Automated detection of congenital heart disease in fetal ultrasound screening
File(s)
Accepted version
OA Location
Author(s)
Type
Conference Paper
Abstract
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.
Date Issued
2020-10-01
Date Acceptance
2020-07-01
Citation
Lecture Notes in Computer Science, 2020, 12437, pp.243-252
ISBN
9783030603335
ISSN
0302-9743
Publisher
Springer
Start Page
243
End Page
252
Journal / Book Title
Lecture Notes in Computer Science
Volume
12437
Copyright Statement
© 2020 Springer Nature Switzerland AG. The final publication is available at Springer via https://link.springer.com/chapter/10.1007/978-3-030-60334-2_24
Sponsor
Engineering & Physical Science Research Council (E
Wellcome Trust
Grant Number
RTJ5557761-1
PO :RTJ5557761-1
Source
ASMUS 2020, PIPPI 2020: Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis
Subjects
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2020-10-04
Finish Date
2020-10-08
Coverage Spatial
Virtual
Date Publish Online
2020-10-01