International Research Journal of Engineering and Technology (IRJET) Volume: 10 Issue: 05 | May 2023
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
CLOUD BASED WEB-APPLICATION FOR RAPID AND PRECISE DETECTION OF TUBERCULOSIS USING DEEP LEARNING Dineshkumar Ganesan1, N. Naveenkumar2 1PG Student, Department of Computer Science and Engineering, Muthayammal Engineering College, Namakkal, Tamil
Nadu.
2Assistant Professor, Department of Computer Science and Engineering, Muthayammal Engineering College,
Namakkal, Tamil Nadu. --------------------------------------------------------------------***--------------------------------------------------------------------ABSTRACT - Tuberculosis (TB) is a communicable disease caused by the bacteria Mycobacterium tuberculosis, which primarily
affects the lungs but can also affect other parts of the body. TB is a major global health problem, and the World Health Organization (WHO) estimates that around 10 million people worldwide became ill with TB in 2019. Early detection and treatment of TB are essential for effective disease management and prevention of transmission. 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 4000TB infected and 4000 normal chest X-ray images for this study. Nine deep CNNs and SVM (ResNet18, ResNet50, ResNet101, ChexNet, InceptionV3, Vgg19, DenseNet201, SqueezeNet, and MobileNet) were used for transfer learning from their pre-trained initial weights. They 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 Traditional diagnostic methods for TB, such as sputum microscopy and culture-based techniques, have limitations in terms of sensitivity and specificity, particularly in detecting TB in its early stages. Machine learning algorithms, such as Support Vector Machine (SVM), have shown promise for the accurate detection of TB. However, classification using segmented lung images outperformed that with whole X-ray images; the accuracy, precision, sensitivity, F1-score, and specificity of DenseNet201 respectively for the segmented lung images. The paper also used a visualization technique to confirm that CNN learns dominantly from the segmented lung regions, resulting in higher detection accuracy. Overall, a cloud-based web application for rapid and precise detection of tuberculosis using SVM would be a valuable tool in the fight against this disease, enabling healthcare professionals to make more informed decisions about diagnosis and treatment. Index Terms: Convolutional Neural Network (CNN), Restnet, Chexnet, Tuberculosis Detection, Support Vector Machine(SVM)
I. INTRODUCTION1
of TB. The application could be accessible from anywhere with an internet connection, making it particularly useful in areas with limited resources and medical infrastructure [2]-[4]. In this project, we propose the development of a cloud-based web application for rapid and precise detection of TB using SVM. We will leverage open-source tools and cloud services to build the application, which will be designed to be user-friendly and accessible to healthcare professionals. The SVM model will be trained using a dataset of medical images, and the application will interface with the model through an API, enabling users to upload images and receive predictions on the presence of TB. The web application could be designed to be userfriendly and accessible, with clear instructions on how to upload images and interpret the results. It could also include additional features such as the ability to download the results or share them with healthcare professionals. Overall, a cloud-based web application for rapid and precise detection of tuberculosis using SVM would be a
Tuberculosis (TB) is a contagious disease that remains a significant global health concern, affecting millions of people each year. Early and accurate detection of TB is critical for effective treatment and control of the disease. Support Vector Machines (SVM) is a machine learning algorithm that has shown promising results in the classification of medical images for the detection of TB. In recent years, cloud computing has become increasingly popular for its scalability, flexibility, and cost-effectiveness. Cloud-based applications have the potential to provide rapid and precise detection of TB using SVM, which can significantly improve the accuracy and efficiency of TB diagnosis. A cloud-based web application for the rapid and precise detection of TB using SVM would enable healthcare professionals to upload medical images and receive a prediction on whether or not the images contain evidence
© 2023, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 1250