Automated COPD Detection with CNN in CT Scans

Automated COPD Detection with CNN in CT Scans

2111CS020314 – Nikhil .U                               2111CS020318 – Nikitha .B

2111CS020326 – Nithya Sree .K                      2111CS020342 – Poojitha .B

2111CS020359 – Pravallika .K

Guided by

Prof. R. Karthik

Department of Artificial Intelligence & Machine Learning

1.ABSTRACT
This study presents an automated approach for early detection of Chronic Obstructive Pulmonary Disease (COPD) using Convolutional Neural Networks (DenseNet-201) on Computed Tomography (CT) scans. The methodology involves preprocessing CT images to enhance features, followed by a CNN trained to recognize patterns indicative of these respiratory conditions. Robustness testing across different imaging devices and acquisition protocols further validates its reliability. The CNN- based approach proves successful in accurately identifying COPD, offering a promising tool for early disease detection. The proposed system has the potential to enhance diagnostic efficiency, reduce reliance on manual interpretation, and contribute to advancements in personalized treatment strategies for respiratory diseases.

Keywords: DenseNet-201, CT Scans, COPD