What question did this study set out to answer?

This research aims to develop a deep learning framework that enhances both brain tumor classification accuracy and the interpretability of model predictions.

April 7, 2026Open Access

NeuroScanXNet: An Explainable CNN Framework for Brain Tumor Classification with Grad-CAM Consistency Analysis and Mini-RAG Diagnostic Reporting

Key Points

This research aims to develop a deep learning framework that enhances both brain tumor classification accuracy and the interpretability of model predictions.
Developed a CNN-based framework named NeuroScanXNet for classifying MRI images of brain tumors.
Utilized Grad-CAM to visualize important regions in the MRI images influencing model predictions.
Implemented masked cosine similarity for quantitative consistency analysis across different inputs.
Incorporated a Mini-RAG module using TF-IDF for generating structured diagnostic reports.
Achieved a test accuracy of 94.66% for brain tumor classification.
Enhanced interpretability of the model's predictions through visualization techniques.
Improved usability for clinical decision support with structured diagnostic reporting.

Abstract

Deep learning has been widely used in medical imaging, significantly improving the accuracy of brain tumor classification. However, many existing models focus primarily on prediction accuracy without explaining how decisions are made, making their deployment in real clinical settings challenging. Convolutional Neural Networks (CNNs), though effective, are often treated as black-box models, which makes it difficult to trust their outputs. This study proposes a framework — NeuroScanXNet — that addresses both classification accuracy and result interpretability. A CNN-based model is used to classify MRI images into various tumour categories. Grad-CAM is applied to highlight the important regions influencing the model's predictions. In addition, a quantitative consistency analysis using masked cosine similarity is introduced to evaluate whether the model focuses on similar regions across different inputs. A Mini-RAG module based on TF-IDF retrieves relevant medical knowledge to generate a structured diagnostic report. The proposed system achieves a test accuracy of 94.66% while improving transparency and usability for real-world clinical decision support.

NeuroScanXNet: An Explainable CNN Framework for Brain Tumor Classification with Grad-CAM Consistency Analysis and Mini-RAG Diagnostic Reporting

Key Points

Abstract

Cite This Study