Glioma Grade Classification From Structural Mri: A Comparative Transfer Learning Study of Deep Learning Feature Extraction and Machine Learning Classifiers Publisher

Summary: Can MRI-based AI distinguish glioma grades? In a test dataset, InceptionV3 features plus KNN reached 97.5% accuracy; prospective validation is still needed. #BrainTumors #MedicalAI

Khorasani A ; Azemi G ; Di Ieva A
Source: Machine Learning and Knowledge Extraction Published:2026

Abstract

Background: Accurate histological grading of gliomas, distinguishing low-grade (LGG) from high-grade (HGG) lesions, remains a critical determinant of treatment planning and patient prognosis. This study systematically investigates the optimal combination of structural MRI sequences, pretrained convolutional neural network (CNN) architectures, and supervised classifiers for automated glioma grade classification. Methods: Deep features were extracted from four MRI sequences (T1, contrast-enhanced T1 (T1Gd), T2, and FLAIR) from the BraTS 2023 dataset using five pretrained CNNs: VGG16, ResNet50, DenseNet121, EfficientNetB0, and InceptionV3. Features were refined via LASSO selection and classified using Random Forest, Support Vector Machine, XGBoost, Gradient Boosting, k-Nearest Neighbors (KNNs), and a shallow deep neural network. A patient-level 80/20 training–test partition was employed, with five-fold cross-validation used within the training set for feature selection and hyperparameter optimization. A total of 120 modality–extractor–classifier configurations were benchmarked on the held-out test set. Results: InceptionV3-derived features paired with KNN classifiers consistently yielded superior performance. Based on a TOPSIS multi-criteria ranking integrating accuracy, precision, recall, F1-score, and AUC, the best-performing configuration combined T1Gd features with KNN (closeness coefficient = 0.971; accuracy = 0.975, precision = 0.997, recall = 0.948, F1-score = 0.969, AUC = 0.996). The second-ranked configuration, using T1 features with KNN (closeness coefficient = 0.962), achieved significantly higher accuracy, recall, and F1-score, despite its slightly lower composite ranking. Conclusion: Deep feature extraction using InceptionV3 from T1-weighted MRI, coupled with KNN classification, represents a promising and practical approach for slice-level glioma grading and merits further validation in prospective clinical cohorts. © 2026 by the authors.