Jun Chen, Yuan Xu

Proceedings Volume 12463, 124630A (2023) https://doi.org/10.1117/12.2652087

KEYWORDS: X-rays, Zinc oxide, Nanowires, Molybdenum, Glasses, Anodes, Electrons, X-ray sources, X-ray imaging, Interferometry

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

An investigation on energy spectral information of computed tomography for machine learning in lesion classification

Daniel Liang, David Liang, Alice Wei, Ryan Kuo, Shaojie Chang, Marc Pomeroy, Yongfeng Gao

Proceedings Volume 12465, 124652S (2023) https://doi.org/10.1117/12.2654401

KEYWORDS: Computer aided detection, Tissues, X-rays, Polyps, X-ray computed tomography, 3D modeling, Machine learning, Principal component analysis

Read Abstract +

Recent advancement of spectral computed tomography (SpCT) technologies by either multi-energy spectral data acquisition with energy-integration detector or single-energy spectral data acquisition with photon counting detector has enabled the reconstruction of virtual monochromatic images (VMIs) at any energy values within and outside the energy spectral ranges of current CTs’ X-ray tubes, resulting in the possibility of not only visualizing the tissue contrast variation characteristics along the X-ray energy dimension, but also quantifying the variation characteristics by machine learning (ML) for prediction of lesion malignancy or computer-aided diagnosis (CADx). This study explored the energy spectral information of SpCT, i.e., the contrast variation characteristics along the X-ray energy dimension, for ML-CADx of lesion type of colorectal polyps. Particularly, the tissue contrast variation patterns, called energy spectral features, along the Xray energy dimension in the VMIs is investigated. A figure of merit (FOM) for the task of ML-CADx is proposed, which ranks the series of VMIs along the X-ray energy dimension by inputting each VMI into a single channel deep learning (DL) pipeline and generating a corresponding a score of AUC (area under the curve of receiver operating characteristics). Then the FOM selects different numbers of the most highly ranked VMIs as the inputs to a multi-channel DL pipeline to generate the corresponding of AUC scores until all VMIs are selected. It is hypothesized that the AUC scores from the multi-channel DL pipeline will increase to reach the highest score and then drop along the ranking order, because all VMIs have the same anatomic structure and, therefore, the strong data redundancy. The FOM reaches the highest AUC score by minimizing the redundancy. We tested the hypothesis by comparing the proposed FOM-rank ML-CADx with the widely used Karhunen-Loève (KL) transform-based ranking method where the principal components are ordered automatically by the KL transform. The lesion data include the CT images of colorectal polyps and the pathological reports after they were resected. The proposed FOM-rank method outperformed the KL-based ranking method with an optimal gain of 4.7%, showing its effectiveness in prediction of lesion malignancy.

Proceedings Article | 7 April 2023 Poster + Paper

Using virtual monoenergetic images in Karhunen–Loève domain to differentiate lesion pathology

Yongfeng Gao, Shaojie Chang, Marc Pomeroy, Lihong Li, Zhengrong Liang

Proceedings Volume 12465, 124652R (2023) https://doi.org/10.1117/12.2654390

KEYWORDS: Pathology, Polyps, Lung, Colon, X-ray computed tomography, 3D modeling, Image classification

Read Abstract +

Proceedings Article | 18 October 2022 Open Access

Using tissue-energy response to generate virtual monoenergetic images from conventional CT for computer-aided diagnosis of lesions

Shaojie Chang, Yongfeng Gao, Marc Pomeroy, Ti Bai, Hao Zhang, Zhengrong Liang

Proceedings Volume 12304, 123041L (2022) https://doi.org/10.1117/12.2646551

KEYWORDS: Tissues, Computer aided diagnosis and therapy, X-ray computed tomography, Lung, Data modeling, 3D modeling, Tumor growth modeling, Computed tomography, Signal attenuation, X-rays

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 18 October 2022 Open Access

Fully utilizing contrast enhancement on lung tissue as a novel basis material for lung nodule characterization by multi-energy CT

Shaojie Chang, Yongfeng Gao, Marc Pomeroy, Ti Bai, Hao Zhang, Zhengrong Liang

Proceedings Volume 12304, 1230429 (2022) https://doi.org/10.1117/12.2646550

KEYWORDS: Tissues, Lung, Computer aided diagnosis and therapy, Bone, X-ray computed tomography, Signal attenuation, Computed tomography, Data modeling, 3D modeling, X-rays

