Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.02493 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918081278771200 |
|---|---|
| author | Parolari, Luca Cherubini, Andrea Ballan, Lamberto Biffi, Carlo |
| author_facet | Parolari, Luca Cherubini, Andrea Ballan, Lamberto Biffi, Carlo |
| contents | Automated polyp counting in colonoscopy is a crucial step toward automated procedure reporting and quality control, aiming to enhance the cost-effectiveness of colonoscopy screening. Counting polyps in a procedure involves detecting and tracking polyps, and then clustering tracklets that belong to the same polyp entity. Existing methods for polyp counting rely on self-supervised learning and primarily leverage visual appearance, neglecting temporal relationships in both tracklet feature learning and clustering stages. In this work, we introduce a paradigm shift by proposing a supervised contrastive loss that incorporates temporally-aware soft targets. Our approach captures intra-polyp variability while preserving inter-polyp discriminability, leading to more robust clustering. Additionally, we improve tracklet clustering by integrating a temporal adjacency constraint, reducing false positive re-associations between visually similar but temporally distant tracklets. We train and validate our method on publicly available datasets and evaluate its performance with a leave-one-out cross-validation strategy. Results demonstrate a 2.2x reduction in fragmentation rate compared to prior approaches. Our results highlight the importance of temporal awareness in polyp counting, establishing a new state-of-the-art. Code is available at https://github.com/lparolari/temporally-aware-polyp-counting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02493 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Temporally-Aware Supervised Contrastive Learning for Polyp Counting in Colonoscopy Parolari, Luca Cherubini, Andrea Ballan, Lamberto Biffi, Carlo Computer Vision and Pattern Recognition Artificial Intelligence Automated polyp counting in colonoscopy is a crucial step toward automated procedure reporting and quality control, aiming to enhance the cost-effectiveness of colonoscopy screening. Counting polyps in a procedure involves detecting and tracking polyps, and then clustering tracklets that belong to the same polyp entity. Existing methods for polyp counting rely on self-supervised learning and primarily leverage visual appearance, neglecting temporal relationships in both tracklet feature learning and clustering stages. In this work, we introduce a paradigm shift by proposing a supervised contrastive loss that incorporates temporally-aware soft targets. Our approach captures intra-polyp variability while preserving inter-polyp discriminability, leading to more robust clustering. Additionally, we improve tracklet clustering by integrating a temporal adjacency constraint, reducing false positive re-associations between visually similar but temporally distant tracklets. We train and validate our method on publicly available datasets and evaluate its performance with a leave-one-out cross-validation strategy. Results demonstrate a 2.2x reduction in fragmentation rate compared to prior approaches. Our results highlight the importance of temporal awareness in polyp counting, establishing a new state-of-the-art. Code is available at https://github.com/lparolari/temporally-aware-polyp-counting. |
| title | Temporally-Aware Supervised Contrastive Learning for Polyp Counting in Colonoscopy |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.02493 |