2003-2004 Academic Year

  Title: Content-Based Image Retrieval for Large Biomedical
  Image Archives

  Abstract:
  Content-Based Image Retrieval (CBIR) has been a topic of
  research interest for nearly a decade. Several approaches have 
  been proposed that  employ the use of image features for 
  describing image content. However, the a survey of the literature
  shows that progress has been limited to prototype systems and
  applications that make several assumptions and approximations. 
  Also, the attention has been largely focused on general imagery, 
  such as those found in the Corel image collection. At the Lister
  Hill National Center for Biomedical Communication, an R&D
  division of the National Library of Medicine, we are conducting 
  research on issues  related to CBIR for biomedical images. We 
  maintain an archive of over 17,000 digitized x-rays of the
  cervical and lumbar spine from the second National Health
  and Nutrition Examination Survey (NHANES II) data. In addition, 
  in collaboration with the NCI, we are in progress of developing an 
  archive of over 60,000 digitized 35mm color slides of uterine cervix. 
  These images along with patient data provide
  us with a real world situation of managing large collections of 
biomedical images. In this talk, I will present the challenges in CBIR 
of biomedical images and results from our research  efforts.