Recommending images of user interests from the biomedical literature

Steven Clukey, Songhua Xu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Every year hundreds of thousands of biomedical images are published in journals and conferences. Consequently, finding images relevant to one's interests becomes an ever daunting task. This vast amount of literature creates a need for intelligent and easy-to-use tools that can help researchers effectively navigate through the content corpus and conveniently locate materials of their interests. Traditionally, literature search tools allow users to query content using topic keywords. However, manual query composition is often time and energy consuming. A better system would be one that can automatically deliver relevant content to a researcher without having the end user manually manifest one's search intent and interests via search queries. Such a computer-aided assistance for information access can be provided by a system that first determines a researcher's interests automatically and then recommends images relevant to the person's interests accordingly. The technology can greatly improve a researcher's ability to stay up to date in their fields of study by allowing them to effciently browse images and documents matching their needs and interests among the vast amount of the biomedical literature. A prototype system implementation of the technology can be accessed via http://www.smartdataware.com.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2013
Subtitle of host publicationAdvanced PACS-Based Imaging Informatics and Therapeutic Applications
DOIs
StatePublished - Jun 5 2013
EventMedical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications - Lake Buena Vista, FL, United States
Duration: Feb 12 2013Feb 14 2013

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8674
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications
CountryUnited States
CityLake Buena Vista, FL
Period2/12/132/14/13

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Keywords

  • Biomedical images
  • Biomedical literature
  • Co-author distance
  • Image recommendation
  • Text mining

Fingerprint Dive into the research topics of 'Recommending images of user interests from the biomedical literature'. Together they form a unique fingerprint.

Cite this