Runtime Freezing: Dynamic Class Loss for Multi-Organ 3D Segmentation
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_ | 1866910483051708416 |
|---|---|
| author | Willoughby, James Voiculescu, Irina |
| author_facet | Willoughby, James Voiculescu, Irina |
| contents | Segmentation has become a crucial pre-processing step to many refined downstream tasks, and particularly so in the medical domain. Even with recent improvements in segmentation models, many segmentation tasks remain difficult. When multiple organs are segmented simultaneously, difficulties are due not only to the limited availability of labelled data, but also to class imbalance. In this work we propose dynamic class-based loss strategies to mitigate the effects of highly imbalanced training data. We show how our approach improves segmentation performance on a challenging Multi-Class 3D Abdominal Organ dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08217 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Runtime Freezing: Dynamic Class Loss for Multi-Organ 3D Segmentation Willoughby, James Voiculescu, Irina Computer Vision and Pattern Recognition Machine Learning Segmentation has become a crucial pre-processing step to many refined downstream tasks, and particularly so in the medical domain. Even with recent improvements in segmentation models, many segmentation tasks remain difficult. When multiple organs are segmented simultaneously, difficulties are due not only to the limited availability of labelled data, but also to class imbalance. In this work we propose dynamic class-based loss strategies to mitigate the effects of highly imbalanced training data. We show how our approach improves segmentation performance on a challenging Multi-Class 3D Abdominal Organ dataset. |
| title | Runtime Freezing: Dynamic Class Loss for Multi-Organ 3D Segmentation |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.08217 |