Uncategorized

Medizinische Bildverarbeitung (VU)

Course Details

Lecturer

Roxane Licandro
Philipp-Seeböck
Georg Langs

LVA-Nr.

193.215

Typ

Vorlesung mit Übung (VU)

Link

TISS

Curricula

066 645 Data Science
066 932 Visual Computing
066 936 Medical Informatics

The course is organised in a blocked-way starting end of April/beginning of May 2026 – more information regarding the schedule  is provided by the end of March 2026.

The aim of the course is to provide insights into medical image analysis, especially in practical clinical and industrial applications.

We will discuss the following topics in the lecture part of the course:

  • Medical imaging modalities
  • Segmentation
  • Model based detection and segmentation of anatomical structures
  • Texture analysis
  • Interactive segmentation
  • Rigid and non-rigid registration
  • Neuroimaging and machine learning, analysis of neuroimaging data
  • Applications in interoperative / interventional visualization
  • Atlas building
Subject of the course

Methods and modalities will be explained based on real world cases. For each we will discuss the mathematical basics, and ways of solving it. For each unit we will distribute reading material, so that we can have an interesting discussion during the lecture.

In the exercise part of the course students learn to solve medical imaging tasks in Python, like generation of shape- and appearance models, model-based segmentations of anatomical structures or texture analysis applied to bone structures, vessel detection, localization of anatomical structures.

The lab exercise is coordinated via TUWEL (available May 2026)

Additional information regarding the lecture and exercise can be found in TISS.

Content:

    • Implementing Medical Imaging Methods
    • Creating a workflow including image loading, feature extraction, feature embedding learning, prediction, evaluation and visualization of results
    • Deepening topics of the Medical Image Processing lecture
    • Constructing a 3D segmentation model for bone representations using deep learning and comparing it to classic machine learning methods
    • Writing a lab report

Organization:

  • Registration: via TISS
  • Initial meeting: End of April/Beginning of May 2026, (hybrid lecture in-person with live streaming and recording). Exact date will be announced end of March 2026. In this meeting an introduction to the lecture and the exercise part is given.  You will also have the opportunity to actively ask questions in this session.
  • Materials: slides of the initial meeting are provided via the TUWEL course
  • Excercise Group size: 3-4
  • Support: Support Forum in TUWEL and additionally, during the term we will have organised online tutorials with defined time slots, for which you can register as a group to ask questions. A teaching assistant will be present to support and guide you.
  • Online lab sessions: see dates in TUWEL.
  • Excercise Submission: Upload in TUWEL.