article · BMC Medical Imaging
Pulmonary diseases range from mild respiratory conditions to life-threatening infections such as viral pneumonia, bacterial pneumonia, and COVID-19. Timely diagnosis is vital, but diagnostic costs remain substantial, particularly within developing nations. To support faster and more accurate screening, a deep convolutional neural network model optimized with data augmentation was developed to detect pulmonary conditions from radiography images, including X-rays and computed tomography scans. The system was trained and evaluated on a dataset containing healthy records alongside cases of COVID-19, bacterial pneumonia, and viral pneumonia. The model recorded average classification accuracies ranging from 94% to 99.4%, while achieving rapid training and detection times of approximately 60 and 50 seconds. This deep learning method outperformed traditional texture descriptor techniques, demonstrating strong potential for automated respiratory disease identification.
Severe pulmonary infections can be fatal and costly to diagnose, especially in developing regions where resources are limited. By providing automated, rapid, and highly accurate analysis of standard X-ray and CT scans, such diagnostic tools can assist healthcare providers during epidemics and routine care, accelerating treatment decisions and reducing diagnostic expenses.
This research could enable computer-aided diagnostic software for clinical radiologists and hospital triage staff interpreting X-ray and CT scans. At present, the technology represents applied and tested algorithmic research evaluated on image datasets. Moving towards commercial deployment would require integration into medical imaging platforms, clinical workflow testing, and formal regulatory clearance for diagnostic medical software.
AI-generated from the published abstract. Always read the original work before citing.
Pulmonary diseases are various pathological conditions that affect respiratory tissues and organs, making the exchange of gas challenging for animals inhaling and exhaling. It varies from gentle and self-limiting such as the common cold and catarrh, to life-threatening ones, such as viral pneumonia (VP), bacterial pneumonia (BP), and tuberculosis, as well as a severe acute respiratory syndrome, such as the coronavirus 2019 (COVID-19). The cost of diagnosis and treatment of pulmonary infections is on the high side, most especially in developing countries, and since radiography images (X-ray and computed tomography (CT) scan images) have proven beneficial in detecting various pulmonary infections, many machine learning (ML) models and image processing procedures have been utilized to identify these infections. The need for timely and accurate detection can be lifesaving, especially during a pandemic. This paper, therefore, suggested a deep convolutional neural network (DCNN) founded image detection model, optimized with image augmentation technique, to detect three (3) different pulmonary diseases (COVID-19, bacterial pneumonia, and viral pneumonia). The dataset containing four (4) different classes (healthy (10,325), COVID-19 (3,749), BP (883), and VP (1,478)) was utilized as training/testing data for the suggested model. The model's performance indicates high potential in detecting the three (3) classes of pulmonary diseases. The model recorded average detection accuracy of 94%, 95.4%, 99.4%, and 98.30%, and training/detection time of about 60/50 s. This result indicates the proficiency of the suggested approach when likened to the traditional texture descriptors technique of pulmonary disease recognition utilizing X-ray and CT scan images. This study introduces an innovative deep convolutional neural network model to enhance the detection of pulmonary diseases like COVID-19 and pneumonia using radiography. This model, notable for its accuracy and efficiency, promises significant advancements in medical diagnostics, particularly beneficial in developing countries due to its potential to surpass traditional diagnostic methods.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1186/s12880-024-01227-2
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
