Application of deep neural networks to improve diagnostic accuracy of rheumatoid arthritis using diffuse optical tomography

Research output: Contribution to journalArticle

Standard

Application of deep neural networks to improve diagnostic accuracy of rheumatoid arthritis using diffuse optical tomography. / Feng , Yangqin; Lighter, D; Zhang Lei; Wang Yan, ; Dehghani, H.

In: Quantum Electronics, Vol. 50, No. 1, 01.01.2020, p. 21-32.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Bibtex

@article{2fe2aece3d9e4abb8d688ea58aae873f,
title = "Application of deep neural networks to improve diagnostic accuracy of rheumatoid arthritis using diffuse optical tomography",
abstract = "A set of deep neural network models for rheumatoid arthritis (RA) classification using a highway network, a convolutional neural network and a residual network is proposed based on the data of diffuse optical tomography (DOT) utilising near-infrared light, which ensures early diagnosis of pathophysiological changes resulting from inflammation. A numerical model of the finger is used to generate images to overcome the inherent problem of insufficient clinical DOT images available. The proposed deep neural network models are applied to automatically classify simulated DOT images of inflamed and non-inflamed joints and transfer learning is also used to improve the performance of the classification. The results demonstrate that all three deep neural network methods improve the diagnostic accuracy as compared to the widely applied support vector machine (SVM), especially for high inter-subject variability databases. In cases of distinct modelled severity of disease, residual network achieved the highest accuracy (> 99%), and both of highway and convolutional neural networks reached 99%, respectively. However, as the severity of the modelled disease is reduced, this accuracy is reduced to 75.2% for residual networks. The results indicate that transfer learning can improve the performance of deep neural network methods on RA classification from DOT data and highlight their potential as a computer aided tool in DOT diagnostic systems.",
keywords = "rheumatoid arthritis diagnosis, diffuse optical tomography, finger joints, deep neural networks, medical image classification",
author = "Yangqin Feng and D Lighter and {Zhang Lei} and {Wang Yan} and H Dehghani",
year = "2020",
month = jan,
day = "1",
doi = "10.1070/QEL17177",
language = "English",
volume = "50",
pages = "21--32",
journal = "Quantum Electronics",
issn = "1063-7818",
publisher = "Turpion Ltd.",
number = "1",

}

RIS

TY - JOUR

T1 - Application of deep neural networks to improve diagnostic accuracy of rheumatoid arthritis using diffuse optical tomography

AU - Feng , Yangqin

AU - Lighter, D

AU - Zhang Lei, null

AU - Wang Yan, null

AU - Dehghani, H

PY - 2020/1/1

Y1 - 2020/1/1

N2 - A set of deep neural network models for rheumatoid arthritis (RA) classification using a highway network, a convolutional neural network and a residual network is proposed based on the data of diffuse optical tomography (DOT) utilising near-infrared light, which ensures early diagnosis of pathophysiological changes resulting from inflammation. A numerical model of the finger is used to generate images to overcome the inherent problem of insufficient clinical DOT images available. The proposed deep neural network models are applied to automatically classify simulated DOT images of inflamed and non-inflamed joints and transfer learning is also used to improve the performance of the classification. The results demonstrate that all three deep neural network methods improve the diagnostic accuracy as compared to the widely applied support vector machine (SVM), especially for high inter-subject variability databases. In cases of distinct modelled severity of disease, residual network achieved the highest accuracy (> 99%), and both of highway and convolutional neural networks reached 99%, respectively. However, as the severity of the modelled disease is reduced, this accuracy is reduced to 75.2% for residual networks. The results indicate that transfer learning can improve the performance of deep neural network methods on RA classification from DOT data and highlight their potential as a computer aided tool in DOT diagnostic systems.

AB - A set of deep neural network models for rheumatoid arthritis (RA) classification using a highway network, a convolutional neural network and a residual network is proposed based on the data of diffuse optical tomography (DOT) utilising near-infrared light, which ensures early diagnosis of pathophysiological changes resulting from inflammation. A numerical model of the finger is used to generate images to overcome the inherent problem of insufficient clinical DOT images available. The proposed deep neural network models are applied to automatically classify simulated DOT images of inflamed and non-inflamed joints and transfer learning is also used to improve the performance of the classification. The results demonstrate that all three deep neural network methods improve the diagnostic accuracy as compared to the widely applied support vector machine (SVM), especially for high inter-subject variability databases. In cases of distinct modelled severity of disease, residual network achieved the highest accuracy (> 99%), and both of highway and convolutional neural networks reached 99%, respectively. However, as the severity of the modelled disease is reduced, this accuracy is reduced to 75.2% for residual networks. The results indicate that transfer learning can improve the performance of deep neural network methods on RA classification from DOT data and highlight their potential as a computer aided tool in DOT diagnostic systems.

KW - rheumatoid arthritis diagnosis

KW - diffuse optical tomography

KW - finger joints

KW - deep neural networks

KW - medical image classification

UR - http://www.scopus.com/inward/record.url?scp=85082399705&partnerID=8YFLogxK

U2 - 10.1070/QEL17177

DO - 10.1070/QEL17177

M3 - Article

VL - 50

SP - 21

EP - 32

JO - Quantum Electronics

JF - Quantum Electronics

SN - 1063-7818

IS - 1

ER -