ABSTRACT
Bone scintigraphy or whole-body bone scan is one of the most common diagnostic procedures in nuclear medicine. Since expert physicians evaluate images manually, some automated procedure for pathology detection is desired. Scintigraphy segmentation into the main skeletal regions is briefly presented. The algorithm is simultaneously applied on anterior and posterior whole-body bone scintigrams. The expert’s knowledge is represented as a set of parameterized rules, used to support image processing algorithms. The segmented bone regions are parameterized with algorithms for classifying patterns so the pathologies can be classified with machine learning algorithms. This approach enables automatic scintigraphy evaluation of pathological changes; thus, in addition to detection of pointlike high-uptake lesions, other types can be discovered. We extend the parameterization of the bone regions with a multiresolutional approach and present an algorithm for image parameterization using the association rules.
