Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities
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
Affiliations
Jing Yan
Department of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China; Glioma Multidisciplinary Research Group, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Yuanshen Zhao
Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
Yinsheng Chen
Department of Neurosurgery/Neuro-oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China
Weiwei Wang
Glioma Multidisciplinary Research Group, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China; Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Wenchao Duan
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Li Wang
Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Shenghai Zhang
Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
Tianqing Ding
Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
Lei Liu
Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
Qiuchang Sun
Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
Dongling Pei
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Yunbo Zhan
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Haibiao Zhao
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Tao Sun
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Chen Sun
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Wenqing Wang
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Zhen Liu
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Xuanke Hong
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Xiangxiang Wang
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Yu Guo
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Wencai Li
Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Jingliang Cheng
Department of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Xianzhi Liu
Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
Xiaofei Lv
Department of Medical Imaging, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China; Corresponding authors at: Department of Neurosurgery, First Affiliated Hospital of Zhengzhou University, Jian she Dong Road 1, Zhengzhou, Henan, 450052, China; Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China; Department of Medical Imaging, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, 651 Dongfeng Road East, Guangzhou, Guangdong, 510060, China.
Zhi-Cheng Li
Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China; National Innovation Center for Advanced Medical Devices, Shenzhen, China; Corresponding authors at: Department of Neurosurgery, First Affiliated Hospital of Zhengzhou University, Jian she Dong Road 1, Zhengzhou, Henan, 450052, China; Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China; Department of Medical Imaging, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, 651 Dongfeng Road East, Guangzhou, Guangdong, 510060, China.
Zhenyu Zhang
Glioma Multidisciplinary Research Group, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China; Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China; Corresponding authors at: Department of Neurosurgery, First Affiliated Hospital of Zhengzhou University, Jian she Dong Road 1, Zhengzhou, Henan, 450052, China; Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China; Department of Medical Imaging, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, 651 Dongfeng Road East, Guangzhou, Guangdong, 510060, China.
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 improvement 0.646, P < 0.001). Five kinds of pathways (synaptic transmission, calcium signaling, glutamate secretion, axon guidance, and glioma pathways) were significantly correlated with the DLS. Average expression value of pathway genes showed prognostic significance in our radiogenomics cohort and TCGA/CGGA cohorts (log-rank P < 0.05). Interpretation: DTI-derived DLS can improve glioma stratification by identifying risk groups with dysregulated biological pathways that contributed to survival outcomes. Therapies inhibiting neuron-to-brain tumor synaptic communication may be more effective in high-risk glioma defined by DTI-derived DLS. Funding: A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.
