23 results about "Imaging flow cytometry" patented technology

The invention relates to the technical field of model analysis, in particular to an imaging flow cytometry cell detection method based on an improved model. The method comprises the following steps: introducing a cell sample to be detected into an imaging flow cytometry system integrated with a micro-fluidic chip for continuous image acquisition to generate an initial cell image sequence; an automatic digital focusing algorithm is applied to the initial cell image sequence, and a cell image frame set with the optimal focal plane is screened out; inputting the cell image frame set into a preset PA-YOLO improved model for multi-dimensional extraction and fusion, and generating a multi-scale cell characteristic spectrum; carrying out refined feature learning and cell target positioning and classification on the multi-scale cell feature spectrum, and outputting a cell detection result; and carrying out validity verification on the cell detection result, and carrying out comparative analysis in combination with an imaging flow cytometry system to generate a cell detection report. According to the method, the imaging quality and the detection accuracy of cell images with different depths can be remarkably improved.

An imaging flow cytometry-based high-throughput drug screening method, comprising: cell incubation, cell staining, acquiring single-cell images by using a flow cytometer, and image extraction and analysis, which combines the high-throughput advantages of flow cytometry and the imaging capability of a microscope, so that multi-channel single-cell images can be generated in a high throughput manner, thereby implementing acquisition of fluorescent images and unmarked images of single cells at a throughput of 102-105 cells per second, which can be used for cell phenotype drug screening and improving the screening efficiency by a factor of 102-104.

The invention discloses a microfluidic image flow cytometry identification system and a microfluidic image flow cytometry identification method based on multi-modal phase imaging and deep learning, relates to a microfluidic image flow cytometry detection technology, and belongs to the crossing field of microfluidics, optical imaging and artificial intelligence. The cell deformation chip is used for inducing a cell sample to generate controllable deformation through the cell deformation chip and discharging deformed cells; the optical imaging unit is used for scanning the deformed cells and collecting multi-modal phase images of the deformed cells; the data processing and analysis unit is used for preprocessing the multi-modal phase image and performing cell intelligent identification analysis on the preprocessed multi-modal phase image by using a deep learning feature extraction network, so that accurate identification and classification of cells are realized, and a leukocyte subpopulation identification model is constructed; and generating a cell imaging result and a cell mechanical parameter thermodynamic diagram. According to the invention, label-free identification of leukocyte subgroups is realized, and the problems of tedious operation and cell damage of traditional fluorescence labeling are solved.

The present disclosure provides apparatuses, systems, and methods for performing particle analysis through flow cytometry at comparatively high event rates and for gathering high resolution images of particles.

The invention belongs to the technical field of biomedical detection, and discloses a blood cell analysis system based on image flow cytometry, which comprises a cell staining module, the dyeing module simultaneously comprises a first fluorescent probe capable of being specifically combined with components in a cell nucleus or enriched in the cell nucleus, a second fluorescent probe capable of being specifically combined with cell nucleus DNA and a third fluorescent probe capable of being specifically combined with a blood cell differentiation antigen; an image flow cytometer; and the image processing module is used for calculating the kernel detection rate and / or the average kernel number. According to the present invention, the combination of the specific types of the cell staining dyes is adopted, the image flow cytometry is matched, and the optimized multi-dimensional fluorescence staining combination and the matched automatic image analysis process are adopted to achieve the synchronous, high-throughput and accurate quantitative analysis of the blood cell immune phenotype and the cell morphology key characteristics at the single cell level;

The application relates to the technical field of medical data analysis, and particularly provides a multi-modal data analysis method and device for an imaging flow cytometer. The method comprises the following steps: acquiring first multi-modal features and first multi-modal feature statistics of an internal reference cell population in each batch; selecting one batch as a reference batch; for each non-reference batch, correcting the corresponding first multi-modal features according to the difference between the corresponding first multi-modal feature statistics and the first multi-modal feature statistics of the reference batch; for each corrected first multi-modal feature, determining the fusion weight of each modal feature according to the residual variation degree and the distinguishing ability, then fusing all modal features contained in the first multi-modal feature according to the fusion weight to obtain a fusion feature vector; and performing cell subpopulation identification according to the fusion feature vector. The method can effectively eliminate technical differences between batches and realize adaptive multi-modal feature fusion.

In one aspect, the present teachings provide a system for performing cytometry that can be operated in three operational modes. In one operational mode, a fluorescence image of a sample is obtained by exciting one or more fluorophore(s) present in the sample by an excitation beam formed as a superposition of a top-hat-shaped beam with a plurality of beams that are radiofrequency shifted relative to one another. In another operational mode, a sample can be illuminated successively over a time interval by a laser beam at a plurality of excitation frequencies in a scanning fashion. In yet another operational mode, the system can be operated to illuminate a plurality of locations of a sample concurrently by a single excitation frequency, which can be generated, e.g., by shifting the central frequency of a laser beam by a radiofrequency. The detected fluorescence radiation can be used to analyze the fluorescence content of the sample, e.g., a cell / particle.

