RP-SAM2: Refining Point Prompts for Stable Surgical Instrument Segmentation
This addresses the need for stable semi-automatic segmentation in data-constrained medical settings like cataract surgery, offering an incremental improvement over existing methods.
The paper tackled the problem of inconsistent surgical instrument segmentation due to sensitivity to point prompt placement in prompt-based methods like SAM2, by introducing RP-SAM2, which improved segmentation accuracy with a 2% mDSC gain and a 21.36% reduction in mHD95 on the Cataract1k dataset.
Accurate surgical instrument segmentation is essential in cataract surgery for tasks such as skill assessment and workflow optimization. However, limited annotated data makes it difficult to develop fully automatic models. Prompt-based methods like SAM2 offer flexibility yet remain highly sensitive to the point prompt placement, often leading to inconsistent segmentations. We address this issue by introducing RP-SAM2, which incorporates a novel shift block and a compound loss function to stabilize point prompts. Our approach reduces annotator reliance on precise point positioning while maintaining robust segmentation capabilities. Experiments on the Cataract1k dataset demonstrate that RP-SAM2 improves segmentation accuracy, with a 2% mDSC gain, a 21.36% reduction in mHD95, and decreased variance across random single-point prompt results compared to SAM2. Additionally, on the CaDIS dataset, pseudo masks generated by RP-SAM2 for fine-tuning SAM2's mask decoder outperformed those generated by SAM2. These results highlight RP-SAM2 as a practical, stable and reliable solution for semi-automatic instrument segmentation in data-constrained medical settings. The code is available at https://github.com/BioMedIA-MBZUAI/RP-SAM2.