PROCESSING CANDIDATE ABNORMALITIES IN MEDICAL IMAGERY BASED ON A HIERARCHICAL CLASSIFICATION

摘要

Techniques are provided for automated detection and processing of abnormalities in medical imagery. The techniques include determining voxels involved with each of a plurality of candidate abnormalities in a medical image. The techniques also include determining whether a candidate abnormality belongs in one of multiple abnormality classes based at least on anatomical location context, size, and shape by successively subjecting the candidate abnormality to hierarchical tests for anatomical context, size range based on anatomical context, and shape parameter value range based on anatomical context and size range. The techniques include rejecting a candidate abnormality that does not fall into any one of the abnormality classes. The techniques also include presenting on a display device a property of the candidate abnormality based on the abnormality class to which the candidate abnormality belong.