Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach

• Published in: BioMed research international Vol. 2021; no. 1; p. 1235314
• Main Authors: Cao, Mengqiu, Suo, Shiteng, Zhang, Xiao, Wang, Xiaoqing, Xu, Jianrong, Yang, Wei, Zhou, Yan
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2021; John Wiley & Sons, Inc
• Subjects: Adolescent; Adult; Age; Aged; Biomarkers; Brain cancer; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - genetics; Brain Neoplasms - pathology; Care and treatment; Decision making; Decision Support Systems, Clinical; Decision trees; Diagnosis; Diffusion coefficient; Feature extraction; Feature selection; Female; Gene mutations; Genotype; Genotypes; Glioma; Glioma - diagnostic imaging; Glioma - genetics; Glioma - pathology; Gliomas; Histograms; Histology; Humans; Image Processing, Computer-Assisted - methods; Isocitrate dehydrogenase; Isocitrate Dehydrogenase - genetics; Learning algorithms; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical prognosis; Methods; Middle Aged; Mutation; Necrosis; Patients; Performance prediction; Predictions; Qualitative analysis; Qualitative research; Radiomics; Redundancy; Retrospective Studies; Risk factors; Software; Statistical methods; Substantia alba; Tumors; Young Adult; Taiwan; United States > US
• ISSN: 2314-6133; 2314-6141; 2314-6141
• DOI: 10.1155/2021/1235314

Purpose. Preoperative prediction of isocitrate dehydrogenase 1 (IDH1) mutation in lower-grade gliomas (LGGs) is crucial for clinical decision-making. This study aimed to examine the predictive value of a machine learning approach using qualitative and quantitative MRI features to identify the IDH1 mutation in LGGs. Materials and Methods. A total of 102 LGG patients were allocated to training (n=67) and validation (n=35) cohorts and were subject to Visually Accessible Rembrandt Images (VASARI) feature extraction (23 features) from conventional multimodal MRI and radiomics feature extraction (56 features) from apparent diffusion coefficient maps. Feature selection was conducted using the maximum Relevance Minimum Redundancy method and 0.632+ bootstrap method. A machine learning model to predict IDH1 mutation was then established using a random forest classifier. The predictive performance was evaluated using receiver operating characteristic (ROC) curves. Results. After feature selection, the top 5 VASARI features were enhancement quality, deep white matter invasion, tumor location, proportion of necrosis, and T1/FLAIR ratio, and the top 10 radiomics features included 3 histogram features, 3 gray-level run-length matrix features, and 3 gray-level size zone matrix features and one shape feature. Using the optimal VASARI or radiomics feature sets for IDH1 prediction, the trained model achieved an area under the ROC curve (AUC) of 0.779±0.001 or 0.849±0.008 on the validation cohort, respectively. The fusion model that integrated outputs of both optimal VASARI and radiomics models improved the AUC to 0.879. Conclusion. The proposed machine learning approach using VASARI and radiomics features can predict IDH1 mutation in LGGs.