Subject description
– Acquisition of digital images: optical and perceptual characteristics of human vision, types and definitions of digital images and videos, color representation and color spaces, quality parameters, technologies for image acquisition with digital photography and cameras for visible and invisible light, on macro- and microscopic levels, fundamentals of radiographic imaging, computed tomography, magnetic resonance imaging and ultrasound, image content understanding.
– Visualization, manipulation and compression of grayscale, color and multidimensional images.
– Image analysis: thresholding, registration-driven (physical, topological, statistical) model based description, regression and analysis based on deep learning models, region-of-interest description and measurement, growth and motion analysis.
– Design and implementation of imaging information systems: software tools for image acquisition and analysis, design, integration and implementation of imaging information systems in bioengineering research and applications (microscopy, food quality control, monitoring of growth and motion of animals, plants and microorganisms, etc.).
The subject is taught in programs
Objectives and competences
To provide an introduction to biomedical image acquisition, computer-assisted image analysis; to develop basic understanding of digital image processing, restoration, calibration and quantitative analysis; to develop basic understanding of machine and deep learning based tools for digital image regression, classification and analysis; and to develop understanding of image processing and analysis methods, which enable objective and quantitative evaluation of the environment, space, objects and subjects in bioengineering.
Teaching and learning methods
An overview of the area and basic theory will be provided through lectures, while practical knowledge and experience will be provided through lab work and projects or seminars, selected by the students to best match their specific interests.
Expected study results
Students completing this course will gain a fundamental understanding of biomedical image acquisition and computer-assisted image processing and analysis; will gain hands-on knowledge of applications of image processing and analysis and be able to apply existing image processing algorithms, and design, train and validate deep learning based models for image-based regression and classification tasks in the field of biosciences.
Basic sources and literature
– Thomas M. Deserno. Biomedical Image Processing. Springer, 2011.
– Klaus D. Tonnies. Guide to Medical Image Analysis: Methods and Algorithms. Springer, 2012.
– Deep Learning (Ian J. Goodfellow, Yoshua Bengio and Aaron Courville), MIT Press, 2016.
– Boštjan Likar. Biomedicinska slikovna informatika in diagnostika, 1. izdaja, Založba FE in FRI,
Ljubljana: Fakulteta za elektrotehniko, 2008.
Stay up to date
University of Ljubljana, Faculty of Electrical Engineering Tržaška cesta 25, 1000 Ljubljana