Data Science Day @ Columbia University

Full-lung (FL) computed tomography (CT) has been widely used for pulmonary emphysema quantification. Cardiac CT scans include approximately 2/3 of the lung and can be obtained more rapidly and with lower radiation exposure than FL scans. This work presents a novel method for emphysema quantification on both FL and cardiac scans, based on parametric modeling of intensity distributions and a hidden Markov measure field model to segment emphysematous regions. The framework adapts to the characteristics of an image to ensure a robust quantification of emphysema under varying CT imaging protocols and scanner types. Compared to standard approaches, the presented model provides 1) very high longitudinal correlation with 87 subjects and a total of 365 FL scans acquired with varying imaging protocols; and 2) more reproducible emphysema segmentation and higher longitudinal correlations from a diverse pool of scanner types and thousands of subjects with ten thousands of cardiac scans.