Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2–4 glioma patients: a deep Radiomics Approach

• Published in: BMC medical imaging Vol. 24; no. 1; pp. 104 - 15
• Main Authors: Yuan, Jialin, Siakallis, Loizos, Li, Hongwei Bran, Brandner, Sebastian, Zhang, Jianguo, Li, Chenming, Mancini, Laura, Bisdas, Sotirios
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 03.05.2024; BioMed Central; BMC
• Subjects: Adult; Aged; Angiogenesis; Anisotropy; Artificial neural networks; Biomarkers; Brain cancer; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - genetics; Central nervous system; Classifiers; Deep neural network; Demographics; Demography; Deoxyribonucleic acid; Diagnostic systems; Diffusion Tensor Imaging - methods; DNA; DTI; Female; Glioma; Glioma - diagnostic imaging; Glioma - genetics; Glioma - pathology; Gliomas; Humans; IDH; Image enhancement; Isocitrate dehydrogenase; Isocitrate Dehydrogenase - genetics; Kurtosis; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical imaging; Middle Aged; Mutation; Mutation status; Neoplasm Grading; Neural networks; Neural Networks, Computer; Neuroimaging; Patients; Performance prediction; Prediction; Predictions; Prognosis; Radiomics; Registration; Research ethics; Retrospective Studies; Sensitivity; Supervised learning; Support Vector Machine; Support vector machines; Tensors; University colleges; CNN; Deep neural network; Mutation status; Supervised learning; Prediction; DTI; SVM; IDH
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-024-01274-9

The role of isocitrate dehydrogenase (IDH) mutation status for glioma stratification and prognosis is established. While structural magnetic resonance image (MRI) is a promising biomarker, it may not be sufficient for non-invasive characterisation of IDH mutation status. We investigated the diagnost...