Imperial College London

ProfessorDanielRueckert

Faculty of EngineeringDepartment of Computing

Head of Department of Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8333d.rueckert Website

 
 
//

Location

 

568Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Howard:2019:10.1016/j.jacep.2019.02.003,
author = {Howard, J and Fisher, L and Shun-Shin, M and Keene, D and Arnold, A and Ahmad, Y and Cook, C and Moon, J and Manisty, C and Whinnett, Z and Cole, G and Rueckert, D and Francis, D},
doi = {10.1016/j.jacep.2019.02.003},
journal = {JACC: Clinical Electrophysiology},
pages = {576--586},
title = {Cardiac rhythm device identification using neural networks},
url = {http://dx.doi.org/10.1016/j.jacep.2019.02.003},
volume = {5},
year = {2019}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - BackgroundMedical staff often need to determine the model of a pacemaker or defibrillator (cardiac rhythm devices) quickly and accurately. Current approaches involve comparing a device’s X-ray appearance with a manual flow chart. We aimed to see whether a neural network could be trained to perform this task more accurately.Methods and ResultsWe extracted X-ray images of 1676 devices, comprising 45 models from 5 manufacturers. We developed a convolutional neural network to classify the images, using a training set of 1451 images. The testing set was a further 225 images, consisting of 5 examples of each model. We compared the network’s ability to identify the manufacturer of a device with those of cardiologists using a published flow-chart.The neural network was 99.6% (95% CI 97.5 to 100) accurate in identifying the manufacturer of a device from an X-ray, and 96.4% (95% CI 93.1 to 98.5) accurate in identifying the model group. Amongst 5 cardiologists using the flow-chart, median manufacturer accuracy was 72.0% (range 62.2% to 88.9%), and model group identification was not possible. The network was significantly superior to all of the cardiologists in identifying the manufacturer (p < 0.0001 against the median human; p < 0.0001 against the best human).ConclusionsA neural network can accurately identify the manufacturer and even model group of a cardiac rhythm device from an X-ray, and exceeds human performance. This system may speed up the diagnosis and treatment of patients with cardiac rhythm devices and it is publicly accessible online.
AU - Howard,J
AU - Fisher,L
AU - Shun-Shin,M
AU - Keene,D
AU - Arnold,A
AU - Ahmad,Y
AU - Cook,C
AU - Moon,J
AU - Manisty,C
AU - Whinnett,Z
AU - Cole,G
AU - Rueckert,D
AU - Francis,D
DO - 10.1016/j.jacep.2019.02.003
EP - 586
PY - 2019///
SN - 2405-5018
SP - 576
TI - Cardiac rhythm device identification using neural networks
T2 - JACC: Clinical Electrophysiology
UR - http://dx.doi.org/10.1016/j.jacep.2019.02.003
UR - http://hdl.handle.net/10044/1/67610
VL - 5
ER -