Suchergebnis: Katalogdaten im Frühjahrssemester 2022

Nummer	Titel	Typ	ECTS	Umfang	Dozierende
MAS in Medical Physics
Fachrichtung: General Medical Physics
Vertiefung Bioimaging
Wahlfächer
151-0622-00L	Measuring on the Nanometer Scale	W	2 KP	2G	A. Stemmer
Kurzbeschreibung	Introduction to theory and practical application of measuring techniques suitable for the nano domain.
Lernziel	Introduction to theory and practical application of measuring techniques suitable for the nano domain.
Inhalt	Conventional techniques to analyze nano structures using photons and electrons: light microscopy with dark field and differential interference contrast; scanning electron microscopy, transmission electron microscopy. Interferometric and other techniques to measure distances. Optical traps. Foundations of scanning probe microscopy: tunneling, atomic force, optical near-field. Interactions between specimen and probe. Current trends, including spectroscopy of material parameters.
Skript	Slides and recordings available via Moodle (registered participants only).
227-0391-00L	Medical Image Analysis Basic knowledge of computer vision would be helpful.	W	3 KP	2G	E. Konukoglu, M. A. Reyes Aguirre
Kurzbeschreibung	It is the objective of this lecture to introduce the basic concepts used in Medical Image Analysis. In particular the lecture focuses on shape representation schemes, segmentation techniques, machine learning based predictive models and various image registration methods commonly used in Medical Image Analysis applications.
Lernziel	This lecture aims to give an overview of the basic concepts of Medical Image Analysis and its application areas.
Voraussetzungen / Besonderes	Prerequisites: Basic concepts of mathematical analysis and linear algebra. Preferred: Basic knowledge of computer vision and machine learning would be helpful. The course will be held in English.
227-0966-00L	Quantitative Big Imaging: From Images to Statistics	W	4 KP	2V + 1U	P. A. Kaestner, M. Stampanoni
Kurzbeschreibung	The lecture focuses on the challenging task of extracting robust, quantitative metrics from imaging data and is intended to bridge the gap between pure signal processing and the experimental science of imaging. The course will focus on techniques, scalability, and science-driven analysis.
Lernziel	1. Introduction of applied image processing for research science covering basic image processing, quantitative methods, and statistics. 2. Understanding of imaging as a means to accomplish a scientific goal. 3. Ability to apply quantitative methods to complex 3D data to determine the validity of a hypothesis
Inhalt	Imaging is a well established field and is rapidly growing as technological improvements push the limits of resolution in space, time, material and functional sensitivity. These improvements have meant bigger, more diverse datasets being acquired at an ever increasing rate. With methods varying from focused ion beams to X-rays to magnetic resonance, the sources for these images are exceptionally heterogeneous; however, the tools and techniques for processing these images and transforming them into quantitative, biologically or materially meaningful information are similar. The course consists of equal parts theory and practical analysis of first synthetic and then real imaging datasets. Basic aspects of image processing are covered such as filtering, thresholding, and morphology. From these concepts a series of tools will be developed for analyzing arbitrary images in a very generic manner. Specifically a series of methods will be covered, e.g. characterizing shape, thickness, tortuosity, alignment, and spatial distribution of material features like pores. From these metrics the statistics aspect of the course will be developed where reproducibility, robustness, and sensitivity will be investigated in order to accurately determine the precision and accuracy of these quantitative measurements. A major emphasis of the course will be scalability and the tools of the 'Big Data' trend will be discussed and how cluster, cloud, and new high-performance large dataset techniques can be applied to analyze imaging datasets. In addition, given the importance of multi-scale systems, a data-management and analysis approach based on modern databases will be presented for storing complex hierarchical information in a flexible manner. Finally as a concluding project the students will apply the learned methods on real experimental data from the latest 3D experiments taken from either their own work / research or partnered with an experimental imaging group. The course provides the necessary background to perform the quantitative evaluation of complicated 3D imaging data in a minimally subjective or arbitrary manner to answer questions coming from the fields of physics, biology, medicine, material science, and paleontology.
