Hayit Greenspan, Tel Aviv University, Israel
Title: Deep Learning in Medical Applications
Marcus Cheetham, Universität Zürich, Switzerland
Title: Virtual Humans: Challenges and Opportunities from a Psychological Perspective
Salvador Pané i Vidal, Swiss Federal Institute of Technology (ETH), Switzerland
Title: Available soon
Deep Learning in Medical Applications
Tel Aviv University
Prof. Greenspan heads the Medical Image Processing and Analysis Lab at the Biomedical Engineering Dept. in the Faculty of Engineering, Tel-Aviv University. Prof. Greenspan has been conducting research in image processing and computer vision for the past 20 years, with a special focus on image modeling and analysis, resolution augmentation, and content-based image retrieval. Prof. Greenspan received the B.S. and M.S. degrees in Electrical Engineering from the Technion- Israel Institute of Technology, in 1986 and 1989, respectively, and the Ph.D. degree in Electrical Engineering from CALTECH – California Institute of Technology, in 1994. She was a Postdoc with the Computer Science Division at U.C. Berkeley from 1995 to 1997. In 1997 she joined Tel-Aviv University.
Prof. Greenspan has 35 journal publications in top-ranking journals, and more than 70 conference publications. She is the inventor of several patents. She is an Associate Editor of the top ranking journal in Medical imaging (IEEE-TMI) and is an active member of several international professional societies.
Machine learning is a key technology in medical image analysis. From unsupervised clustering of data to supervised learning of categories, statistical modeling tools are used across all modalities, from the molecular to MRI brain imagery. A leading trend in the machine learning community is Deep Learning which was termed one of the 10 breakthrough technologies of 2013 (MIT Technology Review, 2013). Within the Deep learning schemes, convolutional neural networks (CNNs) have become the most powerful technique for a range of different tasks in imaging and computer vision domains. CNNs are machine learning models that represent mid-level and high-level abstractions obtained from images. An overview of the leading machine learning tools will be presented in the talk for various medical imaging tasks. I will also present the initial work emerging with Deep learning in this domain, reviewing the challenges facing this field and its initial promising results.
Virtual Humans: Challenges and Opportunities from a Psychological Perspective
Marcus Cheetham is Professor of Cognitive Psychology at Nungin University and Senior Research Associate at the Department of Neuropsychology, Zurich University. He received his Master's Degree in Psychology from Freiburg University, Germany, and his PhD in Neuropsychology from Zurich University. His research focuses on understanding the behavioural and neuropsychological mechanisms that underpin the experience of cognitive and emotional engagement with humanlike characters. This research uses various methodologies including eye-tracking, electroencephalography (EEG), structural and functional neuroimaging (MRI and fMRI) and traditional psychological research techniques.
Advances in computer-graphic technologies in realistically simulating aspects of human appearance, motion and (interactive) behaviour have lead to the question: How does engaging and interacting with ever more realistic virtual humans actually influence human subjective experience and behaviour? One general and seemingly counter-intuitive answer, formulated in the Uncanny Valley Hypothesis, is that relatively high levels of anthropomorphic realism are likely to evoke an unpleasant affective state characterised by feelings of strangeness and the uncanny. Consideration of the inconsistent findings in this new field of research suggests that this general answer is likely to be superseded by a more differentiated perspective that better reflects the psychological complexities of human nature. This perspective suggests that there will be great variability across individuals, stimuli, situations, tasks and over time in the relationship between anthropomorphic realism of virtual humans (or particular aspects of virtual humans) and human experience and behaviour. One of the many challenges that arises from this perspective lies in understanding how realistic a virtual human (or particular aspects of the virtual human) needs to be – in view of differences between individuals, stimuli, situations, tasks and time – to affect the outcomes for which a virtual human is designed. Psychology offers insight into this challenge and the opportunities that follow from this perspective.
Salvador Pané i Vidal
Swiss Federal Institute of Technology (ETH)
Dr. Salvador Pané i Vidal (Barcelona, 1980) is currently a Senior Research Scientist at the Institute of Robotics and Intelligent Systems (IRIS) at ETH Zürich. He received a B.S. (2003), M.S (2004) and a PhD in Chemistry (2008) from the Universitat de Barcelona (UB) in the field of the electrodeposition of magnetic composites and magnetorresistive alloys. He became a postdoctoral researcher at IRIS in August 2008 and Senior Research Scientist in 2012. He has authored or co-authored 50 articles in international peer-reviewed journals and books for education in science. Dr. Pané is currently working on bridging chemistry and electrochemistry with robotics at small scales. In the field of micro- and nanororobotics, his major focus has been the miniaturization of magnetic materials and conductive polymers and hydrogels for targeted drug delivery. He is the head of the IRIS electrochemistry laboratory at ETH, which he established in 2010. At present, he teaches a course on nanorobotics and supervises eight on-going PhD theses. Dr. Pané is the coordinator for the MANAQA project (Magnetic Nanoactuators for Quantitative Analysis), which is funded by the EU commission under the Seventh Framework Programme (FP7/2007-2013) under Information and Communication Technologies (ICT). Dr. Pané was awarded the highly competitive Starting Grant from the European Research Council (ERC). The grant provides 1.5 million euros over five years to investigate composite nanomaterials with magnetoelectric properties for chemical and biomedical applications.