Daniel L. Rubin MD, Presenter: Research grant, General Electric Company

Christopher Frederick Beaulieu MD, PhD, Abstract Co-Author: Nothing to Disclose

Cesar Rodriguez MD, Abstract Co-Author: Nothing to Disclose

Chris Baldassano BSC, Abstract Co-Author: Nothing to Disclose

Sandy Napel PhD, Abstract Co-Author: Medical Advisory Board, Fovia, Inc Medical Advisory Board, Vital Images, Inc Consultant, Carestream Health, Inc

We have created tools to generate structured reporting templates specific to any particular radiology study, and that make the quantitative and qualitative information needed for research machine-accessible. Such tools could streamline the process of collecting these data as part of the radiology reporting workflow.

Capturing quantitative and qualitative aspects of images is an essential activity of radiology research. Our goal was to develop a tool to capture this information as the radiologist records observations about images. Our tool can be customized and applied to any particular study, making all quantitative and qualitative image content explicit as part of the radiology report.

We previously developed a semantic image annotation tool, the image Physician Annotation Device (iPAD), a plugin to OsiriX. iPAD provides a structured reporting template for quantitative and semantic information in images, and stores this in the Annotation and Image Markup format for interoperability. We developed an application for defining and editing custom templates, permitting iPAD’s data capture capabilities to generalize to a diversity of radiology studies. To evaluate this tool, we used it to create structured data capture templates for three radiology studies for describing characteristics of (1) liver lesions, and (2) brain tumors, and (3) for assessing the RECIST criteria in cancer patients. These templates were used and evaluated by three users for sufficiency and efficiency in conducting the respective studies.

The template editor application provides a menu-driven interface permitting users to define the data capture fields desired for a given study, the applicable controlled terminologies, whether or not an item is required, and nesting of items. Templates can then be imported into iPAD and used for structured reporting of quantitative and semantic aspects of studies. The users reported that the templates created for the three studies were sufficient for the data collection tasks and that the workflow in using the templates in the research studies was more efficient than it would have been without the tool because data collection is integrated with image viewing.

Rubin, D, Beaulieu, C, Rodriguez, C, Baldassano, C, Napel, S, Reinventing Radiology Reporting: Combining Structured Capture and Radiology Image Annotation.  Radiological Society of North America 2010 Scientific Assembly and Annual Meeting, November 28 - December 3, 2010 ,Chicago IL. http://archive.rsna.org/2010/9006334.html