TY - GEN
T1 - Weakly Supervised Prostate Tma Classification Via Graph Convolutional Networks
AU - Wang, Jingwen
AU - Chen, Richard J.
AU - Lu, Ming Y.
AU - Baras, Alexander
AU - Mahmood, Faisal
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/4
Y1 - 2020/4
N2 - Histology-based grade classification is clinically important for many cancer types in stratifying patients into distinct treatment groups. In prostate cancer, the Gleason score is a grading system used to measure the aggressiveness of prostate cancer from the spatial organization of cells and the distribution of glands. However, the subjective interpretation of Glea-son score often suffers from large interobserver and intraob-server variability. Previous work in deep learning-based objective Gleason grading requires manual pixel-level annotation. In this work, we propose a weakly-supervised approach for grade classification in tissue micro-arrays (TMA) using graph convolutional networks (GCNs), in which we model the spatial organization of cells as a graph to better capture the proliferation and community structure of tumor cells. We learn the morphometry of each cell using a contrastive predictive coding (CPC)-based self-supervised approach. Using five-fold cross-validation we demonstrate that our method can achieve a 0.9637 ± 0.0131 AUC using only TMA-level labels. Our method also demonstrates a 36.36% improvement in AUC over standard GCNs with texture features and a 15.48% improvement over GCNs with VGG19 features. Our proposed pipeline can be used to objectively stratify low and high-risk cases, reducing inter- and intra-observer variability and pathologist workload.
AB - Histology-based grade classification is clinically important for many cancer types in stratifying patients into distinct treatment groups. In prostate cancer, the Gleason score is a grading system used to measure the aggressiveness of prostate cancer from the spatial organization of cells and the distribution of glands. However, the subjective interpretation of Glea-son score often suffers from large interobserver and intraob-server variability. Previous work in deep learning-based objective Gleason grading requires manual pixel-level annotation. In this work, we propose a weakly-supervised approach for grade classification in tissue micro-arrays (TMA) using graph convolutional networks (GCNs), in which we model the spatial organization of cells as a graph to better capture the proliferation and community structure of tumor cells. We learn the morphometry of each cell using a contrastive predictive coding (CPC)-based self-supervised approach. Using five-fold cross-validation we demonstrate that our method can achieve a 0.9637 ± 0.0131 AUC using only TMA-level labels. Our method also demonstrates a 36.36% improvement in AUC over standard GCNs with texture features and a 15.48% improvement over GCNs with VGG19 features. Our proposed pipeline can be used to objectively stratify low and high-risk cases, reducing inter- and intra-observer variability and pathologist workload.
KW - Deep Learning
KW - Gleason Score Grading
KW - Graph Convolutional Networks
KW - Histopathology Calassification
KW - Objective Grading
KW - Patient Stratification
UR - http://www.scopus.com/inward/record.url?scp=85085866639&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085866639&partnerID=8YFLogxK
U2 - 10.1109/ISBI45749.2020.9098534
DO - 10.1109/ISBI45749.2020.9098534
M3 - Conference contribution
AN - SCOPUS:85085866639
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 239
EP - 243
BT - ISBI 2020 - 2020 IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
T2 - 17th IEEE International Symposium on Biomedical Imaging, ISBI 2020
Y2 - 3 April 2020 through 7 April 2020
ER -