Open Access Open Access  Restricted Access Subscription Access

AI to Explainable Deep Learning in MRI-Based Brain Tumor Detection: A Comprehensive Review

Mr. Sandipkumar Bhandare

Abstract


Magnetic Resonance Imaging (MRI) driven brain tumor analysis has progressed rapidly with the emergence of advanced artificial intelligence techniques, particularly deep neural networks, transfer learning paradigms, and attention-guided architectures. Although these approaches achieve high performance in segmentation and classification tasks, persistent limitations remain in interpretability, cross-domain robustness, dataset imbalance, and clinical implementation. This review synthesizes recent developments in MRI-based tumor detection, spanning classical machine learning pipelines, convolutional and transformer architectures, ensemble strategies, domain adaptation frameworks, and Explainable Artificial Intelligence (XAI) methodologies. A clinically oriented unified framework is outlined to connect experimental research models with deployable hospital systems. Comparative discussions of datasets, evaluation metrics, architectural trends, and open research challenges are provided to support the design of scalable, interpretable, and clinically reliable AI systems for neuro-oncology.

Full Text:

PDF

References


Shagufta Iftikhar et. al, “Explainable CNN for brain tomor detection and classification through XAI based key features identification. ” Springer Nature30 April 2025 https://doi.org/10.1186/s40708-025-00257-y.

Mastoi et al.,” Explainable AI in medical imaging: an interpretable and collaborative federated learning model for brain tomor classification” Front. Oncol. 27 February 2025.doi: 10.3389/fonc.2025.1535478.

Sibi Amaran et.al, “Explainable artificial intelligence with U Net based segmentation and Bayesian machine learning for classification of brain tomoursusing MRI images” 3 January 2025 www.nature.com/scientificreports/https://doi.org/10.1038/s41598-024-84692-7.

Novsheena Rasool et.al, “CNN-Tomor Net: leveraging explainability in deep learning for precise brain tomor diagnosis on MRI images “Front. Oncol. 26 March 2025 doi: 10.3389/fonc.2025.1554559.

Mr. Ankur Raj et.al, Early Brain Cancer Detection through Transfer Learning with Pre-Trained Imaging Models: A Comprehensive Review” JETIR April 2025, Volume 12, Issue 4.

Ahmad Ishaq et.al, “Improved EfficientNet Architecture for Multi-Grade Brain Tomor Detection” Electronics 2025, 14,710. https://doi.org/10.3390/electronics14040710.

Suthar, O. P., et. al, “Visual Intelligence in Neuro-Oncology: Effective Brain Tomor Detection through Optimized Convolutional Neural Networks” ,. 20 March 2025 IECE Transactions on Sensing, Communication, and Control, 2(1).

Salvatore Benfatto et.al, “Explainable artificial intelligence of DNA methylation- based brain tomor diagnostics” 20 February 2025 Nature Communications https://doi.org/10.1038/s41467-025-57078-0.

Md. Nahiduzzaman et al, “A hybrid explainable model based on advanced machine learning and deep learning models for classifying brain tumors using MRI images” 10January 2025 www.nature.com/scientificreports.

Shuvashis Sarker et al, “Transfer Learning and Explainable AI for Brain Tomor Classification: A Study Using MRI Data from Bangladesh” , 2024 6th International Conference on Sustainable Technologies for Industry 5.0 2024 IEEE| DOI: 10.1109/STI64222.2024.10951092.


Refbacks

  • There are currently no refbacks.