An X-ray image-based pruned dense convolution neural network for tuberculosis detection

According to the Ministry of Health in Kenya, tuberculosis (TB) is the fifth greatest cause of death and the main infectious disease killer in Kenya and across the world. In Kenya and throughout Africa, TB continues to wreak havoc on many vulnerable populations, homes, and communities despite being...

Full description

Saved in:
Bibliographic Details
Main Authors: Edna Chebet Too, David Gitonga Mwathi, Lucy Kawira Gitonga, Pauline Mwaka, Saif Kinyori
Format: Article
Language:English
Published: Elsevier 2024-01-01
Series:Computer Methods and Programs in Biomedicine Update
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666990024000363
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850124353287487488
author Edna Chebet Too
David Gitonga Mwathi
Lucy Kawira Gitonga
Pauline Mwaka
Saif Kinyori
author_facet Edna Chebet Too
David Gitonga Mwathi
Lucy Kawira Gitonga
Pauline Mwaka
Saif Kinyori
author_sort Edna Chebet Too
collection DOAJ
description According to the Ministry of Health in Kenya, tuberculosis (TB) is the fifth greatest cause of death and the main infectious disease killer in Kenya and across the world. In Kenya and throughout Africa, TB continues to wreak havoc on many vulnerable populations, homes, and communities despite being preventable and treatable. Common TB diagnostics, like blood and skin tests, frequently fail to identify the precise kind of TB. As a result, the World Health Organization (WHO) advises expanding the use of X-rays, for screening. In TB-prevalent regions of Kenya, a shortage of radiologists hampers effective screening and diagnosis, highlighting the need for scalable solutions for accurate X-ray analysis.Recent advancements in deep learning techniques have shown promise in the healthcare sector, particularly in radiology. However, many deep convolutional neural network (CNN) architectures are computationally intensive due to their size and resource requirements. This study designed and developed a Pruned CNN to address this issue by applying pruning techniques to baseline architectures. This approach significantly reduced model sizes while maintaining accuracy levels. Specifically, the pruned version of the DenseNet model achieved an impressive 99 % accuracy with a reduction rate of 65.8 %. These results highlight the potential of this pruned CNN as an effective and efficient tool for TB detection, particularly in resource-constrained environments. This study addresses the shortage of radiological expertise in many regions by providing a tool that can assist in the interpretation of X-ray images. This capability can help healthcare providers deliver timely and accurate diagnoses, thereby improving patient care.
format Article
id doaj-art-60ebd0312e674ad0a07aefc323a627be
institution OA Journals
issn 2666-9900
language English
publishDate 2024-01-01
publisher Elsevier
record_format Article
series Computer Methods and Programs in Biomedicine Update
spelling doaj-art-60ebd0312e674ad0a07aefc323a627be2025-08-20T02:34:20ZengElsevierComputer Methods and Programs in Biomedicine Update2666-99002024-01-01610016910.1016/j.cmpbup.2024.100169An X-ray image-based pruned dense convolution neural network for tuberculosis detectionEdna Chebet Too0David Gitonga Mwathi1Lucy Kawira Gitonga2Pauline Mwaka3Saif Kinyori4Computer Science, Faculty of Science and Technology, Chuka University, Chuka, Kenya; Corresponding author.Computer Science, Faculty of Science and Technology, Chuka University, Chuka, KenyaNursing, School of Nursing and Public Health, Chuka, KenyaComputer Science, Faculty of Science and Technology, Chuka University, Chuka, KenyaComputer Science, Faculty of Science and Technology, Chuka University, Chuka, Kenya; Information Communication and Technology, Faculty of Science and Technology, Chuka University, Chuka, KenyaAccording to the Ministry of Health in Kenya, tuberculosis (TB) is the fifth greatest cause of death and the main infectious disease killer in Kenya and across the world. In Kenya and throughout Africa, TB continues to wreak havoc on many vulnerable populations, homes, and communities despite being preventable and treatable. Common TB diagnostics, like blood and skin tests, frequently fail to identify the precise kind of TB. As a result, the World Health Organization (WHO) advises expanding the use of X-rays, for screening. In TB-prevalent regions of Kenya, a shortage of radiologists hampers effective screening and diagnosis, highlighting the need for scalable solutions for accurate X-ray analysis.Recent advancements in deep learning techniques have shown promise in the healthcare sector, particularly in radiology. However, many deep convolutional neural network (CNN) architectures are computationally intensive due to their size and resource requirements. This study designed and developed a Pruned CNN to address this issue by applying pruning techniques to baseline architectures. This approach significantly reduced model sizes while maintaining accuracy levels. Specifically, the pruned version of the DenseNet model achieved an impressive 99 % accuracy with a reduction rate of 65.8 %. These results highlight the potential of this pruned CNN as an effective and efficient tool for TB detection, particularly in resource-constrained environments. This study addresses the shortage of radiological expertise in many regions by providing a tool that can assist in the interpretation of X-ray images. This capability can help healthcare providers deliver timely and accurate diagnoses, thereby improving patient care.http://www.sciencedirect.com/science/article/pii/S2666990024000363Pruned CNNTuberculosis detectionDensely convolution neural networkDeep learningImage processingPruning
spellingShingle Edna Chebet Too
David Gitonga Mwathi
Lucy Kawira Gitonga
Pauline Mwaka
Saif Kinyori
An X-ray image-based pruned dense convolution neural network for tuberculosis detection
Computer Methods and Programs in Biomedicine Update
Pruned CNN
Tuberculosis detection
Densely convolution neural network
Deep learning
Image processing
Pruning
title An X-ray image-based pruned dense convolution neural network for tuberculosis detection
title_full An X-ray image-based pruned dense convolution neural network for tuberculosis detection
title_fullStr An X-ray image-based pruned dense convolution neural network for tuberculosis detection
title_full_unstemmed An X-ray image-based pruned dense convolution neural network for tuberculosis detection
title_short An X-ray image-based pruned dense convolution neural network for tuberculosis detection
title_sort x ray image based pruned dense convolution neural network for tuberculosis detection
topic Pruned CNN
Tuberculosis detection
Densely convolution neural network
Deep learning
Image processing
Pruning
url http://www.sciencedirect.com/science/article/pii/S2666990024000363
work_keys_str_mv AT ednachebettoo anxrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT davidgitongamwathi anxrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT lucykawiragitonga anxrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT paulinemwaka anxrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT saifkinyori anxrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT ednachebettoo xrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT davidgitongamwathi xrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT lucykawiragitonga xrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT paulinemwaka xrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection
AT saifkinyori xrayimagebasedpruneddenseconvolutionneuralnetworkfortuberculosisdetection