TY - JOUR
T1 - Pathologist-level interpretable whole-slide cancer diagnosis with deep learning
AU - Zhang, Zizhao
AU - Chen, Pingjun
AU - McGough, Mason
AU - Xing, Fuyong
AU - Wang, Chunbao
AU - Bui, Marilyn
AU - Xie, Yuanpu
AU - Sapkota, Manish
AU - Cui, Lei
AU - Dhillon, Jasreman
AU - Ahmad, Nazeel
AU - Khalil, Farah K.
AU - Dickinson, Shohreh I.
AU - Shi, Xiaoshuang
AU - Liu, Fujun
AU - Su, Hai
AU - Cai, Jinzheng
AU - Yang, Lin
N1 - Publisher Copyright:
© 2019, The Author(s), under exclusive licence to Springer Nature Limited.
PY - 2019/5/1
Y1 - 2019/5/1
N2 - Diagnostic pathology is the foundation and gold standard for identifying carcinomas. However, high inter-observer variability substantially affects productivity in routine pathology and is especially ubiquitous in diagnostician-deficient medical centres. Despite rapid growth in computer-aided diagnosis (CAD), the application of whole-slide pathology diagnosis remains impractical. Here, we present a novel pathology whole-slide diagnosis method, powered by artificial intelligence, to address the lack of interpretable diagnosis. The proposed method masters the ability to automate the human-like diagnostic reasoning process and translate gigapixels directly to a series of interpretable predictions, providing second opinions and thereby encouraging consensus in clinics. Moreover, using 913 collected examples of whole-slide data representing patients with bladder cancer, we show that our method matches the performance of 17 pathologists in the diagnosis of urothelial carcinoma. We believe that our method provides an innovative and reliable means for making diagnostic suggestions and can be deployed at low cost as next-generation, artificial intelligence-enhanced CAD technology for use in diagnostic pathology.
AB - Diagnostic pathology is the foundation and gold standard for identifying carcinomas. However, high inter-observer variability substantially affects productivity in routine pathology and is especially ubiquitous in diagnostician-deficient medical centres. Despite rapid growth in computer-aided diagnosis (CAD), the application of whole-slide pathology diagnosis remains impractical. Here, we present a novel pathology whole-slide diagnosis method, powered by artificial intelligence, to address the lack of interpretable diagnosis. The proposed method masters the ability to automate the human-like diagnostic reasoning process and translate gigapixels directly to a series of interpretable predictions, providing second opinions and thereby encouraging consensus in clinics. Moreover, using 913 collected examples of whole-slide data representing patients with bladder cancer, we show that our method matches the performance of 17 pathologists in the diagnosis of urothelial carcinoma. We believe that our method provides an innovative and reliable means for making diagnostic suggestions and can be deployed at low cost as next-generation, artificial intelligence-enhanced CAD technology for use in diagnostic pathology.
UR - http://www.scopus.com/inward/record.url?scp=85072258127&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072258127&partnerID=8YFLogxK
U2 - 10.1038/s42256-019-0052-1
DO - 10.1038/s42256-019-0052-1
M3 - Article
AN - SCOPUS:85072258127
SN - 2522-5839
VL - 1
SP - 236
EP - 245
JO - Nature Machine Intelligence
JF - Nature Machine Intelligence
IS - 5
ER -