Of all faculties

The graduate of the course is capable of:
- recommending and critically evaluating suitability of individual methods of medical image analysis to a particular purpose, based on theoretical and practical knowledge gained in the course,
- implementing these methods on a suitable software platform, possibly with commercial software,
- being a valid member of a research / experimental interdisciplinary team in the area of biomedical image data.

The generic knowledge on the Bachelor´s degree level is requested, namely in the area of mathematics and signal processing.

Not applicable.

Not applicable.

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

Teaching methods depend on the type of course unit as specified in the article 7 of BUT Rules for Studies and Examinations. Techning methods include lectures and computer laboratories. Course is taking advantage of e-learning (Moodle) system. Students have to write a project/assignment during the course.

Basically:
- obtaining at least 12 points (out of 24 as course-unit credit based on active presence in demonstration exercises),
- successful passing of final written exam (up to 76 points, min. 38 points)

English

Not applicable.

1. Analogue image in continuous space - image as a multidimensional signal - 2D systems with continuous space - 2D integral Fourier transform, 2D spectrum - concept of stochastic image - ideal sampling of image 2. Digital 2D images, systems and spektra - image as a matrix or vector - analogue image reconstruction from samples - discrete 2D operators and systems, linear and nonlinear - discrete 2D linear transforms 3. Image enhancement - purpose - transforms of brightness/contrast or of color scale - sharpening and edge enhancement - image smoothing and noise reduction 4. Image analysis (1) - local properties of images - texture analysis 5. Image analysis (2) methods of image segmentation: - based on homogeneity of areas - region oriented methods 6. Image analysis (3) methods of image segmentation: - watershed-based segmentation - edge-based methods 7. Image analysis (4) methods of image segmentation: - flexible contours - active contours - morphological image analysis 8. Reconstruction of tomographic images 1 - image reconstruction from projections (CT, SPEKT, PET) 9. Reconstruction of tomographic images 2 - image reconstruction in MRI - image reconstruction in ultra-fast ultrasonography (UFUS) 10. Image fusion 1 - geometric transformations of images - interpolation in images 11. Image fusion 2 - similarity of images and their parts - image registration - methods and applications of fusion 12. Introduction to image restoration - model of distortion - deconvolution and inverse filtering - pseudoinversion - Wiener filtering 13. Introduction to image analysis based on artificial intelligence - classical convolutional neural networks (CNN) - convolutional neuronal networks with matrix output (of coder-decoder type) - use of CNN for image analysis, application examples

The goal of the course is to enable the students gaining an overview of, and insight into, the methods of medical image analysis; acquiring practical experience in software realisation of the methods.

Delimitation of controlled teaching and its procedures are specified by a regulation issued by the lecturer responsible for the course and updated for every year (see Rozvrhové jednotky).
Basically:
- obligatory computer-lab tutorial
- voluntary lecture

13 hours, compulsory