仅用10个标注病例，就能实现临床级医学图像分割。
A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning of MedSAM3
- 用低秩适配（LoRA）微调MedSAM3，仅需少量标注数据即可定制化分割模型。
- 10个标注案例即达临床可用性能，胆囊分割Dice达0.68（CT）。
- 训练快3倍，适合资源有限的医院或新器官分割任务快速部署。
医学图像分割对治疗规划与疾病评估至关重要。尽管专业工具如TotalSegmentator和MRSegmentator表现优异，但需大量标注数据训练。医学基础模型通过大规模预训练可减少标注负担，但零样本性能仍有限。通过低秩适配（LoRA）对MedSAM3进行参数高效微调，在仅使用1、2、5、10个标注病例的情况下，针对腹部五种器官（肝脏、双肾、脾脏、胆囊、胰腺）在CT和MRI上进行评估，使用AMOS22数据集。仅用10个标注病例，模型性能已可媲美在海量数据上训练的专业系统。尤其在胆囊分割上表现突出（CT Dice 0.68，MRI Dice 0.59），而现有工具几乎失效（Dice 0.0004），同时在肝脏、肾脏、脾脏上性能仅比MRSegmentator低5–10%，且标注量少100倍以上。外部验证在全心脏分割数据集上也成功扩展至心脏分割任务，仅用10例即实现与主流方法相当的左心室分割效果。每器官训练仅需3–5小时，单卡运行，比nnU-Net快2–3倍。结果表明，10个标注病例足以支撑临床可用分割，显著缓解标注与训练时间瓶颈。
原文摘要 · Abstract (English)
Medical image segmentation is essential for clinical workflows such as treatment planning and disease assessment. While specialist tools like TotalSegmentator and MRSegmentator achieve strong performance, they require large annotated datasets for training. Medical foundation models offer a promising alternative through large-scale pretraining that reduces the annotation burden for new tasks, but zero-shot performance remains limited. Parameter-efficient adaptation via Low-Rank Adaptation (LoRA) enables efficient specialization with few trainable parameters, but a key question remains: how many expert-annotated cases are needed to achieve clinically useful segmentation performance? We address this by adapting MedSAM3 with LoRA for five abdominal organs (liver, kidneys, spleen, gallbladder, and pancreas) in CT and MRI using only 1, 2, 5, and 10 annotated cases, evaluating on AMOS22 dataset. With just 10 cases, models achieve performance competitive with specialist systems trained on orders of magnitude more data. Notably, this includes reliable gallbladder segmentation (Dice 0.68 CT, 0.59 MRI) where existing tools fail almost completely (Dice 0.0004), while remaining within 5--10% of MRSegmentator for liver, kidneys, and spleen using over 100 times fewer annotations. Furthermore, external validation on the Whole Heart Segmentation dataset shows that the approach extends to cardiac segmentation, a use case beyond the scope of TotalSegmentator (MRI) and MRSegmentator, achieving competitive left ventricle (LV) performance with only 10 annotated cases. Training requires only3--5,hours per organ on a single GPU, approximately 2--3 times faster than nnU-Net. These findings suggest that ten annotated cases are sufficient for clinically useful segmentation, effectively reducing bottlenecks for both image annotation and training time.
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。