| Course Unit Code | 450-4111/02 |
|---|
| Number of ECTS Credits Allocated | 4 ECTS credits |
|---|
| Type of Course Unit * | Optional |
|---|
| Level of Course Unit * | Second Cycle |
|---|
| Year of Study * | |
|---|
| Semester when the Course Unit is delivered | Summer Semester |
|---|
| Mode of Delivery | Face-to-face |
|---|
| Language of Instruction | English |
|---|
| Prerequisites and Co-Requisites | Course succeeds to compulsory courses of previous semester |
|---|
| Name of Lecturer(s) | Personal ID | Name |
|---|
| KUB631 | Ing. Jan Kubíček, Ph.D. |
| VON0045 | Ing. Jaroslav Vondrák, Ph.D. |
| Summary |
|---|
| Application of machine learning methods in biomedical engineering. Solution of selected cases of detection, segmentation and classification of biological signals. Design, tuning and implementation of machine learning methods for training and validation of supervised learning. Objective performance assessment of machine learning methods based on selected objectification parameters. |
| Learning Outcomes of the Course Unit |
|---|
| The aim of the course is for students to learn modern intelligent methods of biological data processing, which are applicable both in the field of modeling biological systems and knowledge extraction based on biological signals and images. The course is composed of two related parts that deal with both modeling of selected biological systems and machine learning methods for biological information content recognition. Graduates of the course will be able to apply their knowledge of cybernetics and machine learning to the variable cases of modeling and knowledge extraction in biomedical engineering. |
| Course Contents |
|---|
Lectures:
1. System definition, basic division, basic concepts, feedback, system description, mathematical apparatus.
2. Modeling biological systems, model building procedure, Models of static systems, models of dynamic systems, stochastic models of biological systems, basic attributes of systems.
3. Human organism as a system - basic properties of the organism, principles of homeostatic control, control mechanisms, stimuli, structure of biological system, receptors, homeostatic regulation, thermoregulation
4. Neurophysiology - nervous system. Information transmission and processing in biological systems. Nervous, hormonal and humoral levels of their control.
5. Heart. Cardiac activity and the importance of regulatory mechanisms during stress. The vascular system. Importance of the vasculature for circulation, possibilities and importance of its regulation.
6. Regulation of heart rate, Stabilization of blood pressure
7. Respiratory system. Control of the respiratory system. Lung function and its regulation in extreme conditions. Regulation of breathing
8. Water regulation, glycaemic control, pharmacokinetics
9. Introduction to machine learning: defining the areas of supervised and unsupervised learning.
10. Principles of machine learning system design, tuning, data annotation and hyperparameters of learning.
11. Methods for objective evaluation of machine learning performance: accuracy parameters and loss functions.
12.Examples of using machine learning methods for signal content recognition: signal detection and classification methods.
13. Examples of using machine learning methods for biological image analysis: semantic segmentation and convolutional neural networks.
14. Unsupervised learning methods for biological signal and image processing.
Laboratory exercises:
1. Introduction to the theory of ordinary differential equations: first and second order ODRs and their systems, general and partial solutions, Cauchy problem and Laplace transform.
2. Solution of ordinary differential equations in Simulink. Numerical solvers of differential equations in MATLAB.
3. Analytical solution and simulation of population models.
4. Pharmacokinetics: one-compartment and two-compartment drug passage model.
5. Analysis and simulation of heart rate dependence on exercise.
6. Modeling of renal function during blood pressure stabilization.
7. Pulmonary compartment: model of gas concentration in alveoli and other tissues.
8. Model of gastric acidity regulation.
9. Machine learning model preparation: model design, hyperparameter setting, annotated data generation.
10. Design of selected machine learning models for general examples of significant event detection, classification and regression.
11. Methods for detecting significant events from biological signals using machine learning.
12. Methods for classification of biological signals using machine learning.
13. Semantic segmentation methods for automatic object detection from medical images.
14. Convolutional neural networks for medical image classification. |
| Recommended or Required Reading |
|---|
| Required Reading: |
|---|
[1] Biomedical modeling and simulation on a pc: a workbench. S.l.: Springer, 2012. ISBN 9781461391654.
[2] MEURS, Willem van. Modeling and simulation in biomedical engineering: applications in cardiorespiratory physiology. 1. New York: McGraw-Hill, c2011. ISBN 978-0071714457.
