Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.01038 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912995798417408 |
|---|---|
| author | Zhao, Qiaochu Wei, Wei Horowitz, David Bakst, Richard Yuan, Yading |
| author_facet | Zhao, Qiaochu Wei, Wei Horowitz, David Bakst, Richard Yuan, Yading |
| contents | Automated medical image segmentation has achieved remarkable progress with fully labeled data. However, site-specific clinical priorities and the high cost of manual annotation often yield scans with only a subset of organs labeled, leading to the partially labeled problem that degrades performance. To address this issue, we propose IPnP, an Iteratively Prompting and Pseudo-labeling framework, for partially labeled medical image segmentation. IPnP iteratively generates and refines pseudo-labels for unlabeled organs through collaboration between a trainable segmentation network (specialist) and a frozen foundation model (generalist), progressively recovering full-organ supervision. On the public dataset AMOS with the simulated partial-label setting, IPnP consistently improves segmentation performance over prior methods and approaches the performance of the fully labeled reference. We further evaluate on a private, partially labeled dataset of 210 head-and-neck cancer patients and demonstrate our effectiveness in real-world clinical settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01038 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Foundation Model-guided Iteratively Prompting and Pseudo-Labeling for Partially Labeled Medical Image Segmentation Zhao, Qiaochu Wei, Wei Horowitz, David Bakst, Richard Yuan, Yading Computer Vision and Pattern Recognition Automated medical image segmentation has achieved remarkable progress with fully labeled data. However, site-specific clinical priorities and the high cost of manual annotation often yield scans with only a subset of organs labeled, leading to the partially labeled problem that degrades performance. To address this issue, we propose IPnP, an Iteratively Prompting and Pseudo-labeling framework, for partially labeled medical image segmentation. IPnP iteratively generates and refines pseudo-labels for unlabeled organs through collaboration between a trainable segmentation network (specialist) and a frozen foundation model (generalist), progressively recovering full-organ supervision. On the public dataset AMOS with the simulated partial-label setting, IPnP consistently improves segmentation performance over prior methods and approaches the performance of the fully labeled reference. We further evaluate on a private, partially labeled dataset of 210 head-and-neck cancer patients and demonstrate our effectiveness in real-world clinical settings. |
| title | Foundation Model-guided Iteratively Prompting and Pseudo-Labeling for Partially Labeled Medical Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.01038 |