TY - GEN
T1 - Identifying patch-level MSI from histological images of Colorectal Cancer by a Knowledge Distillation Model
AU - Ke, Jing
AU - Shen, Yiqing
AU - Wright, Jason D.
AU - Jing, Naifeng
AU - Liang, Xiaoyao
AU - Shen, Dinggang
N1 - Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2020/12/16
Y1 - 2020/12/16
N2 - Microsatellite instability (MSI) is the result of a defective DNA mismatch repair (MMR) system, and its presence occurs in a variety of cancers. The determination of MSI in colorectal cancer (CRC) will have a better prognosis and management of cancer patients. As the routine MSI identification via molecular testing is expensive, time-consuming, and region-restricted, novel methods to detect MSI are of great interest. In this work, we propose a multi-stage convolutional neural network (CNN) based framework to identify MSI status in colorectal cancer patients from histopathological images. A mislabel-aware module is designed to deal with the uncertainty problem in global-local labelling. An auto-grading model is proposed to discriminate patches by the degree of their histopathological correlation with recognizable MSI status, and subsequently aggregate the weights to make slide-level predictions. Our proposed methodology outperforms the existing models in the classification accuracy, and explicitly sorts out patches with representative features. The research outcome has the potential to assist in the interpretation of histopathology as a surrogate for MSI testing and also in the study of recognizable morphology of MSI-H/MSS tumors. Furthermore, this approach can be extended and applied to other cancer types.
AB - Microsatellite instability (MSI) is the result of a defective DNA mismatch repair (MMR) system, and its presence occurs in a variety of cancers. The determination of MSI in colorectal cancer (CRC) will have a better prognosis and management of cancer patients. As the routine MSI identification via molecular testing is expensive, time-consuming, and region-restricted, novel methods to detect MSI are of great interest. In this work, we propose a multi-stage convolutional neural network (CNN) based framework to identify MSI status in colorectal cancer patients from histopathological images. A mislabel-aware module is designed to deal with the uncertainty problem in global-local labelling. An auto-grading model is proposed to discriminate patches by the degree of their histopathological correlation with recognizable MSI status, and subsequently aggregate the weights to make slide-level predictions. Our proposed methodology outperforms the existing models in the classification accuracy, and explicitly sorts out patches with representative features. The research outcome has the potential to assist in the interpretation of histopathology as a surrogate for MSI testing and also in the study of recognizable morphology of MSI-H/MSS tumors. Furthermore, this approach can be extended and applied to other cancer types.
KW - convolutional neural network
KW - deep learning
KW - distillation
KW - Microsatellite instability
UR - http://www.scopus.com/inward/record.url?scp=85100342398&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100342398&partnerID=8YFLogxK
U2 - 10.1109/BIBM49941.2020.9313141
DO - 10.1109/BIBM49941.2020.9313141
M3 - Conference contribution
AN - SCOPUS:85100342398
T3 - Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
SP - 1043
EP - 1046
BT - Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
A2 - Park, Taesung
A2 - Cho, Young-Rae
A2 - Hu, Xiaohua Tony
A2 - Yoo, Illhoi
A2 - Woo, Hyun Goo
A2 - Wang, Jianxin
A2 - Facelli, Julio
A2 - Nam, Seungyoon
A2 - Kang, Mingon
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
Y2 - 16 December 2020 through 19 December 2020
ER -