Skript	Available online. https://imaginglectures.github.io/Quantitative-Big-Imaging-2021/weeklyplan.html
Literatur	Will be indicated during the lecture.
Voraussetzungen / Besonderes	Ideally, students will have some familiarity with basic manipulation and programming in languages like Python, Matlab, or R. Interested students who are worried about their skill level in this regard are encouraged to contact Anders Kaestner directly (anders.kaestner@psi.ch). More advanced students who are familiar with Python, C++, (or in some cases Java) will have to opportunity to develop more of their own tools.
227-0967-00L	Computational Neuroimaging Clinic	W	3 KP	2V	K. Stephan
Kurzbeschreibung	This seminar teaches problem solving skills for computational neuroimaging (incl. associated computational analyses of behavioural data). It deals with a wide variety of real-life problems that are brought to this meeting from the neuroimaging community at Zurich, e.g., concerning mass-univariate and multivariate analyses of fMRI/EEG data, or generative models of fMRI, EEG, or behavioural data.
Lernziel	1. Consolidation of theoretical knowledge (obtained in one of the following courses: 'Methods & models for fMRI data analysis', 'Translational Neuromodeling', 'Computational Psychiatry') in a practical setting. 2. Acquisition of practical problem solving strategies for computational modeling of neuroimaging data.
Inhalt	This seminar teaches problem solving skills for computational neuroimaging (incl. associated computational analyses of behavioural data). It deals with a wide variety of real-life problems that are brought to this meeting from the neuroimaging community at Zurich, e.g., concerning mass-univariate and multivariate analyses of fMRI/EEG data, or generative models of fMRI, EEG, or behavioural data.
Voraussetzungen / Besonderes	The participants are expected to be familiar with general principles of statistics and have successfully completed at least one of the following courses: 'Methods & models for fMRI data analysis', 'Translational Neuromodeling', 'Computational Psychiatry'
227-1034-00L	Computational Vision (University of Zurich) No enrolment to this course at ETH Zurich. Book the corresponding module directly at UZH as an incoming student. UZH Module Code: INI402 Mind the enrolment deadlines at UZH: https://www.uzh.ch/cmsssl/en/studies/application/deadlines.html	W	6 KP	2V + 1U + 1A	D. Kiper
Kurzbeschreibung	This course focuses on neural computations that underlie visual perception. We study how visual signals are processed in the retina, LGN and visual cortex. We study the morpholgy and functional architecture of cortical circuits responsible for pattern, motion, color, and three-dimensional vision.
Lernziel	This course considers the operation of circuits in the process of neural computations. The evolution of neural systems will be considered to demonstrate how neural structures and mechanisms are optimised for energy capture, transduction, transmission and representation of information. Canonical brain circuits will be described as models for the analysis of sensory information. The concept of receptive fields will be introduced and their role in coding spatial and temporal information will be considered. The constraints of the bandwidth of neural channels and the mechanisms of normalization by neural circuits will be discussed. The visual system will form the basis of case studies in the computation of form, depth, and motion. The role of multiple channels and collective computations for object recognition will be considered. Coordinate transformations of space and time by cortical and subcortical mechanisms will be analysed. The means by which sensory and motor systems are integrated to allow for adaptive behaviour will be considered.
Inhalt	This course considers the operation of circuits in the process of neural computations. The evolution of neural systems will be considered to demonstrate how neural structures and mechanisms are optimised for energy capture, transduction, transmission and representation of information. Canonical brain circuits will be described as models for the analysis of sensory information. The concept of receptive fields will be introduced and their role in coding spatial and temporal information will be considered. The constraints of the bandwidth of neural channels and the mechanisms of normalization by neural circuits will be discussed. The visual system will form the basis of case studies in the computation of form, depth, and motion. The role of multiple channels and collective computations for object recognition will be considered. Coordinate transformations of space and time by cortical and subcortical mechanisms will be analysed. The means by which sensory and motor systems are integrated to allow for adaptive behaviour will be considered.
