Knowledge-based radiologic image retrieval using axes of clinical relevance

• Published in: Computers and biomedical research Vol. 23; no. 3; pp. 199 - 221
• Main Authors: Cohn, Aaron I., Miller, Perry L., Fisher, Paul R., Mutalik, Pradeep G., Swett, Henry A.
• Format: Journal Article
• Language: English
• Published: San Diego, CA Elsevier Inc 01.06.1990; Academic Press
• Subjects: Biological and medical sciences; Expert Systems; Hospital Information Systems; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Miscellaneous. Technology; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Radiology Information Systems; Software Design; Subject Headings; User-Computer Interface; Radiography; Biomedical data processing; Radiodiagnosis; Expert system; Heuristic method; Medical imagery; Information retrieval; Knowledge base; Artificial intelligence
• ISSN: 0010-4809; 1090-2368
• DOI: 10.1016/0010-4809(90)90017-7

This paper describes an approach to computer-based intelligent retrieval of feature-coded radiographic images relevant to a specific case being evaluated. The approach involves partitioning the search space along clinically natural groups of atributes which we call “axes of clinical relevance.” By embedding knowledge about the domain to help direct the search process, a clinician's needs may be met more comprehensively. Domain knowledge, supplied to the system as “axis heuristics,” may make search more robust. These heuristics provide a graded, progressive relaxation of the search constraints. This approach helps show the user groups of images in order of probable relevance to a current case. AXON is a prototype knowledge-based system constructured to illustrate this approach in the domain of chest imaging. This paper describes the AXON system, demonstrates some searches which illustrate the potential utility of this approach, and discusses preliminary tests of the search strategies used by AXON.