Course detail

Analysis of Biomedical Images

FEKT-MPA-ABOAcad. year: 2025/2026

The course is designed to provide students with a comprehensive overview of methods used for the analysis of biomedical image data and to develop a solid understanding of their underlying principles in relation to the characteristics of images acquired by various imaging modalities used in medicine and biology. The structure of the course enables students to first gain the necessary theoretical foundations of image processing and subsequently connect this theoretical knowledge with real applications in clinical and research practice.

Language of instruction

English

Number of ECTS credits

6

Mode of study

Not applicable.

Guarantor

Ing. Roman Jakubíček, Ph.D.

Department

Department of Biomedical Engineering (UBMI)

Offered to foreign students

Of all faculties

Entry knowledge

Knowledge at bachelor's level is required, especially in mathematics and signal processing.

Basic theory of digital signal and image processing.

Advanced knowledge of python programming is also required. 

 

Rules for evaluation and completion of the course

The conditions for successful completion of the course are determined by the annually updated directive of the course guarantor. Students must meet the following requirements:

  • Continuous assessment through short tests during the semester, focused on theoretical concepts covered in lectures and their direct application in practical exercises.
  • Preparation and presentation of a short expert presentation based on the analysis of a published scientific article addressing a specific problem in the medical domain or medical data processing.
  • Active participation in mandatory computer-based exercises including programming in Python.
  • Completion of a practical project with no minimum point requirement.
  • Successful completion of the final written exam verifying both theoretical knowledge and its practical application.

To obtain credit and successfully complete the course, students must achieve the minimum number of points set by the course guarantor's directive; the structure of the assessment is specified annually by the current directive.

Aims

The aim of the course is to provide students with an overview of methods used in medical image analysis and to develop an understanding of their principles as well as their practical software implementation. Upon completing the course, students are able to select and critically evaluate the suitability of image analysis methods for a specific purpose based on the theoretical and practical knowledge acquired during the course. They are capable of implementing these methods on an appropriate software platform or using commercial software, and they are prepared to contribute effectively as members of a research or experimental interdisciplinary team focused on the analysis of biomedical image data.

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Gengsheng Lawrence Zeng: Image Reconstruction, de Gruyter, 2017 (EN)
J. Jan: Medical Image Processing,Reconstruction and Restoration, CRC Taylor and Francis 2006 (EN)
J. Jan: Medical ImageProcessing, Reconstruction and Analysis 2nd edition CRC Press, Taylor & Francis 2020 (EN)
M. Nixon: Feature Extraction and Image Processing for Computer Vision, Academic Press (EN)

Recommended reading

M. Sonka, V. Hlavac: Image Processing, Analysis And Machine Vision, Cengage Learning, 2017 (EN)

Elearning

eLearning: currently opened course

Classification of course in study plans

  • Programme MPA-BIO Master's 1 year of study, summer semester, compulsory, fundamental theoretical courses of the profile core
  • Programme MPA-BTB Master's 1 year of study, summer semester, compulsory
  • Programme MPAD-BIO Master's 1 year of study, summer semester, compulsory, fundamental theoretical courses of the profile core
  • Programme MPC-BIO Master's 1 year of study, summer semester, compulsory
  • Programme MPC-BTB Master's 1 year of study, summer semester, compulsory

Type of course unit

 

Lecture

26 hours, optionally

Teacher / Lecturer

Ing. Roman Jakubíček, Ph.D.

Syllabus

1. Discrete Image and Its Representation - Mathematical Formulations of Image Discretization and Matrix Representation
2. Discrete 2D Transformations - Mathematical Formulations of Basic Transformations for Image Processing
3. Discrete 2D Operators - Mathematical Foundations of Main Operators in Image Processing (Local, Point-wise, Global)
4. Image Enhancement - Noise Suppression, Contrast and Color Adjustment, Sharpening, Edge Highlighting
5. Feature Extraction from Image Data - Problem Formulation, Basic Overview, and Principles of Methods
6. Edge Representation - Detection and Adjustment of Edges in an Image Using Gradient Operators
7. Image Segmentation - Overview and Basic Principles of Common Image Segmentation Methods
8. Morphological Operators for 2D Binary Images
9. Approaches for Image Classification - Overview of Basic Principles
10. Image Registration - Geometric Transformations, Image Interpolation, Similarity Criteria, and Registration Approach with Optimization Algorithm
11. Reconstruction from Tomographic Projections - Mathematical Principles of Basic CT Data Reconstruction Methods from Projections (FBP, Algebraic, and Combined Approaches) 

 

Exercise in computer lab

26 hours, compulsory

Teacher / Lecturer

Ing. Kateřina Krejčí
Ing. et Ing. Michal Nohel
Ing. Petra Nemčeková
Ing. Madeleine Alabdah

Syllabus

1. Basic operations with discrete images, image spectrum, and basic 2D functions, verification of Fourier transform properties.
2. Discrete 2D operators - point-wise operations (contrast adjustment, gamma correction, etc.) and local operations (edge enhancement, image sharpening, noise reduction).
3. Feature extraction - demonstration of feature extraction from the frequency domain, convolution-based features, texture analysis, and adaptive filtering.
4. Edge detection - implementation of methods based on 1st derivative, 2nd derivative, and combined approaches.
5 .Image segmentation - simple, adaptive, multi and semi-thresholding, Otsu's method, region growing, watershed, parametric and geometric flexible contours, deep-learning approachces, morphological operations.
6. Object recognition - Implementation of the Hough transform for lines and circles.
7. Implementation of 2D interpolation, introduction and implementation of rigid and flexible geometric transformations, final implementation of image registration and fusion.
8. Reconstruction of tomographic images - Implementation of the Radon transform, sinogram construction, plain and filtered back-projection, reconstruction with fan projections.

 

Project

13 hours, compulsory

Teacher / Lecturer

Ing. Roman Jakubíček, Ph.D.

Elearning

eLearning: currently opened course