Browse
Submit Data
Databases
API
Help

Dataset Information

14 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Label-free classification of neurons and glia in neural stem cell cultures using a hyperspectral imaging microscopy combined with machine learning.

ABSTRACT: Due to a growing demand for a viable label-free observation method in the biomedical field, many techniques, such as quantitative phase imaging and Raman spectroscopy, have been studied, and a complementary approach, hyperspectral imaging, has also been introduced. We developed a high-speed hyperspectral imaging microscopy imaging method with commercially available apparatus, employing a liquid crystal tunable bandpass filter combined with a pixel-wise machine learning classification. Next, we evaluated the feasibility of the application of this method for stem cell research utilizing neural stem cells. Employing this microscopy method, with a 562 × 562 μm2 field of view, 2048 × 2048 pixel resolution images containing 63 wavelength pixel-wise spectra could be obtained in 30 seconds. The neural stem cells were differentiated into neurons and astroglia (glia), and a four-class cell classification evaluation (including neuronal cell body, glial cell body, process and extracellular region) was conducted under co-cultured conditions. As a result, an average of 88% of the objects of interest were correctly classified, with an average precision of 94%, and more than 99% of the extracellular pixels were correctly segregated. These results indicated that the proposed hyperspectral imaging microscopy is feasible as a label-free observation method for stem cell research.

SUBMITTER: Ogi H

PROVIDER: S-EPMC6345994 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Label-Free, Noninvasive Bone Cell Classification by Hyperspectral Confocal Raman Microscopy.

Project description:Characterizing and identifying cells in multicellular in vitro models remain a substantial challenge. Here, we utilize hyperspectral confocal Raman microscopy and principal component analysis coupled with linear discriminant analysis to form a label-free, noninvasive approach for classifying bone cells and osteosarcoma cells. Through the development of a library of hyperspectral Raman images of the K7M2-wt osteosarcoma cell lines, 7F2 osteoblast cell lines, RAW 264.7 macrophage cell line, and osteoclasts induced from RAW 264.7 macrophages, we built a linear discriminant model capable of correctly identifying each of these cell types. The model was cross-validated using a k-fold cross validation scheme. The results show a minimum of 72% accuracy in predicting cell type. We also utilize the model to reconstruct the spectra of K7M2 and 7F2 to determine whether osteosarcoma cancer cells and normal osteoblasts have any prominent differences that can be captured by Raman. We find that the main differences between these two cell types are the prominence of the β-sheet protein secondary structure in K7M2 versus the α-helix protein secondary structure in 7F2. Additionally, differences in the CH2 deformation Raman feature highlight that the membrane lipid structure is different between these cells, which may affect the overall signaling and functional contrasts. Overall, we show that hyperspectral confocal Raman microscopy can serve as an effective tool for label-free, nondestructive cellular classification and that the spectral reconstructions can be used to gain deeper insight into the differences that drive different functional outcomes of different cells.

| S-EPMC10900511 | biostudies-literature

Classification of M1/M2-polarized human macrophages by label-free hyperspectral reflectance confocal microscopy and multivariate analysis.

Project description:The possibility of detecting and classifying living cells in a label-free and non-invasive manner holds significant theranostic potential. In this work, Hyperspectral Imaging (HSI) has been successfully applied to the analysis of macrophagic polarization, given its central role in several pathological settings, including the regulation of tumour microenvironment. Human monocyte derived macrophages have been investigated using hyperspectral reflectance confocal microscopy, and hyperspectral datasets have been analysed in terms of M1 vs. M2 polarization by Principal Components Analysis (PCA). Following PCA, Linear Discriminant Analysis has been implemented for semi-automatic classification of macrophagic polarization from HSI data. Our results confirm the possibility to perform single-cell-level in vitro classification of M1 vs. M2 macrophages in a non-invasive and label-free manner with a high accuracy (above 98% for cells deriving from the same donor), supporting the idea of applying the technique to the study of complex interacting cellular systems, such in the case of tumour-immunity in vitro models.

| S-EPMC5566322 | biostudies-literature

Hyperspectral Imaging during Normothermic Machine Perfusion-A Functional Classification of Ex Vivo Kidneys Based on Convolutional Neural Networks.

