PhD Student in Surgical Tool-Tissue Modeling, 3D Reconstruction, and Soft Tissue Simulation

The University of Zurich

Switzerland's largest university, the University of Zurich (UZH), offers a diverse range of attractive positions across various subject areas and professional fields. With approximately 10,000 employees and 12 professional apprenticeship streams, UZH provides an inspiring working environment that fosters cutting-edge research and top-class education. Leverage your talents and skills by joining us. Discover more about UZH as an employer!

Your Responsibilities

The primary responsibility of the PhD student is to conduct original research focused on dynamic 3D modeling of surgical anatomy under tool-tissue interaction. You will work with multi-modal data acquired at OR-X, including CT, RGB-D sequences, tool tracking, and optical surface models, to develop methods for reconstructing and simulating anatomical changes during manipulation.

The core research challenges involve achieving accurate 3D reconstructions that can be continuously updated from sensor data. Possible approaches include:

• Graph neural networks
• NeRF representations
• Point-based and diffusion-based models
• Advanced differentiable rendering frameworks like Gaussian Splatting

The specific direction of the research will be shaped by scientific explorations throughout the project. We expect the work to yield methodological contributions, which will be documented through publications in leading venues such as MICCAI, IPCAI, or Medical Image Analysis. In the initial phase, the candidate will review the state of the art and create a structured multi-year research plan in collaboration with their supervisor. The PhD is part of the graduate school at UZH, which also involves serving as a teaching assistant for 1-2 courses annually.

The PhD project will specifically involve:

• Building multi-modal 3D reconstructions by fusing CT-based anatomical models with photorealistic or depth-based surface reconstructions from optical cameras
• Developing algorithms to integrate real-time camera observations into dynamic anatomical models for tracking tool-tissue interactions
• Exploring learning-based methods for dynamic anatomy modeling, including GNNs, implicit neural representations, and radiance fields
• Investigating simulation approaches ranging from finite element simulation to learned physical models
• Conducting user studies to assess the applicability of the developed methods within a surgical training environment
• Collaborating with surgeons and engineers to ensure the translational relevance of the work
• Disseminating results through scientific publications, patents, and prototype demonstrations

Your Profile

You should hold an excellent MSc degree in computer science, robotics, or electrical engineering, complemented by a strong background in computer graphics, simulation, and computer vision. A combination of exceptional programming skills and experience in medical imaging and camera hardware is required.

We are seeking candidates who demonstrate:

• A solid understanding of generative models and proven experience working with multimodal data
• A strong grasp of 3D geometry processing, reconstruction, and registration techniques
• Experience with modern 3D learning paradigms like graph neural networks, implicit neural representations, or voxel-based models
• Familiarity with physical simulation concepts or deformable modeling (finite elements, mass-spring models, or physics-informed models) is advantageous
• Practical experience with computer vision, including camera calibration and tracking, as well as proficiency in relevant libraries (e.g., OpenCV, Open3D)
• Familiarity with AI/ML frameworks (e.g., PyTorch, TensorFlow) and medical image analysis libraries (Slicer3D, MONAI)
• Excellent communication skills in English (German is a plus), along with initiative, problem-solving capabilities, and teamwork

Apply online using the form below. Please note that only applications matching the job profile will be considered.

Contact Information

Joelle Kunz
Assistant
+41 44 510 73 66
Joinrocs@balgrist.ch