Authors
Jing Yan, Yuanshen Zhao, Yinsheng Chen, Weiwei Wang, Wenchao Duan, Li Wang, Shenghai Zhang, Tianqing Ding, Lei Liu, Qiuchang Sun, Dongling Pei, Yunbo Zhan, Haibiao Zhao, Tao Sun, Chen Sun, Wenqing Wang, Zhen Liu, Xuanke Hong, Xiangxiang Wang, Yu Guo, Wencai Li, Jingliang Cheng, Xianzhi Liu, Xiaofei Lv, Zhi-Cheng Li, Zhenyu Zhang
Publication date
2021/10/1
Journal
EBioMedicine
Volume
72
Publisher
Elsevier
Description
Background
To develop and validate a deep learning signature (DLS) from diffusion tensor imaging (DTI) for predicting overall survival in patients with infiltrative gliomas, and to investigate the biological pathways underlying the developed DLS.
Methods
The DLS was developed based on a deep learning cohort (n = 688). The key pathways underlying the DLS were identified on a radiogenomics cohort with paired DTI and RNA-seq data (n=78), where the prognostic value of the pathway genes was validated in public databases (TCGA, n = 663; CGGA, n = 657).
Findings
The DLS was associated with survival (log-rank P < 0.001) and was an independent predictor (P < 0.001). Incorporating the DLS into existing risk system resulted in a deep learning nomogram predicting survival better than either the DLS or the clinicomolecular nomogram alone, with a better calibration and classification accuracy (net reclassification …
Total citations
Scholar articles
J Yan, Y Zhao, Y Chen, W Wang, W Duan, L Wang… - EBioMedicine, 2021