Theses and Research Projects

You must fulfill all requirements of your FPO before applying to a thesis!

Please directly contact a team member of SPARC if you have a particular interest in a project or topic for a thesis. Do not forget to include a transcript of records with all applications!

Master theses (30 ECTS):

As part of the thesis, a prototyp for keeping the suture thread under tension (on demand) is to be designed and realised.

Required skills:

  • Fluent in English or German
  • Basic knowledge in mechatronics
  • Experience in designing of mechanical prototype
  • Experience in realising said prototype
  • Working independent and self-supervised
  • [optional] Basic coding skills and electrical engineering (if an automated system is used)

Supervisor:

Steffen Peikert

PhD Candidate

AIBE-SPARC
Department Artificial Intelligence in Biomedical Engineering (AIBE)

Relevant video (from 04:40 – 05:03):

Setting:
We have a system that can generate 3D aorta meshes (the main artery carrying blood away from the heart). But this system is based on heuristics and produces aortas that are overly idealistic. We want to produce more “realistic” aortas. For this, we want to use a data-driven approach (learn the generation of aortas from real patient data).
(Bachelor’s/Master’s) Thesis Description:
As part of the thesis, you will develop a generator for aortas using real patient data. The first step involves collecting and preprocessing 3D patient data for training. In the second step, a system will be developed and trained to generate unseen realistic aortas based on this data. This aorta generation must be steerable (it should be possible to “ask” for specific types of aortas).

Task:

  • Explore the current state of the art for steerable 3D object generation.
  • Collect and process patient data (we also have data to get started with).
  • Train and develop your method to generate unseen synthetic aortas.
  • Evaluate the generated aortas (correct distribution, correctly steered, etc.).
  • Participate in team meetings and provide regular updates on progress

Required skills:

  • Good and clean coding skills (Python, PyTorch, Git, Conda/Virtualenv).
  • Understanding of neural networks, training, and validation.
  • Background in computer graphics or geometry processing.
  • Ability to work independently.

It will be beneficial if you have experience with:

  • Writing efficient code (and parallel processing).
  • Volumetric data (voxel grids).
  • Implicit shape representations (e.g. neural signed distance fields).
  • Developing on Linux.

Supervisor:

Jonas Fischer

PhD Candidate

Department Artificial Intelligence in Biomedical Engineering (AIBE)
Surgical Planning and Robotic Cognition Lab

Co-Supervisor:

Pit Henrich

PhD Candidate

Department Artificial Intelligence in Biomedical Engineering (AIBE)

Description

The goal of this thesis is to develop a patient-specific eye model that enables realistic path planning for eye surgeries. The focus lies on generating accurate anatomical representations of the eyes and surrounding structures, as well as defining relevant surgical scenarios. Depending on the scope (Bachelor Thesis, Master Thesis, or Research Project), the work may also include path planning with specific surgical constraints.

Tasks

  • Create anatomically accurate 3D mesh models of the eyes.

  • Develop a head/face model that incorporates the eyes, ensuring that surrounding structures (e.g., nose, skull) are included as potential obstructions in surgical access.

  • Work together with the supervisor to identify and describe relevant eye surgery use cases for testing and validation.

  • Optional (depending on thesis type): Implement and evaluate path planning methods with trocar constraints for minimally invasive access

Required Skills

No single skill is a strict requirement; motivation and willingness to learn are most important. However, the following prior knowledge is advantageous:

  • Fluent in English or German

  • Basic knowledge in CAD modeling and 3D mesh generation

  • Coding skills (e.g., Python, C++, or similar)

  • Ability to work independently and in a structured, self-supervised manner

  • Familiarity with the Robot Operating System (ROS) is a plus

Supervisor:

Dr.-Ing. Christian Kunz

Group Leader / Postdoctoral Fellow

Department Artificial Intelligence in Biomedical Engineering (AIBE)
Surgical Planning and Robotic Cognition Lab

Description

The objective of this thesis is to develop and evaluate methods for three-dimensional (3D) reconstruction based on stereo images acquired with a stereo endoscope. Such reconstructions are essential for enhanced navigation, visualization, and surgical assistance in minimally invasive procedures. The work includes calibration of the stereo endoscope, development of stereo-matching and depth-estimation algorithms, and generation of accurate 3D surface models. Depending on the thesis type (Bachelor, Master, or Research Project), the focus can range from fundamental implementation to advanced optimization and validation in surgical scenarios.

Tasks

  • Calibration of the stereo endoscope: Determination of intrinsic and extrinsic camera parameters. Correction of distortions and alignment of stereo image pairs.

  • Stereo image preprocessing: Rectification and illumination normalization. Handling of reflections and challenging endoscopic imaging conditions.

  • Depth estimation and stereo reconstruction: Implementation and comparison of stereo matching algorithms (e.g., block matching, semi-global matching, deep-learning-based methods). Generation of dense disparity maps and conversion into 3D point clouds or surface meshes.

  • Evaluation and validation: Testing on synthetic datasets and real endoscopic images. Quantitative and qualitative assessment of reconstruction accuracy.

Supervisor:

Dr.-Ing. Christian Kunz

Group Leader / Postdoctoral Fellow

Department Artificial Intelligence in Biomedical Engineering (AIBE)
Surgical Planning and Robotic Cognition Lab

Research Projects and Master Thesis Projects (10 ECTS):