MatchSeg: Towards Better Segmentation via Reference Image Matching
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911992121393152 |
|---|---|
| author | Huo, Jiayu Xiao, Ruiqiang Zheng, Haotian Liu, Yang Ourselin, Sebastien Sparks, Rachel |
| author_facet | Huo, Jiayu Xiao, Ruiqiang Zheng, Haotian Liu, Yang Ourselin, Sebastien Sparks, Rachel |
| contents | Recently, automated medical image segmentation methods based on deep learning have achieved great success. However, they heavily rely on large annotated datasets, which are costly and time-consuming to acquire. Few-shot learning aims to overcome the need for annotated data by using a small labeled dataset, known as a support set, to guide predicting labels for new, unlabeled images, known as the query set. Inspired by this paradigm, we introduce MatchSeg, a novel framework that enhances medical image segmentation through strategic reference image matching. We leverage contrastive language-image pre-training (CLIP) to select highly relevant samples when defining the support set. Additionally, we design a joint attention module to strengthen the interaction between support and query features, facilitating a more effective knowledge transfer between support and query sets. We validated our method across four public datasets. Experimental results demonstrate superior segmentation performance and powerful domain generalization ability of MatchSeg against existing methods for domain-specific and cross-domain segmentation tasks. Our code is made available at https://github.com/keeplearning-again/MatchSeg |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15901 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MatchSeg: Towards Better Segmentation via Reference Image Matching Huo, Jiayu Xiao, Ruiqiang Zheng, Haotian Liu, Yang Ourselin, Sebastien Sparks, Rachel Artificial Intelligence Computer Vision and Pattern Recognition Recently, automated medical image segmentation methods based on deep learning have achieved great success. However, they heavily rely on large annotated datasets, which are costly and time-consuming to acquire. Few-shot learning aims to overcome the need for annotated data by using a small labeled dataset, known as a support set, to guide predicting labels for new, unlabeled images, known as the query set. Inspired by this paradigm, we introduce MatchSeg, a novel framework that enhances medical image segmentation through strategic reference image matching. We leverage contrastive language-image pre-training (CLIP) to select highly relevant samples when defining the support set. Additionally, we design a joint attention module to strengthen the interaction between support and query features, facilitating a more effective knowledge transfer between support and query sets. We validated our method across four public datasets. Experimental results demonstrate superior segmentation performance and powerful domain generalization ability of MatchSeg against existing methods for domain-specific and cross-domain segmentation tasks. Our code is made available at https://github.com/keeplearning-again/MatchSeg |
| title | MatchSeg: Towards Better Segmentation via Reference Image Matching |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.15901 |