Modeling of solitary pulmonary nodules in PET/CT images using Monte Carlo methods

The assessment of solitary pulmonary nodules (SPN) is a very difficult task in PET imaging due to adjacent normal structures. Physicians and computational systems as well, would gain benefit if trained to a large number of SPN cases with controlled topological and morphological characteristics. Our objective was to develop a method for the modeling of the solitary pulmonary nodules in CT and PET images. The modeling of SPN was implemented by Monte Carlo methods taking into consideration morphological characteristics, internal features and Standardized Uptake Value (SUV) activity distribution. For the validation of the model, an observer study from three independent medical experts was performed. The reviewers characterized the lesions as simulated or real and finally they classified them as benign or malignant. According to the results of the human observer study a significant percentage of simulated images could not be differentiated from real ones and the simulated class (benign or malignant) was consistent with the observers´ classification.