Richard Reaven MD, Presenter: Nothing to Disclose

Joseph Jen-Sho Chen MD, Abstract Co-Author: Advisory Board, Bayer AG

Eliot L. Siegel MD, Abstract Co-Author: Research grant, General Electric Company Speakers Bureau, Siemens AG Board of Directors, Carestream Health, Inc Research grant, XYBIX Systems, Inc Research grant, Steelcase, Inc Research grant, Anthro Corp Research grant, RedRick Technologies Inc Research grant, Evolved Technologies Corporation Research grant, Barco nv Research grant, Intel Corporation Research grant, Dell Inc Research grant, Herman Miller, Inc Research grant, Virtual Radiology Research grant, Anatomical Travelogue, Inc Medical Advisory Board, Fovia, Inc Medical Advisory Board, Vital Images Medical Advisory Board, McKesson Corporation Medical Advisory Board, Carestream Health, Inc Medical Advisory Board, Bayer AG Research, TeraRecon, Inc Medical Advisory Board, Bracco Group Researcher, Bracco Group Medical Advisory Board, Merge Healthcare Incorporated Medical Advisory Board, Microsoft Corporation Researcher, Microsoft Corporation

Although initially tested for research and clinical trials, the NCI’s AIM schema can be successfully leveraged with the RSNA’s Structured Reporting Templates to generate structured and machine readable reports using an image interpretation workflow.

The release of the RSNA Radiology Reporting Templates has generated much discussion regarding their practical incorporation into radiology reporting workflow. The NCI’s AIM schema was created to provide a standard means to capture a radiologist’s interpretation and machine based quantitative measurements. We are not aware of any previous reports of the incorporation of the RSNA templates and AIM into a radiologist’s clinical workstation and workflow. The goal of our study is to combine the RSNA’s templates and AIM to demonstrate the potential to quickly and easily generate high quality machine readable structured reports.

The RSNA radiology reporting template, “MR Knee” was chosen. By incorporating this template with standardized terms, predominately using RadLex®, an AIM template was developed and subsequently loaded into an AIM-compatible, free, and open source workstation (ClearCanvas Inc). Using the MR Knee AIM template, musculoskeletal radiologists in an academic department were instructed to interpret randomly selected cases twice; once using their normal method of dictation, and another using the semi-automated AIM template. The method of interpreting each case was reversed in the subsequent case, to reduce lead-time bias. The interpretation of each case and methodology was timed, and the dictated reports were compared with the structured AIM extensible markup language (XML) documents that were generated. A survey was also given to each radiologist to better understand their experience of using the AIM template versus their current method of dictation.

Our initial investigation suggests that it is practical to incorporate RSNA radiology reporting templates and an AIM template into an interpretation workstation to generate reports in an acceptable period of time. Radiologists suggested a number of improvements to the usability of this template to minimize keystrokes and change default values to optimize reporting speed.

Reaven, R, Chen, J, Siegel, E, Structured Reporting on MRI of the Knee: A Feasibility Study Incorporating the Annotation and Markup Imaging (AIM) Process.  Radiological Society of North America 2011 Scientific Assembly and Annual Meeting, November 26 - December 2, 2011 ,Chicago IL. http://archive.rsna.org/2011/11011946.html