127 results about "Cervical cells" patented technology

Methods and compositions for identifying high-grade cervical disease in a patient sample are provided. The methods of the invention comprise detecting overexpression of at least one biomarker in a body sample, wherein the biomarker is selectively overexpressed in high-grade cervical disease. In particular claims, the body sample is a cervical smear or monolayer of cervical cells. The biomarkers of the invention include genes and proteins that are involved in cell cycle regulation, signal transduction, and DNA replication and transcription. In particular claims, the biomarker is an S-phase gene. In some aspects of the invention, overexpression of a biomarker of interest is detected at the protein level using biomarker-specific antibodies or at the nucleic acid level using nucleic acid hybridization techniques. Kits for practicing the methods of the invention are further provided.

Provided is an HPV E6, E7 mRNA assay, referenced herein as the “In Cell HPV Assay,” that is capable of sensitive and specific detection of normal cervical cells undergoing malignant transformation as well as abnormal cervical cells with pre-malignant or malignant lesions. The In Cell HPV Assay identifies HPV E6, E7 mRNA via in situ hybridization with oligonucleotides specific for HPV E6, E7 mRNA and quantitates the HPV E6, E7 mRNA via flow cytometry. The In Cell HPV Assay can be carried out in less than three hours directly from liquid-based cervical (“LBC”) cytology specimens. The In Cell HPV Assay provides an efficient and highly sensitive alternative to the Pap smear for determining abnormal cervical cytology.

The invention discloses a simple thin liquid-based cytology examine method applied for the gynecological examination, the cervical cancer general examine and the cervical cancer preceding lesion of selected crowd, the steps including: using the cervical cells brush and the scraper to collect samples, put samples in the liquid-based cell preservation solution, add base liquid cell processing solution, oscillate, centrifugally separate, take and discard the supernatant samples liquid, using adding samples gun to assimilate sediment samples, smear, sheet drying, using 95% ethanol marinate or spray for fixed, washing and dyeing. The invention has simple method, small steps, high positive detection rate, low misdiagnosis rate, low cost, and it can effectively eliminate the red blood cells, mucus and other interference components from the cervical cytology detection specimens, with good sheet-producing result.

The invention discloses a cervical cell image segmentation method based on an antagonistic generation network, comprising the following steps: a cell image is coarsely segmented, wherein for the cellimage coarse segmentation, a threshold method and a watershed algorithm are used for coarse segmentation of an original image to form guiding factors, and the original image is cut into small images;a virtual body segmentation image is generated, wherein the generated virtual body segmentation image is generated by using an antagonistic generation network designed in combination with a self-encoder, taking a clipped small image as an input, and using the guiding factors to help the neural network to locate a region of interest; a solid cell image is extracted, wherein the solid cell image extraction refers to that a real cell image is extracted from the clipped small image according to the virtual body segmentation image. The cervical cell image segmentation method based on the antagonistic generation network provided by the invention is the first time to use the antagonistic generation network to solve such problems, provides a novel automatic cell image segmentation method, and simultaneously solves the component loss in the traditional overlapped cell segmentation method.

In certain aspects, the invention relates to methods of diagnosing cervical cancer by using a combination of certain biomarkers such as hTERT, IGFBP-3, transferrin receptor, beta-catenin, Myc-HPV E6 interaction, HPV E7, and telomere length. In other aspects, the invention relates to methods of detecting immortalization of cervical cells by using a combination of certain biomarkers. In yet other aspects, the invention relates to methods of classifying the grade of a cervical lesion for diagnostic and prognostic purposes in a female. In further aspects, the invention relates to methods of treating cervical cancer by administering a therapeutic agent that targets one or more of these biomarkers.

The invention discloses a cervical cell image classification method based on a graph convolutional neural network. Firstly, a cervix uteri cell image is prepared as a training sample; 1024-dimensionalfeature representation of a sample is acquired, a sample feature relation graph is constructed, a deep network based on a graph convolutional network is constructed, the sample and the sample featurerelation graph are sent to the deep network model for training, training is stopped after iteration is performed for a certain number of times, and network weight parameters are stored. When the method is used, a target image is segmented into a to-be-predicted area with cell nucleuses, then weight parameters and a network structure obtained through training are loaded, the to-be-predicted area is input into the to-be-predicted area, and a classification result can be obtained through calculation. According to the method, the cervical cell diagnosis accuracy and efficiency are improved, the diagnosis process of a pathologist is optimized, and the workload of the pathologist is reduced.

The invention discloses a cervical cancer cell image recognizing algorithm based on a convolutional neural network. In a traditional method, due to precise dividing and manual feature extracting and selecting of cytoplasms or cell nucleuses, once features with dividing errors or features not accurately extracted are generated, the cell recognizing accuracy can be reduced. By automatically extracting deep features in cell images through the convolutional neural network, a recognizing task is completed. The recognizing algorithm includes the steps of roughly dividing a cervical cell TCT image; secondly, inputting the roughly-divided image into a convolutional neural network model for training; thirdly, storing the trained network model to obtain a final recognizing result. The cervical cancer cell image recognizing algorithm is different from the traditional recognizing method and has a good recognizing effect in actual application.

The invention discloses a novel pasteurization method and an abnormal cervical cell automatic identification method. The novel pasteurization method comprises two modules, the module 1 is used for training a cervical cell classification model based on a mass cervical cell data set, and the module 2 is used for identifying abnormal cervical cells by using the trained classification model. The invention provides the novel pasteurization method, so that the problems existing in the traditional pasteurization method are well solved, and the possibility is provided for realizing automatic and high-precision positioning of cervical cell nuclei by a computer. The invention also provides the abnormal cervical cell automatic identification method, and experiments show that the method realizes the ultrahigh-precision automatic identification of abnormal cervical cells, so that the diagnosis burden of pathologists is greatly reduced, the diagnosis efficiency and the precision of the cervical diseases are improved, and the method has very high practical value and huge social benefits.

