iScience (Jan 2023)
Vision transformer-based weakly supervised histopathological image analysis of primary brain tumors
- Zhongxiao Li,
- Yuwei Cong,
- Xin Chen,
- Jiping Qi,
- Jingxian Sun,
- Tao Yan,
- He Yang,
- Junsi Liu,
- Enzhou Lu,
- Lixiang Wang,
- Jiafeng Li,
- Hong Hu,
- Cheng Zhang,
- Quan Yang,
- Jiawei Yao,
- Penglei Yao,
- Qiuyi Jiang,
- Wenwu Liu,
- Jiangning Song,
- Lawrence Carin,
- Yupeng Chen,
- Shiguang Zhao,
- Xin Gao
Affiliations
- Zhongxiao Li
- Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Kingdom of Saudi Arabia; KAUST Computational Bioscience Research Center (CBRC), King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Kingdom of Saudi Arabia
- Yuwei Cong
- Department of Pathology, The First Affiliated Hospital of Harbin Medical University, 23 Youzheng Street, Nangang District, Harbin 150001, People’s Republic of China
- Xin Chen
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Jiping Qi
- Department of Pathology, The First Affiliated Hospital of Harbin Medical University, 23 Youzheng Street, Nangang District, Harbin 150001, People’s Republic of China; Corresponding author
- Jingxian Sun
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Tao Yan
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- He Yang
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Junsi Liu
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Enzhou Lu
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Lixiang Wang
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Jiafeng Li
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Hong Hu
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Cheng Zhang
- Suffolk University, Boston, MA, USA
- Quan Yang
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Jiawei Yao
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Penglei Yao
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Qiuyi Jiang
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Wenwu Liu
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China
- Jiangning Song
- Biomedicine Discovery Institute and Department of Biochemistry and Molecular Biology, Monash University, Melbourne, VIC 3800, Australia; Monash Data Futures Institute, Monash University, Melbourne, VIC 3800, Australia
- Lawrence Carin
- Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Kingdom of Saudi Arabia; Corresponding author
- Yupeng Chen
- School of Microelectronics, Southern University of Science and Technology, Shenzhen 518055, PR China; Corresponding author
- Shiguang Zhao
- Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province 150001, China; Department of Neurosurgery, Shenzhen University General Hospital, Shenzhen, Guangdong Province 518100, China; Corresponding author
- Xin Gao
- Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Kingdom of Saudi Arabia; KAUST Computational Bioscience Research Center (CBRC), King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Kingdom of Saudi Arabia; Corresponding author
- Journal volume & issue
-
Vol. 26,
no. 1
p. 105872
Abstract
Summary: 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.