The present application relates to a kind of phytoplankton imaging flow trait analysis method and system, wherein the method comprises: the single particle image exported by imaging flow cytometry equipment is defined as a phenotype object to be analyzed;From the JPEG annotation section of single particle image, corresponding optical signal field of phenotype object is obtained by byte analysis;Phytoplankton target region segmentation is carried out on single particle image, and phytoplankton target mask is obtained;The two-dimensional morphological characteristics of phenotype object are calculated based on phytoplankton target mask;Two-dimensional morphological characteristics and optical signal field are bound in corresponding phenotype object, and event-level morphological-optical fusion trait vector of phenotype object is generated, and event-level morphological-optical fusion trait vector is output.Using the present application, image morphological information and optical property information are synchronously acquired and fused from the same data source, and the acquisition efficiency of phytoplankton single particle comprehensive characteristics is improved.

The invention relates to the technical field of illumination control, in particular to an imaging flow cytometry illumination method and device based on DMD control. The method comprises the following steps: a halogen lamp light source emits wide-spectrum continuous light, the wide-spectrum continuous light is homogenized and collimated through a scale reflector lamp cup to form a high-collimation light beam, and a digital micromirror array DMD is used for controlling the deviation angle to form a selective reflection light path; after an optical channel coupled with the optical axis of the imaging system receives a selective reflection light path reflected by the digital micromirror array DMD, light beam calibration is carried out through a collimating lens group, and standard parallel light beams are formed; the standard parallel light beams are guided by the reflection / transmission light guide system to form an illumination area; and monitoring the illumination effect data in the illumination area in real time, and dynamically adjusting the deflection state of each micromirror unit to adapt to the dynamic detection process of the flow cytometry. According to the invention, the illumination direction of the halogen lamp can be controlled by using the digital micromirror array, so that a rapid electronic switching effect is realized, and heat accumulation on a chip in an exposure process can be effectively reduced.

The invention relates to the technical field of medical data analysis, and particularly provides a multi-modal data analysis method and device for an imaging flow cytometry, and the method comprises the steps: obtaining first multi-modal features and first multi-modal feature statistics of an internal reference cell population in each batch; selecting one batch as a reference batch; for each non-reference batch, correcting the corresponding first multi-modal feature according to the difference between the corresponding first multi-modal feature statistic and the first multi-modal feature statistic corresponding to the reference batch; for each first multi-modal feature after correction, determining a fusion weight of each modal feature according to a residual variation degree and a distinguishing capability, and then fusing all modal features included in the first multi-modal feature according to the fusion weight to obtain a fusion feature vector; performing cell subset identification according to the fusion feature vector; according to the method, the technical difference between batches can be effectively eliminated, and adaptive multi-modal feature fusion can be realized.

The present invention provides a method for cell analysis, comprising: preparing a blood sample comprising nucleated cells having surface, cytoplasmic or nuclear antigens (markers); antibody staining the cell markers; fixing and permeabilising the cells; FISH probe hybridising to chromosomes in the cells; performing imaging flow cytometry on the cells; analysing data obtained from performing imaging flow cytometry; and diagnosing, prognosing or monitoring a medical condition based on the data analysis.

Systems and methods for predicting and verifying properties of individual cells using label-free imaging and machine learning are disclosed. In an embodiment, a method for predicting and validating properties of individual cells includes acquiring image data of a mixture of cells and markers using an imaging flow cytometer, and identifying an individual cell by dispensing the mixture onto a cell placement or collection platform and matching a first marker sequence from the image data with a second marker sequence obtained from the platform. The method further includes inputting the image data into a machine-learning model configured to generate a predicted change in one or more properties of the identified cell, determining an actual change in the properties by measuring the cell at two different time points, and updating the machine-learning model by comparing the predicted and measured changes and incorporating the comparison result into the model.

In one aspect, a system for performing flow cytometry is disclosed, which comprises a laser for generating laser radiation for illuminating a sample, at least one detector for detecting at least a portion of a radiation emanating from the sample in response to said illumination so as to generate a temporal signal corresponding to said detected radiation, and an analysis module for receiving said temporal signal and performing a statistical analysis of said signal based on a forward model to reconstruct an image of said sample.

A high-throughput parallel testing method based on imaging flow cytometry and spatially coded reagents combines the high-throughput characteristic of an imaging flow cytometer and the high coding capacity characteristic of spatially coded reagents, thereby achieving high-throughput parallel testing of nucleic acid sequencing, protein testing and single cell analysis, and being capable of being used for liquid biopsy or other biomedical use requirements for performing high-throughput synchronous testing on different biomarkers.

The present disclosure provides apparatuses, systems, and methods for performing particle analysis through flow cytometry at comparatively high event rates and for gathering high resolution images of particles.

