A system and method for automatically segmenting a computed tomography (CT) image of a patient's lung. The method includes the steps of segmenting the CT image to acquire one or more lung regions, intensity thresholding the lung regions to generate a mask region comprising high-intensity regions corresponding to anatomical structures within the lung regions, computing a Euclidean distance map of the mask region, performing watershed segmentation of the Euclidean distance map to generate one or more sub-regions, identifying a seed point for each sub region, growing candidate regions from the seed point of each sub-region, and classifying one or more candidate regions as a lung nodule based on one or more geometric features of the candidate regions.
