Screenpoint MedicalScreenpoint Medical Contact: Jan-Jurre Mordang
ScreenPoint develops Deep Learning and image analysis technology for automated reading of mammograms and digital breast tomosynthesis. We exploit the latest methods in the rapidly evolving field of machine learning, combining these with very large well curated digital image databases and a thorough understanding of the physics of mammogram image formation and the practicalities of the clinical deployment of mammographic image analysis. The technology of ScreenPoint has its roots in the Diagnostic Image Analysis Group (DIAG) of the Radboud University Medical Center in Nijmegen, The Netherlands. DIAG is recognized as a worldwide leader in computer-aided detection (CAD) for mammography. Over a period of more than 20 years, mammographic image analysis techniques were developed by Professor Nico Karssemeijer and his team. As a result of continued innovation and development, algorithms for the detection of mammographic abnormalities have improved markedly in recent years, leading to superior performance. A unique feature is the system’s ability to exploit context in an intelligent way. Interpretation of findings in images in relation to the whole content of an image, and in related images, is one of the most complex problems computer vision faces today. In screening mammography, it is essential, since suspicious abnormalities are always judged in relation to other views of the breast and previous mammograms.