Article

Foundation versus Domain-Specific Models for Left Ventricular Segmentation on Cardiac Ultrasound

2023-09-19

Abstract excerpt

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 str...

Topics

Open a Topic to create a Post that cites this publication.

Fetal and Pediatric Neurological Disorders

Identifiers and source

Literature Corpus work: 1308c494-fa70-5ed0-aa31-cf58ea6169b4
DOI: 10.1101/2023.09.19.23295772

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Foundation versus Domain-Specific Models for Left Ventricular Segmentation on Cardiac UltrasoundDOI 10.1101/2023.09.19.23295772Read

Multi-task artificial intelligence annotation of echocardiographic images: a retrospective multi-cohort studySemantic proximity Read

EchoApex: A General-Purpose Vision Foundation Model for EchocardiographySemantic proximity Read

Generalizability and Quality Control of Deep Learning-Based 2D Echocardiography Segmentation Models in a Large Clinical DatasetSemantic proximity Read

OrganSegBench: Bridging the Translational Gap for Medical Segmentation Foundation Models Through Principled Model SynergySemantic proximity Read

Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound: a multi-center studySemantic proximity Read

A Decade of Deep Learning-based Biomedical Image SegmentationSemantic proximity Read

MHub.ai: A Standardized Platform for Reproducible AI Research in Medical ImagingSemantic proximity Read

OrganSegBench: A Comprehensive Multi-Organ Benchmark for Segmentation Foundation Models with a Practical Synergy Pathway to Clinical ApplicationSemantic proximity Read

Development and multi-dataset evaluation of a unified single-view deep-learning model for the right heart: four-chamber segmentation, biventricular ejection fraction, deformation, and pulmonary-hypertension prediction from the apical four-chamber echocardiogramSemantic proximity Read

ExShall-CNN: An Explainable Shallow Convolutional Neural Network for Medical Image SegmentationSemantic proximity Read

Beyond Doppler: Scalable AI Detection of LVOT Obstruction in HCMSemantic proximity Read

Advancing prenatal healthcare by explainable AI enhanced fetal ultrasound image segmentation using U-Net++ with attention mechanismsSemantic proximity Read