Foreign object segmentation in chest x-rays through anatomy-guided shape insertion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916575048630272 |
|---|---|
| author | Seibold, Constantin Kalisch, Hamza Heine, Lukas Reiß, Simon Kleesiek, Jens |
| author_facet | Seibold, Constantin Kalisch, Hamza Heine, Lukas Reiß, Simon Kleesiek, Jens |
| contents | In this paper, we tackle the challenge of instance segmentation for foreign objects in chest radiographs, commonly seen in postoperative follow-ups with stents, pacemakers, or ingested objects in children. The diversity of foreign objects complicates dense annotation, as shown in insufficient existing datasets. To address this, we propose the simple generation of synthetic data through (1) insertion of arbitrary shapes (lines, polygons, ellipses) with varying contrasts and opacities, and (2) cut-paste augmentations from a small set of semi-automatically extracted labels. These insertions are guided by anatomy labels to ensure realistic placements, such as stents appearing only in relevant vessels. Our approach enables networks to segment complex structures with minimal manually labeled data. Notably, it achieves performance comparable to fully supervised models while using 93\% fewer manual annotations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12022 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Foreign object segmentation in chest x-rays through anatomy-guided shape insertion Seibold, Constantin Kalisch, Hamza Heine, Lukas Reiß, Simon Kleesiek, Jens Computer Vision and Pattern Recognition In this paper, we tackle the challenge of instance segmentation for foreign objects in chest radiographs, commonly seen in postoperative follow-ups with stents, pacemakers, or ingested objects in children. The diversity of foreign objects complicates dense annotation, as shown in insufficient existing datasets. To address this, we propose the simple generation of synthetic data through (1) insertion of arbitrary shapes (lines, polygons, ellipses) with varying contrasts and opacities, and (2) cut-paste augmentations from a small set of semi-automatically extracted labels. These insertions are guided by anatomy labels to ensure realistic placements, such as stents appearing only in relevant vessels. Our approach enables networks to segment complex structures with minimal manually labeled data. Notably, it achieves performance comparable to fully supervised models while using 93\% fewer manual annotations. |
| title | Foreign object segmentation in chest x-rays through anatomy-guided shape insertion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.12022 |