Astrocytoma is the most common type of brain glioma and is classified by the World Health Organization into four grades, providing prognostic insights and guiding treatment decisions. The accurate determination of astrocytoma grade is critical for patient management, especially in high-malignancy-grade cases. This study proposes a fully optimized Convolutional Neural Network (CNN) for the classification of astrocytoma MRI slices across the three malignant grades (G2–4). The training dataset consisted of 1284 pre-operative axial 2D MRI slices from T1-weighted contrast-enhanced and FLAIR sequences derived from 69 patients. To provide the best possible model performance, an extensive hyperparameter tuning was carried out through the Hyperband method, a variant of Successive Halving. Training was conducted using Repeated Hold-Out Validation across four randomized data splits, achieving a mean classification accuracy of 98.05%, low loss values, and an AUC of 0.997. Comparative evaluation against state-of-the-art pre-trained models using transfer learning demonstrated superior performance. For validation purposes, the proposed CNN trained on an altered version of the training set yielded 93.34% accuracy on unmodified slices, which confirms the model’s robustness and potential use for clinical deployment. Model interpretability was ensured through the application of two Explainable AI (XAI) techniques, SHAP and LIME, which highlighted the regions of the slices contributing to the decision-making process.

Gliomas constitute the majority of primary brain tumors, and accurate diagnosis through MRI is essential for patient management. Existing computer-aided diagnosis approaches frequently rely on tumor segmentation frameworks. In this study, a segmentation-independent framework for volumetric low-grade versus high-grade glioma (LGG/HGG) classification is proposed using a Convolutional Neural Network (CNN) designed through task-oriented Neural Architecture Search (NAS). The proposed method was evaluated on a multi-center dataset comprising 1194 patients with pre-operative MRI scans, including T1-CE and FLAIR sequences from four publicly available cohorts. NAS was conducted within a controlled search space to optimize a 3D U-Net–based backbone using Tree-structured Parzen Estimator (TPE) combined with Hyperband pruning. The optimized backbone was enhanced with residual connections and Squeeze-and-Excitation (SE) attention mechanisms to improve feature representation and training stability. Internal validation employed repeated 5-fold cross-validation across all four multi-center datasets. An external experiment used REMBRANDT as a test cohort (49 LGG, 19 HGG). The proposed model achieved 88.25% internal accuracy and 75.51% external accuracy (macro-F1: 87.37% internal, 73.77% external), outperforming benchmark 3D CNNs. Explainable Artificial Intelligence (XAI) analysis based on Grad-CAM revealed robust tumor localization without segmentation supervision, validated against available ground-truth masks. Additional experiments demonstrated the model’s generalization capacity, achieving 89.51% accuracy for IDH mutation prediction and 78.74% for multi-grade classification.

Although numerous studies have developed promising diagnostic algorithms, many have yet to be translated into workflow-integrated tools. Gliomas represent a substantial proportion of primary brain tumors, and their preoperative differentiation by tumor grade can provide critical information for patient management. In this study, we present and evaluate GliomaAI, an open-source 3D Slicer extension for the automated classification of low-grade versus high-grade gliomas from preoperative MRI. The extension is organized into two complementary frameworks for MRI preprocessing and classification with explainability. Four 3D CNN architectures evaluated in our previous work were integrated into a unified segmentation-free workflow, with their final deployment retrained on T1-CE and FLAIR volumes from the multicohort dataset of 1194 patients. GliomaAI offers both individual CNN classification and an ensemble configuration. For single-model predictions, Grad-CAM heatmaps can be interactively overlaid on either MRI volume to aid interpretation of the model’s decision. Explainability is further enhanced through 3D rendering of the generated heatmaps, providing spatial inspection of displayed activations. After excluding overlaps with the model-development cohort, independent validation was conducted on the remaining BraTS-19 cases (26 LGG, 208 HGG). GliomaAI-CNN achieved a balanced accuracy of 82.2% and an AUC of 0.945. The extension provides an accessible, computationally efficient bridge toward clinical application.