Faculty of Technical Sciences

Subject: Medical Image Processing (17.BMI121)

Native organizations units: Department of Power, Electronic and Telecommunication Engineering
General information:
 
Category Professional-applicative
Scientific or art field Telecommunications and Signal Processing
Interdisciplinary No
ECTS 5
Educational goal:

Application of contemporary image analysis and computer vision methods to medical imaging. Introduction into basic tools in medical computer vision and image processing and solving of actual medical imaging problems through computer vision and processing systems.

Educational outcome:

Knowledge of medical image properties. Knowledge of useful tools for digital medical image processing for diagnostic display. Awareness of modern machine vision algorithms in medicine. Practical experience in digital processing of diagnostic medical images from different imaging modalities.

Course content:

- Basic terminology – digital medical imagery 2D and 3D, modalities, resolution, isotropy, dynamic images, temporal resolution, interpolation - Multiscale image analysis – analysis and synthesis processes, pyramidal image representation, wavelets and Discrete Wavelet Transform - Image processing for presentation and analysis – digital x-ray images, properties of raw image data, dynamic range and MTF corrections, image structure enhancement, normalisation, sources and removal of noise, tone scaling - Multimodal diagnostic image fusion – visualisation of different modalities in a single image, structure fusion methods, monochromatic multi-scale fusion, colour spaces and colour fusion - Optimisation – advanced local and global optimisation methods, objective functions and distance measurement, hypothesis testing - Registration – image normalisatin, (perspecte) image transformarions, deformations, deformable registration, deformation fields, objective measures (MI, absolute differences, sum of squares) - Segmentation – iluminatin segmentation, snakes, level sets, mean shift, graf cuts, Markov fields - Shape and appearance modeling – statistical shape and texture models, appearance models, active appearance models (AAM)

Teaching methods:

Oral lectures; computer lab exercises in adequate software packages

Literature:
Authors Title Year Publisher Language
Sonka, M., Hlavac, V., Boyle, R. Image Processing, Analysis and Machine Vision 2008 Thompson Learning, Toronto English
V. Petrović Obrada slike u medicini 2012 Skripta Serbian language
Aubert, G., Kornprobst, P. Mathematical problems in image processing : partial differential equations and the calculus of variations 2006 Springer, New York Serbian language
Knowledge evaluation:
Course activity Pre-examination Obligations Number of points
Test Yes Yes 10.00
Written part of the exam - tasks and theory No Yes 30.00
Computer excersise defence Yes Yes 30.00
Project defence Yes Yes 30.00
Lecturers:
API Image

prof. dr Petrović Vladimir

Full Professor

Lectures
API Image

prof. dr Petrović Vladimir

Full Professor

Computational classes

Asistent Šobot Srđan

Assistant - Master

Computational classes

Faculty of Technical Sciences

© 2024. Faculty of Technical Sciences.

Contact:

Address: Trg Dositeja Obradovića 6, 21102 Novi Sad

Phone:  (+381) 21 450 810
(+381) 21 6350 413

Fax : (+381) 21 458 133
Emejl: ftndean@uns.ac.rs

© 2024. Faculty of Technical Sciences.