RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-Rays

<b>Background:</b> Chest X-rays are rapidly gaining prominence as a prevalent diagnostic tool, as recognized by the World Health Organization (WHO). However, interpreting chest X-rays can be demanding and time-consuming, even for experienced radiologists, leading to potential misinterpre...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanan Aljuaid, Hessa Albalahad, Walaa Alshuaibi, Shahad Almutairi, Tahani Hamad Aljohani, Nazar Hussain, Farah Mohammad
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/13/1728
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704663097540608
author Hanan Aljuaid
Hessa Albalahad
Walaa Alshuaibi
Shahad Almutairi
Tahani Hamad Aljohani
Nazar Hussain
Farah Mohammad
author_facet Hanan Aljuaid
Hessa Albalahad
Walaa Alshuaibi
Shahad Almutairi
Tahani Hamad Aljohani
Nazar Hussain
Farah Mohammad
author_sort Hanan Aljuaid
collection DOAJ
description <b>Background:</b> Chest X-rays are rapidly gaining prominence as a prevalent diagnostic tool, as recognized by the World Health Organization (WHO). However, interpreting chest X-rays can be demanding and time-consuming, even for experienced radiologists, leading to potential misinterpretations and delays in treatment. <b>Method:</b> The purpose of this research is the development of a RadAI model. The RadAI model can accurately detect four types of lung abnormalities in chest X-rays and generate a report on each identified abnormality. Moreover, deep learning algorithms, particularly convolutional neural networks (CNNs), have demonstrated remarkable potential in automating medical image analysis, including chest X-rays. This work addresses the challenge of chest X-ray interpretation by fine tuning the following three advanced deep learning models: Feature-selective and Spatial Receptive Fields Network (FSRFNet50), ResNext50, and ResNet50. These models are compared based on accuracy, precision, recall, and F1-score. <b>Results:</b> The outstanding performance of RadAI shows its potential to assist radiologists to interpret the detected chest abnormalities accurately. <b>Conclusions:</b> RadAI is beneficial in enhancing the accuracy and efficiency of chest X-ray interpretation, ultimately supporting the timely and reliable diagnosis of lung abnormalities.
format Article
id doaj-art-c169b256843043e39ba9ef6d4f2275f3
institution DOAJ
issn 2075-4418
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-c169b256843043e39ba9ef6d4f2275f32025-08-20T03:16:42ZengMDPI AGDiagnostics2075-44182025-07-011513172810.3390/diagnostics15131728RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-RaysHanan Aljuaid0Hessa Albalahad1Walaa Alshuaibi2Shahad Almutairi3Tahani Hamad Aljohani4Nazar Hussain5Farah Mohammad6Computer Science Department, College of Computer and Information Science, Princess Nourah Bint Abdulrahman University, Riyadh 11671, Saudi ArabiaResearch Chair of AI in Healthcare, Princess Nourah Bint Abdulrahman University, Riyadh 11564, Saudi ArabiaResearch Chair of AI in Healthcare, Princess Nourah Bint Abdulrahman University, Riyadh 11564, Saudi ArabiaResearch Chair of AI in Healthcare, Princess Nourah Bint Abdulrahman University, Riyadh 11564, Saudi ArabiaResearch Chair of AI in Healthcare, Princess Nourah Bint Abdulrahman University, Riyadh 11564, Saudi ArabiaResearch Chair of AI in Healthcare, Princess Nourah Bint Abdulrahman University, Riyadh 11564, Saudi ArabiaResearch Chair of AI in Healthcare, Princess Nourah Bint Abdulrahman University, Riyadh 11564, Saudi Arabia<b>Background:</b> Chest X-rays are rapidly gaining prominence as a prevalent diagnostic tool, as recognized by the World Health Organization (WHO). However, interpreting chest X-rays can be demanding and time-consuming, even for experienced radiologists, leading to potential misinterpretations and delays in treatment. <b>Method:</b> The purpose of this research is the development of a RadAI model. The RadAI model can accurately detect four types of lung abnormalities in chest X-rays and generate a report on each identified abnormality. Moreover, deep learning algorithms, particularly convolutional neural networks (CNNs), have demonstrated remarkable potential in automating medical image analysis, including chest X-rays. This work addresses the challenge of chest X-ray interpretation by fine tuning the following three advanced deep learning models: Feature-selective and Spatial Receptive Fields Network (FSRFNet50), ResNext50, and ResNet50. These models are compared based on accuracy, precision, recall, and F1-score. <b>Results:</b> The outstanding performance of RadAI shows its potential to assist radiologists to interpret the detected chest abnormalities accurately. <b>Conclusions:</b> RadAI is beneficial in enhancing the accuracy and efficiency of chest X-ray interpretation, ultimately supporting the timely and reliable diagnosis of lung abnormalities.https://www.mdpi.com/2075-4418/15/13/1728diagnosechest X-raydeep learningimage classificationconvolutional neural networks (CNNs)King Abdullah University Hospital (KAAUH)
spellingShingle Hanan Aljuaid
Hessa Albalahad
Walaa Alshuaibi
Shahad Almutairi
Tahani Hamad Aljohani
Nazar Hussain
Farah Mohammad
RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-Rays
Diagnostics
diagnose
chest X-ray
deep learning
image classification
convolutional neural networks (CNNs)
King Abdullah University Hospital (KAAUH)
title RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-Rays
title_full RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-Rays
title_fullStr RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-Rays
title_full_unstemmed RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-Rays
title_short RADAI: A Deep Learning-Based Classification of Lung Abnormalities in Chest X-Rays
title_sort radai a deep learning based classification of lung abnormalities in chest x rays
topic diagnose
chest X-ray
deep learning
image classification
convolutional neural networks (CNNs)
King Abdullah University Hospital (KAAUH)
url https://www.mdpi.com/2075-4418/15/13/1728
work_keys_str_mv AT hananaljuaid radaiadeeplearningbasedclassificationoflungabnormalitiesinchestxrays
AT hessaalbalahad radaiadeeplearningbasedclassificationoflungabnormalitiesinchestxrays
AT walaaalshuaibi radaiadeeplearningbasedclassificationoflungabnormalitiesinchestxrays
AT shahadalmutairi radaiadeeplearningbasedclassificationoflungabnormalitiesinchestxrays
AT tahanihamadaljohani radaiadeeplearningbasedclassificationoflungabnormalitiesinchestxrays
AT nazarhussain radaiadeeplearningbasedclassificationoflungabnormalitiesinchestxrays
AT farahmohammad radaiadeeplearningbasedclassificationoflungabnormalitiesinchestxrays