Key result
MedSAM model accurately segments femoral vessels on ultrasound, achieving a ~0.82 Dice score.
Why the study?
Current ultrasound-guided central venous access has not sufficiently reduced complications such as accidental arterial puncture, creating a clinical demand for more precise techniques using mixed reality-guided navigation.
Does a MedSAM-based deep learning model accurately segment femoral vessels from ultrasound images compared to cardiologist contour tracing in patients undergoing cardiac catheterization?
Observational (n=50)
Does a MedSAM-based deep learning model accurately segment femoral vessels from ultrasound images compared to cardiologist contour tracing in patients undergoing cardiac catheterization?
This study provides proof of concept that deep learning can accurately segment femoral vessels from hand-scanned ultrasound images to reconstruct 3D models as a foundation for mixed reality-guided vascular access.
Background Current ultrasound-guided central venous access has not sufficiently reduced the incidence of complications, such as accidental arterial puncture. Therefore, there is a clinical demand for more secure and precise techniques utilizing digital health technologies such as mixed reality (MR)-guided navigation. Purpose As a fundamental step toward achieving MR-guided vascular access, we aimed to develop an automated model to segment the contours of femoral arteries and veins from ultrasound images and reconstruct them into 3D models. Methods We prospectively enrolled 50 consecutive patients undergoing cardiac catheterization between June 2023 and December 2025. Ultrasound videos of the femoral region (50 × 100 mm field of view, 50 mm depth) were recorded during manual hand-scans. From these videos, 22 static frames per patient were extracted at regular intervals. Ground truth labels were generated by two board-certified cardiologists through independent contour tracing. A MedSAM architecture was utilized for semantic segmentation, and model performance was evaluated using the Dice coefficient and Intersection over Union (IoU) via 5-fold cross-validation. Results The study cohort (median age, 74.5 years [IQR, 64.3–78.0]; 86% male; median BMI, 24.3 kg/m² [IQR, 21.7–26.3]) yielded a total of 1,100 images. The MedSAM model demonstrated high accuracy in detecting femoral vessels, achieving a Dice coefficient of 0.82 and an IoU of 0.70. Furthermore, 3D vascular structures were successfully reconstructed from the predicted contours. Conclusion We demonstrated a proof of concept for generating 3D vascular models from hand-scanned femoral ultrasound images via semantic segmentation, providing a technical foundation for future MR-guided navigation.
No takes yet. Share an insight, caveat, or question.
Miyabe et al. (2026) conducted an observational in Cardiac catheterization requiring femoral vascular access (n=50). MedSAM semantic segmentation model for femoral ultrasound images vs. Ground truth contour tracing by two board-certified cardiologists was evaluated on Semantic segmentation accuracy of femoral arteries and veins (Dice coefficient and Intersection over Union [IoU]) (Dice coefficient 0.82; IoU 0.70). The MedSAM semantic segmentation model detected femoral vessels from ultrasound images with high accuracy, achieving a Dice coefficient of 0.82 and an Intersection over Union of 0.70.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:
More from European Heart Journal