Mr. Vignesh Selvakumaran Profile

Vignesh Selvakumaran

at Duke Univ

SPIE Involvement:

Author

Publications (4)

Proceedings Article | 15 March 2019 Paper

Deep learning of 3D computed tomography (CT) images for organ segmentation using 2D multi-channel SegNet model

Yingzhou Liu, Wanyi Fu, Vignesh Selvakumaran, Matthew Phelan, W. Paul Segars, Ehsan Samei, Maciej Mazurowski, Joseph Lo, Geoffrey Rubin, Ricardo Henao

Proceedings Volume 10954, 109541D (2019) https://doi.org/10.1117/12.2512887

KEYWORDS: Image segmentation, Data modeling, 3D modeling, Computed tomography, Kidney, 3D image processing, Medical imaging, Machine learning

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Classifying abnormalities in computed tomography radiology reports with rule-based and natural language processing models

Songyue Han, James Tian, Mark Kelly, Vignesh Selvakumaran, Ricardo Henao, Geoffrey Rubin, Joseph Lo

Proceedings Volume 10950, 109504H (2019) https://doi.org/10.1117/12.2513577

KEYWORDS: Computed tomography, Lung, Radiology, Machine learning, Rule based systems, Kidney, Liver, Medical imaging, Performance modeling, Data modeling

Read Abstract +

Purpose: When conducting machine learning algorithms on classification and detection of abnormalities for medical imaging, many researchers are faced with the problem that it is hard to get enough labeled data. This is especially difficult for modalities such as computed tomography (CT) with potentially 1000 or more slice images per case. To solve this problem, we plan to use machine learning algorithms to identify abnormalities within existing radiologist reports, thus creating case-level labels that may be used for weakly supervised training on the image data. We used a two-stage procedure to label the CT reports. In the first stage, a rule-based system labeled a smaller set of cases automatically with high accuracy. In the second stage, we developed machine learing algorithms using the labels from the rule-based system and word vectors learned without supervision from unlabeled CT reports. Method: In this study, we used approximately 24,000 CT reports from Duke University Health System. We initially focused on three organs, the lungs, liver/gallbladder, and kidneys. We first developed a rule-based system that can quickly identify certain types of abnormalities within CT reports with high accuracy. For each organ and disease combination, we produced several hundred cases with rule-based labels. These labels were combined with word vectors generated using word2vec from all the unlabeled reports to train two different machine learning algorithms: (a) average of word vectors merged by logistic regression, and (b) recurrent neural network (RNN). Result: Performance was evaluated by receiver operating characteristic (ROC) area under the curve (AUC) over an independent test set of 440 reports for which those organs were manually labeled as normal or abnormal by clinical experts. For lungs, the performance was 0.796 for average word vector and 0.827 for RNN. Liver performance was 0.683 for average word vector and 0.791 for RNN. For kidneys, it was 0.786 for average word vector and 0.928 for RNN. Conclusion: It is possible to label large numbers of cases automatically. These rule-based labels can then be used to build a classification model for large numbers of medical reports. With word2vec and other transfer learning techniques, we can get a good generalization performance.

Proceedings Article | 13 March 2019 Presentation + Paper

Combining deep learning methods and human knowledge to identify abnormalities in computed tomography (CT) reports

Matias Benitez, James Tian, Mark Kelly, Vignesh Selvakumaran, Matthew Phelan, Maciej Mazurowski, Joseph Lo, Geoffrey Rubin, Ricardo Henao

Proceedings Volume 10950, 109500V (2019) https://doi.org/10.1117/12.2512886

KEYWORDS: Computed tomography, Kidney, Lung, Performance modeling, Machine learning, Statistical modeling, Medicine

Read Abstract +

Proceedings Article | 1 March 2019 Paper

Multi-organ segmentation in clinical-computed tomography for patient-specific image quality and dose metrology

Wanyi Fu, Shobhit Sharma, Taylor Smith, Rui Hou, Ehsan Abadi, Vignesh Selvakumaran, Ruixiang Tang, Joseph Lo, W. Paul Segars, Anuj Kapadia, Justin Solomon, Geoffrey Rubin, Ehsan Samei

Proceedings Volume 10948, 1094829 (2019) https://doi.org/10.1117/12.2512883

KEYWORDS: Image segmentation, Image quality, Computed tomography, 3D modeling, Machine learning, Monte Carlo methods, Imaging systems, Safety

Read Abstract +

The purpose of this study was to develop a robust, automated multi-organ segmentation model for clinical adult and pediatric CT and implement the model as part of a patient-specific safety and quality monitoring system. 3D convolutional neural network (Unet) models were setup to segment 30 different organs and structures at the diagnostic image resolution. For each organ, 200 manually-labeled cases were used to train the network, fitting it to different clinical imaging resolutions and contrast enhancement stages. The dataset was randomly shuffled, and divided with 6/2/2 train/validation/test set split. The model was deployed to automatically segment 1200 clinical CT images as a demonstration of the utility of the method. Each case was made into a patient-specific phantom based on the segmentation masks, with unsegmented organs and structures filled in by deforming a template XCAT phantom of similar anatomy. The organ doses were then estimated using a validated scanner-specific MC-GPU package using the actual scan information. The segmented organ information was likewise used to assess contrast, noise, and detectability index within each organ. The neural network segmentation model showed dice similarity coefficients (DSC) above 0.85 for the majority of organs. Notably, the lungs and liver showed a DSC of 0.95 and 0.94, respectively. The segmentation results produced patient-specific dose and quality values across the tested 1200 patients with representative the histogram distributions. The measurements were compared in global-to-organ (e.g. CTDvol vs. liver dose) and organ-to-organ (e.g. liver dose vs. spleen dose) manner. The global-to-organ measurements (liver dose vs. CTDIvol: 𝑅 = 0.62; liver vs. global d’: 𝑅 = 0.78; liver vs. global noise: 𝑅 = 0.55) were less correlated compared to the organ-to-organ measurements (liver vs. spleen dose: 𝑅 = 0.93; liver vs. spleen d’: 𝑅 = 0.82; liver vs. spleen noise: 𝑅 = 0.78). This variation of measurement is more prominent for iterative reconstruction kernel compared to the filtered back projection kernel (liver vs. global noise: 𝑅𝐼𝑅 = 0.47 vs. 𝑅𝐹𝐵𝑃 = 0.75; liver vs. global d’: 𝑅𝐼𝑅 = 0.74 vs. 𝑅𝐹𝐵𝑃 = 0.83). The results can help derive meaningful relationships between image quality, organ doses, and patient attributes.

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