Leveraging Causal Reasoning Method for Explaining Medical Image Segmentation Models
This addresses the trustworthiness issue in high-stakes medical scenarios by providing explanations for segmentation tasks, which are underexplored compared to classification, though it is incremental as it builds on existing causal frameworks.
The authors tackled the problem of explaining medical image segmentation models by introducing a causal inference-based method that quantifies input and network component influences on segmentation areas, demonstrating more faithful explanations than existing techniques on two medical imaging datasets.
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.