A Novel Interaction-based Methodology Towards Explainable AI with Better Understanding of Pneumonia Chest X-ray Images

TL;DR

This paper introduces an interaction-based influence score method to improve explainability and interpretability of CNNs in pneumonia chest X-ray analysis without compromising prediction accuracy.

Contribution

It proposes a new influence score methodology that filters noisy features, enhancing explainability in medical image classification tasks.

Findings

Achieved state-of-the-art results on pneumonia X-ray dataset

Improved feature interpretability without losing prediction performance

Demonstrated applicability to large-scale data problems

Abstract

In the field of eXplainable AI (XAI), robust "blackbox" algorithms such as Convolutional Neural Networks (CNNs) are known for making high prediction performance. However, the ability to explain and interpret these algorithms still require innovation in the understanding of influential and, more importantly, explainable features that directly or indirectly impact the performance of predictivity. A number of methods existing in literature focus on visualization techniques but the concepts of explainability and interpretability still require rigorous definition. In view of the above needs, this paper proposes an interaction-based methodology -- Influence Score (I-score) -- to screen out the noisy and non-informative variables in the images hence it nourishes an environment with explainable and interpretable features that are directly associated to feature predictivity. We apply the proposed method on a real world application in Pneumonia Chest X-ray Image data set and produced state-of-the-art results. We demonstrate how to apply the proposed approach for more general big data problems by improving the explainability and interpretability without sacrificing the prediction performance. The contribution of this paper opens a novel angle that moves the community closer to the future pipelines of XAI problems.