Dr. Akitoshi Inoue Profile

Dr. Akitoshi Inoue

at Mayo Clinic

SPIE Involvement:

Author

Publications (8)

SPIE Journal Paper | 24 August 2023

Self-trained deep convolutional neural network for noise reduction in CT

Zhongxing Zhou, Akitoshi Inoue, Cynthia McCollough, Lifeng Yu

JMI, Vol. 10, Issue 04, 044008, (August 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.4.044008

KEYWORDS: Education and training, Data modeling, Denoising, Computed tomography, Infrared imaging, Image restoration, Performance modeling, Image quality, Deep convolutional neural networks, Quantum noise

Read Abstract +

PurposeSupervised deep convolutional neural network (CNN)-based methods have been actively used in clinical CT to reduce image noise. The networks of these methods are typically trained using paired high- and low-quality data from a massive number of patients and/or phantom images. This training process is tedious, and the network trained under a given condition may not be generalizable to patient images acquired and reconstructed under different conditions. We propose a self-trained deep CNN (ST_CNN) method for noise reduction in CT that does not rely on pre-existing training datasets.ApproachThe ST_CNN training was accomplished using extensive data augmentation in the projection domain, and the inference was applied to the data itself. Specifically, multiple independent noise insertions were applied to the original patient projection data to generate multiple realizations of low-quality projection data. Then, rotation augmentation was adopted for both the original and low-quality projection data by applying the rotation angle directly on the projection data so that images were rotated at arbitrary angles without introducing additional bias. A large number of paired low- and high-quality images from the same patient were reconstructed and paired for training the ST_CNN model.ResultsNo significant difference was found between the ST_CNN and conventional CNN models in terms of the peak signal-to-noise ratio and structural similarity index measure. The ST_CNN model outperformed the conventional CNN model in terms of noise texture and homogeneity in liver parenchyma as well as better subjective visualization of liver lesions. The ST_CNN may sacrifice the sharpness of vessels slightly compared to the conventional CNN model but without affecting the visibility of peripheral vessels or diagnosis of vascular pathology.ConclusionsThe proposed ST_CNN method trained from the data itself may achieve similar image quality in comparison with conventional deep CNN denoising methods pre-trained on external datasets.

Proceedings Article | 3 April 2023 Presentation + Paper

A training program to reduce reader search errors for liver metastasis detection in CT

Scott Hsieh, Akitoshi Inoue, Mariana Yalon, David Cook, Jeff Fidler, Hao Gong, Parvathy Sudhir Pillai, Andrew Vercnocke, Matthew Johnson, Shuai Leng, Lifeng Yu, David Holmes, Rickey Carter, Cynthia McCollough, Joel Fletcher

Proceedings Volume 12467, 1246704 (2023) https://doi.org/10.1117/12.2654007

KEYWORDS: Education and training, Liver, Cancer detection, Eye tracking, Eye, Error analysis, Calibration

Read Abstract +

SPIE Journal Paper | 31 January 2023 Open Access

Multislice input for 2D and 3D residual convolutional neural network noise reduction in CT

Zhongxing Zhou, Nathan R. Huber, Akitoshi Inoue, Cynthia McCollough, Lifeng Yu

JMI, Vol. 10, Issue 01, 014003, (January 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.1.014003

KEYWORDS: 3D modeling, Performance modeling, Denoising, Computed tomography, Education and training, 3D image processing, Veins, Infrared imaging, Image quality, Convolutional neural networks

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 18 October 2022 Open Access

Self-trained deep convolutional neural network for noise reduction in CT

Zhongxing Zhou, Akitoshi Inoue, Cynthia McCollough, Lifeng Yu

Proceedings Volume 12304, 123042B (2022) https://doi.org/10.1117/12.2646717

KEYWORDS: Denoising, Computed tomography, Convolutional neural networks, Image quality, Performance modeling, Network architectures

Read Abstract +

DOWNLOAD PAPER

SPIE Journal Paper | 13 September 2022

Individualized and generalized models for predicting observer performance on liver metastasis detection using CT

