Keynote 4 : Statistical Analysis and Simulations of Functional Measures in Medical Studies

Prof. Chafik Samir, 
University of Clermont Auvergne, France 


Statistical shape analysis plays an important role in various medical imaging applications. In particular, such methods provide tools for registering, deforming, comparing, averaging, and modeling anatomical shapes. In this talk, we focus on a recent method for statistical shape analysis of elastic parametrized data (surfaces, images, signals) for diseases characterization and to simulation of realistic samples.

Recent advances in medical imaging offer increasingly detailed information on typical anatomical structures. However, there is a lack of validation techniques for automatic image processing strategies, especially for multimodal images, i.e. coming from two different types of imaging equipment. In many medical applications, real data can only be extracted manually by an expert, and then used to validate image/signal processing algorithms. Indeed, scarcity of data for evaluation results in restricted studies.

We present new statistical frameworks to generate realistic simulated data that can be used as ground truth when dealing with deformability of observations (e.g. cells). Standard methods to assess an accurate diagnosis use multiple modalities. However, some limitations due to non-localized pertinent information cannot be directly avoided. An interesting solution is to statistically analyze shapes of real clinical data and provide enough random or simulated samples to validate registration step; registration of different modalities is key for fusing complementary information for diagnostic purposes.

About the Speaker:


Chafik Samir is an Associate Professor at The University of Clermont Auvergne (UCA), France. He obtained his Ph.D. degree in Computer Vision from Lille 1 University of Science and Technology in 2007 and his HDR degree (Habilitation à Diriger des Recherches) in 2014. After spending two years as a post-doc at UCL, he joined UCA as an Assistant Professor in 2009. His main research interests involve fitting curves on Riemannian manifolds, statistical shape analysis, medical imaging, computer vision, and their application to real-world problems. His international experiences include University of California Los Angles, Florida State University, Ohio State University, Catholic University of Louvain, Universidade Do Estado De Santa Catarina. He has been a reviewer for several referred scientific journals and conferences.

                twitter icon      facebook icon

Copyright 2015. Joomla 1.7 templates. Laboratoire LaRIT