Nature Communications (Oct 2023)
Neuropathologist-level integrated classification of adult-type diffuse gliomas using deep learning from whole-slide pathological images
- Weiwei Wang,
- Yuanshen Zhao,
- Lianghong Teng,
- Jing Yan,
- Yang Guo,
- Yuning Qiu,
- Yuchen Ji,
- Bin Yu,
- Dongling Pei,
- Wenchao Duan,
- Minkai Wang,
- Li Wang,
- Jingxian Duan,
- Qiuchang Sun,
- Shengnan Wang,
- Huanli Duan,
- Chen Sun,
- Yu Guo,
- Lin Luo,
- Zhixuan Guo,
- Fangzhan Guan,
- Zilong Wang,
- Aoqi Xing,
- Zhongyi Liu,
- Hongyan Zhang,
- Li Cui,
- Lan Zhang,
- Guozhong Jiang,
- Dongming Yan,
- Xianzhi Liu,
- Hairong Zheng,
- Dong Liang,
- Wencai Li,
- Zhi-Cheng Li,
- Zhenyu Zhang
Affiliations
- Weiwei Wang
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University
- Yuanshen Zhao
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
- Lianghong Teng
- Department of Pathology, Xuanwu Hospital, Capital Medical University
- Jing Yan
- Department of MRI, The First Affiliated Hospital of Zhengzhou University
- Yang Guo
- Department of Neurosurgery, Henan Provincial People’s Hospital
- Yuning Qiu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Yuchen Ji
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Bin Yu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Dongling Pei
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Wenchao Duan
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Minkai Wang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Li Wang
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University
- Jingxian Duan
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
- Qiuchang Sun
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
- Shengnan Wang
- Department of Pathology, Xuanwu Hospital, Capital Medical University
- Huanli Duan
- Department of Pathology, Xuanwu Hospital, Capital Medical University
- Chen Sun
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Yu Guo
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Lin Luo
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Zhixuan Guo
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Fangzhan Guan
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Zilong Wang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Aoqi Xing
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Zhongyi Liu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Hongyan Zhang
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University
- Li Cui
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University
- Lan Zhang
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University
- Guozhong Jiang
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University
- Dongming Yan
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Xianzhi Liu
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- Hairong Zheng
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
- Dong Liang
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
- Wencai Li
- Department of Pathology, The First Affiliated Hospital of Zhengzhou University
- Zhi-Cheng Li
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
- Zhenyu Zhang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University
- DOI
- https://doi.org/10.1038/s41467-023-41195-9
- Journal volume & issue
-
Vol. 14,
no. 1
pp. 1 – 11
Abstract
Abstract Current diagnosis of glioma types requires combining both histological features and molecular characteristics, which is an expensive and time-consuming procedure. Determining the tumor types directly from whole-slide images (WSIs) is of great value for glioma diagnosis. This study presents an integrated diagnosis model for automatic classification of diffuse gliomas from annotation-free standard WSIs. Our model is developed on a training cohort (n = 1362) and a validation cohort (n = 340), and tested on an internal testing cohort (n = 289) and two external cohorts (n = 305 and 328, respectively). The model can learn imaging features containing both pathological morphology and underlying biological clues to achieve the integrated diagnosis. Our model achieves high performance with area under receiver operator curve all above 0.90 in classifying major tumor types, in identifying tumor grades within type, and especially in distinguishing tumor genotypes with shared histological features. This integrated diagnosis model has the potential to be used in clinical scenarios for automated and unbiased classification of adult-type diffuse gliomas.
