Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization

Tuberculosis (TB) is a chronic lung disease that occurs due to bacterial infection and is one of the top 10 leading causes of death. Accurate and early detection of TB is very important, otherwise, it could be life-threatening. In this work, we have detected TB reliably from the chest X-ray images u...

Full description

Saved in:
Bibliographic Details
Main Authors: Tawsifur Rahman, Amith Khandakar, Muhammad Abdul Kadir, Khandaker Rejaul Islam, Khandakar F. Islam, Rashid Mazhar, Tahir Hamid, Mohammad Tariqul Islam, Saad Kashem, Zaid Bin Mahbub, Mohamed Arselene Ayari, Muhammad E. H. Chowdhury
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9224622/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223140059643904
author Tawsifur Rahman
Amith Khandakar
Muhammad Abdul Kadir
Khandaker Rejaul Islam
Khandakar F. Islam
Rashid Mazhar
Tahir Hamid
Mohammad Tariqul Islam
Saad Kashem
Zaid Bin Mahbub
Mohamed Arselene Ayari
Muhammad E. H. Chowdhury
author_facet Tawsifur Rahman
Amith Khandakar
Muhammad Abdul Kadir
Khandaker Rejaul Islam
Khandakar F. Islam
Rashid Mazhar
Tahir Hamid
Mohammad Tariqul Islam
Saad Kashem
Zaid Bin Mahbub
Mohamed Arselene Ayari
Muhammad E. H. Chowdhury
author_sort Tawsifur Rahman
collection DOAJ
description Tuberculosis (TB) is a chronic lung disease that occurs due to bacterial infection and is one of the top 10 leading causes of death. Accurate and early detection of TB is very important, otherwise, it could be life-threatening. In this work, we have detected TB reliably from the chest X-ray images using image pre-processing, data augmentation, image segmentation, and deep-learning classification techniques. Several public databases were used to create a database of 3500 TB infected and 3500 normal chest X-ray images for this study. Nine different deep CNNs (ResNet18, ResNet50, ResNet101, ChexNet, InceptionV3, Vgg19, DenseNet201, SqueezeNet, and MobileNet) were used for transfer learning from their pre-trained initial weights and were trained, validated and tested for classifying TB and non-TB normal cases. Three different experiments were carried out in this work: segmentation of X-ray images using two different U-net models, classification using X-ray images and that using segmented lung images. The accuracy, precision, sensitivity, F1-score and specificity of best performing model, ChexNet in the detection of tuberculosis using X-ray images were 96.47%, 96.62%, 96.47%, 96.47%, and 96.51% respectively. However, classification using segmented lung images outperformed that with whole X-ray images; the accuracy, precision, sensitivity, F1-score and specificity of DenseNet201 were 98.6%, 98.57%, 98.56%, 98.56%, and 98.54% respectively for the segmented lung images. The paper also used a visualization technique to confirm that CNN learns dominantly from the segmented lung regions that resulted in higher detection accuracy. The proposed method with state-of-the-art performance can be useful in the computer-aided faster diagnosis of tuberculosis.
format Article
id doaj-art-d2a9254331be4948af19234b0c77f376
institution Kabale University
issn 2169-3536
language English
publishDate 2020-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-d2a9254331be4948af19234b0c77f3762025-08-25T23:00:40ZengIEEEIEEE Access2169-35362020-01-01819158619160110.1109/ACCESS.2020.30313849224622Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and VisualizationTawsifur Rahman0https://orcid.org/0000-0002-6938-6496Amith Khandakar1https://orcid.org/0000-0001-7068-9112Muhammad Abdul Kadir2https://orcid.org/0000-0002-4535-9215Khandaker Rejaul Islam3https://orcid.org/0000-0003-2863-8156Khandakar F. Islam4Rashid Mazhar5https://orcid.org/0000-0003-4255-8996Tahir Hamid6Mohammad Tariqul Islam7https://orcid.org/0000-0002-4929-3209Saad Kashem8Zaid Bin Mahbub9Mohamed Arselene Ayari10https://orcid.org/0000-0002-8663-886XMuhammad E. H. Chowdhury11https://orcid.org/0000-0003-0744-8206Department of Biomedical Physics and Technology, University of Dhaka, Dhaka, BangladeshDepartment of Electrical Engineering, Qatar University, Doha, QatarDepartment of Biomedical Physics and Technology, University of Dhaka, Dhaka, BangladeshDepartment of Orthodontics, Bangabandhu Sheikh Mujib Medical University, Dhaka, BangladeshDepartment of Electrical Engineering, Qatar University, Doha, QatarThoracic Surgery, Hamad General