Computer-aided diagnosis in full digital mammography

RATIONALE AND OBJECTIVES. The authors clarify the detection rates for breas t cancerous tumors and clustered microcalcifications with computer-aided di agnosis (CAD) based on Fuji Computed Radiography. The authors also determin e whether mammographic reading with CAD contributes to the discovery of bre ast cancer. METHODS. Data acquired by Fuji Computed Radiography 9000, which consisted o f 4148 digital mammograms including 267 cases of breast cancer, was transfe rred directly to an analysis workstation where an original software program determined extraction rates for breast tumors and clustered microcalcifica tions. Furthermore, using another 344 mammograms from 86 women, observer pe rformance studies were conducted on five doctors for receiver operating cha racteristic (ROC) analysis, RESULTS. Sensitivity to breast cancerous tumors and clustered microcalcific ations mere 89.9% and 92.8%, respectively false-positive rates were 1.35 an d 0.40 per image, respectively, The observer performance studies indicate t hat an average Az value for the five doctors was greater with the CAD syste m than with a film-only reading without CAD, and that a reading with CAD wa s significantly superior at P < 0.022, CONCLUSIONS. It has been shown that CAD based on Fuji Computed Radiography offers good detection rates for both breast cancerous tumors and clustered microcalcifications, and that the reading of mammograms with this CAD syste m would provide potential improvement in diagnostic accuracy for breast can cer.