Software Project (BA), Scientific Team- / Individual Project (MA), Lab Project

Here you can find an overview of current student research projects, software internships, scientific team projects and laboratory internships as well as corresponding topics in the AG Visualisierung.

Note: Further topics can be derived from the master thesis topics. If someone does not have a team partner yet, an email can be sent to the appropriate contact person. If several students are interested in a topic, the working group can then get in contact and a team can be formed.


  • Scenarios for Narrative Visualization of Medical 3D Datasets

    Topic: Raw medical image data is hard to interpret for non-experts. However, to communicate medical topics visualization can help a lot. Therefore, this project strives to find appropriate visualization techniques to make medical image data accessible to the broad public.​ Different visualization techniques should be investigated regarding degrees of interactivity, animation, annotations, etc.

    Project Type: There are different possible scenarios, each scenario can be a separate student project. A project can be a Bachelor/Master Thesis, Team project, or Individual project.

    Requirements: The project will be done with the Unity Engine (using C# Scripts). Experience with Unity is beneficial but not obligatory. Programming skills in C# or a similar language as well as knowledge of basic computer graphics or visualization are required. Prior knowledge in medical visualization is beneficial but not obligatory.

    Scenario 1: Nested Structures

    In many cases, the infected tissue lies within healthy tissue. We have to visualize these nested surfaces to not just show the infected tissue but to also provide anatomical context

    • Medical Examples:​
      • Liver Tumor​
      • Brain Lesions​
    • Main Tasks: Implement and Compare Visualization Techniques, e.g.​
      • Transparent Surfaces​
      • Clipping Plane​
      • Cut-a-way-views​
      • Illustrative Techniques​

    Scenario 2: Compare Data Sets

    Some diseases might not be obvious to non-experts because they don’t know how the healthy anatomical structures look like. Therefore, a comparative visualization of multiple data sets can support their understanding.​

    • Medical Examples:​
      • Aneurysm before and after stent​
    • Main Tasks: Investigate Techniques to Compare Multiple Data Sets
      • Visualization techniques (see Scenario 1) that are suited for comparisons​
      • Techniques to link multiple visualizations together​

    Scenario 4: Blood Flow

    Visualizing blood flow is important for the explanation of many vascular diseases. However, blood flow can be very complex and it can be tricky to depict different streams inside a vessel without confusing non-experts.

    • Medical Examples:​
      • Flow inside an aneurysm​
      • Flow inside the aorta​
    • Main Task: Implement and Compare Flow Visualization Techniques​
      • Vessel Wall Depictions​
      • Depict Flow as Particles, Lines, …​
      • (Color Choices)​

    Scenario 5: Functional Data

    Medical visualization includes not only the representation of anatomical structures, but also functional data that is mapped to the anatomical surfaces.​

    • Medical Examples:​
      • Wall shear stress caused by blood flow​
      • (Blood flow velocity)​
    • Main Tasks: Implement and Compare Visualization Techniques for Functional Data​
      • Different Methods for Color-coding​
      • Legends​
      • Glyphs (e.g. like in a weather map)
  • VR: Build your Aneurysm

    Virtual simulations are a common possibility to provide neurosurgeons with additional training for cerebral aneurysm clipping. To provide appropriate training, the data/models (in this case aneurysms) have to be realistic and different cases should be included. This can be done by using patient-specific data. The problem is that the data is not always available and there are rare cases, so the user cannot train with many different models. Therefore, we are searching for a student who will implement an application to build own aneurysms that can be included in an existing clipping simulation.

    Your task would be to:

    • research existing and similar approaches and acquire some knowledge about cerebral aneurysms
    • implement an interactive application where the user virtually builds aneurysms

    The project should be realized in the game engine Unity, thus the following is required:

    • knowledge of basic computer graphics
    • experience with C# (and Unity)
  • VR: Simulating the opening of the Dura Mater

    Virtual simulations are a common possibility to provide neurosurgeons with additional training for cerebral aneurysm clipping. Before opening the brain, the dura mater (cerebral membrane) has to be removed carefully. This process is often missing in clipping simulations.

