Parascript announced Parascript AccuDetect, intended to help radiologists in the early detection of breast cancer during film-based or digital mammography exams, last month in Chicago at the 93rd scientific assembly and annual meeting of the Radiological Society of North America (RSNA).
The new device consists of a set of computer-aided detection (CAD) algorithms designed to deliver low false-positive rates. High false-positive rates have been a major problem in the CAD industry resulting in increased patient call-back levels, unnecessary expense, patient anguish and pain. Parascript anticipates that existing false-positive rates can be reduced by 60 to 80 percent with the use of AccuDetect algorithms.
AccuDetect utilizes Parascript's image analysis and recognition technology to automatically identify and clearly mark suspicious areas without obscuring the region of interest, enabling more accurate interpretation of mammograms and increased detection of calcifications and masses. The technology integrates several complementary algorithms and sophisticated voting methods to achieve high sensitivity and low false-positive rates for greater levels of certainty. AccuDetect reduces oversight errors, automates the comparison of historical mammograms with current mammograms (film or digital-based) and determines changes and anomalies. It easily integrates with existing analog and digital systems to improve accuracy and efficiency of data interpretation.