Design of a Web Portal for Interdisciplinary Image Retrieval from Multiple Online Image Resources

Summary

Objectives: Images play an important role in medicine. Finding the desired images within the multitude of online image databases is a time-consuming and frustrating process. Existing websites do not meet all the requirements for an ideal learning environment for medical students. This work intends to establish a new web portal providing a centralized access point to a selected number of online image databases.

Methods: A back-end system locates images on given websites and extracts relevant meta-data. The images are indexed using UMLS and the MetaMap system provided by the US National Library of Medicine. Specially developed functions allow to create individual navigation structures. The front-end system suits the specific needs of medical students. A navigation structure consisting of several medical fields, university curricula and the ICD-10 was created. The images may be accessed via the given navigation structure or using different search functions. Cross-references are provided by the semantic relations of the UMLS.

Results: Over 25,000 images were identified and indexed. A pilot evaluation among medical students showed good first results concerning the acceptance of the developed navigation structures and search features.

Conclusion: The integration of the images from different sources into the UMLS semantic network offers a quick and an easy-to-use learning environment.

Keywords

Medical education - e-learning - images - World Wide Web - UMLS

• References

• 1 Dawes TJ, Vowler SL, Allen CM, Dixon AK. Training improves medical student performance in image interpretation. Br J Radiol 2004; 77 (921) 775-776.
• 2 Crowley RS, Naus GJ, Stewart 3rd J, Friedman CP. Development of visual diagnostic expertise in pathology – an information-processing study. J Am Med Inform Assoc 2003; 10 (Suppl. 01) 39-51.
• 3 Cliff S, Bedlow AJ, Melia J, Moss S, Harland CC. Impact of skin cancer education on medical students’ diagnostic skills. Clin Exp Dermatol 2003; 28 (Suppl. 02) 214-217.
• 4 Wangel M, Niemitukia L, Katila T, Soimakallio S. WWW – an effective way of teaching radiology. Comput Methods Programs Biomed 2001; 66 (Suppl. 01) 91-98.
• 5 Glatz-Krieger K, Glatz D, Gysel M, Dittler M, Mihatsch MJ. Web-based learning tools in pathology. Pathologe 2003; 24 (Suppl. 05) 394-399.
• 6 MacKenzie JD, Greenes RA. The World Wide Web: redefining medical education. JAMA 1997; 278 (21) 1785-1786.
• 7 JayDoc HistoWeb (homepage on the Internet).. (cited Sep 1, 2008). Available from: http://www.kumc.edu/instruction/medicine/anatomy/histoweb
• 8 Rosset A, Muller H, Martins M, Dfouni N, Vallee JP, Ratib O. Casimage project: a digital teaching files authoring environment. J Thorac Imaging 2004; 19 (Suppl. 02) 103-108.
• 9 DermIS (homepage on the Internet)[cited Sep 1, 2008].. Available from: dermis.multimedica.de/
• 10 Lorence DP, Spink A. Semantics and the medical web: a review of barriers and breakthroughs in effective healthcare query. Health Info Libr J 2004; 21 (Suppl. 02) 109-116.
• 11 Kammerer FJ, Prokosch HU, Frankewitsch T. Review of interdisciplinary online-image-databases and their usability in medical education. GMS Med Inform Biom Epidemiol 2006; 2 (Suppl. 03) Doc17.
• 12 Hamza S, Jones KN, Anderson PG. Utilizing electronic resources in pathology residency education via a pathology education instructional resource (PEIR). Arch Pathol Lab Med 2000; 124: 822.
• 13 Boyer C, Baujard V, Griesser V, Scherrer JR. HONselect: a multilingual and intelligent search tool integrating heterogeneous web resources. Int J Med Inform 2001; 64 2–3 253-258.
• 14 Candler CS, Uijtdehaage SH, Dennis SE. Introducing HEAL: the Health Education Assets Library. Acad Med 2003; 78 (Suppl. 03) 249-253.
• 15 Dennis SE, Dippie SR, Candler CS, McIntyre SA, Uijtdehaage S. An indexing standard for sharing health education multimedia resources: the health education assets library (HEAL) metadata schema. In: Proceedings of the 37th Annual Hawaii international Conference on System Sciences (Hicss’04) – Track 6 – Volume 6. Jan 5-8, 2004. IEEE Computer Society Washington, DC: p 60138.1.
• 16 Lindberg DA, Humphreys BL, McCray AT. The Unified Medical Language System. Methods Inf Med 1993; 32 (Suppl. 04) 281-291.
• 17 Lowe HJ, Antipov I, Hersh W, Smith CA, Mailhot M. Automated semantic indexing of imaging reports to support retrieval of medical images in the multimedia electronic medical record. Methods Inf Med 1999; 38 4–5 303-307.
• 18 Bashyam V, Divita G, Bennett DB, Browne AC, Taira RK. A normalized lexical lookup approach to identifying UMLS concepts in free text. Stud Health Technol Inform 2007; 129 Pt 1 545-549.
• 19 Ruiz ME. Combining image features, case descriptions and UMLS concepts to improve retrieval of medical images. AMIA Annu Symp Proc 2006; pp 674-678.
• 20 Frankewitsch T, Prokosch U. Navigation in medical Internet image databases. Med Inform Internet Med 2001; 26 (Suppl. 01) 1-15.
• 21 Laender A, Ribeiro-Neto B, Silva A, Teixeira J. A Brief Survey of Web Data Extraction Tools. SIGMOD Record 2002; 31 (Suppl. 02) 84-93.
• 22 Kammerer FJ. Entwicklung eines Webportals auf der Basis von UMLS und XML zur interdisziplinären Recherche in medizinischen Online-Bilddatenbanken. Ph. D. thesis, University of ErlangenNuremberg 2008
• 23 W3C Document Object Model.. (homepage on the Internet)(cited Sep 1, 2008). Available from: www.w3.org/DOM
• 24 Aronson AR. Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. Proc AMIA Symp 2001; pp 17-21.
• 25 Meystre S, Haug PJ. Evaluation of Medical Problem Extraction from Electronic Clinical Documents Using MetaMap Transfer (MMTx). Stud Health Technol Inform 2005; 116: 823-828.
• 26 Divita G, Tse T, Roth L. Failure analysis of MetaMap Transfer (MMTx). Medinfo 2004; 11 Pt 2 763-767.
• 27 Liu H, Johnson SB, Friedman C. Automatic resolution of ambiguous terms based on machine learning and conceptual relations in the UMLS. J Am Med Inform Assoc 2002; 9 (Suppl. 06) 621-636.
• 28 Leroy G, Rindflesch TC. Effects of information and machine learning algorithms on word sense disambiguation with small datasets. Int J Med Inform 2005; 74 7–8 573-585.
• 29 Weeber M, Mork JG, Aronson AR. Developing a test collection for biomedical word sense disambiguation. Proc AMIA Symp 2001; pp 746-750.
• 30 Snoussi H, Magnin L, Nie J-Y. Toward an Ontology-based Web Data Extraction. AI’2002: The Fifteenth Canadian Conference on Artificial Intelligence (BASeWEB). 2002