Abstract
This paper presents a summary of the purpose and recent progress of our research work, which is a part of the research project "Computational anatomy for computer-aided diagnosis and therapy: Frontiers of medical image sciences" funded by a Grant-in-Aid for Scientific Research on Innovative Areas, which is awarded by the MEXT, Japan. Our research in this project is mainly aimed at model constructions and their applications to the recognition and analysis of anatomical structures using CT images and functional images (PET). Our work focuses on modeling the universal organ localization approach, developing a shape model for abdominal muscle segmentation in CT images, proposing a localization scheme for vertebrae on CT images, and analyzing normal distributions of the standardized uptake values (SUV) of 2-deoxy-2-fluoro-d-glucose (FDG) in different organs. The preliminary experimental results, based on a large image database, have demonstrated the potential of the constructed models.