The invention discloses a target cell staining kit for displaying the proliferative activity of a cell and a use method thereof. The kit comprises I type and II type which respectively comprise an enzyme substrate, test paper, enzyme stationary liquid, phosphate buffer solution, Mayer hematoxylin and the like. The staining method comprises the steps of preparing pieces, fixing, staining and the like. The method can display acid phosphatase in exfoliative cells on smears such as exfoliative cervical cells, esophagus brush sheet cells and the like and search abnormal proliferated cells according to the target. Compared with the traditional Pasteur smear method, the method has the advantages of higher sensitivity for detecting cancer and precancerous lesions and similar specificity, therefore, the invention can be used for cytology screening of cervical carcinoma, esophageal cancer, lung cancer and other malignant tumors.

Methods of predicting whether a subject has a cervical intraepithelial neoplasia (CIN) lesion are provided. Aspects of the methods include obtaining both morphometric and biomarker data from a liquid cervical cellular sample and then using both types of data to predict whether the subject has a CIN lesion. Also provided are systems that find use in practicing the methods. The methods and systems find use in a variety of applications, including cervical cancer screening applications.

The invention provides a fine-grained cervical cell image three-stage identification method, which comprises the following steps: firstly, denoising a whole cervical cell image acquired by electronicimaging equipment to improve the image quality, removing a background to determine a foreground cell region, and segmenting out cell nucleuses and cytoplasm; secondly, extracting shape, color, textureand abstract features from the segmented cell regions, and carrying out selective fusion on the features by adopting a multi-kernel learning method so as to optimize a feature mode; and finally, removing non-cervical cell impurities according to the optimized characteristic mode, and performing multi-classification on the cervical cell images by adopting a cost-sensitive active learning method. The identification process system is complete, can extract medical features of multiple types of cervical cell images, performs selective fusion optimization on feature modes, removes impurities by using a cost-sensitive learning method, solves the problem of unbalanced dichotomy, and can effectively improve the accuracy of cervical cell classification and identification.

The invention provides a method and a device for processing cervical cell slice images, wherein the method comprises the following steps of: A, collecting a single free non-overlapping cell material and a slice background material from a real cervical cell slice image with cell level labeling information, and establishing a single cell database and a slice background database; B, according to a single cell database and a slice background database, synthesizing a simulated cervical cell slice image with cell instance level label; C, training a cervical cell instance segmentation depth model byusing a simulated cervical cell slice image, and segmenting cervical cells by use that trained cervical cell instance segmentation depth model to detect the real cervical cell slice image to obtain acervical cell segmentation result.

The embodiment of the invention belongs to the technical field of artificial intelligence, and relates to a cervix uteri cell image screening method which comprises the following steps: receiving an image screening request sent by a user, the image screening request at least carrying an original image; performing down-sampling operation on the original image to obtain a target picture block; inputting the target picture block into a preset image screening model, and obtaining prediction category information and prediction probability information corresponding to the target picture block; taking the target picture block meeting a preset prediction threshold and prediction category information as a screening result; and outputting the screening result to the user. The invention further provides a cervix uteri cell image screening device, computer equipment and a storage medium. According to the invention, the screening efficiency of cervical cell images is greatly improved, and the screening accuracy can be ensured while the workload of cytopathologists is reduced.

The invention relates to a method and a device for identifying an abnormal cell image in a cervical cell image. The method comprises the following steps: inputting a multi-scale cervical cell image into a pre-trained multi-scale fusion network, wherein multi-scale cervical cells comprise different sizes of the same cervical cell image; key node features of the cervical cell image of each scale in the multi-scale cervical cell images are extracted through a multi-scale fusion network; determining a grading result of an abnormal cell image in the cervical cell image corresponding to the key node feature of the cervical cell image of each scale through a Bersada grading system; and fusing the grading results of the abnormal cell images in the cervical cell images of each scale, and outputting the abnormal cell images in the cervical cell images and the abnormal cell image with the highest grade in the grading results. By adopting the method, the abnormal cell image in the cervical cell image does not need to be manually identified and determined, and the abnormal cell image can be graded.

The invention relates to the technical field of a medicine preparation, and particularly relates to a kit for screening abnormal cervical cells, and enzyme-labeled liquid based cell preservation solution. The kit for screening abnormal cervical cells has excellent sensitivity and good specificity; and the enzyme-labeled liquid based cell preservation solution disclosed by the invention can well keep acid phosphatase activity of cervical exfoliated cells and the cellular morphology, and has the functions of preventing corrosion, removing impurities and dissolving red blood cells; and the effects of tabletting and dyeing the stored cells are superior to the effect of the traditional preservation solution during the usage period.

The invention discloses a cervical liquid-based cell classification method based on a double attention mechanism and multi-scale feature fusion. The method comprises the following steps: 1, acquiring labeled N types of cervical cell images; 2, establishing a deep learning network based on multi-head self-attention, channel attention and multi-scale feature fusion; 3, constructing a cervical cell image classifier; and 4, realizing image category prediction by using the established classifier. Capturing of correlation of internal features of the image is enhanced through a self-attention mechanism, the defect that the self-attention mechanism lacks channel and multi-scale information is overcome by combining channel attention and multi-scale feature fusion, and accurate classification of cervical cells is completed.