改进点提示稳定性，让手术器械分割更准更省力。
RP-SAM2: Refining Point Prompts for Stable Surgical Instrument Segmentation
- 引入新模块和复合损失函数，稳定点提示位置敏感性。
- 在Cataract1k上提升2%的mDSC，mHD95降低21.36%。
- 适合数据少的医疗场景，减少人工标注负担。
准确的手术器械分割对白内障手术中的技能评估与流程优化至关重要，但标注数据有限，难以构建全自动模型。基于提示的方法如SAM2虽灵活，却对点提示位置高度敏感，常导致分割结果不一致。本文提出RP-SAM2，通过引入新型位移模块和复合损失函数，提升点提示的稳定性。该方法降低了对精确点位的依赖，同时保持强分割能力。在Cataract1k数据集上的实验表明，与SAM2相比，RP-SAM2实现2%的mDSC提升、mHD95下降21.36%，且单点提示结果方差显著减小。此外，在CaDIS数据集上，用RP-SAM2生成的伪掩码用于微调SAM2掩码解码器，性能优于SAM2生成的伪掩码。结果表明，RP-SAM2是数据受限医疗环境下半自动器械分割的可靠解决方案。代码已开源：https://github.com/BioMedIA-MBZUAI/RP-SAM2。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。