AUTOMATED CLASSIFICATION OF EMPHYSEMA USING CONVOLUTIONAL NEURAL NETWORKS

The analysis of CT scans for emphysema diagnosis can be formulated as a computer vision problem, where predefined patterns are used to automatically classify the images. This paper investigates a method for classifying emphysema subtypes in High-Resolution Computed Tomography (HRCT) scans using convolutional neural networks (CNNs). This classification is crucial for accurate diagnosis and management of emphysema, a chronic lung disease causing shortness of breath. Our approach leverages transfer learning to extract informative features from HRCT images labeled as centrilobular (CLE), paraseptal (PLE), panlobular (PSE), and non-emphysematous (NT). We evaluate various CNN architectures, with InceptionV3 demonstrating exceptional performance, achieving an accuracy of 98% while effectively distinguishing between all subtypes. The trained InceptionV3 model is then integrated into a user-friendly front-end application developed using Streamlit and ngrok. This application allows real-time emphysema classification from HRCT scans, potentially aiding clinicians in diagnosis and treatment decisions.