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 18 October 2022 Open Access

S2MS: self-supervised learning driven multi-spectral CT image enhancement

Chaoyang Zhang, Shaojie Chang, Ti Bai, Xi Chen

Proceedings Volume 12304, 1230425 (2022) https://doi.org/10.1117/12.2647001

KEYWORDS: Denoising, X-ray computed tomography, Image denoising, Signal attenuation, Computed tomography, Sensors, Image enhancement, Signal to noise ratio, Photon counting, Mass attenuation coefficient

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 4 April 2022 Presentation + Paper

Markov random field texture generation with an internalized database using a conditional encoder-decoder structure

Yongfeng Gao, Ti Bai, Siming Lu, Shaojie Chang, Hao Zhang, Mahsa Hoshmand-Kochi, Zhengrong Liang

Proceedings Volume 12031, 120311G (2022) https://doi.org/10.1117/12.2613033

KEYWORDS: Tissues, Databases, Computed tomography, Neural networks, Magnetorheological finishing, CT reconstruction, Computer programming, Brain-machine interfaces, Lung, Image filtering

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

A feasibility study of computer-aided diagnosis with DECT Bayesian reconstruction for polyp classification

Shaojie Chang, Yongfeng Gao, Marc Pomeroy, Siming Lu, Zhengrong Liang

Proceedings Volume 12033, 1203302 (2022) https://doi.org/10.1117/12.2611448

KEYWORDS: Computer aided diagnosis and therapy, Computed tomography, Tissues, Solid modeling, Mass attenuation coefficient, Tumor growth modeling, Receivers, Convolution, X-ray computed tomography, Sensors

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Parameter-free Bayesian reconstruction for dual energy computed tomography

Shaojie Chang, Yongfeng Gao, Siming Lu, Hao Yan, Zhengrong Liang

Proceedings Volume 11595, 115952U (2021) https://doi.org/10.1117/12.2581886

KEYWORDS: Computed tomography, Dual energy imaging, Tolerancing, Reconstruction algorithms, Image restoration, CT reconstruction, Abdomen

Read Abstract +

Proceedings Article | 19 May 2020 Paper

Spectrum estimation based on a parametric physical model for CT

Shaojie Chang, Xi Chen, Yang Li, Xuanqin Mou

Proceedings Volume 11312, 113122P (2020) https://doi.org/10.1117/12.2548002

KEYWORDS: X-rays, Affine motion model, X-ray computed tomography, Image segmentation, Signal attenuation, X-ray imaging, Aluminum, Optical filters, Algorithm development, Physics

Read Abstract +

Proceedings Article | 28 May 2019 Paper

A hybrid ring artifact reduction algorithm based on CNN in CT images

Shaojie Chang, Xi Chen, Jiayu Duan, Xuanqin Mou

Proceedings Volume 11072, 1107226 (2019) https://doi.org/10.1117/12.2534726

KEYWORDS: Image fusion, Databases, Computed tomography, Sensors, X-ray computed tomography, Image processing, Detection and tracking algorithms, Image quality, CT reconstruction, Convolutional neural networks

Read Abstract +

Proceedings Article | 9 March 2018 Paper

Algorithmic scatter correction based on physical model and statistical iterative reconstruction for dual energy cone beam CT

Shaojie Chang, Ti Bai, Xi Chen, Xuanqin Mou

Proceedings Volume 10573, 105734P (2018) https://doi.org/10.1117/12.2293470

KEYWORDS: Reconstruction algorithms, Bone, Dual energy imaging, CT reconstruction, X-rays, Signal attenuation, Tissues, Statistical modeling, Image quality, X-ray computed tomography

Read Abstract +

Proceedings Article | 20 September 2016 Presentation + Paper

A statistical iterative reconstruction framework for dual energy computed tomography without knowing tube spectrum

Shaojie Chang, Xuanqin Mou

Proceedings Volume 9967, 99671L (2016) https://doi.org/10.1117/12.2236588

KEYWORDS: Reconstruction algorithms, Dual energy imaging, Computed tomography, Statistical analysis, Image quality, Bone, CT reconstruction, X-rays, Abdomen, Data modeling

Read Abstract +

Showing 5 of 17 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years