Automated classification of cell morphology by coherence-controlled holographic microscopy

Comparison of holotomographic microscopy and coherence-controlled holographic microscopy

Quantitative phase imaging (QPI) is a powerful tool for label-free visualisation of living cells. Here, we compare two QPI microscopes - the Telight Q-Phase microscope and the Nanolive 3D Cell Explorer-fluo microscope. Both systems provide unbiased information about cell morphology, such as individual cell dry mass, perimeter and area. The Q-Phase microscope uses artefact-free, coherence-controlled holographic imaging technology to visualise cells in real time with minimal phototoxicity. The 3D Cell Explorer-fluo employs laser-based holotomography to reconstruct 3D images of living cells, visualising their internal structures and dynamics. Here, we analysed the strengths and limitations of both microscopes when examining two morphologically distinct cell lines - the cuboidal epithelial MDCK cells which form multicellular clusters and solitary growing Rat2 fibroblasts. We focus mainly on the ability of the devices to generate images suitable for single-cell segmentation by the built-in software, and we discuss the segmentation results and quantitative data generated from the segmented images. We show that both microscopes offer slightly different advantages, and the choice between them depends on the specific requirements and goals of the user.

Fourier ptychographic and deep learning using breast cancer histopathological image classification

Automated, as well as accurate classification with breast cancer histological images, was crucial for medical applications because of detecting malignant tumors via histopathological images. In this work create a Fourier ptychographic (FP) and deep learning using breast cancer histopathological image classification. Here the FP method used in the process begins with such a random guess that builds a high-resolution complex hologram, subsequently uses iterative retrieval using FP constraints to stitch around each other low-resolution multi-view means of production owned from either the hologram's high-resolution hologram's elemental images captured via integral imaging. Next, the feature extraction process includes entropy, geometrical features, and textural features. The entropy-based normalization is used to optimize the features. Finally, it attains the classification process of the proposed ENDNN classifies the breast cancer images into normal or abnormal. The experimental outcomes demonstrate that our presented technique overtakes the traditional techniques.

Primary assessment of medicines for expected migrastatic potential with holographic incoherent quantitative phase imaging

Solid tumor metastases cause most cancer-related deaths. The prevention of their occurrence misses suitable anti-metastases medicines newly labeled as migrastatics. The first indication of migrastatics potential is based on an inhibition of in vitro enhanced migration of tumor cell lines. Therefore, we decided to develop a rapid test for qualifying the expected migrastatic potential of some drugs for repurposing. The chosen Q-PHASE holographic microscope provides reliable multifield time-lapse recording and simultaneous analysis of the cell morphology, migration, and growth. The results of the pilot assessment of the migrastatic potential exerted by the chosen medicines on selected cell lines are presented.

Cellular analysis using label-free parallel array microscopy with Fourier ptychography

Quantitative phase imaging (QPI) is an ideal method to non-invasively monitor cell populations and provide label-free imaging and analysis. QPI offers enhanced sample characterization and cell counting compared to conventional label-free techniques. We demonstrate this in the current study through a comparison of cell counting data from digital phase contrast (DPC) imaging and from QPI using a system based on Fourier ptychographic microscopy (FPM). Our FPM system offers multi-well, parallel imaging and a QPI-specific cell segmentation method to establish automated and reliable cell counting. Three cell types were studied and FPM showed improvement in the ability to resolve fine details and thin cells, despite limitations of the FPM system incurred by imaging artifacts. Relative to manually counted fluorescence ground-truth, cell counting results after automated segmentation showed improved accuracy with QPI over DPC.

Learning Cellular Phenotypes through Supervision

Image-based cell phenotyping is an important and open problem in computational pathology. The two principal challenges are: 1) making the cell cluster properties insensitive to experimental settings (like seed point and feature selection) and 2) ensuring that the phenotypes emerging are biologically relevant and support clinical reporting. To gauge robustness, we first compare the consistency of the phenotypes using self-supervised and supervised features. Through case classification, we analyse the relevance of the self-supervised and supervised feature sets with respect to the clinical diagnosis. In addition, we demonstrate how we can add model explainability through Shapley values to identify more disease relevant cellular phenotypes and measure their importance in context of the disease. Here, myeloproliferative neoplasms, a haematopoietic stem cell disorder, where one particular cell type is of diagnostic relevance is used as an exemplar. The experiments conducted on a set of bone marrow trephines demonstrate an improvement of 7.4 % in accuracy for case classification using cellular phenotypes derived from the supervised scenario.

