An Integrated Database and Smart Search Tool for Medical Knowledge Extraction from Radiology Teaching Files

Accurate and timely diagnosis is crucial for an e‚ective medical treatment. Teaching €les are widely used by radiologists as a resource in the diagnostic process and to teach students of radiology. Teaching €les contain images, recorded discussion and notes, external references, augmenting annotations, and patient history. Most hospitals maintain an active collection of teaching €les for their internal purposes, but many publically available teaching €les are available through online sources that typically provide a basic keyword search interface but liŠle else that can help physicians €nd the most relevant examples. Other secondary sources (e.g., journals or radiology textbooks) might also be referenced from a teaching €le or provide an independent source of information; however, journal and textbook search capabilities, if available, can be very ad hoc and even more limited than for public teaching €le repositories. Œerefore, in order to access multiple resources, radiologists need to manually navigate each particular source and aggregate the search results into a full answer. In this paper, we describe our integration of multiple public data sources into a uni€ed medical resource repository and the design of advanced search features that make it easier to €nd relevant teaching €les as well as journals or textbooks. Our approach supports incorporating diverse public data that can be further combined with a hospital’s in-house teaching €les to provide an integrated radiological knowledge repository. We tested our Integrated Radiological Image Search (IRIS) engine using a set of representative queries. Our search engine €nds more accurate and relevant results compared to search engines available for public data sources. Œe IRIS engine is tailored to facilitate understanding of natural language queries, including negation statements, synonym terms, adjectives, and di‚erent sources of text. In addition, the search engine is designed to allow further integration of a module for image-based search to allow €nding of visually similar cases.