TY - GEN
T1 - Deep learning of 3D computed tomography (CT) images for organ segmentation using 2D multi-channel SegNet model
AU - Liu, Yingzhou
AU - Fu, Wanyi
AU - Selvakumaran, Vignesh
AU - Phelan, Matthew
AU - Segars, W. Paul
AU - Samei, Ehsan
AU - Mazurowski, Maciej
AU - Lo, Joseph Y.
AU - Rubin, Geoffrey D.
AU - Henao, Ricardo
N1 - Funding Information:
UL1TR002553. The Duke PACE is supported by Duke’s Clinical and Translational Science Award (CTSA) grant (UL1TR002553) and by Duke University Health System. We thank Duke Research Computing for the use of the Duke Compute Cluster for high-throughput computation. The Duke Data Commons storage is supported by the National Institutes of Health (1S10OD018164-01).
Funding Information:
This work was supported by the Duke Forge. Health Data Science at Duke is supported by the Center for Advancing Translational Sciences of the National Institutes of Health under Award Number
Publisher Copyright:
© 2019 SPIE.
PY - 2019
Y1 - 2019
N2 - Purpose To accurately segment organs from 3D CT image volumes using a 2D, multi-channel SegNet model consisting of a deep Convolutional Neural Network (CNN) encoder-decoder architecture. Method We trained a SegNet model on the extended cardiac-Torso (XCAT) dataset, which was previously constructed based on patient Chest-Abdomen-Pelvis (CAP) Computed Tomography (CT) studies from 50 Duke patients. Each study consists of one low-resolution (5-mm section thickness) 3D CT image volume and its corresponding 3D, manually labeled volume. To improve modeling on such small sample size regime, we performed median frequency class balancing weighting in the loss function of the SegNet, data normalization adjusting for intensity coverage of CT volumes, data transformation to harmonize voxel resolution, CT section extrapolation to virtually increase the number of transverse sections available as inputs to the 2D multi-channel model, and data augmentation to simulate mildly rotated volumes. To assess model performance, we calculated Dice coefficients on a held-out test set, as well as qualitative evaluation of segmentation on high-resolution CTs. Further, we incorporated 50 patients high-resolution CTs with manually-labeled kidney segmentation masks for the purpose of quantitatively evaluating the performance of our XCAT trained segmentation model. The entire study was conducted from raw, identifiable data within the Duke Protected Analytics Computing Environment (PACE). Result We achieved median Dice coefficients over 0.8 for most organs and structures on XCAT test instances and observed good performance on additional images without manual segmentation labels, qualitatively evaluated by Duke Radiology experts. Moreover, we achieved 0.89 median Dice Coefficients for kidneys on high-resolution CTs. Conclusion 2D, multi-channel models like SegNet are effective for organ segmentations of 3D CT image volumes, achieving high segmentation accuracies.
AB - Purpose To accurately segment organs from 3D CT image volumes using a 2D, multi-channel SegNet model consisting of a deep Convolutional Neural Network (CNN) encoder-decoder architecture. Method We trained a SegNet model on the extended cardiac-Torso (XCAT) dataset, which was previously constructed based on patient Chest-Abdomen-Pelvis (CAP) Computed Tomography (CT) studies from 50 Duke patients. Each study consists of one low-resolution (5-mm section thickness) 3D CT image volume and its corresponding 3D, manually labeled volume. To improve modeling on such small sample size regime, we performed median frequency class balancing weighting in the loss function of the SegNet, data normalization adjusting for intensity coverage of CT volumes, data transformation to harmonize voxel resolution, CT section extrapolation to virtually increase the number of transverse sections available as inputs to the 2D multi-channel model, and data augmentation to simulate mildly rotated volumes. To assess model performance, we calculated Dice coefficients on a held-out test set, as well as qualitative evaluation of segmentation on high-resolution CTs. Further, we incorporated 50 patients high-resolution CTs with manually-labeled kidney segmentation masks for the purpose of quantitatively evaluating the performance of our XCAT trained segmentation model. The entire study was conducted from raw, identifiable data within the Duke Protected Analytics Computing Environment (PACE). Result We achieved median Dice coefficients over 0.8 for most organs and structures on XCAT test instances and observed good performance on additional images without manual segmentation labels, qualitatively evaluated by Duke Radiology experts. Moreover, we achieved 0.89 median Dice Coefficients for kidneys on high-resolution CTs. Conclusion 2D, multi-channel models like SegNet are effective for organ segmentations of 3D CT image volumes, achieving high segmentation accuracies.
KW - Deep Learning
KW - Dice Coefficient
KW - Kidneys
KW - PACE
KW - SegNet
KW - XCAT
UR - http://www.scopus.com/inward/record.url?scp=85068580950&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068580950&partnerID=8YFLogxK
U2 - 10.1117/12.2512887
DO - 10.1117/12.2512887
M3 - Conference contribution
AN - SCOPUS:85068580950
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2019
A2 - Chen, Po-Hao
A2 - Bak, Peter R.
PB - SPIE
T2 - Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications
Y2 - 17 February 2019 through 18 February 2019
ER -