Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.00748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913086531698688 |
|---|---|
| author | Liu, Ke Gao, Shangde Fu, Yichao Shen, Shuaike Gao, Shangqi Shen, Chunhua |
| author_facet | Liu, Ke Gao, Shangde Fu, Yichao Shen, Shuaike Gao, Shangqi Shen, Chunhua |
| contents | Lesion segmentation is inherently influenced by imaging uncertainty, arising from ill-defined lesion boundaries and inter-observer variability in diagnosis. To address this challenge, previous works formulated the multi-rater medical image segmentation task, where multiple experts provide separate annotations for each image. However, existing models are typically constrained to either generate diverse segmentation that lacks expert specificity or to produce personalized outputs that merely replicate individual annotators. We propose \textbf{Pro}babilistic modeling of multi-rater lesion \textbf{Seg}mentation (\textbf{ProSeg}) that simultaneously enables both diversification and personalization. Specifically, we introduce two latent variables to model expert annotation preferences and lesion boundary ambiguity. Their conditional probabilistic distributions are then obtained through variational inference, allowing segmentation outputs to be generated by sampling from these distributions. Extensive experiments on both the nasopharyngeal carcinoma dataset (NPC) and the lung nodule dataset (LIDC-IDRI) demonstrate that our ProSeg achieves a new state-of-the-art performance, providing segmentation results that are both diverse and expert-personalized. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_00748 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization Liu, Ke Gao, Shangde Fu, Yichao Shen, Shuaike Gao, Shangqi Shen, Chunhua Computer Vision and Pattern Recognition Artificial Intelligence Lesion segmentation is inherently influenced by imaging uncertainty, arising from ill-defined lesion boundaries and inter-observer variability in diagnosis. To address this challenge, previous works formulated the multi-rater medical image segmentation task, where multiple experts provide separate annotations for each image. However, existing models are typically constrained to either generate diverse segmentation that lacks expert specificity or to produce personalized outputs that merely replicate individual annotators. We propose \textbf{Pro}babilistic modeling of multi-rater lesion \textbf{Seg}mentation (\textbf{ProSeg}) that simultaneously enables both diversification and personalization. Specifically, we introduce two latent variables to model expert annotation preferences and lesion boundary ambiguity. Their conditional probabilistic distributions are then obtained through variational inference, allowing segmentation outputs to be generated by sampling from these distributions. Extensive experiments on both the nasopharyngeal carcinoma dataset (NPC) and the lung nodule dataset (LIDC-IDRI) demonstrate that our ProSeg achieves a new state-of-the-art performance, providing segmentation results that are both diverse and expert-personalized. |
| title | Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.00748 |