Effective pneumonia detection using ResNet based transfer learning

Pneumonia is a deadly lungs disease known as silent killer is due to bacterial, viral, or fungal infection and causes lung alveoli to fill with pus or fluids. The most common diagnostic tool for pneumonia is Chest X-rays. However, due to several other medical conditions in the lungs, such as volume...

Full description

Bibliographic Details
Main Authors: Ansari, Naseem, Faizabadi, Ahmed Rimaz, Motakabber, S. M. A., Ibrahimy, Muhammad Ibn
Format: Article
Language:English
Published: The Mattingley Publishing Co., Inc. 2020
Subjects:
Online Access:http://irep.iium.edu.my/79986/
http://irep.iium.edu.my/79986/1/Effective%20Pneumonia%20Detection%20using%20ResNet%20based%20Transfer%20Learning.pdf
_version_ 1848788885124939776
author Ansari, Naseem
Faizabadi, Ahmed Rimaz
Motakabber, S. M. A.
Ibrahimy, Muhammad Ibn
author_facet Ansari, Naseem
Faizabadi, Ahmed Rimaz
Motakabber, S. M. A.
Ibrahimy, Muhammad Ibn
author_sort Ansari, Naseem
building IIUM Repository
collection Online Access
description Pneumonia is a deadly lungs disease known as silent killer is due to bacterial, viral, or fungal infection and causes lung alveoli to fill with pus or fluids. The most common diagnostic tool for pneumonia is Chest X-rays. However, due to several other medical conditions in the lungs, such as volume loss, bleeding,lung cancer,fluid overload,post-radiation or surgery, the diagnosis of pneumonia using chest X-rays becomes very complicated. Therefore, there is a dire need for computer-aided diagnosis systems to assist clinicians in making better decisions. This work proposes an effective, deep convolutional neural network with ResNet-50 architecture for pneumonia detection ResNet has performed quite well on the image recognition task and was a winner of the ImageNet challenge.A pre-trained ResNet-50 model is re-trained with the use of Transfer Learning on two different datasets of chest x-ray images. ResNet-50 based diagnostics model is found useful for pneumonia diagnostics despite significant variations in two datasets. The trained model has achieved an accuracy of 96.76%, which is at par with state-of-the-art techniques available. RSNA dataset, with five times more images than the Chest X-ray Image dataset, took very little time for training. Also, because of the use of the Transfer Learning technique, both the models were able to learn the significant features of pneumonia with only 50% training dataset size.However, the model can be improvised by using more deeper networks. Work can be extended to detect and classify both lung cancer and pneumonia using X-ray images.
first_indexed 2025-11-14T17:47:56Z
format Article
id iium-79986
institution International Islamic University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T17:47:56Z
publishDate 2020
publisher The Mattingley Publishing Co., Inc.
recordtype eprints
repository_type Digital Repository
spelling iium-799862020-11-24T08:27:44Z http://irep.iium.edu.my/79986/ Effective pneumonia detection using ResNet based transfer learning Ansari, Naseem Faizabadi, Ahmed Rimaz Motakabber, S. M. A. Ibrahimy, Muhammad Ibn T Technology (General) Pneumonia is a deadly lungs disease known as silent killer is due to bacterial, viral, or fungal infection and causes lung alveoli to fill with pus or fluids. The most common diagnostic tool for pneumonia is Chest X-rays. However, due to several other medical conditions in the lungs, such as volume loss, bleeding,lung cancer,fluid overload,post-radiation or surgery, the diagnosis of pneumonia using chest X-rays becomes very complicated. Therefore, there is a dire need for computer-aided diagnosis systems to assist clinicians in making better decisions. This work proposes an effective, deep convolutional neural network with ResNet-50 architecture for pneumonia detection ResNet has performed quite well on the image recognition task and was a winner of the ImageNet challenge.A pre-trained ResNet-50 model is re-trained with the use of Transfer Learning on two different datasets of chest x-ray images. ResNet-50 based diagnostics model is found useful for pneumonia diagnostics despite significant variations in two datasets. The trained model has achieved an accuracy of 96.76%, which is at par with state-of-the-art techniques available. RSNA dataset, with five times more images than the Chest X-ray Image dataset, took very little time for training. Also, because of the use of the Transfer Learning technique, both the models were able to learn the significant features of pneumonia with only 50% training dataset size.However, the model can be improvised by using more deeper networks. Work can be extended to detect and classify both lung cancer and pneumonia using X-ray images. The Mattingley Publishing Co., Inc. 2020-02-28 Article PeerReviewed application/pdf en http://irep.iium.edu.my/79986/1/Effective%20Pneumonia%20Detection%20using%20ResNet%20based%20Transfer%20Learning.pdf Ansari, Naseem and Faizabadi, Ahmed Rimaz and Motakabber, S. M. A. and Ibrahimy, Muhammad Ibn (2020) Effective pneumonia detection using ResNet based transfer learning. Test Engineering and Management, 82 (Jan/Feb). pp. 15146-15153. ISSN 0193 -4120 http://www.testmagzine.biz/index.php/testmagzine/article/view/3228/2851
spellingShingle T Technology (General)
Ansari, Naseem
Faizabadi, Ahmed Rimaz
Motakabber, S. M. A.
Ibrahimy, Muhammad Ibn
Effective pneumonia detection using ResNet based transfer learning
title Effective pneumonia detection using ResNet based transfer learning
title_full Effective pneumonia detection using ResNet based transfer learning
title_fullStr Effective pneumonia detection using ResNet based transfer learning
title_full_unstemmed Effective pneumonia detection using ResNet based transfer learning
title_short Effective pneumonia detection using ResNet based transfer learning
title_sort effective pneumonia detection using resnet based transfer learning
topic T Technology (General)
url http://irep.iium.edu.my/79986/
http://irep.iium.edu.my/79986/
http://irep.iium.edu.my/79986/1/Effective%20Pneumonia%20Detection%20using%20ResNet%20based%20Transfer%20Learning.pdf