Abir Baazaoui, Walid Barhoumi, Ezzeddine Zagrouba and Rostom Mabrouk Pages 13 - 27 ( 15 )
Positron Emission Tomography, which is a functional imaging technique, measures in three-dimension the bio-distribution of a radiotracer in a specific organ or tissue. Thanks to tracer characteristics, the PET imaging was successfully experimented into several applications in oncology, cardiology and neurology for clinical and research trials. The segmentation of PET image is a mandatory step in all PET applications since it allows to relay imaged tracer uptake within a region of interest to its underlying biology. However, manual segmentation was limited by its time consuming, labor intensive and its high intra- and inter-operator variability. Therefore, several automated PET image segmentation methods were developed. In this paper, we presented the most relevant methods in the literature including thresholding-based methods of static PET images, deformable models for cardiac PET studies and mono and multi-modal segmentation methods for brain PET images.
Cardiology, deformable models, multi-modal segmentation, neurology, oncology, PET image, thresholding-based segmentation.
Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA)RIADI Laboratory. Institut Superieur d`Informatique, Universite de Tunis ElManar, Tunis, Tunisia