Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization
This addresses the problem of handling data uncertainty and inter-observer variability in medical image segmentation for healthcare applications, representing an incremental improvement over prior methods.
The paper tackled the challenge of multi-rater medical image segmentation by proposing ProSeg, a probabilistic model that simultaneously enables diverse and personalized segmentation outputs, achieving state-of-the-art performance on datasets like NPC and LIDC-IDRI.
Medical image segmentation is inherently influenced by data uncertainty, arising from ambiguous boundaries in medical scans 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 Probabilistic modeling of multi-rater medical image Segmentation (ProSeg) that simultaneously enables both diversification and personalization. Specifically, we introduce two latent variables to model expert annotation preferences and image 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. Code can be found in https://github.com/AI4MOL/ProSeg.