Segmentation Style Discovery: Application to Skin Lesion Images
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909280433602560 |
|---|---|
| author | Abhishek, Kumar Kawahara, Jeremy Hamarneh, Ghassan |
| author_facet | Abhishek, Kumar Kawahara, Jeremy Hamarneh, Ghassan |
| contents | Variability in medical image segmentation, arising from annotator preferences, expertise, and their choice of tools, has been well documented. While the majority of multi-annotator segmentation approaches focus on modeling annotator-specific preferences, they require annotator-segmentation correspondence. In this work, we introduce the problem of segmentation style discovery, and propose StyleSeg, a segmentation method that learns plausible, diverse, and semantically consistent segmentation styles from a corpus of image-mask pairs without any knowledge of annotator correspondence. StyleSeg consistently outperforms competing methods on four publicly available skin lesion segmentation (SLS) datasets. We also curate ISIC-MultiAnnot, the largest multi-annotator SLS dataset with annotator correspondence, and our results show a strong alignment, using our newly proposed measure AS2, between the predicted styles and annotator preferences. The code and the dataset are available at https://github.com/sfu-mial/StyleSeg. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02787 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Segmentation Style Discovery: Application to Skin Lesion Images Abhishek, Kumar Kawahara, Jeremy Hamarneh, Ghassan Computer Vision and Pattern Recognition Variability in medical image segmentation, arising from annotator preferences, expertise, and their choice of tools, has been well documented. While the majority of multi-annotator segmentation approaches focus on modeling annotator-specific preferences, they require annotator-segmentation correspondence. In this work, we introduce the problem of segmentation style discovery, and propose StyleSeg, a segmentation method that learns plausible, diverse, and semantically consistent segmentation styles from a corpus of image-mask pairs without any knowledge of annotator correspondence. StyleSeg consistently outperforms competing methods on four publicly available skin lesion segmentation (SLS) datasets. We also curate ISIC-MultiAnnot, the largest multi-annotator SLS dataset with annotator correspondence, and our results show a strong alignment, using our newly proposed measure AS2, between the predicted styles and annotator preferences. The code and the dataset are available at https://github.com/sfu-mial/StyleSeg. |
| title | Segmentation Style Discovery: Application to Skin Lesion Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.02787 |