Hospital, Doha, QatarDepartment of Medicine, Weill Cornell Medicine-Qatar, Doha, QatarDepartment of Electrical, Electronic, and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi, MalaysiaFaculty of Robotics and Advanced Computing, Qatar Armed Forces-Academic Bridge Program, Qatar Foundation, Doha, QatarDepartment of Mathematics and Physics, North South University, Dhaka, BangladeshCollege of Engineering, Qatar University, Doha, QatarDepartment of Biomedical Physics and Technology, University of Dhaka, Dhaka, BangladeshTuberculosis (TB) is a chronic lung disease that occurs due to bacterial infection and is one of the top 10 leading causes of death. Accurate and early detection of TB is very important, otherwise, it could be life-threatening. In this work, we have detected TB reliably from the chest X-ray images using image pre-processing, data augmentation, image segmentation, and deep-learning classification techniques. Several public databases were used to create a database of 3500 TB infected and 3500 normal chest X-ray images for this study. Nine different deep CNNs (ResNet18, ResNet50, ResNet101, ChexNet, InceptionV3, Vgg19, DenseNet201, SqueezeNet, and MobileNet) were used for transfer learning from their pre-trained initial weights and were trained, validated and tested for classifying TB and non-TB normal cases. Three different experiments were carried out in this work: segmentation of X-ray images using two different U-net models, classification using X-ray images and that using segmented lung images. The accuracy, precision, sensitivity, F1-score and specificity of best performing model, ChexNet in the detection of tuberculosis using X-ray images were 96.47%, 96.62%, 96.47%, 96.47%, and 96.51% respectively. However, classification using segmented lung images outperformed that with whole X-ray images; the accuracy, precision, sensitivity, F1-score and specificity of DenseNet201 were 98.6%, 98.57%, 98.56%, 98.56%, and 98.54% respectively for the segmented lung images. The paper also used a visualization technique to confirm that CNN learns dominantly from the segmented lung regions that resulted in higher detection accuracy. The proposed method with state-of-the-art performance can be useful in the computer-aided faster diagnosis of tuberculosis.https://ieeexplore.ieee.org/document/9224622/Tuberculosis detectionTB screeningdeep learningtransfer learninglungs segmentationimage processing
spellingShingle Tawsifur Rahman
Amith Khandakar
Muhammad Abdul Kadir
Khandaker Rejaul Islam
Khandakar F. Islam
Rashid Mazhar
Tahir Hamid
Mohammad Tariqul Islam
Saad Kashem
Zaid Bin Mahbub
Mohamed Arselene Ayari
Muhammad E. H. Chowdhury
Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization
IEEE Access
Tuberculosis detection
TB screening
deep learning
transfer learning
lungs segmentation
image processing
title Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization
title_full Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization
title_fullStr Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization
title_full_unstemmed Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization
title_short Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization
title_sort reliable tuberculosis detection using chest x ray with deep learning segmentation and visualization
topic Tuberculosis detection
TB screening
deep learning
transfer learning
lungs segmentation
image processing
url https://ieeexplore.ieee.org/document/9224622/
work_keys_str_mv AT tawsifurrahman reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT amithkhandakar reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT muhammadabdulkadir reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT khandakerrejaulislam reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT khandakarfislam reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT rashidmazhar reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT tahirhamid reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT mohammadtariqulislam reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT saadkashem reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT zaidbinmahbub reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT mohamedarseleneayari reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization
AT muhammadehchowdhury reliabletuberculosisdetectionusingchestxraywithdeeplearningsegmentationandvisualization