Français Presentation English

IMPORTANT: The MedGIFT project has a new Web page.

The MedGIFT project

Demos

Content-based image retrieval

Content-based visual information retrieval (CBVIR) or content-based image retrieval (CBIR) has been one on the most vivid research areas in the field of computer vision over the last 10 years. The availability of large amounts of visual and multimedia data, and the development of the Internet underline the need to create access methods that offer more than simple text-based queries or requests based on matching exact database fields. Many programs and tools have been developed to formulate and execute queries based on the content and to help browsing large image repositories.

Still, no general breakthrough has been achieved with respect to large, varied databases with images of differing sorts and with varying characteristics. It has to be underlined that content-based access to data by visual features is complementary to text-based queries and is unlikely to ever replace them completely. One of the problems is the loss in semantic information when visual features are extracted automatically.

Several retrieval systems can be found as web demonstrations or descriptions on the Internet such as:

Retrieval of Medical Images by their visual Content

In the medical field, images, and especially digital images, are produced and used for diagnostics and therapy in large amounts. The Radiology Department of the University Hospitals of Geneva alone produced more than 12,000 images per day in 2002. With DICOM, a standard for image communication has been set and patient information can be stored with the actual image(s).

In several articles, content-based access to medical images has been proposed and scenarios for the integration of content-based access methods into picture archival and communication systems (PACS) or into the diagnostic process are created. There are also several technical articles on technologies to search medical images by the content. Unfortunately, only very few systems have yet been integrated into the diagnostic process and there is, to our knowledge, only one study on possible clinical benefits of content-based retrieval techniques in the medical domain. It rather seems that medical doctors write what they think they need and computer scientists evaluate their algorithms with the images that they get but few common efforts have been started where the technologies are really tested in medical practice.

Information on some of the few existing projects can be found at:

Our projects for medical image retrieval

Lung Image Retrieval: the Talisman project
A couple of steps have to be taken for proper lung image retrieval. The first steps can not be done in an automatic way. A medical doctor (MD) has to supply the necessary information. Only like this, a proper evaluation of the retrieval quality is possible. Tools have to be developed to make this interactive process as easy as possible for the MD. At the University Hospitals of the Geneva a set of tools is the CasImage program that is a collection of medical cases including medical images, especially for teaching but that could also be used for case-based diagnostics.

  • Choose slices of the HRCT that represent the disease well;
  • link a diagnosis with a number of slices;
  • give a verbal description of the abnormalities of the tissue;
  • mark the region(s) in the slices that correspond best to the pathology.

Evaluation of retrieval systems and medical reference databases
Currently we have a clear lack of image databases available free of charge for evaluation purposes that include ground truth (or a gold standard). To really evaluate the performance of retrieval systems such databases and gold standards need to be created at several scales, for varied (PACS-like) databases where the goal needs to be to find visually similar images and specialized databases such as those containing lung high-resolution lung CTs, where the goal can be a diagnostic aid. Some of the available databases on the internet include the database of the Casimage project containing more than 8200 images free of copyright. This databases is in the accessible in the MIRC standard that offers some more free radiological resources. The European Federation for Medical Informatics has also founded an iniative to create a Reference Image Database. The National Library of medicine (NLM) offers access to some images such as those of the visible human project.

Combination of visual and textual features
Image retrieval by visual features can only be a complement to textual search for images and not a replacement. Best results can be expected when combining visual and textual cues. This has to our knowledge never been done in an in an integrated form with medical images. A web demonstration with a combination of visual and textual features for museum images can be found at Monash University.

Other important aspects of the medGIFT project

Besides the main focus on image retrieval, the medGIFT projects is also working on computer architectures in the hospital environment. One of the focuses is on grid networks to efficiently distribute the storage and processing of large amounts of data. We are taking part in the healthgrid organization and we have several related cooperations with organization that work actively on grid networks such as the CERN here in Geneva, and the IN2P3 in Lyon, France.


[ 15 mars, 2006 ]