A benchmark for 2D foetal brain ultrasound analysis

TL;DR

This paper introduces a comprehensive dataset of 2D fetal brain ultrasound images with annotations and a template, facilitating development and evaluation of segmentation, registration, and anomaly detection methods in fetal brain imaging.

Contribution

It provides a new benchmark dataset with co-registered images, landmark annotations, and probabilistic maps for advancing fetal brain ultrasound analysis.

Findings

Dataset of 104 co-registered 2D ultrasound images provided

Annotated landmark points for brain structures included

Template and probabilistic maps enable new analysis methods

Abstract

Brain development involves a sequence of structural changes from early stages of the embryo until several months after birth. Currently, ultrasound is the established technique for screening due to its ability to acquire dynamic images in real-time without radiation and to its cost-efficiency. However, identifying abnormalities remains challenging due to the difficulty in interpreting foetal brain images. In this work we present a set of 104 2D foetal brain ultrasound images acquired during the 20th week of gestation that have been co-registered to a common space from a rough skull segmentation. The images are provided both on the original space and template space centred on the ellipses of all the subjects. Furthermore, the images have been annotated to highlight landmark points from structures of interest to analyse brain development. Both the final atlas template with probabilistic maps and the original images can be used to develop new segmentation techniques, test registration approaches for foetal brain ultrasound, extend our work to longitudinal datasets and to detect anomalies in new images.