Project description:Facing an ongoing organ shortage in transplant medicine, strategies to increase the use of organs from marginal donors by objective organ assessment are being fostered. In this context, normothermic machine perfusion provides a platform for ex vivo organ evaluation during preservation. Consequently, analytical tools are emerging to determine organ quality. In this study, hyperspectral imaging (HSI) in the wavelength range of 550-995 nm was applied. Classification of 26 kidneys based on HSI was established using KidneyResNet, a convolutional neural network (CNN) based on the ResNet-18 architecture, to predict inulin clearance behavior. HSI preprocessing steps were implemented, including automated region of interest (ROI) selection, before executing the KidneyResNet algorithm. Training parameters and augmentation methods were investigated concerning their influence on the prediction. When classifying individual ROIs, the optimized KidneyResNet model achieved 84% and 62% accuracy in the validation and test set, respectively. With a majority decision on all ROIs of a kidney, the accuracy increased to 96% (validation set) and 100% (test set). These results demonstrate the feasibility of HSI in combination with KidneyResNet for non-invasive prediction of ex vivo kidney function. This knowledge of preoperative renal quality may support the organ acceptance decision.

| S-EPMC8962340 | biostudies-literature

Combined kernel-based BDT-SMO classification of hyperspectral fused images.

Project description:To solve the poor generalization and flexibility problems that single kernel SVM classifiers have while classifying combined spectral and spatial features, this paper proposed a solution to improve the classification accuracy and efficiency of hyperspectral fused images: (1) different radial basis kernel functions (RBFs) are employed for spectral and textural features, and a new combined radial basis kernel function (CRBF) is proposed by combining them in a weighted manner; (2) the binary decision tree-based multiclass SMO (BDT-SMO) is used in the classification of hyperspectral fused images; (3) experiments are carried out, where the single radial basis function- (SRBF-) based BDT-SMO classifier and the CRBF-based BDT-SMO classifier are used, respectively, to classify the land usages of hyperspectral fused images, and genetic algorithms (GA) are used to optimize the kernel parameters of the classifiers. The results show that, compared with SRBF, CRBF-based BDT-SMO classifiers display greater classification accuracy and efficiency.

| S-EPMC4163336 | biostudies-other

Rapid, label-free classification of tumor-reactive T cell killing with quantitative phase microscopy and machine learning.

Project description:Quantitative phase microscopy (QPM) enables studies of living biological systems without exogenous labels. To increase the utility of QPM, machine-learning methods have been adapted to extract additional information from the quantitative phase data. Previous QPM approaches focused on fluid flow systems or time-lapse images that provide high throughput data for cells at single time points, or of time-lapse images that require delayed post-experiment analyses, respectively. To date, QPM studies have not imaged specific cells over time with rapid, concurrent analyses during image acquisition. In order to study biological phenomena or cellular interactions over time, efficient time-dependent methods that automatically and rapidly identify events of interest are desirable. Here, we present an approach that combines QPM and machine learning to identify tumor-reactive T cell killing of adherent cancer cells rapidly, which could be used for identifying and isolating novel T cells and/or their T cell receptors for studies in cancer immunotherapy. We demonstrate the utility of this method by machine learning model training and validation studies using one melanoma-cognate T cell receptor model system, followed by high classification accuracy in identifying T cell killing in an additional, independent melanoma-cognate T cell receptor model system. This general approach could be useful for studying additional biological systems under label-free conditions over extended periods of examination.

| S-EPMC8484462 | biostudies-literature

Structured illumination microscopy combined with machine learning enables the high throughput analysis and classification of virus structure.

Project description:Optical super-resolution microscopy techniques enable high molecular specificity with high spatial resolution and constitute a set of powerful tools in the investigation of the structure of supramolecular assemblies such as viruses. Here, we report on a new methodology which combines Structured Illumination Microscopy (SIM) with machine learning algorithms to image and classify the structure of large populations of biopharmaceutical viruses with high resolution. The method offers information on virus morphology that can ultimately be linked with functional performance. We demonstrate the approach on viruses produced for oncolytic viriotherapy (Newcastle Disease Virus) and vaccine development (Influenza). This unique tool enables the rapid assessment of the quality of viral production with high throughput obviating the need for traditional batch testing methods which are complex and time consuming. We show that our method also works on non-purified samples from pooled harvest fluids directly from the production line.

| S-EPMC6331195 | biostudies-literature

Label-free hyperspectral nonlinear optical microscopy of the biofuel micro-algae Haematococcus Pluvialis.

