2013 | OriginalPaper | Chapter
Content-Based and Similarity-Based Querying for Broad-Usage Medical Image Retrieval
Author : Christopher Town
Published in: Advances in Biomedical Infrastructure 2013
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Health-related information, much of it consisting of images, is being predominantly accessed online by diverse groups of users ranging from medical professionals and researchers to students and the general public. This paper argues that broad-usage medical image retrieval is best approached as a sub-domain of generic image search. We discuss how search over a diverse corpus of biomedical and healthcare related images can benefit from a modern content-based image retrieval (CBIR) system based upon general photographic content classification techniques. The system features a flexible query language based upon a generic image concept ontology which can utilise both metadata (where available) and automatically extracted image content descriptors. Furthermore, the system supports both text-based querying as well as similarity-based searching and is thus well suited to iterative refinement of initial search results without the need for specialist knowledge of relevant keywords.