Algorithm Composition for Characterizing Small Pulmonary Nodule from CT Scans

Evaluation of pulmonary nodules consists of detection of the locations of possible nodules from computed tomography (CT) scans and characterization of measured features for final nodule classification. Radiologists are challenged to review and accurately interpret the vast amount of information resulted from a CT scan. Therefore, objective and accurate diagnostic tools are needed.

Researchers at Weill Cornell Medical College have developed a method, apparatus, and system for small pulmonary nodule computer aided diagnosis (CAD) by analyzing and manipulating CT scans with tremendously improved diagnostic accuracy. The incorporated CAD is a multi-stage detection algorithm using a successive nodule candidate refinement approach. The detection algorithm involves four major steps. First, the lung region is segmented from a whole lung CT scan. Second is a hypothesis generation stage in which nodule candidate locations are identified from the lung region. In the third stage, nodule candidate sub-images pass through a streaking artifact removal process. The nodule candidates are then successively refined using a sequence of filters of increasing complexity. Detailed descriptions technology can be found at Patent No.: US 7,499,578 B2.