|
|
Biophysical interpretation of quantitative phase image
Štrbková, Lenka ; Kozubek,, Michal (oponent) ; Hoppe, Andreas (oponent) ; Chmelík, Radim (vedoucí práce)
This work deals with the interpretation of the quantitative phase images gained by coherence-controlled holographic microscopy. Since the datasets of quantitative phase images are of substantial size, the manual analysis would be time-consuming and inefficient. In order to speed up the analysis of images gained by coherence-controlled holographic microscopy, the methodology for automated interpretation of quantitative phase images by means of supervised machine learning is proposed in this work. 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 behaviour. The aim of this work is to propose a methodology for automated classification of cells while employing the quantitative information from both the single-time-point and time-lapse quantitative phase images. The proposed methodology was tested in the experiments with live cells, where the performance of the classification was evaluated and the relevance of the features derived from the quantitative phase image was assessed.
|
|
|
Analysis of Microscopic Images of Cancer Cells
Vičar, Tomáš ; Matula,, Petr (oponent) ; Sladoje, Natasa (oponent) ; Kolář, Radim (vedoucí práce)
This dissertation focuses on the analysis of various forms of microscopic image data of cancer cells (static 2D images, static 3D stacks, 2D timelapse live cell imaging). The main focus is on data acquired with a~coherence controlled holographic microscope, which is a~relatively new modality capable of contrast imaging of live cells without staining (label-free) and provide quantitative information (Quantitative Phase Imaging - QPI). In this thesis, the basic procedure for the analysis of cell images is described, where new methods for the individual steps are developed and refined. The largest part of the thesis is devoted to cell segmentation, where classical and deep learning-based methods are summarized. New methods suitable specifically for QPI data are also developed. A~part of the thesis is devoted to the segmentation of 3D fluorescence nuclei and the detection of DNA breaks using deep learning. The thesis also deals with further processing in the form of cell tracking, feature extraction and subsequent analysis, where cell death is detected and suitable interpretable features are developed to classify cell death into apoptotic and lytic. Overall, this thesis contributes to the development of different steps of image analysis of cancer cells and reflects current advances in the image analysis field, deep learning approaches in particular, which is also demonstrated in several research applications.
|
|
|
Analysis of Microscopic Images of Cancer Cells
Vičar, Tomáš ; Matula,, Petr (oponent) ; Sladoje, Natasa (oponent) ; Kolář, Radim (vedoucí práce)
This dissertation focuses on the analysis of various forms of microscopic image data of cancer cells (static 2D images, static 3D stacks, 2D timelapse live cell imaging). The main focus is on data acquired with a~coherence controlled holographic microscope, which is a~relatively new modality capable of contrast imaging of live cells without staining (label-free) and provide quantitative information (Quantitative Phase Imaging - QPI). In this thesis, the basic procedure for the analysis of cell images is described, where new methods for the individual steps are developed and refined. The largest part of the thesis is devoted to cell segmentation, where classical and deep learning-based methods are summarized. New methods suitable specifically for QPI data are also developed. A~part of the thesis is devoted to the segmentation of 3D fluorescence nuclei and the detection of DNA breaks using deep learning. The thesis also deals with further processing in the form of cell tracking, feature extraction and subsequent analysis, where cell death is detected and suitable interpretable features are developed to classify cell death into apoptotic and lytic. Overall, this thesis contributes to the development of different steps of image analysis of cancer cells and reflects current advances in the image analysis field, deep learning approaches in particular, which is also demonstrated in several research applications.
|
|
|
Prostatic Cells Classification Using Deep Learning
Majerčík, Jakub ; Špaček, Michal
Human prostate cancer PC-3 cell line is widely used in cancer research. Previously, Zinc- Resistant variant was described characteristically by higher dry cellular mass determined by quantitative phase imaging. This work aims to classify these 2 cell types into corresponding categories using machine learning methods. We have achieved 97.5% accuracy with the correct preprocessing using Res-Net network.
|
|
|
Biophysical interpretation of quantitative phase image
Štrbková, Lenka ; Kozubek,, Michal (oponent) ; Hoppe, Andreas (oponent) ; Chmelík, Radim (vedoucí práce)
This work deals with the interpretation of the quantitative phase images gained by coherence-controlled holographic microscopy. Since the datasets of quantitative phase images are of substantial size, the manual analysis would be time-consuming and inefficient. In order to speed up the analysis of images gained by coherence-controlled holographic microscopy, the methodology for automated interpretation of quantitative phase images by means of supervised machine learning is proposed in this work. 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 behaviour. The aim of this work is to propose a methodology for automated classification of cells while employing the quantitative information from both the single-time-point and time-lapse quantitative phase images. The proposed methodology was tested in the experiments with live cells, where the performance of the classification was evaluated and the relevance of the features derived from the quantitative phase image was assessed.
|
host ::
RSS.