Capturing and Computer Reasoning with Quantitative and Semantic Information in Radiology Images


The use of semantic Web technologies to make the myriad of data in cyberspace accessible to intelligent agents is well established. However, a crucial type of information on the Web--and especially in life sciences--is imaging, which is largely being overlooked in current semantic Web endeavors. We are developing methods and tools to enable the transparent discovery and use of large distributed collections of medical images within hospital information systems and ultimately on the Web.  Our approach is to make the human and machine descriptions of image content machine-accessible through "semantic annotation" using ontologies, capturing semantic and quantitative information from images as physicians view them in a manner that minimally affects their current workflow.  We exploit new standards for making image contents explicit and publishable on the semantic Web. We will describe tools and methods we are developing and preliminary results using them for response assessment in cancer.  While this work is focused on images in the life sciences, it has broader applicability to all images on the Web. Our ultimate goal is to enable semantic integration of images and all the related scientific data pertaining to their content so that physicians and basic scientists can have the best understanding of the biological and physiological significance of image content.  

Daniel L. Rubin, MD, MS is Assistant Professor of Radiology and Medicine (Biomedical Informatics Research) at Stanford University.  He is a Member of the Stanford Cancer Center and the Bio-X interdisciplinary research program. His NIH-funded research program focuses on the intersection of biomedical informatics and imaging science, developing computational methods and applications to extract quantitative information and meaning from clinical, molecular, and imaging data, and to translate these methods into practice through applications to improve diagnostic accuracy and clinical effectiveness. He is Principal Investigator of one of the centers in the National Cancer Institute's recently-established Quantitative Imaging Network (QIN), Chair of the RadLex Steering Committee of the Radiological Society of North America (RSNA), and Chair of the Informatics Committee of the American College of Radiology Imaging Network (ACRIN). Dr. Rubin has published over 100 scientific publications in biomedical imaging informatics and radiology.