IBO: Inpainting-Based Occlusion to Enhance Explainable Artificial Intelligence Evaluation in Histopathology

TL;DR

This paper introduces IBO, a novel inpainting-based occlusion method using diffusion models to improve the evaluation of XAI techniques in histopathology by reducing out-of-distribution artifacts and enhancing interpretability assessment accuracy.

Contribution

The paper presents a new occlusion strategy that employs diffusion models for realistic inpainting, significantly improving the fidelity of occluded histopathological images for XAI evaluation.

Findings

IBO nearly doubles LPIPS score improvement over existing methods.

IBO increases XAI performance prediction precision from 42% to 71%.

Results demonstrate more reliable XAI evaluation in histopathology.

Abstract

Histopathological image analysis is crucial for accurate cancer diagnosis and treatment planning. While deep learning models, especially convolutional neural networks, have advanced this field, their "black-box" nature raises concerns about interpretability and trustworthiness. Explainable Artificial Intelligence (XAI) techniques aim to address these concerns, but evaluating their effectiveness remains challenging. A significant issue with current occlusion-based XAI methods is that they often generate Out-of-Distribution (OoD) samples, leading to inaccurate evaluations. In this paper, we introduce Inpainting-Based Occlusion (IBO), a novel occlusion strategy that utilizes a Denoising Diffusion Probabilistic Model to inpaint occluded regions in histopathological images. By replacing cancerous areas with realistic, non-cancerous tissue, IBO minimizes OoD artifacts and preserves data integrity. We evaluate our method on the CAMELYON16 dataset through two phases: first, by assessing perceptual similarity using the Learned Perceptual Image Patch Similarity (LPIPS) metric, and second, by quantifying the impact on model predictions through Area Under the Curve (AUC) analysis. Our results demonstrate that IBO significantly improves perceptual fidelity, achieving nearly twice the improvement in LPIPS scores compared to the best existing occlusion strategy. Additionally, IBO increased the precision of XAI performance prediction from 42% to 71% compared to traditional methods. These results demonstrate IBO's potential to provide more reliable evaluations of XAI techniques, benefiting histopathology and other applications. The source code for this study is available at https://github.com/a-fsh-r/IBO.