Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913579365564416 |
|---|---|
| author | Li, Shiman Wang, Haoran Meng, Yucong Zhang, Chenxi Song, Zhijian |
| author_facet | Li, Shiman Wang, Haoran Meng, Yucong Zhang, Chenxi Song, Zhijian |
| contents | Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning. Thus, it is of great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly and witnessed remarkable progress in multi-organ segmentation. However, obtaining an appropriately sized and fine-grained annotated dataset of multiple organs is extremely hard and expensive. Such scarce annotation limits the development of high-performance multi-organ segmentation models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer learning leveraging external datasets, semi-supervised learning using unannotated datasets and partially-supervised learning integrating partially-labeled datasets have led the dominant way to break such dilemma in multi-organ segmentation. We first review the traditional fully supervised method, then present a comprehensive and systematic elaboration of the 3 abovementioned learning paradigms in the context of multi-organ segmentation from both technical and methodological perspectives, and finally summarize their challenges and future trends. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_03296 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation Li, Shiman Wang, Haoran Meng, Yucong Zhang, Chenxi Song, Zhijian Image and Video Processing Computer Vision and Pattern Recognition Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning. Thus, it is of great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly and witnessed remarkable progress in multi-organ segmentation. However, obtaining an appropriately sized and fine-grained annotated dataset of multiple organs is extremely hard and expensive. Such scarce annotation limits the development of high-performance multi-organ segmentation models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer learning leveraging external datasets, semi-supervised learning using unannotated datasets and partially-supervised learning integrating partially-labeled datasets have led the dominant way to break such dilemma in multi-organ segmentation. We first review the traditional fully supervised method, then present a comprehensive and systematic elaboration of the 3 abovementioned learning paradigms in the context of multi-organ segmentation from both technical and methodological perspectives, and finally summarize their challenges and future trends. |
| title | Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2302.03296 |