Robust Box Prompt based SAM for Medical Image Segmentation
This addresses the need for reliable medical image segmentation in clinical settings, though it is incremental as it builds on the existing SAM framework.
The study tackled the problem of SAM's segmentation performance declining with low-quality box prompts in medical imaging by proposing RoBox-SAM, which improved robustness and achieved state-of-the-art results on a dataset of 99,299 images across 5 modalities and 25 targets.
The Segment Anything Model (SAM) can achieve satisfactory segmentation performance under high-quality box prompts. However, SAM's robustness is compromised by the decline in box quality, limiting its practicality in clinical reality. In this study, we propose a novel Robust Box prompt based SAM (\textbf{RoBox-SAM}) to ensure SAM's segmentation performance under prompts with different qualities. Our contribution is three-fold. First, we propose a prompt refinement module to implicitly perceive the potential targets, and output the offsets to directly transform the low-quality box prompt into a high-quality one. We then provide an online iterative strategy for further prompt refinement. Second, we introduce a prompt enhancement module to automatically generate point prompts to assist the box-promptable segmentation effectively. Last, we build a self-information extractor to encode the prior information from the input image. These features can optimize the image embeddings and attention calculation, thus, the robustness of SAM can be further enhanced. Extensive experiments on the large medical segmentation dataset including 99,299 images, 5 modalities, and 25 organs/targets validated the efficacy of our proposed RoBox-SAM.