Abstract:

The detection and classification of lung diseases is a crucial task in the medical field, as early detection can significantly improve patient outcomes. Convolutional neural networks (CNNs), a type of deep learning model, have recently demonstrated promising outcomes in the processing of medical images. In this article, we present a method for the detection and classification of lung illnesses utilising a pre-trained VGG16 model and a specially designed CNN. The proposed approach involves training the VGG16 model on a large dataset of lung X-ray images to extract meaningful features, which are then used to train a custom-built CNN to classify images into one of the five categories: normal, pneumonia, COVID-19, tuberculosis, and lung cancer. The proposed method was evaluated on a dataset of 10,000 lung X-ray images, achieving an accuracy of 97.3% for the classification of five lung disease categories. The proposed method shows promising results for automated detection and classification of lung diseases, which can aid healthcare professionals in making accurate diagnoses and improving patient outcomes.

Description:

Deep Learning, VGG16 algorithm, Convolutional Neural Network, Python