Deep learning algorithms with demographic information help to detect tuberculosis in chest radiographs in annual workers’ health examination data

Seok Jae Heo, Yangwook Kim, Sehyun Yun, Sung Shil Lim, Jihyun Kim, Chung Mo Nam, Euncheol Park, Inkyung Jung, JinHa Yoon

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We aimed to use deep learning to detect tuberculosis in chest radiographs in annual workers’ health examination data and compare the performances of convolutional neural networks (CNNs) based on images only (I-CNN) and CNNs including demographic variables (D-CNN). The I-CNN and D-CNN models were trained on 1000 chest X-ray images, both positive and negative, for tuberculosis. Feature extraction was conducted using VGG19, InceptionV3, ResNet50, DenseNet121, and InceptionResNetV2. Age, weight, height, and gender were recorded as demographic variables. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated for model comparison. The AUC values of the D-CNN models were greater than that of I-CNN. The AUC values for VGG19 increased by 0.0144 (0.957 to 0.9714) in the training set, and by 0.0138 (0.9075 to 0.9213) in the test set (both p < 0.05). The D-CNN models show greater sensitivity than I-CNN models (0.815 vs. 0.775, respectively) at the same cut-off point for the same specificity of 0.962. The sensitivity of D-CNN does not attenuate as much as that of I-CNN, even when specificity is increased by cut-off points. Conclusion: Our results indicate that machine learning can facilitate the detection of tuberculosis in chest X-rays, and demographic factors can improve this process.

Original languageEnglish
Article number250
JournalInternational journal of environmental research and public health
Volume16
Issue number2
DOIs
Publication statusPublished - 2019 Jan 2

Fingerprint

Neural Networks (Computer)
Tuberculosis
Thorax
Demography
Learning
Area Under Curve
Health
X-Rays
ROC Curve
Weights and Measures

All Science Journal Classification (ASJC) codes

  • Public Health, Environmental and Occupational Health
  • Health, Toxicology and Mutagenesis

Cite this

@article{525d94fa6e4a473480f35c2619fa40c5,
title = "Deep learning algorithms with demographic information help to detect tuberculosis in chest radiographs in annual workers’ health examination data",
abstract = "We aimed to use deep learning to detect tuberculosis in chest radiographs in annual workers’ health examination data and compare the performances of convolutional neural networks (CNNs) based on images only (I-CNN) and CNNs including demographic variables (D-CNN). The I-CNN and D-CNN models were trained on 1000 chest X-ray images, both positive and negative, for tuberculosis. Feature extraction was conducted using VGG19, InceptionV3, ResNet50, DenseNet121, and InceptionResNetV2. Age, weight, height, and gender were recorded as demographic variables. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated for model comparison. The AUC values of the D-CNN models were greater than that of I-CNN. The AUC values for VGG19 increased by 0.0144 (0.957 to 0.9714) in the training set, and by 0.0138 (0.9075 to 0.9213) in the test set (both p < 0.05). The D-CNN models show greater sensitivity than I-CNN models (0.815 vs. 0.775, respectively) at the same cut-off point for the same specificity of 0.962. The sensitivity of D-CNN does not attenuate as much as that of I-CNN, even when specificity is increased by cut-off points. Conclusion: Our results indicate that machine learning can facilitate the detection of tuberculosis in chest X-rays, and demographic factors can improve this process.",
author = "Heo, {Seok Jae} and Yangwook Kim and Sehyun Yun and Lim, {Sung Shil} and Jihyun Kim and Nam, {Chung Mo} and Euncheol Park and Inkyung Jung and JinHa Yoon",
year = "2019",
month = "1",
day = "2",
doi = "10.3390/ijerph16020250",
language = "English",
volume = "16",
journal = "International Journal of Environmental Research and Public Health",
issn = "1661-7827",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "2",

}

Deep learning algorithms with demographic information help to detect tuberculosis in chest radiographs in annual workers’ health examination data. / Heo, Seok Jae; Kim, Yangwook; Yun, Sehyun; Lim, Sung Shil; Kim, Jihyun; Nam, Chung Mo; Park, Euncheol; Jung, Inkyung; Yoon, JinHa.

In: International journal of environmental research and public health, Vol. 16, No. 2, 250, 02.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Deep learning algorithms with demographic information help to detect tuberculosis in chest radiographs in annual workers’ health examination data

AU - Heo, Seok Jae

AU - Kim, Yangwook

AU - Yun, Sehyun

AU - Lim, Sung Shil

AU - Kim, Jihyun

AU - Nam, Chung Mo

AU - Park, Euncheol

AU - Jung, Inkyung

AU - Yoon, JinHa

PY - 2019/1/2

Y1 - 2019/1/2

N2 - We aimed to use deep learning to detect tuberculosis in chest radiographs in annual workers’ health examination data and compare the performances of convolutional neural networks (CNNs) based on images only (I-CNN) and CNNs including demographic variables (D-CNN). The I-CNN and D-CNN models were trained on 1000 chest X-ray images, both positive and negative, for tuberculosis. Feature extraction was conducted using VGG19, InceptionV3, ResNet50, DenseNet121, and InceptionResNetV2. Age, weight, height, and gender were recorded as demographic variables. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated for model comparison. The AUC values of the D-CNN models were greater than that of I-CNN. The AUC values for VGG19 increased by 0.0144 (0.957 to 0.9714) in the training set, and by 0.0138 (0.9075 to 0.9213) in the test set (both p < 0.05). The D-CNN models show greater sensitivity than I-CNN models (0.815 vs. 0.775, respectively) at the same cut-off point for the same specificity of 0.962. The sensitivity of D-CNN does not attenuate as much as that of I-CNN, even when specificity is increased by cut-off points. Conclusion: Our results indicate that machine learning can facilitate the detection of tuberculosis in chest X-rays, and demographic factors can improve this process.

AB - We aimed to use deep learning to detect tuberculosis in chest radiographs in annual workers’ health examination data and compare the performances of convolutional neural networks (CNNs) based on images only (I-CNN) and CNNs including demographic variables (D-CNN). The I-CNN and D-CNN models were trained on 1000 chest X-ray images, both positive and negative, for tuberculosis. Feature extraction was conducted using VGG19, InceptionV3, ResNet50, DenseNet121, and InceptionResNetV2. Age, weight, height, and gender were recorded as demographic variables. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated for model comparison. The AUC values of the D-CNN models were greater than that of I-CNN. The AUC values for VGG19 increased by 0.0144 (0.957 to 0.9714) in the training set, and by 0.0138 (0.9075 to 0.9213) in the test set (both p < 0.05). The D-CNN models show greater sensitivity than I-CNN models (0.815 vs. 0.775, respectively) at the same cut-off point for the same specificity of 0.962. The sensitivity of D-CNN does not attenuate as much as that of I-CNN, even when specificity is increased by cut-off points. Conclusion: Our results indicate that machine learning can facilitate the detection of tuberculosis in chest X-rays, and demographic factors can improve this process.

UR - http://www.scopus.com/inward/record.url?scp=85060181347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060181347&partnerID=8YFLogxK

U2 - 10.3390/ijerph16020250

DO - 10.3390/ijerph16020250

M3 - Article

C2 - 30654560

AN - SCOPUS:85060181347

VL - 16

JO - International Journal of Environmental Research and Public Health

JF - International Journal of Environmental Research and Public Health

SN - 1661-7827

IS - 2

M1 - 250

ER -