Machine Learning Assisted Classification of Cell Lines and Cell States on Quantitative Phase Images

In this report, we present implementation and validation of machine-learning classifiers for distinguishing between cell types (HeLa, A549, 3T3 cell lines) and states (live, necrosis, apoptosis) based on the analysis of optical parameters derived from cell phase images. Validation of the developed classifier shows the accuracy for distinguishing between the three cell types of about 93% and between different cell states of the same cell line of about 89%. In the field test of the developed algorithm, we demonstrate successful evaluation of the temporal dynamics of relative amounts of live, apoptotic and necrotic cells after photodynamic treatment at different doses.

Classification of cell morphology with quantitative phase microscopy and machine learning

We describe and compare two machine learning approaches for cell classification based on label-free quantitative phase imaging with transport of intensity equation methods. In one approach, we design a multilevel integrated machine learning classifier including various individual models such as artificial neural network, extreme learning machine and generalized logistic regression. In another approach, we apply a pretrained convolutional neural network using transfer learning for the classification. As a validation, we show the performances of both approaches on classification between macrophages cultured in normal gravity and microgravity with quantitative phase imaging. The multilevel integrated classifier achieves average accuracy 93.1%, which is comparable to the average accuracy 93.5% obtained by convolutional neural network. The presented quantitative phase imaging system with two classification approaches could be helpful to biomedical scientists for easy and accurate cell analysis.

Automated interpretation of time-lapse quantitative phase image by machine learning to study cellular dynamics during epithelial-mesenchymal transition

SIGNIFICANCE

Machine learning is increasingly being applied to the classification of microscopic data. In order to detect some complex and dynamic cellular processes, time-resolved live-cell imaging might be necessary. Incorporating the temporal information into the classification process may allow for a better and more specific classification.

AIM

We propose a methodology for cell classification based on the time-lapse quantitative phase images (QPIs) gained by digital holographic microscopy (DHM) with the goal of increasing performance of classification of dynamic cellular processes.

APPROACH

The methodology was demonstrated by studying epithelial-mesenchymal transition (EMT) which entails major and distinct time-dependent morphological changes. The time-lapse QPIs of EMT were obtained over a 48-h period and specific novel features representing the dynamic cell behavior were extracted. The two distinct end-state phenotypes were classified by several supervised machine learning algorithms and the results were compared with the classification performed on single-time-point images.

RESULTS

In comparison to the single-time-point approach, our data suggest the incorporation of temporal information into the classification of cell phenotypes during EMT improves performance by nearly 9% in terms of accuracy, and further indicate the potential of DHM to monitor cellular morphological changes.

CONCLUSIONS

Proposed approach based on the time-lapse images gained by DHM could improve the monitoring of live cell behavior in an automated fashion and could be further developed into a tool for high-throughput automated analysis of unique cell behavior.

Quantitative Phase Imaging of Spreading Fibroblasts Identifies the Role of Focal Adhesion Kinase in the Stabilization of the Cell Rear

Cells attaching to the extracellular matrix spontaneously acquire front-rear polarity. This self-organization process comprises spatial activation of polarity signaling networks and the establishment of a protruding cell front and a non-protruding cell rear. Cell polarization also involves the reorganization of cell mass, notably the nucleus that is positioned at the cell rear. It remains unclear, however, how these processes are regulated. Here, using coherence-controlled holographic microscopy (CCHM) for non-invasive live-cell quantitative phase imaging (QPI), we examined the role of the focal adhesion kinase (FAK) and its interacting partner Rack1 in dry mass distribution in spreading Rat2 fibroblasts. We found that FAK-depleted cells adopt an elongated, bipolar phenotype with a high central body mass that gradually decreases toward the ends of the elongated processes. Further characterization of spreading cells showed that FAK-depleted cells are incapable of forming a stable rear; rather, they form two distally positioned protruding regions. Continuous protrusions at opposite sides results in an elongated cell shape. In contrast, Rack1-depleted cells are round and large with the cell mass sharply dropping from the nuclear area towards the basal side. We propose that FAK and Rack1 act differently yet coordinately to establish front-rear polarity in spreading cells.

