Lecture + Exercises · Informatics / Mathematics & Natural Sciences

Computational Medical Imaging (Lecture) (CoMI)

The core module of the Computational Medical Imaging curriculum in the M.Sc. Computer Science (lecture 4 h/week, exercises 2 h/week). It covers the physics of image formation and the classical and deep-learning methods for medical image segmentation, registration, quantitative imaging and radiomics, together with uncertainty, bias and the ethical and regulatory side of clinical translation.

Medical Imaging

Learning objectives

  • Explain the fundamental paradigms and mathematical foundations of computational medical imaging, from image formation (CT and MRI physics) to discrete reconstruction.
  • Apply classical and modern methods for segmentation, registration, feature extraction and radiomics, and deep learning (U-Net, GANs, vision transformers) to medical images.
  • Formulate imaging problems as optimisation tasks and derive and implement the cost functions and solvers.
  • Evaluate methods with the performance measures and protocols used in research and clinical practice (Dice, Hausdorff distance, ROC/AUC).
  • Discuss uncertainty, bias, data privacy, regulation and explainability in clinical translation, and emerging topics such as federated learning and large language models in radiology.

Target audience

Students of the M.Sc. Computer Science at the University of Bonn (optional module, 3rd semester).

Prerequisites

  • Recommended: basic knowledge of linear algebra, analysis, Matlab and Python.
  • Recommended: MA-INF 2312 Image Acquisition and Analysis in Neuroscience (or equivalent knowledge of medical imaging modalities) and/or MA-INF 2222 Visual Data Analysis (or equivalent knowledge of statistical data analysis).

Evaluation

  • Graded written exam.
  • Admission to the exam requires successful participation in the exercises.

Semesters

SemesterCourseFormatAudienceLecturers & tutors