Chao Chieh-Ju, Gu Yunqi Richard, Kumar Wasan, Xiang Tiange, Appari Lalith, Wu Justin, Farina Juan M, Wraith Rachael, Jeong Jiwoon, Arsanjani Reza, Kane Garvan C, Oh Jae K, Langlotz Curtis P, Banerjee Imon, Fei-Fei Li, Adeli Ehsan
Department of Cardiovascular Medicine, Mayo Clinic Rochester, Rochester, MN, USA.
Stanford Institute for Human-Centered Artificial Intelligence, Stanford University, Stanford, CA, USA.
NPJ Digit Med. 2025 Jun 6;8(1):341. doi: 10.1038/s41746-025-01730-y.
The Segment Anything Model (SAM) was fine-tuned on the EchoNet-Dynamic dataset and evaluated on external transthoracic echocardiography (TTE) and Point-of-Care Ultrasound (POCUS) datasets from CAMUS (University Hospital of St Etienne) and Mayo Clinic (99 patients: 58 TTE, 41 POCUS). Fine-tuned SAM was superior or comparable to MedSAM. The fine-tuned SAM also outperformed EchoNet and U-Net models, demonstrating strong generalization, especially on apical 2-chamber (A2C) images (fine-tuned SAM vs. EchoNet: CAMUS-A2C: DSC 0.891 ± 0.040 vs. 0.752 ± 0.196, p < 0.0001) and POCUS (DSC 0.857 ± 0.047 vs. 0.667 ± 0.279, p < 0.0001). Additionally, SAM-enhanced workflow reduced annotation time by 50% (11.6 ± 4.5 sec vs. 5.7 ± 1.7 sec, p < 0.0001) while maintaining segmentation quality. We demonstrated an effective strategy for fine-tuning a vision foundation model for enhancing clinical workflow efficiency and supporting human-AI collaboration.
分割一切模型（SAM）在EchoNet-Dynamic数据集上进行了微调，并在来自圣艾蒂安大学医院（CAMUS）和梅奥诊所的外部经胸超声心动图（TTE）和床旁超声（POCUS）数据集上进行了评估（99例患者：58例TTE，41例POCUS）。微调后的SAM优于或可与MedSAM相媲美。微调后的SAM也优于EchoNet和U-Net模型，展现出强大的泛化能力，尤其是在心尖两腔（A2C）图像上（微调后的SAM与EchoNet对比：CAMUS-A2C：DSC为0.891±0.040，而EchoNet为0.752±0.196，p<0.0001）以及POCUS上（DSC为0.857±0.047，而EchoNet为0.667±0.279，p<0.0001）。此外，SAM增强的工作流程在保持分割质量的同时，将注释时间减少了50%（从11.6±4.5秒降至5.7±1.7秒，p<0.0001）。我们展示了一种有效的策略，用于微调视觉基础模型，以提高临床工作流程效率并支持人机协作。
