ONCO-MEDIA 

 

ONtology and COntext related MEdical image Distributed Intelligent Access

Regional program ICT-Asia

2006-2010

· 1^st Assessment (ICT Asia seminar, Taipei, Taiwan, 19-21 Nov. 2007)

· MAEE/AFD intermediate report

Goals: 

 

1. Develop a novel grid-distributed, contextual and semantic based, intelligent information access framework for medical images and associated medical reports focusing on:

a. Robust visual indexing and retrieval algorithms for medical images;
b. Robust fusion indexing intelligent techniques for medical images and associated medical reports;
c.  Developing a grid-distributed medical image retrieval application that links the medical concepts of the images and text documents based on medical ontology using intelligent methods;
d.  Methods for context-sensitive navigation and query;

 

2. Explore new medical image diagnosis assistance, teaching and research access applications using semantic, visual and context-sensitive medical information with the grid computing facilities; 

 

3. Crystallize a network of research excellence in the field of distributed medical images access among Asian, French and French Switzerland partners, leveraging on their complementary scientific values and experience.

Contact: 

 

Daniel RACOCEANU

French National Research Center - CNRS

A/Prof. (Dr. Habil.) University of Franche-Comté, France

Director of  IPAL - Image & Pervasive Access Lab, Singapore

International Research Unit (UMI CNRS, NUS, I2R A*STAR, UJF),

E-mail: daniel.racoceanu@ens2m.fr

URL : http://www.comp.nus.edu.sg/~danielr/

Summary:

 

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 years. In the medical field, images, and especially digital images, are produced in ever-increasing quantities and used for diagnostics and therapy. The availability of large and steadily growing amounts of visual medical data and the development of the Internet underline the need to create thematic access methods that offer more than simple text-based queries or requests based on matching exact database fields. 

 

Many CBIR programs and tools have been developed to formulate and execute queries based on the medical image visual content and to help browsing. Still, no general breakthrough has been achieved with respect to large varied databases with documents of differing sorts (modalities) and with varying characteristics (anatomy, pathology). Answers to many questions with respect to semantic descriptors, semantic gap, medical image and report fusion indexing or context-sensitive navigation and query are still unanswered.

 

On the other hand, computation and data grids have also encountered a large success among the scientific computing community in the past few years. The medical imaging community is increasingly aware of the potential benefit of these technologies in facing today medical image analysis and retrieval challenges. 

 

In this context, the aim of ONCO-MEDIA project is to deploy a medical image semantic content-based application on a large scale grid test bed, by taking into account the context of the user and of the navigation / query and by matching semantic visual concepts extracted from the medical image with those (textual) extracted from the associated medical reports.

The Project