Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities
| العنوان: | Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities |
|---|---|
| المؤلفون: | Xiangxiang Wang, Tianqing Ding, Wencai Li, Xuanke Hong, Yinsheng Chen, Li Wang, Wenchao Duan, Dongling Pei, Chen Sun, Jing Yan, Shenghai Zhang, Weiwei Wang, Zhen-Yu Zhang, Yunbo Zhan, Zhicheng Li, Zhen Liu, Jingliang Cheng, Yu Guo, Xianzhi Liu, Lei Liu, Yuanshen Zhao, Wenqing Wang, Haibiao Zhao, Xiaofei Lv, Qiuchang Sun, Tao Sun |
| المصدر: | EBioMedicine EBioMedicine, Vol 72, Iss, Pp 103583-(2021) |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Oncology, Male, AIC, Akaike information criterion, Medicine (General), CNN, convolutional neural networks, DEGs, differentially expressing genes, GSVA, gene set variation analysis, Cohort Studies, Risk Factors, M,D, mean diffusivity, FA, fractional anisotropy, NBTSC, neuron-to-brain tumor synaptic communication, Glutamate secretion, Brain Neoplasms, General Medicine, Glioma, Middle Aged, Prognosis, RD, radial diffusivity, Diffusion tensor imaging, Cohort, Medicine, Female, DLS, deep learning signature, AD, axial diffusivity, Signal Transduction, Research Paper, Adult, TCIA, The Cancer Imaging Archive, medicine.medical_specialty, Adolescent, FDR, false discovery rate, Radiogenomics, CAM, Class activation map, KEGG, Kyoto Encyclopedia of Genes and Genomes, General Biochemistry, Genetics and Molecular Biology, WHO, World Health Organization, Young Adult, R5-920, Deep Learning, Internal medicine, Fractional anisotropy, GO, Gene Ontology, medicine, Humans, KEGG, Aged, LGG, lower-grade gliomas, business.industry, GSA, Genome Sequence Archive, technology, industry, and agriculture, RNA-seq, RNA sequencing, Nomogram, medicine.disease, HR, hazard ratio, NRI, net reclassification improvement, CI, confidence interval, CGGA, China Cancer Genome Atlas, GBM, glioblastoma, TCGA, The Cancer Genome Atlas, DTI, diffusion tensor imaging, business, Diffusion MRI, Pathway |
| الوصف: | 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. |
| تدمد: | 2352-3964 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af9b054c5ef9229827f3e793a4fae647Test https://pubmed.ncbi.nlm.nih.gov/34563923Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....af9b054c5ef9229827f3e793a4fae647 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 23523964 |
|---|