NDAK10005U Medical Image Analysis (MIA)

Volume 2023/2024
Education

MSc Programme in Computer Science
MSc Programme in Physics

Content

Medical diagnosis, prognosis and quantification of progression is in general based on biomarkers. These may be blood or urine markers, but currently, imaging is taking over as a more indicative biomarker for many purposes.
This course will give an introduction to medical image formation in the different scanning modalities: X-ray, CT, MR, fMRI, PET, US etc. We will continue with the underlying image analysis disciplines of segmentation, registration and end with specific machine learning applications in clinical practise. A key to achieving success in the medical image analysis is formal evaluation of methodologies, thus an introduction to performance characterisation will also be a central topic.

We will use techniques from image analysis and real-world examples from the clinic.

The course aims to provide sufficient background knowledge for doing master theses (specialer) as well as student projects within medical image analysis.
 

The course is primarily aimed at students from computer science, physics and mathematics with an interest in applications to medical image analysis and related technologies.

 

 

Learning Outcome

The student will at the end of the course have:

 

Knowledge of

  • Physics of X-ray formation.
  • Computed tomography.
  • Magnetic Resonance Imaging.
  • Functional MRI.
  • Positron Emission Tomography.
  • Single Photon Emission Tomography.
  • Medical statistics.
  • Segmentation/Pixel classification.
  • Shape modelling and statistics.
  • Rigid & Non-rigid registration + Multi-modal registration.
  • Machine learning with medical data
  • Applications in lung diseases.
  • Applications in neurology.

 

Skills in

  • Explaining the basics of the underlying physics behind medical image acquisition techniques such as CT, MRI and PET. 
  • Explaining the role of medical image analysis in relation to detection and prognosis of pathologies and clinical investigations.
  • Reading and implementing methods described in the scientific literature in the field of medical imaging.
  • Finding and using existing tools within medical image analysis and assessing the quality of the output produced.
  • Applying the implemented methods to medical images with the purpose of analysing a specific pathology.


Competences in

  • Analysing, creating and using pipelines of methods for the purpose of analysing medical images in a scientific context.
  • Understanding the fundamental challenges in medical image analysis.
  • Understanding the representation of images in a computer.

See Absalon when the course is set up.

The students are expected to have a mature and operational mathematical knowledge. Linear algebra, geometry, basic mathematical analysis, and basic statistics are mandatory disciplines.

In the course, we will be using Python as the programming language, and programming skills in Python are highly recommended.

Academic qualifications equivalent to a BSc degree are recommended.
Lectures, exercises, and assignments.
  • Category
  • Hours
  • Lectures
  • 32
  • Preparation
  • 78
  • Exercises
  • 16
  • Exam
  • 80
  • Total
  • 206
Written
Individual
Continuous feedback during the course of the semester
Credit
7,5 ECTS
Type of assessment
Continuous assessment
Type of assessment details
Continuous assessment based on 4-6 written assignments.

The final grade is based on an overall assessment of the assignments.
Aid
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners
Re-exam

The re-exam consist of two parts:

1. Handing in (potentially revised) solutions to at least 75% of the course assignments no later than 3 weeks before the oral re-exam 

2. A 25 minutes oral examination (including grading) without preparation, covering the entire course syllabus

The final grade is based on an overall assessment.

 

 

Criteria for exam assesment

See Learning Outcome.