Invited SpeakersProfessor Alexandro Frangi
Electronic & Electrical Engineering Department
University of Sheffield
Computational medicine: towards integrated management of cerebral aneurysms
Current availability of and access to multifactorial and multiscale disease biomarkers opens the promise of comprehensive and personalised profiling of the health status of individuals. Ultimately, this is expected to deliver more effective diagnosis, prognosis, and treatment outcome. However, abundance of biomedical data in itself does not equate, in general, to improved patient care; it also contributes to the current information deluge and fragmented picture of health that clinicians have to deal with daily. A modern and integrative approach to decision making in healthcare requires the ability to discover quantitative disease biomarkers (e.g. genetics, biochemistry, anatomy, physiology, etc.) and to construct multifactorial decision support systems able dealing with the complexity and heterogeneity of current data sources. Computational methods, particularly those stemming from computational imaging and computational physiology are fundamental here. In turn, national and international initiatives are creating increasingly larger and richer multi-modal databases of cross-sectional and longitudinal data from where principled disease and disease progression models are to be derived by computational methods.
Computational Medicine aims at developing the framework and tools to tackle these challenges, address the unmet clinical need of such integrated investigation of the human body from modern data sources, and render practical methods and systems for personalized and predictive medicine. This lecture will focus on and illustrate two specific aspects: a) how the integration of biomedical imaging and sensing, signal and image computing, and computational physiology are essential components in addressing the challenge of a more personalized, predictive and integrative healthcare, and b) how such principles are pragmatically put at work to address specific clinical questions in the neurovascular domain. The latter, are taken from @neurIST (www.aneurist.org), an EU project led by the speaker.
Finally, this lecture will also underline the importance of model validation as a key factor in translational credibility and success; and how such validations span from technical validation of specific modelling components to clinical assessment of the proposed tools. The talk will conclude by outlining some of the areas where current research efforts fall short and where further investigation is required in the upcoming years.
Frangi AF, Hose DR, Hunter PJ, Ayache N, Brooks D. Guest editorial special issue on medical imaging and image computing in computational physiology. IEEE Trans Med Imaging. 2013;32:1-7.
Professor Matti Pietikäinen
Department of Computer Science and Engineering
University of Oulu
Face Analysis for Intelligent Human-Computer Interaction
Computer vision will play an important role in future human-computer interaction (HCI). In order to achieve natural HCI, there is a need for the computer to be able to interact with the user similar to the way human-human interaction takes place. The computer should, for example, detect and identify the user, recognize his or her emotional state, communicate easily by recognizing speech and gestures, and provide a natural response based on its observations. In recent years, we have been investigating various methods needed for intelligent face to face interaction. This talk provides an introduction to the vision-based perceptual interfaces, and overviews our recent progress in face recognition and biometrics, recognition of facial expressions and emotions, remote heart rate measurement from videos, recognition of spoken phrases from visual speech, visual speech animation from video sequences, and face analysis for wearable smart glasses. Results of our research with experimental systems for face analysis and intelligent human-robot interaction are also demonstrated. Finally, future challenges for research are briefly discussed.
Professor Jiri Matas
Department of Cybernetics
Faculty of Electrical Engineering
Czech Technical University
Novel Formulations of Large Scale Image Retrieval
After introducing the classical setting of the problem, I will focus on retrieval methods based on the bag of words image representation that exploit geometric constrains. Novel formulations of image retrieval problem will be discussed, showing that the standard ranking of images based on similarity addresses only one of possible user requirements.
Retrieval methods efficiently solving the new formulations by exploiting geometric constraints will be used in different scenarios. These include online browsing of image collections, image analysis based on large collections of photographs, or 3D model construction.
For online browsing, I will show queries that try to answer question such as: "What is this?" (zoom in at a detail), "Where is that?" (zoom-out to larger visual context), or "What is to the left / right of this?". For image analysis, two novel problems straddling the boundary between image retrieval and data mining are formulated: for every pixel in the query image, (i) find the database image with the maximum resolution depicting the pixel and (ii) find the frequency with which it is photographed in detail.
Professor B. John Oommen
Chancellor’s Professor; Fellow: IEEE; Fellow: IAPR
Sequence-based Estimation of Multinomial Random Variables
This paper deals with the relatively new field of sequence based estimation in which the goal is to estimate the parameters of a distribution by utilizing both the information in the observations and in their sequence of appearance. Traditionally, the Maximum Likelihood (ML) and Bayesian estimation paradigms work within the model that the data, from which the parameters are to be estimated, is known, and that it is treated as a set rather than as a sequence. The position that we take is that these methods ignore, and thus discard, valuable sequence- based information, and our intention is to obtain ML estimates by “extracting” the information contained in the observations when perceived as a sequence. Our earlier results introduced the concepts of Sequence Based Estimation (SBE) for the Binomial distribution, where the authors derived the corresponding MLE results when the samples are taken two-at-a-time, and then extended these for the cases when they are processed three-at-a-time, four-at-a-time etc. This current paper generalizes these results for the multinomial case. The strategy we invoke involves a novel phenomenon called “Occlusion” that has not been reported in the field of estimation. The phenomenon can be described as follows: By occluding (hiding or concealing) certain observations, we map the estimation problem onto a lower-dimensional space, i.e., onto a binomial space. Once these occluded SBEs have been computed, we demonstrate how the overall Multinomial SBE (MSBE) can be obtained by mapping several lower-dimensional estimates, that are all bound by rigid probability constraints, onto the original higher-dimensional space. In each case, we formally prove and experimentally demonstrate the convergence of the corresponding estimates. We also discuss how various MSBEs can be fused to yield a superior MSBE, and present some potential applications of MSBEs. Our new estimates have great potential for practitioners, especially when the cardinality of the observation set is small.
This is a joint work with Prof. S-W. Kim, from Myongji University, in Yongin, South Korea. Being a Plenary/Keynote talk, we will concentrate and survey the new paradigm of Binomial “Sequence-based Estimation”. Thereafter, we shall concentrate on the multinomial aspects of SBE.
ICIAR - International Conference on Image Analysis and Recognition
Send your comments to firstname.lastname@example.org