We are offering challenging medical topics such as camera tracking, robotic navigation, therapy planning and medical image analysis. All PhD students at MTEC offer theses for a variety of topics. If you are interested in a topic and there is no specific thesis available, feel free to contact the PhD student as new research questions arise every day.

When contacting a PhD student, please attach your transcript of records, both from bachelor and master. Also, briefly explain your technical interests and skills (e.g. programming, ML, robotics, image processing).

Radiation Therapy Planning

In intensity-modulated radiation therapy, for example with the CyberKnife system, tumors are irradiated with an external source. By combining hundreds of beams from various directions with different shapes and activation times, it is possible to reach high doses in the target structures while keeping the dose in other structures low. The beams and parameters are obtained by solving a large-scale (linear) optimization problem.

Possible thesis topics involve modeling of treatment-planning problems and simulation of the developed algorithms with actual patient data. Potential scenarios are for example:

  • Influence of robotic ultrasound guidance on treatment planning and dose delivery
  • Machine learning for efficient planning
  • Needle placement for brachytherapy

Generally required are comprehensive programming skills (Java, Python) and basic knowledge in mathematical optimization.

OCT-Based Tracking

Optical Coherence Tomography is an optical imaging modality based on interferometric measurement of reflections of near-infrared light from different tissue depths. It offers a field of view of few millimeters but micrometer-scale spatial resolution. The very high temporal resolution of modern OCT systems and the its sub-surface information make it promising for tracking applications. 

Possible thesis topics are based on an existing prototypical OCT tracking setup in our lab and could involve for example:

  • Evaluation and improvement of opto-mechanical and electronic components of the setup
  • Efficient algorithms for 4D OCT tracking
  • Investigation of OCT tracking for different structures and tissues

General requirements are enthusiasm for experimental work with hardware in a lab and, depending on the topic, programming skills (especially C++).

Deep Learning for Medical Image Analysis

Deep learning methods are today's standard approach for medical image analysis. Typical learning problems are disease detection or tumor and organ segmentation. Deep learning models such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs) directly learn the relevant properties from image source.

For example, the imaging modality intravascular optical coherence tomography (IVOCT) is typically used to detect plaque deposits in coronary arteries in order to prevent coronary heart disease. Currently, medical practitioners manually examine the IVOCT images which is time consuming and subjective. This motivates automated image analysis with deep learning methods.

Current thesis topics:

  • Semi-Supervised Deep Learning with IVOCT Image Data for Plaque Detection [studIP Link]

Deep Learning for Force Estimation and Tracking

Typically, deep learning and machine learning methods are used for the analysis of patient images for disease related problems. However, they can also be applied to tracking and force estimation problems that arise during surgery. For example, an intraoperative imaging modality in conjunction with a machine learning model can be used to track surgical tools and patients or to estimate forces that tools are exerting on patient tissue.

Current thesis topics:

  • Surgical Tool Tracking and Accurate Tool Control Using Multi-Input-Multi-Output Machine Learning methods [studIP Link]

Requirements

The general requirements are:

  • Very good academic record
  • Very good programming skills (e.g. Python/Java/C/C++)
  • Background knowledge on machine learning and deep learning
  • Motivation and the ability to think critically and work independently

Please provide in your E-Mail:

  • Bachelor certificate and current transcript of records
  • Curriculum Vitae
  • A short text where you highlight your technical interests and related prior experiences

     mareike.wendebourgtuhh.de      +49 (0)40 42878 3547       E.3087

Tissue Phantoms

At MTEC, we often utilize gelatin phantoms as a substitute for human tissue. The process of gelatin phantom production is prone to variation, causing differences in the mechanical properties of the produced phantoms. Accurate insights into the factors influencing the phantom's mechanical properties may help to improve reproducability of phantoms with similar mechanical properties. A possible thesis topic can be found here: [studIP Link]

Seizure Detection

Nocturnal tonic-clonic seizures can be life-threatening when undetected. The use of depth cameras may facilitate a comfortable and affordable seizure detection system for clonic seizures. A possible thesis topic involves the further development of an existing seizure detection method, acquisition of clinical data and evaluation of the method's seizure detection capabilities.

     martin.gromniaktuhh.de      +49 (0)40 42878 3828       E.3088

Deep Learning for Medical Image Data

Deep learning methods are today's standard approach for medical image analysis. Typical learning problems are disease detection or tumor and organ segmentation. Deep learning models such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs) directly learn the relevant properties from image source. In the medical domain, the amount of labeled image data is often limited, which motivates the use of semi-supervised and transfer learning methods.

Current thesis topics:

  • Semi-Supervised Deep Learning with IVOCT Image Data for Plaque Detection [studIP Link]

Force Feedback

In the context of robot-assisted minimally invasive surgery, the use of haptic feedback force has the potential to greatly improve the dexterity of the surgeon. At MTEC we are examining how general-purpose light-weight robot (LWRs) can be used as high quality haptic feedback devices.

Current thesis topics:

  • Evaluating the Force Controller of an LWR Robot on the basis of a constant-force needle insertion scenario.
  • Design of a Force Feedback Controller for an LWR robot with the goal of steering a surgery device

 

 

 

 

     maximilian.neidhardttuhh.de      +49 (0)40 42878 3389       E.3083

     stefan.soltautuhh.de      +49 (0)40 42878 3389       E.3083

     antonituhh.de      +49 (0)40 42878 3547       E.3087

     omer.rajputtuhh.de      +49 (0)40 42878 3547       E.3087