An automated detection method of normal and abnormal lesions from image data is presented. This method is based on local intensity dispersion analysis and can be used in many medical computed-aided detection (CAD) systems. A complete explanation is presented for a colon CAD system, but the invention can be utilized in other imaging modalities and can be extended as well to other CAD applications. Conventional CTC Colon CAD lesion detectors are often based on simple shape-specific methods and therefore they can miss some deformed lesions that have complex shapes. Embodiments of the invention extract highly probable lesions including and not limited to certain classes of shapes, using a fast and a robust method based on local intensity dispersion information provided by the Hessian-matrix at each voxel. Furthermore, the processing requirements are minimal, and the implementation is simple in comparison to other known techniques.
|Patent number||WO2010034968 A1|
|Publication status||Published - 1 Apr 2010|
- medical device
- computed-aided diagnosis
- computed-aided detection