CAD developer targets false positives

RSNA newcomer Parascript is demonstrating at the RSNA meeting this week algorithms its executives claim could dramatically reduce false positives in mammography computer-aided detection. AccuDetect software could cut false positives by 60% to 80% below those typically encountered in mammography CAD, according to Yuri Prizemin, Parascript director of product marketing.

Prizemin is careful, however, not to claim too much.

"We are saying that we 'anticipate' that existing false-positive rates can be reduced (by this much) with the use of AccuDetect algorithms," he said.

Actual claims about the software's performance must wait until it is actually integrated with mammography systems, according to Prizemin. The company is grooming AccuDetect for sale to OEM customers. It is compatible with both film-based or digital mammography exams.

Underlying AccuDetect algorithms is a dozen years' experience in software that digitizes and analyzes printed information for the U.S. Postal Service and corporations such as Lockheed Martin, NCR, Siemens, and Unisys.

"Medical imaging is a natural extension of our technology into areas that face significant challenges and require further technology advancements," he said. "We believe the medical imaging breast cancer detection market is facing the challenge of high false-positive rates, and we are confident our proprietary image analysis technology can address these issues."

A differentiator between AccuDetect and other such software is the way its algorithms mark suspected lesions without obscuring the region of interest, he said. Marked areas can be either de-emphasized or temporarily deleted, enabling more accurate interpretation of mammograms and increased detection of calcifications and masses, according to Prizemin.

Adding to the power of AccuDetect is the ability of its algorithms to learn. With increasing experience, the software learns to better utilize the programmed knowledge, automatically locating and recognizing similar but not necessarily identical lesions and cases.