TY - JOUR
T1 - PSA-Net
T2 - Deep learning–based physician style–aware segmentation network for postoperative prostate cancer clinical target volumes
AU - Balagopal, Anjali
AU - Morgan, Howard
AU - Dohopolski, Michael
AU - Timmerman, Ramsey
AU - Shan, Jie
AU - Heitjan, Daniel F.
AU - Liu, Wei
AU - Nguyen, Dan
AU - Hannan, Raquibul
AU - Garant, Aurelie
AU - Desai, Neil
AU - Jiang, Steve
N1 - Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/11
Y1 - 2021/11
N2 - Purpose: Automatic segmentation of medical images with deep learning (DL) algorithms has proven highly successful in recent times. With most of these automation networks, inter-observer variation is an acknowledged problem that leads to suboptimal results. This problem is even more significant in segmenting postoperative clinical target volumes (CTV) because they lack a macroscopic visible tumor in the image. This study, using postoperative prostate CTV segmentation as the test case, tries to determine 1) whether physician styles are consistent and learnable, 2) whether physician style affects treatment outcome and toxicity, and 3) how to explicitly deal with different physician styles in DL-assisted CTV segmentation to facilitate its clinical acceptance. Methods: A dataset of 373 postoperative prostate cancer patients from UT Southwestern Medical Center was used for this study. We used another 83 patients from Mayo Clinic to validate the developed model and its adaptability. To determine whether physician styles are consistent and learnable, we trained a 3D convolutional neural network classifier to identify which physician had contoured a CTV from just the contour and the corresponding CT scan. Next, we evaluated whether adapting automatic segmentation to specific physician styles would be clinically feasible based on a lack of difference between outcomes. Here, biochemical progression–free survival (BCFS) and grade 3+ genitourinary and gastrointestinal toxicity were estimated with the Kaplan-Meier method and compared between physician styles with the log rank test and subsequently with a multivariate Cox regression. When we found no statistically significant differences in outcome or toxicity between contouring styles, we proposed a concept called physician style–aware (PSA) segmentation by developing an encoder-multidecoder network with perceptual loss to model different physician styles of CTV segmentation. Results: The classification network captured the different physician styles with 87% accuracy. Subsequent outcome analysis showed no differences in BCFS and grade 3+ toxicity among physicians. With the proposed physician style–aware network (PSA-Net), Dice similarity coefficient (DSC) accuracy for all physicians was 3.4% higher on average than with a general model that does not differentiate physician styles. We show that these stylistic contouring variations also exist between institutions that follow the same segmentation guidelines, and we show the proposed method's effectiveness in adapting to new institutional styles. We observed an accuracy improvement of 5% in terms of DSC when adapting to the style of a separate institution. Conclusion: The performance of the classification network established that physician styles are learnable, and the lack of difference between outcomes among physicians shows that the network can feasibly adapt to different styles in the clinic. Therefore, we developed a novel PSA-Net model that can produce contours specific to the treating physician, thus improving segmentation accuracy and avoiding the need to train multiple models to achieve different style segmentations. We successfully validated this model on data from a separate institution, thus supporting the model's generalizability to diverse datasets.
AB - Purpose: Automatic segmentation of medical images with deep learning (DL) algorithms has proven highly successful in recent times. With most of these automation networks, inter-observer variation is an acknowledged problem that leads to suboptimal results. This problem is even more significant in segmenting postoperative clinical target volumes (CTV) because they lack a macroscopic visible tumor in the image. This study, using postoperative prostate CTV segmentation as the test case, tries to determine 1) whether physician styles are consistent and learnable, 2) whether physician style affects treatment outcome and toxicity, and 3) how to explicitly deal with different physician styles in DL-assisted CTV segmentation to facilitate its clinical acceptance. Methods: A dataset of 373 postoperative prostate cancer patients from UT Southwestern Medical Center was used for this study. We used another 83 patients from Mayo Clinic to validate the developed model and its adaptability. To determine whether physician styles are consistent and learnable, we trained a 3D convolutional neural network classifier to identify which physician had contoured a CTV from just the contour and the corresponding CT scan. Next, we evaluated whether adapting automatic segmentation to specific physician styles would be clinically feasible based on a lack of difference between outcomes. Here, biochemical progression–free survival (BCFS) and grade 3+ genitourinary and gastrointestinal toxicity were estimated with the Kaplan-Meier method and compared between physician styles with the log rank test and subsequently with a multivariate Cox regression. When we found no statistically significant differences in outcome or toxicity between contouring styles, we proposed a concept called physician style–aware (PSA) segmentation by developing an encoder-multidecoder network with perceptual loss to model different physician styles of CTV segmentation. Results: The classification network captured the different physician styles with 87% accuracy. Subsequent outcome analysis showed no differences in BCFS and grade 3+ toxicity among physicians. With the proposed physician style–aware network (PSA-Net), Dice similarity coefficient (DSC) accuracy for all physicians was 3.4% higher on average than with a general model that does not differentiate physician styles. We show that these stylistic contouring variations also exist between institutions that follow the same segmentation guidelines, and we show the proposed method's effectiveness in adapting to new institutional styles. We observed an accuracy improvement of 5% in terms of DSC when adapting to the style of a separate institution. Conclusion: The performance of the classification network established that physician styles are learnable, and the lack of difference between outcomes among physicians shows that the network can feasibly adapt to different styles in the clinic. Therefore, we developed a novel PSA-Net model that can produce contours specific to the treating physician, thus improving segmentation accuracy and avoiding the need to train multiple models to achieve different style segmentations. We successfully validated this model on data from a separate institution, thus supporting the model's generalizability to diverse datasets.
KW - Deep learning
KW - Medical image segmentation
KW - Observer variation
KW - Radiation therapy
UR - http://www.scopus.com/inward/record.url?scp=85118112560&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85118112560&partnerID=8YFLogxK
U2 - 10.1016/j.artmed.2021.102195
DO - 10.1016/j.artmed.2021.102195
M3 - Article
C2 - 34763810
AN - SCOPUS:85118112560
SN - 0933-3657
VL - 121
JO - Artificial Intelligence in Medicine
JF - Artificial Intelligence in Medicine
M1 - 102195
ER -