What question did this study set out to answer?

This review examines recent advancements in MRI-based brain tumor classification using deep learning techniques. It aims to identify existing research gaps and propose a conceptual model for improvement.

June 3, 2026Open Access

Deep Learning Meets Explainability in MRI Brain Tumor Analysis: A Review and Future Research Framework

Key Points

This review examines recent advancements in MRI-based brain tumor classification using deep learning techniques. It aims to identify existing research gaps and propose a conceptual model for improvement.
Review of recent literature on MRI and brain tumor classification using deep learning
Exploration of transfer learning and hybrid deep learning algorithms
Discussion of explainable AI technologies and their application in healthcare
Highlighted the efficacy of deep learning models in identifying brain tumors
Identified the black box problem as a significant barrier to the implementation of deep learning in healthcare
Proposed a conceptual model for improved brain tumor identification systems

Abstract

Abstract Brain tumors (BT) constitute significant diseases that require an early diagnosis with accurate assessment to plan appropriate treatment strategies. MRI scans are utilized extensively to diagnose BTs;however, manual examination is both tedious and prone to inconsistencies. In the past few years, significant advances have been made in BTC using DL models, which have shown exceptional efficacy.Unfortunately, the black box problem associated with DL models prevents their wider implementation in healthcare institutions.The current review aims to explore recent developments in MRI-based BTC through the use of transfer learning and hybrid deep learning algorithms combined with XAI technologies.This review also explores recent developments in this field, identifies existing gaps in current research,and provides a conceptual model to advance BT identification systems.

Mark Helpful

Bookmark

Relay

View Full Paper