Themen in Magdeburg
Adapted InfoVis Graphics to Communicate Medical Data
The comprehensible communication of medical research to the broad public plays an important role in many situations, such as education about preventive examinations or vaccinations. Recently, narrative visualization, i.e. the combination of storytelling techniques with interactive graphics is used to communicate scientific findings. A variety of information visualizations such as diagrams and 2D maps have been used to visually communicate scientific findings. However, little research has been done on how comprehensible annotated diagrams such as bubble charts or medical expert diagrams such as Kaplan-Meier plots are for the broad public or how these representations need to be adapted.
Goal: The goal should be to investigate different information visualization techniques regarding their suitability to visually communicate medical information to the broad public. Based on this analysis, guidelines should be derived on how information visualizations need to be adapted to become understandable for people without specific medical background knowledge. The adapted visualizations should be evaluated with participants from the broad public to validate their understandability.
Type: Bachelor/ or Master Thesis (Team project (2 FIN students) would also be possible)
Requirements: Good skills in scientific reading; critical thinking; good skills in graphics programming (exact languages like D3 or OpenGL can be chosen freely)
References
[1] Morris, T., et al. “Proposals on Kaplan–Meier plots in medical research and a survey of stakeholder views: KMunicate.” BMJ open 9.9 (2019): e030215.: https://bmjopen.bmj.com/content/9/9/e030215.abstract
[2] Drucker, S., et al. “Communicating data to an audience.” In Data-driven storytelling, pp. 211-31. AK Peters/CRC Press, 2018: chrome-extension://oemmndcbldboiebfnladdacbdfmadadm/https://hal.archives-ouvertes.fr/hal-02310515/document
[3] Meuschke, M., et al. “Towards Narrative Medical Visualization.” arXiv preprint arXiv:2108.05462 (2021).: https://arxiv.org/abs/2108.05462
Develop VR/Web Radiochemistry Application for Students
Within the European A-CINCH project, which addresses the loss of the young generation’s interest for nuclear knowledge, virtual experiments are developed.
Tasks:
- Develop a radiochemistry experiement as a VR and web application
- Evaluate its user experience and usability
The project has to be realised in the game engine Unity, thus the following is required:
- Knowledge of basic computer graphics
- Experience with C# and Unity
Visual Analytics to Support Tumor Boards in Dermatology
A tumor board is a discussion among multiple physicians to determine the most appropriate treatment option for a specific cancer patient with a complex disease course. Treatment recommendations are often influenced by previous experience with patients exhibiting similar disease courses. While patient-related image data is displayed during the discussion, clinical patient data, such as the course of tumor days, histological parameters and previously performed treatments, cannot be retrieved at any time and must be repeatedly asked for or memorized. In addition, there is not yet a method to automatically identify and visualize the k most similar patients with their respective therapy trajectories.
Goal: To support physicians during tumor boards in therapy planning for skin cancer patients, the goal of the project is to develop a tumor board visual analytics system that (i) effectively displays longitudinal patient data and (ii) identifies and visualizes characteristics and treatment histories of the most similar previously treated patients.
Team size: 2-3 Master FIN students or Bachelor/Master Thesis
Requirements: Programming experience in D3, Python, or R; critical thinking
References:
[1] Hörbrügger M, Steinhauer N, et al. “Comprehensive Visualization of Longitudinal Patient Data for the Dermatological Oncological Tumor Board.” Proc. of EuroVis 2020. URL: https://diglib.eg.org/handle/10.2312/evs20201067
[2] Prakash S, Unnikrishnan V, Pryss R, Kraft R, Schobel J, Hannemann R, Langguth B, Schlee W, Spiliopoulou M. “Interactive System for Similarity-Based Inspection and Assessment of the Well-Being of mHealth Users.” Entropy. 2021; 23(12):1695. https://doi.org/10.3390/e23121695
Student Project – Gamification concepts for a VR application to train access in skull surgeries
Immersive virtual reality (VR) simulations are a common possibility to provide surgeons with additional training. One of the main benefits is the high motivation due to a high sense of presence. Nevertheless, the motivation can be increased by adding feedback and gamification aspects. Therefore, we are looking for a student, who will investigate and implement gamification concepts that are appropriate for an already existing medical VR training application.
