A multi-centre, multi-device benchmark dataset for landmark-based comprehensive fetal biometry

TL;DR

This paper introduces a comprehensive, publicly available multi-centre, multi-device dataset of fetal ultrasound images with expert annotations for key biometric measurements, aiming to improve AI-based fetal growth assessment across diverse clinical settings.

Contribution

It provides the first extensive multi-centre, multi-device benchmark dataset with standardized annotations, facilitating fair comparison and development of robust AI methods for fetal biometry.

Findings

Training on single-centre data overestimates performance

Multi-centre testing reveals significant domain shift

Baseline models demonstrate the dataset's utility for domain adaptation

Abstract

Accurate fetal growth assessment from ultrasound (US) relies on precise biometry measured by manually identifying anatomical landmarks in standard planes. Manual landmarking is time-consuming, operator-dependent, and sensitive to variability across scanners and sites, limiting the reproducibility of automated approaches. There is a need for multi-source annotated datasets to develop artificial intelligence-assisted fetal growth assessment methods. To address this bottleneck, we present an open, multi-centre, multi-device benchmark dataset of fetal US images with expert anatomical landmark annotations for clinically used fetal biometric measurements. These measurements include head bi-parietal and occipito-frontal diameters, abdominal transverse and antero-posterior diameters, and femoral length. The dataset comprises 4,513 de-identified US images from 1,904 subjects acquired at three clinical sites using seven different US devices. We provide standardised, subject-disjoint train/test splits, evaluation code, and baseline results to enable fair and reproducible comparison of methods. Using an automatic biometry model, we quantify domain shift and demonstrate that training and evaluation confined to a single centre substantially overestimate performance relative to multi-centre testing. To the best of our knowledge, this is the first publicly available multi-centre, multi-device, landmark-annotated dataset that covers all primary fetal biometry measures, providing a robust benchmark for domain adaptation and multi-centre generalisation in fetal biometry and enabling more reliable AI-assisted fetal growth assessment across centres. All data, annotations, training code, and evaluation pipelines are made publicly available.