Health care professionals ’ image use and search behaviour

Images and visual information in general are produced in increasing quantities in health care settings. The variety of their use has increased as well. They are used for many tasks such as diagnosis, treatment planning, research, and teaching. Many health care institutions have started to make all images available in digital form as part of the electronic health record. Despite its importance, little is known about how health care professionals would like to access images or search for them, particularly for teaching or research. To learn more about the image use and search behaviour, we conducted a survey of image users at the University Hospitals of Geneva from March to May 2005. Methods: Six questions were asked to 18 individuals aiming to clarify how they would use and search for images in their roles as clinicians, educators, researchers, librarians, and/or students. Results: We found that many clinicians create their personal archives of images from clinical routine for further use. They usually add clinical information to illustrate interesting or typical cases, particularly for teaching and research. Image search for the various roles (clinician, lecturer, researcher, etc.) was not restricted to the hospital archive or teaching file. Many individuals searched for images on the Internet (Google and specialized scientific or university sites) but said that quality was a problem and was hard to judge. With respect to desired functionalities for image search, several subjects said they would like to search for images by pathology from the entire picture archive of the hospital (PACS). Some also mentioned that a search for similar cases to a current one would be very beneficial to aid diagnosis. The results of this survey will be used to create query topics for an international benchmark in medical visual information retrieval to investigate its value in the health care setting. The ImageCLEF benchmark currently contains four teaching files with over 50’000 images and aims to centre research in visual information retrieval on important medical search tasks.

[1]  James S. Duncan,et al.  Synthesis of Research: Medical Image Databases: A Content-based Retrieval Approach , 1997, J. Am. Medical Informatics Assoc..

[2]  Patrice Degoulet,et al.  Unified modeling language and design of a case-based retrieval system in medical imaging , 1998, AMIA.

[3]  Henry J. Lowe,et al.  Towards knowledge-based retrieval of medical images. The role of semantic indexing, image content representation and knowledge-based retrieval , 1998, AMIA.

[4]  W R Hersh,et al.  How well do physicians use electronic information retrieval systems? A framework for investigation and systematic review. , 1998, JAMA.

[5]  Rudolf Hanka,et al.  A review of intelligent content-based indexing and browsing of medical images , 1999 .

[6]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  C P Friedman,et al.  Information Needs and Information Seeking in Community Medical Education , 2000, Academic medicine : journal of the Association of American Medical Colleges.

[8]  O. Ratib,et al.  Integration of a multimedia teaching and reference database in a PACS environment. , 2002, Radiographics : a review publication of the Radiological Society of North America, Inc.

[9]  Paula Gould.  The rise and rise of medical imaging , 2003 .

[10]  A. Kak,et al.  Automated storage and retrieval of thin-section CT images to assist diagnosis: system description and preliminary assessment. , 2003, Radiology.

[11]  A. Erden,et al.  [Evidence based radiology]. , 2004, Tanisal ve girisimsel radyoloji : Tibbi Goruntuleme ve Girisimsel Radyoloji Dernegi yayin organi.

[12]  Thomas Martin Deserno,et al.  The CLEF 2005 Cross-Language Image Retrieval Track , 2003, CLEF.

[13]  Patrick Ruch,et al.  A Qualitative Task Analysis of Biomedical Image Use and Retrieval , 2005 .