TY - JOUR
T1 - A self-supervised contrastive learning approach for whole slide image representation in digital pathology
AU - Fashi, Parsa Ashrafi
AU - Hemati, Sobhan
AU - Babaie, Morteza
AU - Gonzalez, Ricardo
AU - Tizhoosh, H. R.
N1 - Publisher Copyright:
© 2022 The Authors
PY - 2022/1
Y1 - 2022/1
N2 - Image analysis in digital pathology has proven to be one of the most challenging fields in medical imaging for AI-driven classification and search tasks. Due to their gigapixel dimensions, whole slide images (WSIs) are difficult to represent for computational pathology. Self-supervised learning (SSL) has recently demonstrated excellent performance in learning effective representations on pretext objectives, which may improve the generalizations of downstream tasks. Previous self-supervised representation methods rely on patch selection and classification such that the effect of SSL on end-to-end WSI representation is not investigated. In contrast to existing augmentation-based SSL methods, this paper proposes a novel self-supervised learning scheme based on the available primary site information. We also design a fully supervised contrastive learning setup to increase the robustness of the representations for WSI classification and search for both pretext and downstream tasks. We trained and evaluated the model on more than 6000 WSIs from The Cancer Genome Atlas (TCGA) repository provided by the National Cancer Institute. The proposed architecture achieved excellent results on most primary sites and cancer subtypes. We also achieved the best result on validation on a lung cancer classification task.
AB - Image analysis in digital pathology has proven to be one of the most challenging fields in medical imaging for AI-driven classification and search tasks. Due to their gigapixel dimensions, whole slide images (WSIs) are difficult to represent for computational pathology. Self-supervised learning (SSL) has recently demonstrated excellent performance in learning effective representations on pretext objectives, which may improve the generalizations of downstream tasks. Previous self-supervised representation methods rely on patch selection and classification such that the effect of SSL on end-to-end WSI representation is not investigated. In contrast to existing augmentation-based SSL methods, this paper proposes a novel self-supervised learning scheme based on the available primary site information. We also design a fully supervised contrastive learning setup to increase the robustness of the representations for WSI classification and search for both pretext and downstream tasks. We trained and evaluated the model on more than 6000 WSIs from The Cancer Genome Atlas (TCGA) repository provided by the National Cancer Institute. The proposed architecture achieved excellent results on most primary sites and cancer subtypes. We also achieved the best result on validation on a lung cancer classification task.
KW - Computational pathology
KW - Digital pathology
KW - Image search
KW - Multiple instance learning
KW - Representation learning
KW - Self-supervised learning
KW - Supervised contrastive learning
UR - http://www.scopus.com/inward/record.url?scp=85140238987&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85140238987&partnerID=8YFLogxK
U2 - 10.1016/j.jpi.2022.100133
DO - 10.1016/j.jpi.2022.100133
M3 - Article
AN - SCOPUS:85140238987
SN - 2229-5089
VL - 13
JO - Journal of Pathology Informatics
JF - Journal of Pathology Informatics
M1 - 100133
ER -