Automatic Deep Learning-Based Pipeline for Automatic Delineation and Measurement of Fetal Brain Structures in Routine Mid-Trimester Ultrasound Images
Fetal Diagnosis and Therapy · 2023 · 50 (6) · 480-490
DOI: 10.1159/000533203 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fetal Diagnosis and Therapy, online erschienen am 11.08.2023. Verfasst von David Coronado-Gutiérrez und 7 weiteren Autor:innen. Beteiligte Einrichtung: BCNatal | Fetal Medicine Research Center (Hospital Clínic and Hospital Sant Joan de Déu, University of Barcelona), Barcelona, Spain, david.coronado@t…. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Introduction
The aim of this study was to develop a pipeline using state-of-the-art deep learning methods to automatically delineate and measure several of the most important brain structures in fetal brain ultrasound (US) images.
Methods
The dataset was composed of 5,331 images of the fetal brain acquired during the routine mid-trimester US scan. Our proposed pipeline automatically performs the following three steps: brain plane classification (transventricular, transthalamic, or transcerebellar plane); brain structures delineation (9 different structures); and automatic measurement (from the structure delineations). The methods were trained on a subset of 4,331 images and each step was evaluated on the remaining 1,000 images.
Results
Plane classification reached 98.6% average class accuracy. Brain structure delineation obtained an average pixel accuracy higher than 96% and a Jaccard index higher than 70%. Automatic measurements get an absolute error below 3.5% for the four standard head biometries (head circumference, biparietal diameter, occipitofrontal diameter, and cephalic index), 9% for transcerebellar diameter, 12% for cavum septi pellucidi ratio, and 26% for Sylvian fissure operculization degree.
Conclusions
The proposed pipeline shows the potential of deep learning methods to delineate fetal head and brain structures and obtain automatic measures of each anatomical standard plane acquired during routine fetal US examination.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- BCNatal | Fetal Medicine Research Center (Hospital Clínic and Hospital Sant Joan de Déu, University of Barcelona), Barcelona, Spain, david.coronado@transmuralbiotech.com.
- Transmural Biotech S. L., Barcelona, Spain, david.coronado@transmuralbiotech.com.
- BCNatal | Fetal Medicine Research Center (Hospital Clínic and Hospital Sant Joan de Déu, University of Barcelona), Barcelona, Spain.
- Institut d'Investigacions Biomèdiques August Pi I Sunyer (IDIBAPS), Barcelona, Spain.
- Centre for Biomedical Research on Rare Diseases (CIBERER), Barcelona, Spain.
- Barcelona Tech, Universitat Politècnica de Catalunya, Barcelona, Spain.
Zitieren
APA
Coronado-Gutiérrez, D., Eixarch, E., Monterde, E., Matas, I., Traversi, P., Gratacós, E., Bonet-Carne, E., & Burgos-Artizzu, X. P. (2023). Automatic Deep Learning-Based Pipeline for Automatic Delineation and Measurement of Fetal Brain Structures in Routine Mid-Trimester Ultrasound Images. Fetal Diagnosis and Therapy, 50(6), 480-490. https://doi.org/10.1159/000533203
Vancouver
Coronado-Gutiérrez D, Eixarch E, Monterde E, Matas I, Traversi P, Gratacós E, et al. Automatic Deep Learning-Based Pipeline for Automatic Delineation and Measurement of Fetal Brain Structures in Routine Mid-Trimester Ultrasound Images. Fetal Diagnosis and Therapy. 2023;50(6):480-490. doi:10.1159/000533203
BibTeX
@article{CoronadoGutirrez2023,
author = {Coronado-Gutiérrez, David and Eixarch, Elisenda and Monterde, Elena and Matas, Isabel and Traversi, Paola and Gratacós, Eduard and Bonet-Carne, Elisenda and Burgos-Artizzu, Xavier P},
title = {Automatic Deep Learning-Based Pipeline for Automatic Delineation and Measurement of Fetal Brain Structures in Routine Mid-Trimester Ultrasound Images},
journal = {Fetal Diagnosis and Therapy},
year = {2023},
volume = {50},
number = {6},
pages = {480--490},
doi = {10.1159/000533203}
}
EUVIMED