Enhancing Deep Learning Model Explainability in Brain Tumor Datasets using Post-Heuristic Approaches

TL;DR

This paper improves the interpretability of deep learning models in brain tumor diagnosis by applying post-heuristic rule-based refinements to existing explanation methods, leading to more robust and concrete explanations.

Contribution

It introduces a novel post-heuristic approach to enhance the explainability of deep learning models in medical imaging, specifically targeting LIME explanations for brain tumor datasets.

Findings

Enhanced explanation robustness demonstrated on brain tumor datasets

Significant improvements in interpretability quality of model decisions

Post-heuristic methods outperform baseline explanation techniques

Abstract

The application of deep learning models in medical diagnosis has showcased considerable efficacy in recent years. Nevertheless, a notable limitation involves the inherent lack of explainability during decision-making processes. This study addresses such a constraint, by enhancing the interpretability robustness. The primary focus is directed towards refining the explanations generated by the LIME Library and LIME image explainer. This is achieved throuhg post-processing mechanisms, based on scenario-specific rules. Multiple experiments have been conducted using publicly accessible datasets related to brain tumor detection. Our proposed post-heuristic approach demonstrates significant advancements, yielding more robust and concrete results, in the context of medical diagnosis.