Learning normal appearance for fetal anomaly screening: Application to the unsupervised detection of Hypoplastic Left Heart Syndrome

Elisa Chotzoglou1, Thomas Day2, Jeremy Tan1, Jacqueline Matthew2, David Lloyd2, Reza Razavi2, John Simpson2, Bernhard Kainz1
1: Imperial College London, UK, 2: King’s College London, UK
September 2021 issue
Publication date: 2021/10/22
PDF · arXiv

Abstract

Congenital heart disease is considered as one the most common groups of congenital malformations which affects 6 − 11 per 1000 newborns. In this work, an automated framework for detection of cardiac anomalies during ultrasound screening is proposed and evaluated on the example of Hypoplastic Left Heart Syndrome (HLHS), a sub-category of congenital heart disease. We propose an unsupervised approach that learns healthy anatomy exclusively from clinically confirmed normal control patients. We evaluate a number of known anomaly detection frameworks together with a new model architecture based on the α-GAN network and find evidence that the proposed model performs significantly better than the state-of-the-art in image-based anomaly detection, yielding average 0.81 AUC and a better robustness towards initialisation compared to previous works.

Keywords

fetal screening · detection · unsupervised learning

Bibtex @article{melba:2021:012:chotzoglou, title = "Learning normal appearance for fetal anomaly screening: Application to the unsupervised detection of Hypoplastic Left Heart Syndrome", author = "Chotzoglou, Elisa and Day, Thomas and Tan, Jeremy and Matthew, Jacqueline and Lloyd, David and Razavi, Reza and Simpson, John and Kainz, Bernhard", journal = "Machine Learning for Biomedical Imaging", volume = "1", issue = "September 2021 issue", year = "2021", issn = "2766-905X", url = "https://melba-journal.org/papers/2021:012.html" }
RISTY - JOUR AU - Chotzoglou, Elisa AU - Day, Thomas AU - Tan, Jeremy AU - Matthew, Jacqueline AU - Lloyd, David AU - Razavi, Reza AU - Simpson, John AU - Kainz, Bernhard PY - 2021 TI - Learning normal appearance for fetal anomaly screening: Application to the unsupervised detection of Hypoplastic Left Heart Syndrome T2 - Machine Learning for Biomedical Imaging VL - 1 IS - September 2021 issue SN - 2766-905X UR - https://www.melba-journal.org/papers/2021:012.html ER -

2021:012 cover