[3] CHRISTOPOULOS, Arthur. Biomedical applications of computer modeling. Boca Raton: CRC Press, c2001. Pharmacology & toxicology (Boca Raton, Fla.). ISBN 9780849301001.
[4] KITTNAR, Otomar a Mikuláš MLČEK. Atlas fyziologických regulací: 329 schémat. Praha: Grada, 2009, 316 s. ISBN 978-80-247-2722-6.
[4] MITCHELL, Tom Michael. Machine learning. McGraw-Hill series in computer science. Boston: WCB/McGraw-Hill, c1997. ISBN 0-07-042807-7.
[5] DEISENROTH, Marc Peter; FAISAL, A. Aldo a ONG, Cheng Soon. Mathematics for machine learning. Cambridge: Cambridge University Press, 2020. ISBN 978-1-108-47004-9.
|
[1] Biomedical modeling and simulation on a pc: a workbench. S.l.: Springer, 2012. ISBN 9781461391654.
[2] MEURS, Willem van. Modeling and simulation in biomedical engineering: applications in cardiorespiratory physiology. 1. New York: McGraw-Hill, c2011. ISBN 978-0071714457.
[3] CHRISTOPOULOS, Arthur. Biomedical applications of computer modeling. Boca Raton: CRC Press, c2001. Pharmacology & toxicology (Boca Raton, Fla.). ISBN 9780849301001.
[4] KITTNAR, Otomar a Mikuláš MLČEK. Atlas fyziologických regulací: 329 schémat. Praha: Grada, 2009, 316 s. ISBN 978-80-247-2722-6.
[4] MITCHELL, Tom Michael. Machine learning. McGraw-Hill series in computer science. Boston: WCB/McGraw-Hill, c1997. ISBN 0-07-042807-7.
[5] DEISENROTH, Marc Peter; FAISAL, A. Aldo a ONG, Cheng Soon. Mathematics for machine learning. Cambridge: Cambridge University Press, 2020. ISBN 978-1-108-47004-9.
|
| Recommended Reading: |
|---|
[1] Tiefenbach,P: Biokybernetika, Sylaby na WWW stránkách katedry, 2002,
[2] Penhaker,M: Biokybernetika, Sylaby na WWW stránkách katedry, 2002,
[3] Samson Wright: Klinická fyziologie Praha 1987.
[4] Stefan Silbernagl, Agamemnom Despopoulos: Atlas fyziologie člověka. Praha 1984.
[5] Wiliam F. Canong: Přehled lékařské fyziologie. Praha 1976.
[6] Hrazdíra, I.: Biofyzika. Praha, Avicenum 1990.
[7] Nečas, O.: Biologie. Praha, Avicenum 1982.
[8] Dvořák - Maršík - Andrej: Biotermodynamika. Praha, Akademia, 1985.
|
[1] Tiefenbach,P: Biokybernetika, Sylaby na WWW stránkách katedry, 2002,
[2] Penhaker,M: Biokybernetika, Sylaby na WWW stránkách katedry, 2002,
[3] Samson Wright: Klinická fyziologie Praha 1987.
[4] Stefan Silbernagl, Agamemnom Despopoulos: Atlas fyziologie člověka. Praha 1984.
[5] Wiliam F. Canong: Přehled lékařské fyziologie. Praha 1976.
[6] Hrazdíra, I.: Biofyzika. Praha, Avicenum 1990.
[7] Nečas, O.: Biologie. Praha, Avicenum 1982.
[8] Dvořák - Maršík - Andrej: Biotermodynamika. Praha, Akademia, 1985.
Hrazdíra, I.: Biofyzika. Praha, Avicenum 1990.
Nečas, O.: Biologie. Praha, Avicenum 1982.
Dvořák - Maršík - Andrej: Biotermodynamika. Praha, Akademia, 1985.
Babloyantz, A.: Molecules, dynamics and life, J.Wiley, New York, 1986.
Talbot, S.a.: Systems physiology, J.Wiley, New York 1973.
|
| Planned learning activities and teaching methods |
|---|
| Lectures, Individual consultations, Tutorials, Other activities |
| Assesment methods and criteria |
|---|
| Tasks are not Defined |