Medical imagery can be as helpful as medical information. However, searching for them may be a challenge. Researchers at Case Western Reserve University in Cleveland, Ohio are building a large-scale medical image retrieval system for consumers, using a medical ontology. Fierce Health IT brought this interesting news to our attention in their article, “Medical ontology helps automate image-retrieval system.”
The CWRU researchers combined visual object detection techniques with the Unified Medical Language System (UMLS), a gigantic medical ontology maintained by the U.S. National Library of Medicine. Their goal has been to reduce the amount of manual labeling required to detect each disease.
They have had minor successes and additional challenges, and are continuing to fine-tune the system. Just in time, too. It is reported that the overall storage and archiving volume requirements for U.S. medical imaging data will surpass the one exabyte mark by 2016.
Melody K. Smith
Sponsored by Access Innovations, the world leader in taxonomies, metadata, and semantic enrichment to make your content findable.
