FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening

2026-08-05

AI Summary

This study addresses the critical lack of publicly available datasets for first-trimester fetal ultrasound screening, which has hindered the development of intelligent diagnostic assistance. To bridge this gap, we present FUSEP—the first multi-center, publicly accessible benchmark dataset tailored to this task—comprising 4,017 images and 45,820 bounding-box annotations across 14 key anatomical structures, aligned with international guidelines for crown-rump length (CRL) and nuchal translucency (NT) standard planes from three hospitals. Leveraging FUSEP, we establish comprehensive multi-object detection baselines under diverse learning paradigms, including fully supervised, semi-supervised, and unsupervised domain adaptation settings, and validate their robustness across multiple centers, ultrasound devices, and operators. This work provides a unified benchmark for standard plane identification, image quality control, and assisted diagnosis, significantly advancing research in intelligent first-trimester ultrasound screening.

Abstract

A large number of infants with congenital anomalies are born each year globally, especially in areas with underdeveloped medical resources. Currently, fetal ultrasound screening is the most common modality for early pregnancy anatomy detection. This modality can detect anomalies earlier and provide opportune treatment advice. However, the lack of an ultrasound dataset on early fetal gestation has slowed down the development of automated assisted diagnosis. In this work, we present a benchmark dataset for Fetal Ultrasound Screening in Early Pregnancy to facilitate intelligent ultrasound examination and assisted diagnosis called FUSEP. Our dataset consists of two ultrasound views recommended by the international guideline, i.e., Crown-rump Length (CRL) and Nuchal Translucency (NT) views in three hospitals, totaling 4,017 ultrasound images, with 45,820 box-level expert-level annotations. Our dataset and baseline present the following three contributions: 1) Our medical experts annotated a total of 14 key anatomical structures in two views using a box-level format; 2) Our data is collected extensively from different sonographers, devices, scanning angles, hospitals, etc; 3) We report the performance of the semi-supervised learning, fully supervised learning, unsupervised domain adaptation (UDA), and source-free UDA in ultrasound images multi-object detection. To the best of our knowledge, this is the first publicly available dataset and benchmark for fetal early pregnancy ultrasound screening. We believe that FUSEP and benchmark can contribute to the medical community in the development of multiple tasks such as standard plane recognition, quality control on ultrasound images, automated assisted diagnostics in early fetal pregnancy, medical multi-object detection, domain adaptation for object detection, etc.

Problem

• fetal ultrasound screening
• early pregnancy
• benchmark dataset
• congenital anomalies
• automated assisted diagnosis

Innovation

• fetal ultrasound screening
• multi-center dataset
• box-level annotation
• unsupervised domain adaptation
• early pregnancy