Iterative Explainability for Weakly Supervised Segmentation in Medical PE Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909909819326464 |
|---|---|
| author | Condrea, Florin Rapaka, Saikiran Leordeanu, Marius |
| author_facet | Condrea, Florin Rapaka, Saikiran Leordeanu, Marius |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07384 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Iterative Explainability for Weakly Supervised Segmentation in Medical PE Detection Condrea, Florin Rapaka, Saikiran Leordeanu, Marius Image and Video Processing Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Iterative Explainability for Weakly Supervised Segmentation in Medical PE Detection |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2412.07384 |