Course detail

Analysis of Biomedical Images

FEKT-MPC-ABOAcad. year: 2019/2020

The subject is oriented towards providing an overview of the methods of biomedical image analysis, and a good insight into their concepts, as related to the properties of the medical image data obtained by individual imaging modalities used in medicine and biology.

Language of instruction

Czech

Number of ECTS credits

6

Mode of study

Not applicable.

Guarantor

doc. Ing. Radim Kolář, Ph.D.

Department

Department of Biomedical Engineering (UBMI)

Learning outcomes of the course unit

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.

Prerequisites

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

Co-requisites

Not applicable.

Planned learning activities and teaching methods

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.

Assesment methods and criteria linked to learning outcomes

Requirements for completion of a course are elaborated by the lecturer responsible for the course every year;
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)

Course curriculum

1. Two-dimensional signal as image representation, 2D Fourier transform and 2D spectra, spatial 3D images, with temporal development (4D), profiles and slices.
2. Digital image representation, basic image properties, 2D DFT and further 2D transforms, discrete spectra, temporal sequences of 2D and 3D images – 4D data.
3. Pre-processing of medical image data 1: contrast and colour transforms.
4. Pre-processing of medical image data 2: Mask operators, sharpening, noise suppression, field homogenisation, spectral domain processing.
5. Local features, statistical and spectral parameters, parametric images, edge, line and corner detection, raw and pure edge representation.
6. Texture analysis: texture descriptors in original and spectral domains, feature based and syntactic texture analysis, texture parametric images, textural gradient.
7. Image segmentation 1: edge oriented segmentation and Hough transform, segmentation based on parametric and texture-parametric images, region oriented segmentation (region growing, splitting and merging), watershed method.
8. Image segmentation 2: flexible contours, level-set based contours, active contours, pattern recognition based segmentation.
9. Registration and fusion of medical images: similarity criteria, optimization registration, mono- and multimodal registration, fusion based acquisition of image information.
10. Properties of image data in planar X-ray imaging and in X-ray computer tomography (CT).
11. Reconstruction of images from tomographic data: reconstruction from CT projections – algebraic methods, reconstruction via spectral domain, filtered back-projection; modifications needed in nuclear imaging.
12. Image data properties in magnetic resonance imaging (MRI) and principles of image reconstruction in MRI. Properties of data in nuclear imaging, in ultrasonography, electron microscopy, infra-imaging and electric impedance tomography.
13. Medical image processing environment – hardware and software requirements, data formats of medical images, compatibility of image data. Trends in analysis of medical multidimensional and multimodal images.

Work placements

Not applicable.

Aims

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.

Specification of controlled education, way of implementation and compensation for absences

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

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

J.Jan: Medical Image Processing,Reconstruction and Restoration, CRC Taylor and Francis 2006
P. Walek, M. Lamoš, J. Jan: Analýza biomedicínských obrazů, VUT v Brně, 2013 (CS)

Recommended reading

A.K.Jain: Fundamentals of Digital Image Processing. Prentice Hall, 1989

Elearning

eLearning: currently opened course

Classification of course in study plans

  • Programme MPC-BTB Master's 1 year of study, summer semester, compulsory

  • Programme EEKR-CZV lifelong learning

    branch EE-FLE , 1 year of study, summer semester, compulsory

Type of course unit

 

Lecture

26 hod., optionally

Teacher / Lecturer

prof. Ing. Jiří Jan, CSc.

Syllabus

1. Two-dimensional signal as image representation, 2D Fourier transform and 2D spectra, spatial 3D images, also with temporal development (4D), profiles and slices
2. Digital image representation, basic image properties, 2D DFT and other 2D transforms, discrete spectra, temporal sequences of 2D and 3D images - 4D data
3. Data properties in planar X-ray imaging, and in X-Ray computed tomography (CT)
4. Data properties in Magnetic Resonance Imaging (MRI) and nuclear imaging
5. Data properties in ultrasonography, electron microscopy, infrared imaging, electric impedance tomography
6. Pre-processing of medical image data: contrast and colour transforms, mask operations, denoising, field homogenisation, distortion restitution - geometric transforms, frequency domain processing
7. Medical image registration and fusion: similarity criteria, registration via optimisation, methods for monomodal and multimodal registration, fusion of image information
8. Tomographic data reconstruction: reconstruction from X-ray CT projections - algebraic and frequency-domain methods, filtered back projection, modifications needed in nuclear imaging, principles of image reconstruction in MRI
9. Local features, statistical and frequency-domain parameters, parametric images; edge-, line- and corner detection, raw- and modified edge representation
10. Texture analysis: original domain and frequency domain texture descriptors, feature based and syntactic texture analysis, textural parametric images, textural gradient
11. Image segmentation 1: edge based segmentation and Hough transform, segmentation based on parametric and textural images, region-based segmentation (region growing, splitting and merging, watershed-based segmentation)
12. Image segmentation 2: flexible contour segmentation - parametric flexible contours, level-set contours, active shape contours; pattern-recognition based segmentation
13. Medical image processing environment, hardware and software requirements, medical image data formats, compatibility of image data, trends in analysis of medical images and multidimensional image data

Exercise in computer lab

26 hod., compulsory

Teacher / Lecturer

Ing. Roman Jakubíček, Ph.D.
Ing. Jiří Chmelík, Ph.D.

Syllabus

1. PC demonstrations and simulations: Two-dimensional signal as image representation, 2D Fourier transform and 2D spectra, spatial 3D images, also with temporal development (4D), profiles and slices
2. PC demonstrations and simulations: Digital image representation, basic image properties, 2D DFT and other 2D transforms, discrete spectra, temporal sequences of 2D and 3D images - 4D data
3. Working with clinical data and visits to clinics: Data properties in planar X-ray imaging, and in X-Ray computed tomography (CT)
4. Working with clinical data and visits to clinics: Data properties in Magnetic Resonance Imaging (MRI) and nuclear imaging
5. Working with clinical data and visits to clinics: Data properties in ultrasonography, electron microscopy, infrared imaging, electric impedance tomography
6. PC demonstrations and simulations: Pre-processing of medical image data: contrast and colour transforms, mask operations, denoising, field homogenisation, distortion restitution - geometric transforms, frequency domain processing
7. PC demonstrations and simulations: Medical image registration and fusion: similarity criteria, registration via optimisation, methods for monomodal and multimodal registration, fusion of image information
8. PC demonstrations and simulations: Tomographic data reconstruction: reconstruction from X-ray CT projections - algebraic and frequency-domain methods, filtered back projection, modifications needed in nuclear imaging, principles of image reconstruction in MRI
9. PC demonstrations and simulations: Local features, statistical and frequency-domain parameters, parametric images; edge-, line- and corner detection, raw- and modified edge representation
10. PC demonstrations and simulations: Texture analysis: original domain and frequency domain texture descriptors, feature based and syntactic texture analysis, textural parametric images, textural gradient
11. PC demonstrations and simulations: Image segmentation 1: edge based segmentation and Hough transform, segmentation based on parametric and textural images, region-based segmentation (region growing, splitting and merging, watershed-based segmentation)
12. PC demonstrations and simulations: Image segmentation 2: flexible contour segmentation - parametric flexible contours, level-set contours, active shape contours; pattern-recognition based segmentation
13. PC demonstrations and simulations: Medical image processing environment, hardware and software requirements, medical image data formats, compatibility of image data, trends in analysis of medical images and multidimensional image data

Elearning

eLearning: currently opened course