Development of an Integrated Deep Learning Approach for Detecting Fetal Brain Abnormalities at Routine Second Trimester US Scan: A Multicenter Study

Radiology Artificial Intelligence 2026

View at publisher
Authors: Ruben Ramirez Zegarra, Alessandra Familiari, A. Dall’Asta, Chiara Di Ilio, Beatrice Valentini, Tiziana Fanelli, Paolo Volpe, Monica Minopoli, Basky Thilaganathan, E. Quarello, Ricciarda Raffaelli, Julia Binder
+7 more Veronica Falcone, Gianpaolo Grisolia, Giuseppe Rizzo, Gianluca Gragnaniello, Huong Elena Tran, Luca Boldrini, T. Ghi
DOI: 10.1148/ryai.250737
Cited by: 1
References: 28

Abstract

An anatomy-aware, two-stage, end-to-end deep learning pipeline was developed for classifying second-trimester fetal brain US images as normal or abnormal and achieved strong diagnostic performance, sensitivity, and specificity.

Fields of Study & Subjects

Fetal and Pediatric Neurological Disorders Prenatal Screening and Diagnostics Neonatal and fetal brain pathology

Publication details

Journal / source
Radiology Artificial Intelligence
Publisher
Radiological Society of North America (RSNA)
Volume
8
Issue
3
Pages
e250737–e250737
Publication date
8 April 2026
Language
EN