Your task would be to:
- research existing and similar approaches regarding gamification and acquire some medical background
- develop appropriate gamification concepts
- implement these concepts in an existing VR training application
- conduct a user study to evaluate the developed concepts
The project has to be realised in the game engine Unity, thus the following is required:
- knowledge of basic computer graphics
- experience with C# (and Unity)
AG Visualisierung
Master Thesis: Deep Learning Based Segmentation Task of medical CT-Images based on advanced Preprocessing
Current state:
The chances of success of tumor treatment are highly dependent on the patient’s physical condition. In everyday clinical practice, the patient’s BMI is calculated for this purpose. However, this is a rather inaccurate measure, since the distribution of muscle to fat tissue is a decisive indicator. For a more accurate evaluation, the patient’s CT images must be evaluated. However, this is a time-consuming task.
Scope of the thesis:
This work is intended to address the problem. Currently, data are being acquired in clinical practice and segmented by experts. These are CT data sets in which muscle and fur tissues were segmented in one layer. Your task is to create an automatic segmentation using Deep Learning methods. Subsequently, the segmented regions are to be evaluated with the help of a measure. The explicitly mentioned preprocessing step is to split the given segmentation (symmetry of the body) to provide more data to the network during the learning process. An optional extension would be the automatic selection of the layer in which the evaluation should take place.
We offer:
- interesting clinically relevant research
- support in technical questions and writing of the thesis
We expect:
- good programming skills (Python)
- knowledge of image processing
- experience with Deep Learning and frameworks (Pytorch, Tensorflow, Keras)
- good study achievements
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!
Master Thesis: Mesh generation with machine learning
Extension of Shrinkingtubemesh-generation (as illustrated below) with machine learning. The current version was written in matlab and is only suitable for cylinder-like structures, for example vessels. The program should be adjusted to fit a wider variation of shapes.
Subtasks: The task can be solved in two ways: using classical machine learning or with deep learning.
Option 1: Maschine Learning
- including development of a range of suitable startshapes, definition of point cloud features for machine learning, generation of a Testdatabase, usage of Machine Learning to predict a suitable startshape and shrinkingtubemesh-algorithm parameter for a given pointcloud .
Option 2: Deep Learning:
- Generate startshapes (simple, roughly the pointcloud describing meshes) using deep learning (for example using a pointcloud to mesh approach like AtlasNet);
- use these startshapes for the shrinkingtubemesh generation and compare to other mesh generation approaches .
Requirements: Knowledge of Python (Pytorch) and Matlab; Experience in Machine Learning/Deep Learning
We expect high-qualified students interested in this project (hiwi job / student assistant or team projects, bachelor or master thesis). Please send your application!
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!
Klinische Entscheidungsunterstützung für die Therapie zerebraler Aneurysmen
Bei der klinischen Entscheidungsfindung werden klinische Richtlinien herangezogen, die auf Evidenzen basieren und Empfehlungen eines Gremiums von Experten beinhalten. Einige der Richtlinien sind auf logischen „Wenn-dann“-Regeln und komplexeren, mehrstufige Regeln aufgebaut. Obwohl diese Regeln als Algorithmus zur Entscheidungsunterstützung formalisiert werden können, liegen die Richtlinien zumeist nur in Textform vor und müssen für die klinische Routine in übersichtliche Handlungsempfehlungen „übersetzt“ werden. Innerhalb der Arbeit soll ein durch Ärzte bedienbarer Prototyp entwickelt werden, der die „Übersetzung“ einer klinischen Richtlinie in einen Algorithmus zur Entscheidungsunterstützung ermöglicht.
Anforderungen: Gute bis sehr gute Programmierkenntnisse