Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.10462 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908588880953344 |
|---|---|
| author | Zhong, Chen Yang, Yuxuan Zhang, Xinyue Ma, Ruohan Guo, Yong Li, Gang Li, Jupeng |
| author_facet | Zhong, Chen Yang, Yuxuan Zhang, Xinyue Ma, Ruohan Guo, Yong Li, Gang Li, Jupeng |
| contents | Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in disagreements. We introduce a fundamentally new approach with our group decision simulation framework, which works by mimicking the collaborative decision-making process of a clinical panel. Under this framework, an Expert Signature Generator (ESG) learns to represent individual annotator styles in a unique latent space. A Simulated Consultation Module (SCM) then intelligently generates the final segmentation by sampling from this space. This method achieved state-of-the-art results on challenging CBCT and MRI datasets (92.11% and 90.72% Dice scores). By treating expert disagreement as a useful signal instead of noise, our work provides a clear path toward more robust and trustworthy AI systems for healthcare. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10462 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation Zhong, Chen Yang, Yuxuan Zhang, Xinyue Ma, Ruohan Guo, Yong Li, Gang Li, Jupeng Computer Vision and Pattern Recognition Artificial Intelligence Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in disagreements. We introduce a fundamentally new approach with our group decision simulation framework, which works by mimicking the collaborative decision-making process of a clinical panel. Under this framework, an Expert Signature Generator (ESG) learns to represent individual annotator styles in a unique latent space. A Simulated Consultation Module (SCM) then intelligently generates the final segmentation by sampling from this space. This method achieved state-of-the-art results on challenging CBCT and MRI datasets (92.11% and 90.72% Dice scores). By treating expert disagreement as a useful signal instead of noise, our work provides a clear path toward more robust and trustworthy AI systems for healthcare. |
| title | Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10462 |