OBJECTIVE: To present a locally developed system of computer vision for use with HRCT images, designated SIStema para a Detecção e a quantificação de Enfisema Pulmonar (SISDEP, System to Detect and Quantify Pulmonary Emphysema), and to compare this system with a freeware system tool. METHODS: Thirty-three HRCT images scanned at the apex, hilum and base of the lungs of 11 patients with COPD were analyzed. The SISDEP was compared with the Osiris Medical Imaging Software Program regarding lung parenchyma segmentation, precision of the measurement of the cross-sectional area of the lungs in mm², mean lung density (MLD), relative area (RA) of the lung occupied by voxels with attenuation values < -950 hounsfield units (ra -950), 15th percentile point (perc15) and visualization of hyperinflated areas using a color mask. RESULTS: Although both computational systems were efficient in segmenting the lungs, the SISDEP performed this task automatically and more rapidly. There were significant correlations between the two systems in terms of the results obtained for lung cross-sectional area, MLD, RA -950 and Perc15 (r² = 0.99, 0.99, 0.99 and 1.00, respectively). The color mask tool of the SISDEP allowed excellent visualization of hyperinflated areas, discriminating them from normal areas. CONCLUSIONS: The SISDEP was efficient in segmenting the lungs and quantifying lung hyperinflation, presenting an excellent correlation with the Osiris system. The SISDEP constitutes a promising computational tool for diagnosing and assessing the progression of emphysema in HRCT images of COPD patients.
Pulmonary disease, chronic obstructive; Emphysema; Tomography, X-ray computed; Decision making, computer-assisted