Morphology, Motility, and Cytoskeletal Architecture of Breast Cancer Cells Depend on Keratin 19 and Substrate

Cancer cells gain motility through events that accompany modulation of cell shape and include altered expression of keratins. However, the role of keratins in change of cancer cell architecture is not well understood. Therefore, we ablated the expression of keratin 19 (K19) in breast cancer cells of the MDA-MB-231 cell line and found that cells lacking K19 become more elongated in culture, with morphological reversion toward the parental phenotype upon transduction of KRT19. Also, the number of actin stress fibers and focal adhesions were significantly reduced in KRT19 knockout (KO) cells. The altered morphology of KRT19 KO cells was then characterized quantitatively using digital holographic microscopy (DHM), which not only confirmed the phenotypic change of KRT19 KO cells but also identified that the K19-dependent morphological change is dependent on the substrate type. A new quantitative method of single cell analysis from DHM, via average phase difference maps, facilitated evaluation of K19-substrate interactive effects on cell morphology. When plated on collagen substrate, KRT19 KO cells were less elongated and resembled parental cells. Assessing single cell motility further showed that while KRT19 KO cells moved faster than parental cells on a rigid surface, this increase in motility became abrogated when cells were plated on collagen. Overall, our study suggests that K19 inhibits cell motility by regulating cell shape in a substrate-dependent manner. Thus, this study provides a potential basis for the altered expression of keratins associated with change in cell shape and motility of cancer cells. © 2020 International Society for Advancement of Cytometry.

Machine Learning with Optical Phase Signatures for Phenotypic Profiling of Cell Lines

Robust and reproducible profiling of cell lines is essential for phenotypic screening assays. The goals of this study were to determine robust and reproducible optical phase signatures of cell lines for classification with machine learning and to correlate optical phase parameters to motile behavior. Digital holographic microscopy (DHM) reconstructed phase maps of cells from two pairs of cancer and non-cancer cell lines. Seventeen image parameters were extracted from each cell's phase map, used for linear support vector machine learning, and correlated to scratch wound closure and Boyden chamber chemotaxis. The classification accuracy was between 90% and 100% for the six pairwise cell line comparisons. Several phase parameters correlated with wound closure rate and chemotaxis across the four cell lines. The level of cell confluence in culture affected phase parameters in all cell lines tested. Results indicate that optical phase features of cell lines are a robust set of quantitative data of potential utility for phenotypic screening and prediction of motile behavior. © 2019 International Society for Advancement of Cytometry.

Whole-Cell Multiparameter Assay for Ricin and Abrin Activity-Based Digital Holographic Microscopy

Ricin and abrin are ribosome-inactivating proteins leading to inhibition of protein synthesis and cell death. These toxins are considered some of the most potent and lethal toxins against which there is no available antidote. Digital holographic microscopy (DHM) is a time-lapse, label-free, and noninvasive imaging technique that can provide phase information on morphological features of cells. In this study, we employed DHM to evaluate the morphological changes of cell lines during ricin and abrin intoxication. We showed that the effect of these toxins is characterized by a decrease in cell confluence and changes in morphological parameters such as cell area, perimeter, irregularity, and roughness. In addition, changes in optical parameters such as phase-shift, optical thickness, and effective-calculated volume were observed. These effects were completely inhibited by specific neutralizing antibodies. An enhanced intoxication effect was observed for preadherent compared to adherent cells, as was detected in early morphology changes and confirmed by annexin V/propidium iodide (PI) apoptosis assay. Detection of the dynamic changes in cell morphology at initial stages of cell intoxication by DHM emphasizes the highly sensitive and rapid nature of this method, allowing the early detection of active toxins.

