loading page

Multimodal data integration using deep learning predicts overall survival of patients with glioma
  • +9
  • Yifan Yuan,
  • Xuan Zhang,
  • Yining Wang,
  • Hongyan Li,
  • Zengxin Qi,
  • Zunguo Du,
  • Ying-hua Chu,
  • Danyang Feng,
  • Qingguo Xie,
  • Jianping Song,
  • Yuqing Liu,
  • Jiajun Cai
Yifan Yuan
Huashan Hospital Fudan University
Author Profile
Xuan Zhang
Huazhong University of Science and Technology School of Artificial Intelligence and Automation
Author Profile
Yining Wang
Huashan Hospital Fudan University
Author Profile
Hongyan Li
University of Science and Technology of China School of Information Science and Technology
Author Profile
Zengxin Qi
Huashan Hospital Fudan University
Author Profile
Zunguo Du
Huashan Hospital Fudan University
Author Profile
Ying-hua Chu
Siemens Healthineers China
Author Profile
Danyang Feng
Fudan University Institute of Science and Technology for Brain-inspired Intelligence
Author Profile
Qingguo Xie
Huazhong University of Science and Technology School of Artificial Intelligence and Automation
Author Profile
Jianping Song
Huashan Hospital Fudan University
Author Profile
Yuqing Liu
Hefei Comprehensive National Science Center
Author Profile
Jiajun Cai
Huashan Hospital Fudan University

Corresponding Author:caijiajun1988@126.com

Author Profile

Abstract

Gliomas are highly heterogenous diseases with poor prognosis. Precise survival prediction could benefit further clinical decision-making, clinical trial incursion and health economics. Recent research has emphasized the prognostic value of magnetic resonance imaging, pathological specimens and circulating biomarkers. However, the integrative potential and efficacy of these modalities require to be further validated. After incorporating 218 patients of TCGA glioma datasets of and 54 patients of Huashan cohort with complementary prognostic information, we established Squeeze-and-excitation deep learning feature extractor (SE-DLFE) for T1-contrast enhanced images and histological slides, and explored to screen significant circulating 5-hydroxymethylcytosines (5hmC) profiles for glioma survival by LASSO-Cox regression. Therefore, a prognostication predictive model with high efficiency was obtained through survival support vector machine (SVM) multimodal integration of radiologic imaging, histopathologic imaging features, genome-wide 5hmC in circulating cell-free DNA (cf-DNA) and clinical variables, suggesting a valid strategy (C-index = 0.897; Brier score = 0.118) for improved survival risk stratification of glioma patients.
Submitted to View
05 Feb 2024Reviewer(s) Assigned
08 May 2024Review(s) Completed, Editorial Evaluation Pending
08 May 2024Editorial Decision: Revise Major
17 Jun 20241st Revision Received
19 Jun 2024Assigned to Editor
19 Jun 2024Submission Checks Completed
19 Jun 2024Review(s) Completed, Editorial Evaluation Pending
28 Jun 2024Reviewer(s) Assigned
18 Jul 2024Editorial Decision: Accept