Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models

Analysis of 3D segmentation models, especially in the context of medical imaging, is often limited to segmentation performance metrics that overlook the crucial aspect of explainability and bias. Currently, effectively explaining these models with saliency maps is challenging due to the high dimensions of input images multiplied by the ever-growing number of segmented class labels. To this end, we introduce AGG<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>Exp, a methodology for aggregating fine-grained voxel attributions of the segmentation model's pre-dictions. Unlike classical explanation methods that primar-ily focus on the local feature attribution, Agg2 Exr enables a more comprehensive global view on the importance of predicted segments in 3D images. Our benchmarking exper-iments show that gradient-based voxel attributions are more faithful to the model's predictions than perturbation-based explanations. As a concrete use-case, we apply AGG<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>Exp to discover knowledge acquired by the Swin UNEt TRans-former model trained on the TotalSegmentator v2 dataset for segmenting anatomical structures in computed tomogra-phy medical images. AGG<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>Exp facilitates the explanatory analysis of large segmentation models beyond their predictive performance. The source code is publicly available at https://github.com/mi2datalab/agg2exp.