For my CE21 B students: Those who were not able to attend the lecture may find the lecture slides on the course website. montagnat-grid.pdf

Title: Biomedical applications using the grid
Speaker: Johan Montagnat, Ph.D

Abstract:

With the generalization of digital imaging in medicine and the emergence of ever growing medical archives, efficient tools for retrieving clinically relevant data are needed. Medical images are usually indexed with medical records (patient information, acquisition parameters, etc.) but for applications such as epidemiology or diagnostic assistance, images also need to be identified from their content. Content-based image retrieval in medical databases is challenging both in terms of computing power (size of image databases, complexity of algorithms) and in terms of performance of image content analysis algorithms (difficulty to identify relevant features in medical images).
Our research project is addressing the problem of content-based medical image retrieval in large databases. We are exploiting grids to tackle the computational requirement of this problem. We developed strategies to optimize the load distribution over the very large scale EGEE (Enabling Grids for E-sciencE) grid infrastructure, taking into account its properties and load. We have explored several
strategies to identify relevant images. Texture features extracted using Gabor filters proved to be an efficient and relevant mean of indexing medical databases. The texture feature could be correlated to image modality, tissues, and subtle changes such as myocardium tissues variation using the cardiac cycle.

About the Speaker:

Dr. Johan Montagnat has obtained his PhD in Computer Science (with highest honors) from the University of Nice-Sophia Antipolis (France). He is currently a research scientist at the French National Center for Scientific Research (CNRS), working in the fields of medical image processing and grid computing. Dr. Montagnat is a co-principal investigator of the ONCO-MEDIA project ( http://www.onco-media.com), an international research collaboration on biomedical applications of grid computing, wherein Ateneo de Manila University is one of the partner institutions.

Technorati Tags: grid computing, biomedical imaging, image retrieval