Integrating auxiliary detection and voting algorithms into clinical CAD workflow

摘要

Methods, systems, and related computer program products for computer-aided detection (CAD) of anatomical abnormalities in medical images are described. A preexisting CAD environment includes a review workstation and a primary CAD processor programmed with a primary CAD algorithm. Installed into the preexisting CAD environment is an auxiliary processing system programmed to receive a first CAD report from the primary CAD processor, apply an auxiliary CAD algorithm that is independent of the primary CAD algorithm to the underlying medical image, apply a voting algorithm to the primary and auxiliary CAD findings, and generate a second CAD report that includes the voting results. The second CAD report is configured to result in a rendering by the review workstation that is highly similar to a rendering that would result from the first CAD report except that the voted CAD findings are substituted in place of the primary CAD findings.