Key result
Fine-tuned SAM achieves excellent left ventricular segmentation, nearly matching the domain-specific EchoNet model.
Why the study?
Does a fine-tuned Segment Anything Model (SAM) improve left ventricular segmentation performance compared to domain-specific models in transthoracic echocardiography and point-of-care ultrasound images?
Cohort (n=10,629)
Yes
Does a fine-tuned Segment Anything Model (SAM) improve left ventricular segmentation performance compared to domain-specific models in transthoracic echocardiography and point-of-care ultrasound images?
Absolute Event Rate: 0.911% vs 0.915%
p-value: p=<0.0001
Fine-tuning the Segment Anything Model (SAM) on echocardiography data yields strong generalization for left ventricular segmentation across different institutions and ultrasound modalities, including POCUS, reducing the need for extensive manual data curation.
Supports efficient LV segmentation workflows; leaves open prospective validation before clinical adoption.
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.
No takes yet. Share an insight, caveat, or question.
Chao et al. (2023) conducted a cohort in Left ventricular segmentation on cardiac ultrasound (n=10,629). Fine-tuned Segment Anything Model (SAM) vs. EchoNet model (domain-specific model) was evaluated on Dice similarity coefficient (DSC) on EchoNet test set (p=<0.0001). Fine-tuned SAM achieved excellent left ventricular segmentation performance on the EchoNet dataset (DSC 0.911) compared to the domain-specific EchoNet model (DSC 0.915, p<0.0001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: