Beyond the Black Box: Do More Complex Deep Learning Models Provide Superior XAI Explanations?

TL;DR

This study examines whether more complex deep learning models provide better explanations in XAI, finding that increased complexity does not significantly improve interpretability or performance in medical image classification.

Contribution

It systematically evaluates the relationship between model complexity and XAI explanation quality using multiple ResNet architectures on lung X-ray data.

Findings

Higher model complexity reduces classification accuracy.

No significant difference in XAI explanation metrics across models.

Complexity does not enhance interpretability or performance.

Abstract

The increasing complexity of Artificial Intelligence models poses challenges to interpretability, particularly in the healthcare sector. This study investigates the impact of deep learning model complexity and Explainable AI (XAI) efficacy, utilizing four ResNet architectures (ResNet-18, 34, 50, 101). Through methodical experimentation on 4,369 lung X-ray images of COVID-19-infected and healthy patients, the research evaluates models' classification performance and the relevance of corresponding XAI explanations with respect to the ground-truth disease masks. Results indicate that the increase in model complexity is associated with a decrease in classification accuracy and AUC-ROC scores (ResNet-18: 98.4%, 0.997; ResNet-101: 95.9%, 0.988). Notably, in eleven out of twelve statistical tests performed, no statistically significant differences occurred between XAI quantitative metrics - Relevance Rank Accuracy and the proposed Positive Attribution Ratio - across trained models. These results suggest that increased model complexity does not consistently lead to higher performance or relevance of explanations for models' decision-making processes.