| TBMI02 |
Medical Image Analysis, 6 ECTS credits.
/Medicinsk bildanalys/
For:
BME
D
IT
MED
U
Y
|
| |
Prel. scheduled
hours: 48
Rec. self-study hours: 112
|
| |
Area of Education: Technology
Main field of studies: Biomedical Engineering, Electrical Engineering
|
| |
Advancement level
(G1, G2, A): A
|
|
Aim:
The aim of the course is to give profound knowledge of how different medical images, volumes and sequences are generated and analyzed. Focus is especially on techniques and methods related to magnetic resonance tomography (MRT). A central part of the course is devoted to the design of multi dimensional filters and algorithms for the purpose of extracting different types of information from the medical data sets. After the course the student will be able to:
- Be able to optimize multi dimensional filters with respect to both frequency and spatial requirements.
- Compute local structure descriptors (Tensors) from image data.
- Use the local structure description to perform adaptive image enhancement.
- Describe image segmentation methods as: watershed, levelsets, and region growing. Implement a segmentation algorithm using active contours.
- Describe transformations and similarity measures for registration/fusion of images. Be able to implement a simple registration.
- Explain the behavior of multi-dimensional signals in the Fourier domain.
- In detail tell how the MRI data are sampled in k-space, and how to avoid related sampling problems.
|
|
Prerequisites: (valid for students admitted to programmes within which the course is offered)
Basic Linear Algebra: bases, scalar product, least squares problem, eigenvalue problems. Basic signal processing (corresponding to Linear Systems): sampling, convolution and Fourier transform of one-variable signals. Basic skills in Matlab is recommended.
Note: Admission requirements for non-programme students usually also include admission requirements for the programme and threshhold requirements for progression within the programme, or corresponding.
|
|
Supplementary courses:
Multidimensional Signal Analysis, Computer Vision, Medical Imaging, Neural Networks and Learning Systems
|
|
Organisation:
The course consists of lectures, laboratory exercises and a mini project. Lab exercises and the mini project are done in groups of 2 students. Lab exercises are presented orally at scheduled seminars. The mini project consists of 3 scheduled lab sessions and is presented in a written report. To pass the laboratory work you have to show the working code for the lab instructor, participate
in the lab seminars and present the written mini project report.
|
|
Course contents:
Medical imaging systems: Physical principles and image reconstruction algorithms for magnetic resonance tomography (MRI), ultrasound and computer tomography (CT). Analysis methods: Multidimensional Fourier analysis, local structure analysis in 2D, 3D and 4D (3D + time), motion/velocity estimation, registration, segmentation using adaptive contours and surfaces. Applications: Image enhancement, image registration, functional magnetic resonance imaging (fMRI).
|
|
Course literature:
Signal Processing for Computer Vision. G.H. Granlund and H. Knutsson. Kluwer 1994. ISBN 0792395301
Supplementary material
|
|
Examination: |
|
A written examination
Laboratory work
|
4 ECTS
2 ECTS
|
| |
|
|
Course language is English.
Department offering the course: IMT.
Director of Studies: Marcus Larsson
Examiner: Anders Eklund
Link to the course homepage at the department
Course Syllabus in Swedish
|