Segmenting Extra Pulmonary Tuberculous Lesions in Computed Tomography Images Using Positron Emission Tomography Intensity Markers

Various studies have been conducted to expand the utilization of combined positron emission tomography and computed tomography (PET/CT) covering cases of infection and inflammation. PET images provide the functional activity of a lesion while CT images demonstrate the anatomical location. Hence, existence of infected lesions can be recognized in PET image but since the structural position can not be precisely defined on PET images, we need to retrieve this information from CT. We highlight localization of extra pulmonary tuberculosis infection using high activity points on PET image as references to extract regions of interest on CT image. Once PET and CT images have been registered, coordinates of the candidate points on PET are fed into seeded region growing algorithm to define the boundary of lesion on CT. The region growing process continues until a significant change in bilinear pixel values is reached. Results show that this algorithm works well considering the limitations of seeded region growing algorithm.