Vacancies & Student Research Projects
Are you interested in our research and would like to do an undergraduate research project, bachelor, master or diploma thesis? Or are you looking for a PhD position in our department?
Our young, highly motivated and creative team is always open for new talent. We have changing funds and open positions and interesting thesis topics. Please email to Mrs. Abdel Bary (ricarda.abdel-bary(at)nct-dresden.de) with your application and include the following in a single PDF file:
- A motivational letter describing why you want to join our group. Also mention if you are interested in a specific project and how your experience/education relates to this project
- A short CV, including an overview of your programming skills
- A recent overview of grades from your studies, include final grades if available
- A copy of your school graduation certificate
- Letters of references (if any)
You can find some of the current positions and thesis topics by following the link below. For more possible positions and thesis topics, you can always send an initiative application to Mrs. Abdel Bary (ricarda.abdel-bary(at)nct-dresden.de).
Positions
- SHK: Advancing Simulation Methods: Tissue Manipulation and Remeshing
- SHK: Designing an Experimental Test Bench for Synthetic Tissue Deformation and Cuts
- SHK: Developing a Synthetic Data Generation Pipeline for Surgical Navigation
- Master thesis: OCT data synthesis with diffusion models
Topics
Master Thesis: Adapting Foundation Models for Surgical Outcome Prediction
Foundation models, such as BiomedParse, have demonstrated exceptional generalization capabilities across various tasks using multimodal healthcare data. In this project, we want to finetune such foundation models for predicting surgical outcomes with limited available data. We also want to investigate techniques for fusing domain knowledge during the finetuning process, and measure the impact of domain knowledge on model performance and interpretability. (contact)
Bachelor Thesis: Rendering Methods for Correct Depth Perception in Augmented Reality Overlays
In potential navigation systems for minimally invasive surgeries, models created by CT and MRT scans are rendered and overlaid transparently to be shown on the endoscopic video stream. This might lead to sorting errors, because occlusions that usually work as visual cues for depth perception are ambiguous due to the transparent rendering. Explore and implement different rendering methods that could help users in the correct interpretation of the augmented reality overlay. (contact)
Investigating Tracking and Optical Flow for Scene Segmentation in Videos
Develop and evaluate tracking methods or optical flow techniques to propagate full-scene segmentations from a single video frame onto subsequent frames.
The project aims to generate additional annotations by leveraging temporal consistency in video data, reducing the need for extensive manual labeling.
The topic includes challenges such as handling occlusions, dynamic object movements, and ensuring accurate alignment across frames. This work will
contribute to improving annotation efficiency in large-scale video datasets. (contact)
Minimally Invasive: Benchmarking Tiny VLMs for Surgical VQA
Visual Question Answering (VQA) in surgical contexts is a challenging task due to the domains inherent data scarcity and the complexity of surgical scenes. While specialized Vision-Language-Models (VLMs) have been proposed, this project focuses on evaluating how effectively general-purpose VLMs can be adapted to the surgical domain. Help us benchmark pre-trained VLMs on surgical VQA tasks. Fine-tune state-of-the-art VLMs on existing datasets and evaluate question-answer biases to check for text-prior contamination. (contact)
Master Thesis: Recognition of phase and action triplets in laparoscopic video and sensor data
In order to take the next steps in automating surgical tasks in laparascopy, robot assistance systems have to gain a deeper understanding of the surgical procedure. In this project we aim to solve the problem of detecting and predicting fine grained surgical actions. Make use of supervised deep learning methods and annotated video/sensor data. Compare different model architectures to investigate the relevance of temporal information for the learning task. (contact)