Dynamically evolving segment anything model with continuous learning for medical image segmentation
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_ | 1866929748588888064 |
|---|---|
| author | Liu, Zhaori Li, Mengyang Han, Hu Zhang, Enli Shan, Shiguang Zhao, Zhiming |
| author_facet | Liu, Zhaori Li, Mengyang Han, Hu Zhang, Enli Shan, Shiguang Zhao, Zhiming |
| contents | Medical image segmentation is essential for clinical diagnosis, surgical planning, and treatment monitoring. Traditional approaches typically strive to tackle all medical image segmentation scenarios via one-time learning. However, in practical applications, the diversity of scenarios and tasks in medical image segmentation continues to expand, necessitating models that can dynamically evolve to meet the demands of various segmentation tasks. Here, we introduce EvoSAM, a dynamically evolving medical image segmentation model that continuously accumulates new knowledge from an ever-expanding array of scenarios and tasks, enhancing its segmentation capabilities. Extensive evaluations on surgical image blood vessel segmentation and multi-site prostate MRI segmentation demonstrate that EvoSAM not only improves segmentation accuracy but also mitigates catastrophic forgetting. Further experiments conducted by surgical clinicians on blood vessel segmentation confirm that EvoSAM enhances segmentation efficiency based on user prompts, highlighting its potential as a promising tool for clinical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06236 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamically evolving segment anything model with continuous learning for medical image segmentation Liu, Zhaori Li, Mengyang Han, Hu Zhang, Enli Shan, Shiguang Zhao, Zhiming Computer Vision and Pattern Recognition Medical image segmentation is essential for clinical diagnosis, surgical planning, and treatment monitoring. Traditional approaches typically strive to tackle all medical image segmentation scenarios via one-time learning. However, in practical applications, the diversity of scenarios and tasks in medical image segmentation continues to expand, necessitating models that can dynamically evolve to meet the demands of various segmentation tasks. Here, we introduce EvoSAM, a dynamically evolving medical image segmentation model that continuously accumulates new knowledge from an ever-expanding array of scenarios and tasks, enhancing its segmentation capabilities. Extensive evaluations on surgical image blood vessel segmentation and multi-site prostate MRI segmentation demonstrate that EvoSAM not only improves segmentation accuracy but also mitigates catastrophic forgetting. Further experiments conducted by surgical clinicians on blood vessel segmentation confirm that EvoSAM enhances segmentation efficiency based on user prompts, highlighting its potential as a promising tool for clinical applications. |
| title | Dynamically evolving segment anything model with continuous learning for medical image segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.06236 |