A classifier engine provides cell morphology identification and cell classification in computer-automated systems, methods and diagnostic tools. The classifier engine performs multispectral segmentation of thousands of cellular images acquired by a multispectral imaging flow cytometer. As a function of imaging mode, different ones of the images provide different segmentation masks for cells and subcellular parts. Using the segmentation masks, the classifier engine iteratively optimizes model fitting of different cellular parts. The resulting improved image data has increased accuracy of location of cell parts in an image and enables detection of complex cell morphologies in the image. The classifier engine provides automated ranking and selection of most discriminative shape based features for classifying cell types.

The present invention provides a bioluminescence imaging flow cytometry method and apparatus, comprising: a free reflection unit configured to obtain a bioluminescence signal by irradiating a sample suspension, and to re-reflect and converge the collected bioluminescence signal to enhance the detected bioluminescence signal; the sample control unit is configured to comprise a multi-channel flow type assembly, a fixing mechanism and a three-axis displacement table; the multi-channel flow type assembly is used for fixing and bearing a sample suspension, the fixing mechanism is used for fixing the multi-channel flow type assembly, and the three-axis displacement table drives the fixing mechanism to perform three-axis movement so as to adjust an imaging area of the sample suspension fixedly borne by the multi-channel flow type assembly; and an optical imaging unit configured to capture a bioluminescent cell image at a low signal level in space.

The present disclosure relates to an intelligent event imaging flow cytometer, comprising a microfluidic system, an optical system and a hardware processing system. The microfluidic system is used for continuously importing a cell sample comprising at least two kinds of cells, and exporting each kind of cell according to the classification result fed back by the hardware processing system. The optical system is used for jointly irradiating the cell sample by a bright field light source and a fluorescent light source, and collecting multiple double-channel coupling information simultaneously comprising bright field cells and fluorescent cells. The hardware processing system is used for obtaining the classification result of the target cell according to multiple target coupling information corresponding to the target cell determined in the double-channel coupling information, and feeding back the classification result to the microfluidic system. In the present disclosure, the cell classification in the cell sample can be realized through the information interaction transmission of the three systems, which simplifies the overall structure of the cytometer. At the same time, the cell classification result is improved in accuracy by jointly judging the cell classification through the cell characteristics collected under the bright field and fluorescent light sources.

Disclosed herein are machine learning-based particle classification systems, and related methods, computing devices, and computer-readable media. For example, in some embodiments, a particle classification system can include an electronic processing device configured to: receive, from an imaging flow cytometer instrument, a test set comprising unlabeled data to be classified; pool the test set and a training set into a concatenated data set comprising a plurality of parameters, wherein the training set comprises labeled data; normalize the concatenated data set by making each parameter in the plurality of parameters variance one; non-linearly reduce a dimensionality of the normalized concatenated data set to a reduced dimensionality space; compute a classification parameter by classifying the unlabeled data from the reduced dimensionality space using the labeled data from the reduced dimensionality space; and provide the classification parameter for further processing.

The embodiment of the utility model provides an image flow cytometry detection device. The image flow cytometry detection device comprises a sample inlet; the micro-pipeline system is used for conveying a sample; wherein the micro-pipeline system is transparent, a spiral conveying structure is arranged on the inner wall of the micro-pipeline system, and the micro-pipeline system is gradually shrunk in a trumpet shape at the position close to the sample inlet; the lighting unit is mounted on the side surface of the micro-pipeline system; the detection unit is positioned on one side of the downstream section of the micro-pipeline system; the waste liquid outlet is positioned at the tail end of the micro-pipeline system and is used for discharging the detected liquid sample; wherein a spiral conveying structure on the inner wall of the micro-pipeline system comprises a flow guide sheet and a flow guide shaft, and a heating rod is arranged in the flow guide shaft so as to avoid sample deterioration or sedimentation caused by temperature difference change; the spiral conveying structure further comprises a plurality of micro-protruding units which are evenly distributed on the flow deflectors at intervals. According to the scheme of the embodiment of the invention, adhesion and blockage of the sample in transmission can be reduced.

1. The name of the design product: image labeling button area of machine learning model training graphical user interface of electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The use of the graphical user interface: the present graphical user interface relates to the creation of training set in the field of artificial intelligence, and can be used to facilitate the operation personnel to create and train customized model for labeling analysis of image flow cytometry data. The image labeling button area of the graphical user interface is used to arrange buttons for the user to select subsequent operations. 6. The human-computer interaction mode of the graphical user interface: the user selects subsequent operations by clicking three circular buttons in the interface, which can include selecting the base model to be trained, selecting the image for training, and labeling the image to be processed to train the data set. 7. Other circumstances that need to be explained: the dashed line in the figure is not claimed.

A method images flow cytometry by moving a sample along an axis of movement, and generating recorded images of the sample. Each recorded image is generated by illuminating the sample by illumination light, forming an image of the sample by collecting detection light originating from or interacting with the sample, and generating a recorded image of the sample by recording the image of the sample during its movement. A combined image of the sample is then generated by selecting at least two recorded images, generating a transformed recorded image for each selected recorded image, and combining the transformed recorded images into a combined image. The transformed recorded image is generated by: extracting at least part of the selected recorded image, and applying a transformation to the extracted part of the selected recorded image.