Automatic lung segmentation in functional SPECT images using active shape models trained on reference lung shapes from CT

摘要

Abstract Objective Image segmentation is an essential step in quantifying the extent of reduced or absent lung function. The aim of this study is to develop and validate a new tool for automatic segmentation of lungs in ventilation and perfusion SPECT images and compare automatic and manual SPECT lung segmentations with reference computed tomography (CT) volumes. Methods A total of 77 subjects (69 patients with obstructive lung disease, and 8 subjects without apparent perfusion of ventilation loss) performed low-dose CT followed by ventilation/perfusion (V/P) SPECT examination in a hybrid gamma camera system. In the training phase, lung shapes from the 57 anatomical low-dose CT images were used to construct two active shape models (right lung and left lung) which were then used for image segmentation. The algorithm was validated in 20 patients, comparing its results to reference delineation of corresponding CT images, and by comparing automatic segmentation to manual delineations in SPECT images. Results The Dice coefficient between automatic SPECT delineations and manual SPECT delineations were 0.83?±?0.04% for the right and 0.82?±?0.05% for the left lung. There was statistically significant difference between reference volumes from CT and automatic delineations for the right ( R ?=?0.53, p ?=?0.02) and left lung ( R ?=?0.69, p ? R ?=?0.60, p ?=?0.005) right lung (bias 36?±?524?ml, R ?=?0.62, p ?=?0.004). Conclusion Automated segmentation on SPECT images are on par with manual segmentation on SPECT images. Relative large volumetric differences between manual delineations of functional SPECT images and anatomical CT images confirms that lung segmentation of functional SPECT images is a challenging task. The current algorithm is a first step towards automatic quantification of wide range of measurements.