Iterative Explainability for Weakly Supervised Segmentation in Medical PE Detection

TL;DR

This paper introduces iExplain, an iterative explainability-based weakly supervised learning method that improves pulmonary embolism segmentation in CT scans by progressively refining pixel-level masks from coarse annotations.

Contribution

The paper presents a novel iterative approach that transforms coarse image labels into detailed segmentation masks, enhancing PE detection without requiring extensive manual annotations.

Findings

Achieves PE detection performance comparable to fully supervised methods.

Effectively captures complete PE regions and detects multiple embolisms.

Outperforms existing weakly supervised segmentation techniques.

Abstract

Pulmonary Embolism (PE) are a leading cause of cardiovascular death. Computed tomographic pulmonary angiography (CTPA) is the gold standard for PE diagnosis, with growing interest in AI-based diagnostic assistance. However, these algorithms are limited by scarce fine-grained annotations of thromboembolic burden. We address this challenge with iExplain, a weakly supervised learning algorithm that transforms coarse image-level annotations into detailed pixel-level PE masks through iterative model explainability. Our approach generates soft segmentation maps used to mask detected regions, enabling the process to repeat and discover additional embolisms that would be missed in a single pass. This iterative refinement effectively captures complete PE regions and detects multiple distinct embolisms. Models trained on these automatically generated annotations achieve excellent PE detection performance, with significant improvements at each iteration. We demonstrate iExplain's effectiveness on the RSPECT augmented dataset, achieving results comparable to strongly supervised methods while outperforming existing weakly supervised methods.