Parvathy Sudhir Pillai, David Holmes, Rickey Carter, Akitoshi Inoue, David Cook, Ron Karwoski, Jeff Fidler, Joel Fletcher, Shuai Leng, Lifeng Yu, Cynthia McCollough, Scott Hsieh

JMI, Vol. 9, Issue 05, 055501, (September 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.5.055501

KEYWORDS: Performance modeling, Liver, Computed tomography, Feature extraction, Data modeling, 3D modeling, Radiology, RGB color model, Reconstruction algorithms, Convolutional neural networks

Read Abstract +

Purpose: Radiologists exhibit wide inter-reader variability in diagnostic performance. This work aimed to compare different feature sets to predict if a radiologist could detect a specific liver metastasis in contrast-enhanced computed tomography (CT) images and to evaluate possible improvements in individualizing models to specific radiologists.Approach: Abdominal CT images from 102 patients, including 124 liver metastases in 51 patients were reconstructed at five different kernels/doses using projection domain noise insertion to yield 510 image sets. Ten abdominal radiologists marked suspected metastases in all image sets. Potentially salient features predicting metastasis detection were identified in three ways: (i) logistic regression based on human annotations (semantic), (ii) random forests based on radiologic features (radiomic), and (iii) inductive derivation using convolutional neural networks (CNN). For all three approaches, generalized models were trained using metastases that were detected by at least two radiologists. Conversely, individualized models were trained using each radiologist’s markings to predict reader-specific metastases detection.Results: In fivefold cross-validation, both individualized and generalized CNN models achieved higher area under the receiver operating characteristic curves (AUCs) than semantic and radiomic models in predicting reader-specific metastases detection ability (p < 0.001). The individualized CNN with an AUC of mean (SD) 0.85(0.04) outperformed the generalized one [AUC = 0.78 ( 0.06 ) , p = 0.004]. The individualized semantic [AUC = 0.70 ( 0.05 ) ] and radiomic models [AUC = 0.68 ( 0.06 ) ] outperformed the respective generalized versions [semantic AUC = 0.66 ( 0.03 ) , p = 0.009; radiomic AUC = 0.64 ( 0.06 ) , p = 0.03].Conclusions: Individualized models slightly outperformed generalized models for all three feature sets. Inductive CNNs were better at predicting metastases detection than semantic or radiomic features. Generalized models have implementation advantages when individualized data are unavailable.

Proceedings Article | 4 April 2022 Poster + Paper

Residual-based convolutional-neural-network (CNN) for low-dose CT denoising: impact of multi-slice input

Zhongxing Zhou, Nathan Huber, Akitoshi Inoue, McCollough Cynthia, Lifeng Yu

Proceedings Volume 12031, 120312B (2022) https://doi.org/10.1117/12.2612872

KEYWORDS: Denoising, Computed tomography, Network architectures

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Implementation and initial experience with an interactive eye-tracking system for measuring radiologists' visual search in diagnostic tasks using volumetric CT images

Hao Gong, Scott Hsieh, David Holmes, David Cook, Akitoshi Inoue, David Bartlett, Francis Baffour, Hiroaki Takahashi, Shuai Leng, Lifeng Yu, Joel Fletcher, Cynthia McCollough

Proceedings Volume 12031, 120310Q (2022) https://doi.org/10.1117/12.2611808

KEYWORDS: Visualization, Diagnostics, Liver, Computed tomography, Cameras, X-ray computed tomography, Head, Target detection, Radiology, Manufacturing

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

A 25-reader performance study for hepatic metastasis detection: lessons from unsupervised learning

Scott Hsieh, Akitoshi Inoue, Parvathy Sudhir Pillai, Hao Gong, David Holmes, David Cook, Shuai Leng, Lifeng Yu, Rickey Carter, Joel Fletcher, Cynthia McCollough

Proceedings Volume 12031, 1203116 (2022) https://doi.org/10.1117/12.2611543

KEYWORDS: Machine learning, Liver, Visualization, MATLAB, Abdomen, Temporal resolution, Spatial resolution, Scanners, Radiology

Read Abstract +

Showing 5 of 8 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