Development of a whole-slide-level segmentation-based dMMR/pMMR deep learning detector for colorectal cancer
Zhou Tong,
Yin Wang,
Xuanwen Bao,
Yu Deng,
Bo Lin,
Ge Su,
Kejun Ye,
Xiaomeng Dai,
Hangyu Zhang,
Lulu Liu,
Wenyu Wang,
Yi Zheng,
Weijia Fang,
Peng Zhao,
Peirong Ding,
Shuiguang Deng,
Xiangming Xu
Affiliations
Zhou Tong
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Yin Wang
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
Xuanwen Bao
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Yu Deng
Department of Pathology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Bo Lin
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; Innovation Centre for Information, Binjiang Institute of Zhejiang University, Hangzhou 310053, China
Ge Su
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
Kejun Ye
Department of Colorectal Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Xiaomeng Dai
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Hangyu Zhang
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Lulu Liu
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Wenyu Wang
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Yi Zheng
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China
Weijia Fang
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China; Zhejiang Provincial Key Laboratory of Pancreatic Disease, Hangzhou 310003, China; Corresponding author
Peng Zhao
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China; Corresponding author
Peirong Ding
Sun Yat-sen University Cancer Center; State Key Laboratory of Oncology in South China; Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, P.R. China; Department of Colorectal Surgery, Sun Yat-sen University Cancer Center, Guangzhou, P.R. China; Corresponding author
Shuiguang Deng
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; Corresponding author
Xiangming Xu
Department of Colorectal Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China; Department of Colorectal Surgery and Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310000, China; Corresponding author
Summary: To investigate whole-slide-level prediction in the field of artificial intelligence identification of dMMR/pMMR from hematoxylin and eosin (H&E) in colorectal cancer (CRC), we established a segmentation-based dMMR/pMMR deep learning detector (SPEED). Our model was approximately 1,700 times faster than that of the classification-based model. For the internal validation cohort, our model yielded an overall AUC of 0.989. For the external validation cohort, the model exhibited a high performance, with an AUC of 0.865. The human‒machine strategy further improved the model performance for external validation by an AUC up to 0.988. Our whole-slide-level prediction model provided an approach for dMMR/pMMR detection from H&E whole slide images with excellent predictive performance and less computer processing time in patients with CRC.
