IDH-mutant glioma risk stratification via whole slide images: Identifying pathological feature associations

Xiaotao Wang; Zilong Wang; Weiwei Wang; Zaoqu Liu; Zeyu Ma; Yang Guo; Dingyuan Su; Qiuchang Sun; Dongling Pei; Wenchao Duan; Yuning Qiu; Minkai Wang; Yongqiang Yang; Wenyuan Li; Haoran Liu; Caoyuan Ma; Miaomiao Yu; Yinhui Yu; Te Chen; Jing Fu; Sen Li; Bin Yu; Yuchen Ji; Wencai Li; Dongming Yan; Xianzhi Liu; Zhi-Cheng Li; Zhenyu Zhang

doi:10.1016/j.isci.2024.111605

IDH-mutant glioma risk stratification via whole slide images: Identifying pathological feature associations

iScience. 2024 Dec 16;28(1):111605. doi: 10.1016/j.isci.2024.111605. eCollection 2025 Jan 17.

Authors

Xiaotao Wang¹, Zilong Wang¹, Weiwei Wang², Zaoqu Liu³, Zeyu Ma¹, Yang Guo⁴, Dingyuan Su¹, Qiuchang Sun⁵, Dongling Pei¹, Wenchao Duan¹, Yuning Qiu¹, Minkai Wang¹, Yongqiang Yang¹, Wenyuan Li¹, Haoran Liu¹, Caoyuan Ma¹, Miaomiao Yu¹, Yinhui Yu¹, Te Chen¹, Jing Fu¹, Sen Li¹, Bin Yu¹, Yuchen Ji¹, Wencai Li², Dongming Yan¹, Xianzhi Liu¹, Zhi-Cheng Li^{5

6}, Zhenyu Zhang¹

Affiliations

¹ Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
² Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
³ Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China.
⁴ Department of Neurosurgery, Henan Provincial People's Hospital, Zhengzhou, Henan, China.
⁵ Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
⁶ The Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, Shenzhen, China.

Abstract

This article aims to develop and validate a pathological prognostic model for predicting prognosis in patients with isocitrate dehydrogenase (IDH)-mutant gliomas and reveal the biological underpinning of the prognostic pathological features. The pathomic model was constructed based on whole slide images (WSIs) from a training set (N = 486) and evaluated on internal validation set (N = 209), HPPH validation set (N = 54), and TCGA validation set (N = 352). Biological implications of PathScore and individual pathomic features were identified by pathogenomics set (N = 100). The WSI-based pathological signature was an independent prognostic factor. Incorporating the pathological features into a clinical model resulted in a pathological-clinical model that predicted survival better than either the pathological model or clinical model alone. Ten categories of pathways (metabolism, proliferation, immunity, DNA damage response, disease, migrate, protein modification, synapse, transcription and translation, and complex cellular functions) were significantly correlated with the WSI-based pathological features.

Keywords: Bioinformatics; Cancer; Medical imaging.