Unlocking the Potential of Radiomics in Identifying Fibrosing and Inflammatory Patterns in Interstitial Lung Disease

The purpose of this thesis is to develop a system capable of segmenting interstitial involvement in chest CT scans and identifying radiomic features characteristic of distinct patterns of lung disease. Specifically, the study focuses on differentiating fibrotic patterns, such as Usual Interstitial Pneumonia (UIP), from inflammatory patterns like Non-Specific Interstitial Pneumonia (NSIP) and distinguishing NSIP from viral pneumonia, including COVID-19. By leveraging advanced image analysis and machine learning techniques, the proposed system aims to enhance diagnostic accuracy and provide automated tools to assist clinicians in differentiating these complex and overlapping conditions.