    Your task would be to:

    • research existing and similar approaches
    • implement an interactive virtual reality application where the user removes the dura mater

    The project should be realised in the game engine Unity, thus the following is required:

    • knowledge of basic computer graphics
    • experience with C# (and Unity)

  • 3D Deep learning for wall shear stress prediction of intracranial aneurysms

    Wall shear stress is a parameter derived from hemodynamic simulation and can be used in the diagnosis of intracranial aneurysms. We want to train a neural net to predict areas of high wall shear stress in intracranial aneurysms. This is a research oriented topic. Beside familiarization with recent research in deep learning on 3d structures it requires initiative and own ideas to advance the ongoing research.
    Material: surface meshes of (artificial) aneurysms and results of hemodynamic simulations
    Requirements: Programming experience (python), Experience with deep learning We expect high-qualified students interested in this project (team projects, bachelor or master thesis. Please send your application!

  • 4D-Segmentierung von Herzklappen mit Deep Learning

    In einem laufenden Forschungsprojekt zusammen mit der Herzchirurgie des Universitätsklinikums Heidelberg untersuchen wir CNN Deep Learning-Verfahren für die 4D-Segmentierung von Herzklappen auf klinischen Datensätzen. Basierend auf einer annotierten Trainingsdatenbank sollen verschiedene Netzwerke entwickelt und miteinander verglichen werden. Die Aufgabe eignet sich als Teamprojekt, kann aber auch für eine Abschlussarbeit angepasst werden.

    Anforderungen: Gute bis sehr gute Kenntnisse in Python und C++, Tensorflow/Keras/Pytorch

  • Wissenschaftliches Team-/Individualprojekt: Rekonstruktion und Visualisierung von Aneurysmen

    Im Rahmen aktueller Forschungsprojekte werden Strömungsverhältnisse und die Wanddicke bei Aneurysmen untersucht. Bisherige Bildgebungs-methoden können die Wanddicke nur unzureichend abbilden. Mit intravaskulärem Ultraschall kann auch die äußere Gefäßwand erfasst werden. Im Rahmen des STIMULATE Projekts wird die Eignung von intravaskulärem Ultraschall zur Beurteilung von zerebralen Aneurysmen untersucht. Das Projekt umfasst die neuartige und spannende Analyse von Gefäßinnen- und außenwand (basierend auf Tierpräparaten), die Evaluation von Stentplatzierungen und Auswertung von Strömungssimulationen.
    Für die Segmentierung von Gefäßinnen- und außenwand steht bereits eine Softwarebibliothek zur Verfügung, die an die neuen, speziellen Datensätze angepasst werden soll indem geeignete Parameter ermittelt werden. Für die Visualisierung sind verschiedene Erweiterungen denkbar, z.B. die Darstellung von Streamlines.


    • Eigenständige Einarbeitung in neues Themengebiet
    • Programmiererfahrung (vorrangig MATLAB, C++ wünschenswert)
  • DL Segmentation of Meningiomas

    We need you for our brain tumor segmentation project!
    We want to support our clinical cooperation partners from the University Hospital in Magdeburg. You will work with real medical data sets and you should develop a Deep Learning-based solution. Advantages: We have a Deep Learning server for remote work and the clinicians already provide sufficient ground truth data, so the data augmentation will be possible in feasible time.
    We expect high-qualified students interested in this project (hiwi job / student assistant or team projects, bachelor or master thesis). Please send your application!

  • 4D-CT und Therapieplanung

    Die Physikgruppe in der Klinik für Strahlentherapie der Medizinischen Fakultät bietet verschiedene Themen für wissenschaftliche Team- und Individualprojekte sowie Bachelor- und Masterarbeiten an. Die Beschreibung der einzelnen Themen sind den unter “weitere Infos” stehenden Dokumenten zu entnehmen. Es handelt sich dabei vorrangig um das Testen einer 4D-CT Anlage, der Optimierung von Therapien sowie um die Erprobung von virtuellen Simulationen. Ein Anpassung der Themen an die entsprechenden Projektarten ist möglich.


    • Eigenständige Einarbeitung in neues Themengebiet
    • u.U. Programmiererfahrung (C++ o.ä.)

Laufende Projekte und Praktika

Name, VornameRubrikTitel der ArbeitBetreuer