Authors:
Rui Zhang
;
Takako Sato
and
Hiroshi Arisawa
Affiliation:
Graduate School of Yokohama Nat. Univ., Japan
Keyword(s):
PET/CT, Whole-body delayed scan, CAD, CADS, Tumor detection, SUV, DTA.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Cardiovascular Technologies
;
Clinical Problems and Applications
;
Computing and Telecommunications in Cardiology
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Medical and Nursing Informatics
;
Software Systems in Medicine
;
Therapeutic Systems and Technologies
Abstract:
In this paper, a new method for CADS (computer assisted diagnosis system) is proposed: whole-body PET/CT delayed scan. Whole-body PET/CT imaging is quite useful for detecting cancerous regions, however sometimes too many “suspicious areas” due to ambiguous signs within 3D images. We propose a method in which two images i.e. original images and whole-body delayed scan images are compared and the true positive regions are identified. For the purpose of detection, a matching algorithm for comparing each region on both two images has been developed. It contributes not only to improve accuracy of a diagnosis but to reduce “false positive” regions. We compare this new method with the routine one and show its supporting technologies and advantages. In the end we indicate our research emphasis.