UIMOIBP063 Advanced Methods of Medical Image Data Processing

Faculty of Philosophy and Science in Opava
Summer 2024
Extent and Intensity
2/2/0. 5 credit(s). Type of Completion: zk (examination).
Teacher(s)
doc. Ing. Petr Čermák, Ph.D. (lecturer)
doc. Ing. Petr Čermák, Ph.D. (seminar tutor)
RNDr. Šárka Vavrečková, Ph.D. (assistant)
Guaranteed by
doc. Ing. Petr Čermák, Ph.D.
Institute of Computer Science – Faculty of Philosophy and Science in Opava
Timetable
Wed 8:55–10:30 PU-UF
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
fields of study / plans the course is directly associated with
Course objectives
The course Advanced Methods of Medical Image Data Processing is primarily intended for students who are interested in the field of image processing in the context of modeling information from medical image data. During the course, students will be acquainted with the basic techniques for medical image editing with the aim of digital interpretation and visualization of image data. The next part of the course will deal with methods of image preprocessing in order to optimize image information (luminance and geometric transformations). In the following part of the course, methods of image filtering and analysis of objectification parameters will be discussed, which enable an objective analysis of the effectiveness of the respective filtering. The last part of the course will be devoted to segmentation methods, enabling the extraction of clinical information from medical images. Students will be acquainted with conventional principles of regional segmentation, time-deformable curves and cluster analysis methods. Attention will also be paid to unconventional methods of image segmentation, containing elements of heuristics with the aim of genesis of an optimized mathematical model of biological tissue. An integral part of part of the segmentation techniques will be methods for extracting the symptoms of the model of appropriate tissues.
Learning outcomes
After completing the course, the student will be able to:
- describe basic techniques for medical image editing with the aim of digital interpretation and visualization of image data,
- apply image preprocessing methods in order to optimize image information
- describe segmentation methods
Syllabus
  • 1. Basic methods for interpretation and visualization of digital image (RGB and monochrome image and their mutual conversions, image histogram and image analysis in time and frequency domain).
  • 2. Analysis of methods for image preprocessing - luminance transformations.
  • 3. Analysis of methods for image preprocessing - geometric transformations.
  • 4. Basic principles of signal filtering: FIR and IIR filter analysis, filter frequency response and image noise analysis. 5. Design of digital filters for image processing: cyclic convolution, average and median filter, Gaussian filter, and objective evaluation of filtration efficiency.
  • 6. 1D Wavelet transform: types of waves, analysis of continuous and discrete transformation, multicode, packet decomposition, approximation, and detailed signal coefficients, time-scale analysis of the signal, and examples of the application of Wavelet transform on real medical data.
  • 7. 2D Wavelet transform: image signal decomposition using Wavelet transform and Wavelet transform application for medical image data processing (filtering, compression, and segmentation).
  • 8. Binary image analysis: the genesis of binary image, morphological operations, and their applications for medical image data processing.
  • 9. Image segmentation: basic principles of segmentation, regional segmentation, analysis, and implementation of basic methods for segmentation of medical image data. 10. Cluster analysis: principles of non-hierarchical methods of cluster analysis (K-means, FCM, etc.) and implementation of these methods for image segmentation. 11. Unconventional methods of image segmentation: analysis of segmentation methods, containing elements of heuristics (genetic algorithms and evolutionary algorithms), and soft thresholding for image segmentation.
  • 12. Basic methods of image data classification and flags for classification
Literature
    required literature
  • RUSS, John C. The image processing handbook. 5th ed. Boca Raton: CRC/Taylor & Francis. ISBN 978-0-8493-7254-4. 2007. info
  • Gonzales R. C., Woods R. E. Digital Image Processing (2nd ed.). Prentice Hall, 2002. info
    recommended literature
  • JAN, Jiří. Medical image processing, reconstruction and restoration: concepts and methods. Boca Raton: Taylor & Francis. Signal processing and communications, 25. ISBN 0-8247-5849-8. 2006. info
  • SURI, Jasjit S., David Lynn WILSON a Swamy LAXMINARAYAN, ed. and SURI, Jasjit S., David Lynn WILSON a Swamy LAXMINARAYAN, ed. Handbook of biomedical image analysis. New York: Kluwer Academic/Plenum Publishers. Volume I, Segmentation Models. ISBN 0-306-48550-8. 2005. info
  • ROMESBURG, H Charles. Cluster analysis for researchers. Morrisville: Lulu Press. ISBN 1-4116-0617-5. 2004. info
  • COSTA, Luciano da Fontoura and Roberto Marcondes CESAR. Shape analysis and classification: theory and practice. Boca Raton: CRC Press. Image processing series. ISBN 0-8493-3493-4. 2001. info
Teaching methods
interactive lecture exercises
Assessment methods
75% attendance at exercises, active approach
Written test: 60 points
Elaboration of a semester project: 40 points
Fulfillment of min. 51 points
Language of instruction
Czech
Further Comments
Study Materials
The course is also listed under the following terms Summer 2021, Summer 2022, Summer 2023.
  • Enrolment Statistics (recent)
  • Permalink: https://is.slu.cz/course/fpf/summer2024/UIMOIBP063