Peer-Reviewed Publication
J Ultrasound Med2026March 11, 2026Journal Article
AI-Driven Analysis of the Fetal Left Ventricular Outflow Tract: Diagnostic Value and Applications.
Sifa Turan1, Camille Velly2, Marta Bisanti3, Julien Mancini4, Antoine Lafouge5, Ivan Voznyuk6, Edwin Quarello6,7,8
1Division of Maternal-Fetal Medicine, Department of Obstetrics, Gynecology and Reproductive Sciences, University of Maryland School of Medicine, Baltimore, MD, USA.
2Pediatric and Congenital Cardiology Department, M3C Regional Reference CHD Centre, APHM La Timone Hospital, Marseille, France.
3Department of Women and Child Health, Women Health Area, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
4Aix-Marseille University, Marseille, France; Biostatistics Department, Aix-Marseille University, INSERM, IRD, ISSPAM, APHM, SESSTIM, Timone Hospital, Marseille, France.
5Cabinet de Gynécologie et Obstétrique, Hyères, France.
6Diagnoly, Terra Mundi, Lyon, France.
7Institut Méditerranéen d'Imagerie Médicale Appliquée à la Gynécologie, La Grossesse Et l'Enfance (IMAGE2), Marseille, France.
8Unité de Dépistage et de Diagnostic Prénatal, Hôpital Saint-Joseph, Marseille, France.
Abstract
OBJECTIVES: To develop and validate a deep-learning pipeline that identifies left ventricular outflow tract (LVOT) views in routine obstetric screening report images and audits 7 predefined LVOT image-quality criteria with an interpretable 0-7 summary score.
METHODS: We randomly selected 180 screening report files from low-risk pregnancies (90 second trimester, 20-25 weeks; 90 third trimester, 30…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans