Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study.

The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases.

MODELING AIRWAY PROBABILITY.

We present a probability model for lung airways in computed tomography (CT) images. Lung airways are tubular structures that display specific features, such as low intensity and proximity to vessels and bronchial walls. From these features, the posterior probability for the airway feature space was computed using a Bayesian model based on 20 CT images from subjects with different degrees of Chronic Obstructive Pulmonary Disease (COPD). The likelihood probability was modeled using both a Gaussian distribution and a nonparametric kernel density estimation method. After exhaustive feature selection, good specificity and sensitivity were achieved in a cross-validation study for both the Gaussian (0.83, 0.87) and the nonparametric method (0.79, 0.89). The model generalizes well when trained using images from a late stage COPD group. This probability model may facilitate airway extraction and quantitative assessment of lung diseases, which is useful in many clinical and research settings.

Individual nodule tracking in micro-CT images of a longitudinal lung cancer mouse model.

We present and evaluate an automatic and quantitative method for the complex task of characterizing individual nodule volumetric progression in a longitudinal mouse model of lung cancer. Fourteen A/J mice received an intraperitoneal injection of urethane. Respiratory-gated micro-CT images of the lungs were acquired at 8, 22, and 37 weeks after injection. A radiologist identified a total of 196, 585 and 636 nodules, respectively. The three micro-CT image volumes from every animal were then registered and the nodules automatically matched with an average accuracy of 99.5%. All nodules detected at week 8 were tracked all the way to week 37, and volumetrically segmented to measure their growth and doubling rates. 92.5% of all nodules were correctly segmented, ranging from the earliest stage to advanced stage, where nodule segmentation becomes more challenging due to complex anatomy and nodule overlap. Volume segmentation was validated using a foam lung phantom with embedded polyethylene microspheres. We also correlated growth rates with nodule phenotypes based on histology, to conclude that the growth rate of malignant tumors is significantly higher than that of benign lesions. In conclusion, we present a turnkey solution that combines longitudinal imaging with nodule matching and volumetric nodule segmentation resulting in a powerful tool for preclinical research.