Imperial College London

ProfessorDarrelFrancis

Faculty of MedicineNational Heart & Lung Institute

Professor of Cardiology
 
 
 
//

Contact

 

+44 (0)20 7594 3381d.francis Website

 
 
//

Assistant

 

Miss Juliet Holmes +44 (0)20 7594 5735

 
//

Location

 

Block B Hammersmith HospitalHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Howard:2020:10.21037/jmai.2019.10.03,
author = {Howard, JP and Tan, J and Shun-Shin, MJ and Mahdi, D and Nowbar, AN and Arnold, AD and Ahmad, Y and McCartney, P and Zolgharni, M and Linton, NWF and Sutaria, N and Rana, B and Mayet, J and Rueckert, D and Cole, GD and Francis, DP},
doi = {10.21037/jmai.2019.10.03},
journal = {J Med Artif Intell},
title = {Improving ultrasound video classification: an evaluation of novel deep learning methods in echocardiography.},
url = {http://dx.doi.org/10.21037/jmai.2019.10.03},
volume = {3},
year = {2020}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Echocardiography is the commonest medical ultrasound examination, but automated interpretation is challenging and hinges on correct recognition of the 'view' (imaging plane and orientation). Current state-of-the-art methods for identifying the view computationally involve 2-dimensional convolutional neural networks (CNNs), but these merely classify individual frames of a video in isolation, and ignore information describing the movement of structures throughout the cardiac cycle. Here we explore the efficacy of novel CNN architectures, including time-distributed networks and two-stream networks, which are inspired by advances in human action recognition. We demonstrate that these new architectures more than halve the error rate of traditional CNNs from 8.1% to 3.9%. These advances in accuracy may be due to these networks' ability to track the movement of specific structures such as heart valves throughout the cardiac cycle. Finally, we show the accuracies of these new state-of-the-art networks are approaching expert agreement (3.6% discordance), with a similar pattern of discordance between views.
AU - Howard,JP
AU - Tan,J
AU - Shun-Shin,MJ
AU - Mahdi,D
AU - Nowbar,AN
AU - Arnold,AD
AU - Ahmad,Y
AU - McCartney,P
AU - Zolgharni,M
AU - Linton,NWF
AU - Sutaria,N
AU - Rana,B
AU - Mayet,J
AU - Rueckert,D
AU - Cole,GD
AU - Francis,DP
DO - 10.21037/jmai.2019.10.03
PY - 2020///
TI - Improving ultrasound video classification: an evaluation of novel deep learning methods in echocardiography.
T2 - J Med Artif Intell
UR - http://dx.doi.org/10.21037/jmai.2019.10.03
UR - https://www.ncbi.nlm.nih.gov/pubmed/32226937
VL - 3
ER -