发表机构
The Chinese University of Hong Kong; XGEN Labs（香港中文大学; XGEN实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对手术数据与预训练数据的领域差距及现有方法计算消耗大效率低的问题，提出用低秩适配（LoRA）对 SAM3 进行参数高效适配用于手术概念分割，该方法在单个 GPU 上训练且性能优于主流基线，结果可支持下游手术场景重建和模拟。
AI 中文摘要
高效的手术分割有助于临床诊断、术中监测以及用于重建和模拟的下游机器人管道。尽管像 Segment Anything Model 3（SAM3）这样的提示驱动基础模型在自然图像上取得了强大的分割性能，但手术数据与预训练数据存在领域差距，导致分割精度下降。此外，现有的医学 SAM 方法需要全参数微调，计算消耗大且效率低。为解决这些限制，本文提出了一种用于手术概念分割的 SAM3 的参数高效低秩适配（LoRA）方法。我们将低秩适配器注入到提示编码器、检测器和跟踪器中，同时完全冻结视觉主干，仅优化 0.98%的总模型参数，并支持在单个消费级 GPU 上训练。综合实验表明，我们的方法始终优于零样本 SAM3 和其他主流基线，生成的分割结果可直接用于支持下游机器人手术场景重建和物理模拟管道。
英文摘要
Efficient surgical segmentation empowers clinical diagnosis, intraoperative monitoring, and downstream robotic pipelines for reconstruction and simulation. Although prompt-driven foundation models like Segment Anything Model 3 (SAM3) achieve strong segmentation performance on natural images, surgical data exhibits domain gaps against its pre-training data, resulting in degraded segmentation accuracy. Furthermore, existing medical SAM methods require full-parameter fine-tuning, incurring heavy computational consumption and low efficiency. To address these limitations, this work proposes a parameter-efficient Low-Rank Adaptation (LoRA) adaptation of SAM3 for surgical concept segmentation. We inject low-rank adapters into the prompt encoder, detector and tracker while fully freezing the vision backbone, which only optimizes 0.98% of the total model parameters and supports training on a single consumer GPU. Comprehensive experiments demonstrate that our method consistently outperforms zero-shot SAM3 and other mainstream baselines, and the generated segmentation results can be directly deployed to support downstream robotic surgical scene reconstruction and physical simulation pipelines.
CommentsAccepted by The 2nd MICCAI Workshop on Efficient Medical AI
