Automated Detection of Congenital Heart Disease in Fetal Ultrasound Screening

被引：10

作者：

Tan, Jeremy ^{[1
]}

Au, Anselm ^{[1
]}

Meng, Qingjie

FinesilverSmith, Sandy ^{[2
]}

Simpson, John ^{[2
]}

Rueckert, Daniel ^{[1
]}

Razavi, Reza ^{[2
]}

Day, Thomas ^{[2
]}

Lloyd, David ^{[2
]}

Kainz, Bernhard ^{[1
]}

机构：

[1] Imperial Coll London, London SW7 2AZ, England

[2] Kings Coll London, St Thomas Hosp, London SE1 7EH, England

来源：

MEDICAL ULTRASOUND, AND PRETERM, PERINATAL AND PAEDIATRIC IMAGE ANALYSIS, ASMUS 2020, PIPPI 2020 | 2020年 / 12437卷

基金：

英国惠康基金;

关键词：

Congenital heart disease; Fetal ultrasound; PRENATAL DETECTION; LOCALIZATION;

D O I：

10.1007/978-3-030-60334-2_24

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Prenatal screening with ultrasound can lower neonatal mortality significantly for selected cardiac abnormalities. However, the need for human expertise, coupled with the high volume of screening cases, limits the practically achievable detection rates. In this paper we discuss the potential for deep learning techniques to aid in the detection of congenital heart disease (CHD) in fetal ultrasound. We propose a pipeline for automated data curation and classification. During both training and inference, we exploit an auxiliary view classification task to bias features toward relevant cardiac structures. This bias helps to improve in F1-scores from 0.72 and 0.77 to 0.87 and 0.85 for healthy and CHD classes respectively.

引用

页码：243 / 252

页数：10

共 22 条

[1]

Arnaout R, 2018, Arxiv, DOI arXiv:1809.06993

[2] SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound [J].