Image of Jan Kybic
Jan Kybic
Available positions

If you are interested by any of the positions advertised below, please send me your CV, recommendation letters, sample publications, study result reports and other relevant documents.

Multimodal digital pathology

The current methods in digital pathology try to model the human expert approach for understanding the histopathology images and to propose a number of quantitative descriptors of the images. However, this approach provides a limited view on the underlying biology and will likely lag behind the human expertise in interpreting the histopathology image data for the foreseeable future.

On the other hand, nowadays a biological sample is characterized by a richer set of features raging from clinical to molecular information. It is not uncommon to have whole-genome expression data, mutational and clinical data available for analysis.

In this context, the present project aims at combining gene expression, clinical and imaging features to provide a more comprehensive description of the pathology slides, description that will rather complement than replace the usual pathologist assessment. This represents a paradigm shift in digital pathology and is expected to advance the current state of the art. Using gene expression data to guide the development, the project will create and implement novel software tools for histopathology image analysis. The utility of the resulting methods will be evaluated in collaboration with an expert pathologist. In collaboration with Vlad Popovici

Requirements: image processing; Java/Python; pattern recognition

Identification of tumor cells in microscope images

(PhD or master thesis topic) A typical histopathology slide contains not only tumor cells but also normal tissue cells and other regions of less interest from a diagnostic perspective. Thus, one of the tasks a pathologists performs routinely is the identification of tumor regions in the microscope slide (if there are any) and eventually delineating them for further analysis.

The purpose of the project is to produce the software tools that would automate the identification of tumor cells in digital images of H&E-stained microscope slides. These tools will be applied to high resolution images of colon cancer samples and they will need to demonstrate high performance (detection rate and computation time) in order to be accepted by the pathologists. In collaboration with Vlad Popovici

Requirements: image processing; Java/Python; pattern recognition

Nuclear morphology in digital pathology

(Part of a PhD thesis or a master thesis topic) The type of cells and the morphology of their nuclei are key variables that are considered by the pathologist when assessing a tissue sample. The standard staining of the histopathology slides reveals the regions containing nuclei, but precisely segmenting their contours remains a non-trivial task.

The purpose of the project is to produce the software tools that would automatically segment and identify the nuclei in digital pathology images. The identified nuclei will be then characterized in terms of shape, orientation, budding, etc, to help the human expert in assessing the tumor sample. These tools will be applied to high resolution images of colon cancer samples and they will need to demonstrate high performance (detection rate and computation time) in order to be accepted by the pathologists. In collaboration with Vlad Popovici.

Requirements: image processing; Java/Python; pattern recognition

Fast and precise motion estimation

We are looking for a PhD or postdoc candidate for a joint project with Prof. Rudolf Mester.

Analysis of images in biology and medicine

I am constantly looking for new PhD students, post-docs, or experienced independent programmers for various projects concerning analysis of images in biology and medicine, for example histology slice registration or perfusion CT data processing. The candidates should have excellent knowledge of programming, mathematics, and image processing.

Valid CSS! Valid XHTML 1.0 Transitional