Warning
This page is located in archive. Go to the latest version of this course pages. Go the latest version of this page.

Semester work

The task is to implement a simple image processing algorithm with medical imaging applications or apply it to some (bio)medical imaging task. It should take you about 10 hours, so it should not be completely trivial. You can either choose your own task or it will be assign to you by the instructors. The implementation needs to be yours, written from scratch. You are not allowed to use any existing code, or trivial modifications thereof. Such attempts will be considered a plagiarism and will result in a failure from the course. Libraries can be used for supporting tasks such as the deep learning infrastructure, numerical methods or classifiers, if they are not the focus of the project. Library functions may be used for common tasks (e.g. reading or displaying image, solving systems of linear equations etc.). You If in doubt, check with the instructor. The required output of the project is the implementation itself and a short report, describing the task in the context of the state of the art methods, the method and its implementation and how to use it, and the experimental results.

The students are expected to write a short description of the task of their choice and send it to their lab instructor for approval. The tasks must be proposed and approved by November 2.

Project ideas

The project might involve, for example:

  • active contour segmentation based on edge terms
  • active contour segmentation based on intensity (Chan-Vese)
  • gradient vector flow segmentation
  • level set segmentation (2D is enough)
  • segmentation with active shape and appearance models (synthetic data is sufficient)
  • finding superpixels (e.g. SLIC)
  • superpixel segmentation (superpixels can be found using an existing library)
  • normalized cut segmentation
  • GraphCut segmentation - implement the optimization yourself
  • random walker segmentation
  • texture classification using wavelet descriptors
  • texture classification using textons
  • U-net segmentation - study the dependence on parameters and architecture
  • anatomically constrained neural networks - test a simplified case on synthetic data
  • cell nuclei detection using simplified Al-Kofahi's method
  • cell nuclei detection using simplified deep regression
  • implement Frangi's vesselness, generalize and optimize parameters
  • deep regression based retina vessel segmentation (e.g. IOSTAR dataset)
courses/zmo/semestral/start.txt · Last modified: 2022/09/19 14:34 by barucden