Dual Agreement Consistency Learning with Foundation Models for Semi-Supervised Fetal Heart Ultrasound Segmentation and Diagnosis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Fangyijie, Silvestre, Guénolé, Curran, Kathleen M.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910058904813568
author Wang, Fangyijie
Silvestre, Guénolé
Curran, Kathleen M.
author_facet Wang, Fangyijie
Silvestre, Guénolé
Curran, Kathleen M.
contents Congenital heart disease (CHD) screening from fetal echocardiography requires accurate analysis of multiple standard cardiac views, yet developing reliable artificial intelligence models remains challenging due to limited annotations and variable image quality. In this work, we propose FM-DACL, a semi-supervised Dual Agreement Consistency Learning framework for the FETUS 2026 challenge on fetal heart ultrasound segmentation and diagnosis. The method combines a pretrained ultrasound foundation model (EchoCare) with a convolutional network through heterogeneous co-training and an exponential moving average teacher to better exploit unlabeled data. Experiments on the multi-center challenge dataset show that FM-DACL achieves a Dice score of 59.66 and NSD of 42.82 using heterogeneous backbones, demonstrating the feasibility of the proposed semi-supervised framework. These results suggest that FM-DACL provides a flexible approach for leveraging heterogeneous models in low-annotation fetal cardiac ultrasound analysis. The code is available on https://github.com/13204942/FM-DACL.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18119
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dual Agreement Consistency Learning with Foundation Models for Semi-Supervised Fetal Heart Ultrasound Segmentation and Diagnosis
Wang, Fangyijie
Silvestre, Guénolé
Curran, Kathleen M.
Image and Video Processing
Congenital heart disease (CHD) screening from fetal echocardiography requires accurate analysis of multiple standard cardiac views, yet developing reliable artificial intelligence models remains challenging due to limited annotations and variable image quality. In this work, we propose FM-DACL, a semi-supervised Dual Agreement Consistency Learning framework for the FETUS 2026 challenge on fetal heart ultrasound segmentation and diagnosis. The method combines a pretrained ultrasound foundation model (EchoCare) with a convolutional network through heterogeneous co-training and an exponential moving average teacher to better exploit unlabeled data. Experiments on the multi-center challenge dataset show that FM-DACL achieves a Dice score of 59.66 and NSD of 42.82 using heterogeneous backbones, demonstrating the feasibility of the proposed semi-supervised framework. These results suggest that FM-DACL provides a flexible approach for leveraging heterogeneous models in low-annotation fetal cardiac ultrasound analysis. The code is available on https://github.com/13204942/FM-DACL.
title Dual Agreement Consistency Learning with Foundation Models for Semi-Supervised Fetal Heart Ultrasound Segmentation and Diagnosis
topic Image and Video Processing
url https://arxiv.org/abs/2603.18119