Challenge Summary U-MedSAM: Uncertainty-aware MedSAM for Medical Image Segmentation
This work addresses uncertainty estimation for medical image segmentation, which is incremental as it builds on existing MedSAM models.
The paper tackled the challenge of accurately assessing uncertainty in medical image segmentation foundation models by proposing U-MedSAM, which integrates MedSAM with an uncertainty-aware loss function and Sharpness-Aware Minimization optimizer, demonstrating promising performance in the CVPR24 MedSAM on Laptop challenge.
Medical Image Foundation Models have proven to be powerful tools for mask prediction across various datasets. However, accurately assessing the uncertainty of their predictions remains a significant challenge. To address this, we propose a new model, U-MedSAM, which integrates the MedSAM model with an uncertainty-aware loss function and the Sharpness-Aware Minimization (SharpMin) optimizer. The uncertainty-aware loss function automatically combines region-based, distribution-based, and pixel-based loss designs to enhance segmentation accuracy and robustness. SharpMin improves generalization by finding flat minima in the loss landscape, thereby reducing overfitting. Our method was evaluated in the CVPR24 MedSAM on Laptop challenge, where U-MedSAM demonstrated promising performance.