Literatur	Books: (recommended references, not required) 1. An Introduction to Natural Computation, D. Ballard (Bradford Books, MIT Press) 1997. 2. The Handbook of Brain Theorie and Neural Networks, M. Arbib (editor), (MIT Press) 1995.
227-0424-00L	Model- and Learning-Based Inverse Problems in Imaging	W	4 KP	2V + 1P	V. Vishnevskiy
Kurzbeschreibung	Reconstruction is an inverse problem which estimates images from noisy measurements. Model-based reconstructions use analytical models of the imaging process and priors. Data-based methods directly approximate inversion using training data. Combining these two approaches yields physics-aware neural nets and state-of-the-art imaging accuracy (MRI, US, CT, microscopy, non-destructive imaging).
Lernziel	The goal of this course is to introduce the mathematical models of imaging experiments and practice implementation of numerical methods to solve the corresponding inverse problem. Students will learn how to improve reconstruction accuracy by introducing prior knowledge in the form of regularization models and training data. Furthermore, students will practice incorporating imaging model knowledge into deep neural networks.
Inhalt	The course is based on following fundamental fields: (i) numerical linear algebra, (ii) mathematical statistics and learning theory, (iii) convex optimization and (iv) signal processing. The first part of the course introduces classical linear and nonlinear methods for image reconstruction. The second part considers data-based regularization and covers modern deep learning approaches to inverse problems in imaging. Finally, we introduce advances in the actively developing field of experimental design in biomedical imaging (i.e. how to conduct an experiment in a way to enable the most accurate reconstruction). 1. Introduction: Examples of inverse problems, general introduction. Refresh prerequisites. 2. Linear algebra in imaging: Refresh prerequisites. Demonstrate properties of operators employed in imaging. 3. Linear inverse problems and regularization: Classical theory of inverse problems. Introduce notion of ill-posedness and regularization. 3. Compressed sensing: Sparsity, basis-CS, TV-CS. Notion of analysis and synthesis forms of reconstruction problems. Application of PGD and ADMM to reconstruction. 4. Advanced priors and model selection: Total generalized variation, GMM priors, vectorial TV, low-rank, and tensor models. Stein's unbiased risk estimator. 5. Dictionary and prior learning: Classical dictionary learning. Gentle intro to machine learning. A lot of technical details about patch-models. 6. Deep learning in image reconstruction: Generic convolutional-NN models (automap, residual filtering, u-nets). Talk about the data generation process. Characterized difference between model- and data-based reconstruction methods. Mode averaging. 7. Loop unrolling and physics-aware networks for reconstruction: Autograd, Variational Networks, a lot of examples and intuition. Show how to use them efficiently, e.g. adding preconditioners, attention, etc. 8. Generative models and uncertainty quantification: Amortized posterior, variational autoencoders, adversarial learning. Estimation uncertainty quantification. 9. Inversible networks for estimation: Gradient flows in networks, inversible neural networks for estimation problems. 10. Experimental design in imaging: Acquisition optimization for continuous models. How far can we exploit autograd? 11. Signal sampling optimization in MRI. Reinforcement learning: Acquisition optimization for discrete models. Reinforce and policy gradients, variance minimization for discrete variables (RELAX, REBAR). Cartesian under-sampling pattern design 12. Summary and exam preparation.
Skript	Lecture slides with references will be provided during the course.
Voraussetzungen / Besonderes	Students are expected to know the basics of (i) numerical linear algebra, (ii) applied methods of convex optimization, (iii) computational statistics, (iv) Matlab and Python.
262-5140-00L	Biomedical Imaging and Scientific Visualization (University of Zurich) No enrolment to this course at ETH Zurich. Book the corresponding module directly at UZH as an incoming student. UZH Module Code: BIO219 Mind the enrolment deadlines at UZH: https://www.uzh.ch/cmsssl/en/studies/application/deadlines.html	W	2 KP	2V	Uni-Dozierende
Kurzbeschreibung
Lernziel

Seite 1 von 1