TY - GEN
T1 - CNN-based hierarchical coarse-to-fine segmentation of pelvic CT images for prostate cancer radiotherapy
AU - Sultana, Sharmin
AU - Robinson, Adam
AU - Song, Daniel Y.
AU - Lee, Junghoon
N1 - Funding Information:
This work was supported by the NIH/NCI under the grant R01CA151395.
Funding Information:
This work was supported by the NIH/NCI under the grant R01CA151395. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU.
Publisher Copyright:
© 2020 SPIE.
PY - 2020
Y1 - 2020
N2 - Accurate segmentation of organs-at-risk is important in prostate cancer radiation therapy planning. However, poor soft tissue contrast in CT makes the segmentation task very challenging. We propose a deep convolutional neural network approach to automatically segment the prostate, bladder, and rectum from pelvic CT. A hierarchical coarse-to-fine segmentation strategy is used where the first step generates a coarse segmentation from which an organ-specific region of interest (ROI) localization map is produced. The second step produces detailed and accurate segmentation of the organs. The ROI localization map is generated using a 3D U-net. The localization map helps adjusting the ROI of each organ that needs to be segmented and hence improves computational efficiency by eliminating irrelevant background information. For the fine segmentation step, we designed a fully convolutional network (FCN) by combining a generative adversarial network (GAN) with a U-net. Specifically, the generator is a 3D U-net that is trained to predict individual pelvic structures, and the discriminator is an FCN which fine-tunes the generator predicted segmentation map by comparing it with the ground truth. The network was trained using 100 CT datasets and tested on 15 datasets to segment the prostate, bladder and rectum. The average Dice similarity (mean±SD) of the prostate, bladder and rectum are 0.90±0.05, 0.96±0.06 and 0.91±0.09, respectively, and Hausdorff distances of these three structures are 5.21±1.17, 4.37±0.56 and 6.11±1.47 (mm), respectively. The proposed method produces accurate and reproducible segmentation of pelvic structures, which can be potentially valuable for prostate cancer radiotherapy treatment planning.
AB - Accurate segmentation of organs-at-risk is important in prostate cancer radiation therapy planning. However, poor soft tissue contrast in CT makes the segmentation task very challenging. We propose a deep convolutional neural network approach to automatically segment the prostate, bladder, and rectum from pelvic CT. A hierarchical coarse-to-fine segmentation strategy is used where the first step generates a coarse segmentation from which an organ-specific region of interest (ROI) localization map is produced. The second step produces detailed and accurate segmentation of the organs. The ROI localization map is generated using a 3D U-net. The localization map helps adjusting the ROI of each organ that needs to be segmented and hence improves computational efficiency by eliminating irrelevant background information. For the fine segmentation step, we designed a fully convolutional network (FCN) by combining a generative adversarial network (GAN) with a U-net. Specifically, the generator is a 3D U-net that is trained to predict individual pelvic structures, and the discriminator is an FCN which fine-tunes the generator predicted segmentation map by comparing it with the ground truth. The network was trained using 100 CT datasets and tested on 15 datasets to segment the prostate, bladder and rectum. The average Dice similarity (mean±SD) of the prostate, bladder and rectum are 0.90±0.05, 0.96±0.06 and 0.91±0.09, respectively, and Hausdorff distances of these three structures are 5.21±1.17, 4.37±0.56 and 6.11±1.47 (mm), respectively. The proposed method produces accurate and reproducible segmentation of pelvic structures, which can be potentially valuable for prostate cancer radiotherapy treatment planning.
KW - CT image
KW - Hierarchical segmentation
KW - Male pelvic organ
KW - Prostate cancer
KW - Radiotherapy
UR - http://www.scopus.com/inward/record.url?scp=85085247615&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085247615&partnerID=8YFLogxK
U2 - 10.1117/12.2549979
DO - 10.1117/12.2549979
M3 - Conference contribution
C2 - 32341620
AN - SCOPUS:85085247615
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Medical Imaging 2020
A2 - Fei, Baowei
A2 - Linte, Cristian A.
PB - SPIE
T2 - Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling
Y2 - 16 February 2020 through 19 February 2020
ER -