Biophysical interpretation of quantitative phase image by means of coherence-controlled holographic microscopy and machine learning

The work will be dealing with the interpretation of the quantitative phase images gained by coherence-controlled holographic microscopy (CCHM). The possibilities for automated analysis of quantitative phase images by means of supervised and unsupervised machine learning will be investigated. The quantitative phase images enable extraction of valuable features characterizing the distribution of dry mass within the cell and hence provide important information about the live cell behavior. The work would focus on refinement of the present automated classification of cells while employing the quantitative information from both the single-time-point and time-lapse quantitative phase images. The proposed methods will be tested on the images of live cells in order to estimate the applicability in the cancer cell biology.

Supervisor: Radim Chmelík

Consultant: Lenka Štrbková