Leveraging Causal Reasoning Method for Explaining Medical Image Segmentation Models

TL;DR

This paper introduces a causal inference-based explanation method for medical image segmentation models, providing more faithful insights into model decisions and revealing heterogeneity in segmentation strategies across different models and inputs.

Contribution

The paper presents a novel causal inference framework for explaining segmentation models, addressing the gap in explainability techniques for segmentation tasks.

Findings

Our method outperforms existing explainability techniques in faithfulness.

It uncovers heterogeneity in segmentation strategies across models.

Provides insights for model optimization.

Abstract

Medical image segmentation plays a vital role in clinical decision-making, enabling precise localization of lesions and guiding interventions. Despite significant advances in segmentation accuracy, the black-box nature of most deep models has raised growing concerns about their trustworthiness in high-stakes medical scenarios. Current explanation techniques have primarily focused on classification tasks, leaving the segmentation domain relatively underexplored. We introduced an explanation model for segmentation task which employs the causal inference framework and backpropagates the average treatment effect (ATE) into a quantification metric to determine the influence of input regions, as well as network components, on target segmentation areas. Through comparison with recent segmentation explainability techniques on two representative medical imaging datasets, we demonstrated that our approach provides more faithful explanations than existing approaches. Furthermore, we carried out a systematic causal analysis of multiple foundational segmentation models using our method, which reveals significant heterogeneity in perceptual strategies across different models, and even between different inputs for the same model. Suggesting the potential of our method to provide notable insights for optimizing segmentation models. Our code can be found at https://github.com/lcmmai/PdCR.