A multi-center performance assessment for automated histopathological classification and grading of glioma using whole slide images

Lei Jin; Tianyang Sun; Xi Liu; Zehong Cao; Yan Liu; Hong Chen; Yixin Ma; Jun Zhang; Yaping Zou; Yingchao Liu; Feng Shi; Dinggang Shen; Jinsong Wu

doi:10.1016/j.isci.2023.108041

A multi-center performance assessment for automated histopathological classification and grading of glioma using whole slide images

iScience. 2023 Sep 29;26(11):108041. doi: 10.1016/j.isci.2023.108041. eCollection 2023 Nov 17.

Authors

Lei Jin^{1

2}, Tianyang Sun³, Xi Liu^{1

2}, Zehong Cao³, Yan Liu^{1

2}, Hong Chen^{2

4}, Yixin Ma^{1

2}, Jun Zhang⁵, Yaping Zou⁵, Yingchao Liu⁶, Feng Shi³, Dinggang Shen^{3

7

8}, Jinsong Wu^{1

2}

Affiliations

¹ Glioma Surgery Division, Neurologic Surgery Department, Huashan Hospital Fudan University, Shanghai 200040, China.
² National Center for Neurological Disorders, Huashan Hospital Fudan University, Shanghai 200040, China.
³ Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd, Shanghai 200030, China.
⁴ Department of Pathology, Huashan Hospital Fudan University, Shanghai 200040, China.
⁵ Wuhan Zhongji Biotechnology Co., Ltd, Wuhan 430206, China.
⁶ Department of Neurosurgery, The Provincial Hospital Affiliated to Shandong First Medical University, Shandong 250021, China.
⁷ School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China.
⁸ Shanghai Clinical Research and Trial Center, Shanghai 201210, China.

Abstract

Accurate pathological classification and grading of gliomas is crucial in clinical diagnosis and treatment. The application of deep learning techniques holds promise for automated histological pathology diagnosis. In this study, we collected 733 whole slide images from four medical centers, of which 456 were used for model training, 150 for internal validation, and 127 for multi-center testing. The study includes 5 types of common gliomas. A subtask-guided multi-instance learning image-to-label training pipeline was employed. The pipeline leveraged "patch prompting" for the model to converge with reasonable computational cost. Experiments showed that an overall accuracy of 0.79 in the internal validation dataset. The performance on the multi-center testing dataset showed an overall accuracy to 0.73. The findings suggest a minor yet acceptable performance decrease in multi-center data, demonstrating the model's strong generalizability and establishing a robust foundation for future clinical applications.

Keywords: Cancer; Computational bioinformatics; Health informatics; Pathology.