Project description:We consider multi-modal four-wave mixing microscopies to be ideal tools for the in vivo study of carotenoid distributions within the important biofuel microalgae Haematococcus pluvialis. We show that hyperspectral coherent anti-Stokes Raman scattering (CARS) microscopy generates non-invasive, quantitative real-time concentrations maps of intracellular carotenoid distributions in live algae.

| S-EPMC4206310 | biostudies-other

A Versatile Deep Learning Architecture for Classification and Label-Free Prediction of Hyperspectral Images.

Project description:Hyperspectral imaging is a technique that provides rich chemical or compositional information not regularly available to traditional imaging modalities such as intensity imaging or color imaging based on the reflection, transmission, or emission of light. Analysis of hyperspectral imaging often relies on machine learning methods to extract information. Here, we present a new flexible architecture, the U-within-U-Net, that can perform classification, segmentation, and prediction of orthogonal imaging modalities on a variety of hyperspectral imaging techniques. Specifically, we demonstrate feature segmentation and classification on the Indian Pines hyperspectral dataset and simultaneous location prediction of multiple drugs in mass spectrometry imaging of rat liver tissue. We further demonstrate label-free fluorescence image prediction from hyperspectral stimulated Raman scattering microscopy images. The applicability of the U-within-U-Net architecture on diverse datasets with widely varying input and output dimensions and data sources suggest that it has great potential in advancing the use of hyperspectral imaging across many different application areas ranging from remote sensing, to medical imaging, to microscopy.

| S-EPMC8528004 | biostudies-literature

Identifying subpopulations in multicellular systems by quantitative chemical imaging using label-free hyperspectral CARS microscopy.

Project description:Quantitative hyperspectral coherent Raman scattering microscopy merges imaging with spectroscopy and utilises quantitative data analysis algorithms to extract physically meaningful chemical components, spectrally and spatially-resolved, with sub-cellular resolution. This label-free non-invasive method has the potential to significantly advance our understanding of the complexity of living multicellular systems. Here, we have applied an in-house developed hyperspectral coherent anti-Stokes Raman scattering (CARS) microscope, combined with a quantitative data analysis pipeline, to imaging living mouse liver organoids as well as fixed mouse brain tissue sections xenografted with glioblastoma cells. We show that the method is capable of discriminating different cellular sub-populations, on the basis of their chemical content which is obtained from an unsupervised analysis, i.e. without prior knowledge. Specifically, in the organoids, we identify sub-populations of cells at different phases in the cell cycle, while in the brain tissue, we distinguish normal tissue from cancer cells, and, notably, tumours derived from transplanted cancer stem cells versus non-stem glioblastoma cells. The ability of the method to identify different sub-populations was validated by correlative fluorescence microscopy using fluorescent protein markers. These examples expand the application portfolio of quantitative chemical imaging by hyperspectral CARS microscopy to multicellular systems of significant biomedical relevance, pointing the way to new opportunities in non-invasive disease diagnostics.

| S-EPMC8359792 | biostudies-literature

Weakly Supervised Identification and Localization of Drug Fingerprints Based on Label-Free Hyperspectral CARS Microscopy.

Project description:Understanding drug fingerprints in complex biological samples is essential for the development of a drug. Hyperspectral coherent anti-Stokes Raman scattering (HS-CARS) microscopy, a label-free nondestructive chemical imaging technique, can profile biological samples based on their endogenous vibrational contrast. Here, we propose a deep learning-assisted HS-CARS imaging approach for the investigation of drug fingerprints and their localization at single-cell resolution. To identify and localize drug fingerprints in complex biological systems, an attention-based deep neural network, hyperspectral attention net (HAN), was developed. By formulating the task to a multiple instance learning problem, HAN highlights informative regions through the attention mechanism when being trained on whole-image labels. Using the proposed technique, we investigated the drug fingerprints of a hepatitis B virus therapy in murine liver tissues. With the increase in drug dosage, higher classification accuracy was observed, with an average area under the curve (AUC) of 0.942 for the high-dose group. Besides, highly informative tissue structures predicted by HAN demonstrated a high degree of similarity with the drug localization shown by the in situ hybridization staining results. These results demonstrate the potential of the proposed deep learning-assisted optical imaging technique for the label-free profiling, identification, and localization of drug fingerprints in biological samples, which can be extended to nonperturbative investigations of complex biological systems under various biological conditions.

| S-EPMC10372874 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data