Related Experiment Video
Updated: Jun 15, 2025
10:02
State of the Art Cranial Ultrasound Imaging in Neonates
Published on: February 2, 2015
24.2K
A benchmark for 2D foetal brain ultrasound analysis
Mariano Cabezas1, Yago Diez2, Clara Martinez-Diago3
1Brain and Mind Centre, University of Sydney, Sydney, Australia. mariano.cabezas@sydney.edu.au.
Scientific Data
|August 24, 2024
Summary
This study introduces a dataset of 104 2D fetal brain ultrasound images for improved analysis of brain development. The annotated images and template aid in developing new techniques for anomaly detection in fetal ultrasounds.
Area of Science:
- Medical Imaging
- Neuroscience
- Developmental Biology
Background:
- Fetal brain development involves complex structural changes.
- Ultrasound is a standard, cost-effective imaging technique for prenatal screening.
- Interpreting fetal brain ultrasound images for abnormalities is challenging.
Purpose of the Study:
- To present a dataset of 2D fetal brain ultrasound images for research.
- To facilitate the development of new methods for analyzing fetal brain development and detecting anomalies.
- To provide co-registered and annotated images for improved interpretation.
Main Methods:
- Acquisition of 104 2D fetal brain ultrasound images at 20 weeks gestation.
- Co-registration of images to a common space using rough skull segmentation.
- Annotation of images highlighting key anatomical landmarks.
Main Results:
- A dataset of 104 co-registered 2D fetal brain ultrasound images.
- Images available in original and template spaces.
- Annotated landmarks for structures of interest.
Conclusions:
- The dataset and template can advance segmentation and registration techniques for fetal brain ultrasound.
- This resource supports the development of anomaly detection methods.
- Potential for extension to longitudinal studies and complex analyses.
