SURGIVID: Annotation-Efficient Surgical Video Object Discovery
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916390698483712 |
|---|---|
| author | Köksal, Çağhan Ghazaei, Ghazal Navab, Nassir |
| author_facet | Köksal, Çağhan Ghazaei, Ghazal Navab, Nassir |
| contents | Surgical scenes convey crucial information about the quality of surgery. Pixel-wise localization of tools and anatomical structures is the first task towards deeper surgical analysis for microscopic or endoscopic surgical views. This is typically done via fully-supervised methods which are annotation greedy and in several cases, demanding medical expertise. Considering the profusion of surgical videos obtained through standardized surgical workflows, we propose an annotation-efficient framework for the semantic segmentation of surgical scenes. We employ image-based self-supervised object discovery to identify the most salient tools and anatomical structures in surgical videos. These proposals are further refined within a minimally supervised fine-tuning step. Our unsupervised setup reinforced with only 36 annotation labels indicates comparable localization performance with fully-supervised segmentation models. Further, leveraging surgical phase labels as weak labels can better guide model attention towards surgical tools, leading to $\sim 2\%$ improvement in tool localization. Extensive ablation studies on the CaDIS dataset validate the effectiveness of our proposed solution in discovering relevant surgical objects with minimal or no supervision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07801 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SURGIVID: Annotation-Efficient Surgical Video Object Discovery Köksal, Çağhan Ghazaei, Ghazal Navab, Nassir Computer Vision and Pattern Recognition Surgical scenes convey crucial information about the quality of surgery. Pixel-wise localization of tools and anatomical structures is the first task towards deeper surgical analysis for microscopic or endoscopic surgical views. This is typically done via fully-supervised methods which are annotation greedy and in several cases, demanding medical expertise. Considering the profusion of surgical videos obtained through standardized surgical workflows, we propose an annotation-efficient framework for the semantic segmentation of surgical scenes. We employ image-based self-supervised object discovery to identify the most salient tools and anatomical structures in surgical videos. These proposals are further refined within a minimally supervised fine-tuning step. Our unsupervised setup reinforced with only 36 annotation labels indicates comparable localization performance with fully-supervised segmentation models. Further, leveraging surgical phase labels as weak labels can better guide model attention towards surgical tools, leading to $\sim 2\%$ improvement in tool localization. Extensive ablation studies on the CaDIS dataset validate the effectiveness of our proposed solution in discovering relevant surgical objects with minimal or no supervision. |
| title | SURGIVID: Annotation-Efficient Surgical Video Object Discovery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.07801 |