Vision transformer-based weakly supervised histopathological image analysis of primary brain tumors

• Published in: iScience 2023-01, Vol.26 (1), p.105872-105872, Article 105872
• Main Authors: Li, Zhongxiao, Cong, Yuwei, Chen, Xin, Qi, Jiping, Sun, Jingxian, Yan, Tao, Yang, He, Liu, Junsi, Lu, Enzhou, Wang, Lixiang, Li, Jiafeng, Hu, Hong, Zhang, Cheng, Yang, Quan, Yao, Jiawei, Yao, Penglei, Jiang, Qiuyi, Liu, Wenwu, Song, Jiangning, Carin, Lawrence, Chen, Yupeng, Zhao, Shiguang, Gao, Xin
• Format: Article
• Language: English
• Subjects: Cancer; Machine learning; Pathology
• ISSN: 2589-0042; 2589-0042
• DOI: 10.1016/j.isci.2022.105872

Diagnosis of primary brain tumors relies heavily on histopathology. Although various computational pathology methods have been developed for automated diagnosis of primary brain tumors, they usually require neuropathologists’ annotation of region of interests or selection of image patches on whole-slide images (WSI). We developed an end-to-end Vision Transformer (ViT) – based deep learning architecture for brain tumor WSI analysis, yielding a highly interpretable deep-learning model, ViT-WSI. Based on the principle of weakly supervised machine learning, ViT-WSI accomplishes the task of major primary brain tumor type and subtype classification. Using a systematic gradient-based attribution analysis procedure, ViT-WSI can discover diagnostic histopathological features for primary brain tumors. Furthermore, we demonstrated that ViT-WSI has high predictive power of inferring the status of three diagnostic glioma molecular markers, IDH1 mutation, p53 mutation, and MGMT methylation, directly from H&E-stained histopathological images, with patient level AUC scores of 0.960, 0.874, and 0.845, respectively. [Display omitted] •ViT-WSI, is suitable for weakly supervised learning on histopathological images•ViT-WSI performs tumor typing, subtyping and molecular marker prediction•ViT-WSI automatically discovers brain tumor histological features Pathology; Cancer; Machine learning