Forschungspraxis/Master’s thesis - Interactive/Active Learning and Image Segmentation


Topic

This student work will be carried out in conjunction with the CellFace project, which investigates the potential of computer vision and machine learning techniques for the task of automated blood cell diagnosis. You can read more about CellFace here.

Latest advancements in artificial intelligence show great promise for medical imaging. Automated screening and diagnosis tools based on machine learning techniques could help make medical tests faster, cheaper, and more readily available to patients. The focus in this project lies on digital holographic microscopy images of blood cells. Large datasets of such blood cell images, as well as successful machine learning architectures from the field of computer vision, already exist. However, a major hurdle to actually using these models on the available datasets is to bring the images into a shape that facilitates labeling, training, and classification. The first step in this data processing pipeline is image segmentation, i.e., identifying which image areas contain relevant objects or structures. The goal of the proposed Forschungspraxis or Master’s thesis is to design, implement, and evaluate a prototype segmentation tool that interactively learns to select relevant parts of holographic microscopy images, based on user input.

Requirements

  • Python coding skills
  • Prior experience with (or interest in) computer vision
  • Knowledge of JavaScript (VueJS) and Git 
  • Capacity for teamwork

For a more in-depth introduction to the relevant research topics, see:

Fails, Jerry Alan, and Dan R. Olsen. 2003. “Interactive Machine Learning.” In Proceedings of the 8th International Conference on Intelligent User Interfaces - IUI ’03, 39. Miami, Florida, USA: ACM Press. https://doi.org/10.1145/604045.604056.

Harvey, Neal, and Reid Porter. 2016. “User-Driven Sampling Strategies in Image Exploitation.” Information Visualization 15 (1): 64–74. https://doi.org/10.1177/1473871614557659.

Supervisors

Alice Hein, M.Sc. and Stefan Röhrl, M.Sc.

Chair for Data Processing

Contact Information

Alice Hein, M.Sc.

Chair for Data Processing

TUM Department of Electrical and Computer Engineering

Technical University of Munich

 

Arcisstr. 21, 80333 Munich

Room Z942
alice.hein@tum.de