Medical Image Analysis

Course description

  1. Introduction: history, importance and areas of computer-aided analysis of medical images.
  2. Medical image sources: X-ray imaging, computed tomography, magnetic resonance imaging, ultrasound, nuclear medicine and molecular imaging.
  3. Image segmentation and quantitative analysis: classification and applicability of methods, (adaptive) thresholding, edge-based segmentation techniques, region growing, segmentation with clustering, deformable models,atlas- based methods. Validation of image segmentation methods.
  4. Image registration: clinical applications of image registration, classification of registration methods, spatial transformation models, within- and across-modality registration, landmark- based registrations, surface based registrations, intensity based registrations, similarity measures. Validation of registration methods.
  5. Image guided procedures: tracking devices, visualization in image-guided procedures, planning, registration of preoperative images, models and plan with intraoperative images, 3D-2D registration, validation of image guided procedures, clinical applications.

Course is carried out on study programme

Objectives and competences

To gain understanding of the importance and the basic principles of medical image analysis, which are nowadays an indispensable tool for diagnosis, planning, simulation and execution of medical procedures and for monitoring the effects of therapy and progression of disease. To acquire basic knowledge for analytical, numerical and experimental analysis of medical images.

Learning and teaching methods

Lectures throughout the semester if a sufficient number of students select this course. Otherwise, some introductory lectures, followed by individual research, tutorials and seminars under the supervision of the lecturer.

Intended learning outcomes

Knowledge and understanding:  The students will gain an understanding of the importance of medical images and of the basic principles of image segmentation, registration and information integration. They will gain knowledge to analytically, numerically and experimentally analyse the medical images.

Application: Equip the students with the knowledge and skills required for a career in an image-related field in clinical practice, clinical research, scientific research or technical development.

Transferable skills: The students will be equipped with generic transferrable skills required in a multidisciplinary scientific or clinical research environment. They will be able to use their skills in automated visual inspection in industry.

Reference nosilca

Galimzianova A, Pernuš F, Likar B, Špiclin Ž (2015) Robust Estimation of Unbalanced Mixture Models on Samples with Outliers. IEEE Tr on Pattern Analysis Machine Intelligence 37/11:2273-2285

Ibragimov B, Likar B, Pernuš F, Vrtovec T (2014) Shape representation for efficient landmark-based segmentation in 3-D. IEEE Tr on Medical Imaging 33/4:861-874

Mitrović U, Špiclin Ž, Likar B, Pernuš F (2013) 3D-2D registration of cerebral angiograms : a method and evaluation on clinical images. IEEE Tr on Medical Imaging 32/8:1550-1563

Špiclin Ž, Likar B, Pernuš F (2012) Groupwise registration of multimodal images by an efficient joint entropy minimization scheme. IEEE Tr. on Image Processing 21/5:2546-2558

Ibragimov B, Likar B, Pernuš F, Vrtovec T (2012) A game-theoretic framework for landmark-based image segmentation. IEEE Tr on Medical Imaging 31/9:1761-1776

Study materials

Sonka M,  Fitzpatrick JM (eds) (2009) Handbook of Medical Imaging, Vol 2, Medical Image Processing and Analysis, SPIE Publications

Bankman IN(ed) (2008) Handbook of Medical Image Processing and Analysis, 2nd edn., Academic Press, San Diego

Peters T, Cleary K (eds) (2008) Image-Guided Interventions: Technology and Applications, Springer

Birkfellner W (2014) Applied Medical Image Processing. A basic course, 2nd edn., CRC Press

Bodi na tekočem

Univerza v Ljubljani, Fakulteta za elektrotehniko, Tržaška cesta 25, 1000 Ljubljana

E: T:  01 4768 411