Geometric-Phase Microscopy for Quantitative Phase Imaging of Isotropic, Birefringent and Space-Variant Polarization Samples

We present geometric-phase microscopy allowing a multipurpose quantitative phase imaging in which the ground-truth phase is restored by quantifying the phase retardance. The method uses broadband spatially incoherent light that is polarization sensitively controlled through the geometric (Pancharatnam-Berry) phase. The assessed retardance possibly originates either in dynamic or geometric phase and measurements are customized for quantitative mapping of isotropic and birefringent samples or multi-functional geometric-phase elements. The phase restoration is based on the self-interference of polarization distinguished waves carrying sample information and providing pure reference phase, while passing through an inherently stable common-path setup. The experimental configuration allows an instantaneous (single-shot) phase restoration with guaranteed subnanometer precision and excellent ground-truth accuracy (well below 5 nm). The optical performance is demonstrated in advanced yet routinely feasible noninvasive biophotonic imaging executed in the automated manner and predestined for supervised machine learning. The experiments demonstrate measurement of cell dry mass density, cell classification based on the morphological parameters and visualization of dynamic dry mass changes. The multipurpose use of the method was demonstrated by restoring variations in the dynamic phase originating from the electrically induced birefringence of liquid crystals and by mapping the geometric phase of a space-variant polarization directed lens.

Quantitative phase imaging unravels new insight into dynamics of mesenchymal and amoeboid cancer cell invasion

Observation and analysis of cancer cell behaviour in 3D environment is essential for full understanding of the mechanisms of cancer cell invasion. However, label-free imaging of live cells in 3D conditions is optically more challenging than in 2D. Quantitative phase imaging provided by coherence controlled holographic microscopy produces images with enhanced information compared to ordinary light microscopy and, due to inherent coherence gate effect, enables observation of live cancer cells' activity even in scattering milieu such as the 3D collagen matrix. Exploiting the dynamic phase differences method, we for the first time describe dynamics of differences in cell mass distribution in 3D migrating mesenchymal and amoeboid cancer cells, and also demonstrate that certain features are shared by both invasion modes. We found that amoeboid fibrosarcoma cells' membrane blebbing is enhanced upon constriction and is also occasionally present in mesenchymally invading cells around constricted nuclei. Further, we demonstrate that both leading protrusions and leading pseudopods of invading fibrosarcoma cells are defined by higher cell mass density. In addition, we directly document bundling of collagen fibres by protrusions of mesenchymal fibrosarcoma cells. Thus, such a non-invasive microscopy offers a novel insight into cellular events during 3D invasion.

Quantitative assessment of cancer cell morphology and motility using telecentric digital holographic microscopy and machine learning

The noninvasive, fast acquisition of quantitative phase maps using digital holographic microscopy (DHM) allows tracking of rapid cellular motility on transparent substrates. On two-dimensional surfaces in vitro, MDA-MB-231 cancer cells assume several morphologies related to the mode of migration and substrate stiffness, relevant to mechanisms of cancer invasiveness in vivo. The quantitative phase information from DHM may accurately classify adhesive cancer cell subpopulations with clinical relevance. To test this, cells from the invasive breast cancer MDA-MB-231 cell line were cultured on glass, tissue-culture treated polystyrene, and collagen hydrogels, and imaged with DHM followed by epifluorescence microscopy after staining F-actin and nuclei. Trends in cell phase parameters were tracked on the different substrates, during cell division, and during matrix adhesion, relating them to F-actin features. Support vector machine learning algorithms were trained and tested using parameters from holographic phase reconstructions and cell geometric features from conventional phase images, and used to distinguish between elongated and rounded cell morphologies. DHM was able to distinguish between elongated and rounded morphologies of MDA-MB-231 cells with 94% accuracy, compared to 83% accuracy using cell geometric features from conventional brightfield microscopy. This finding indicates the potential of DHM to detect and monitor cancer cell morphologies relevant to cell cycle phase status, substrate adhesion, and motility. © 2017 International Society for Advancement of Cytometry.