58 results about "Cervical cell" patented technology

The invention discloses an overlapped cervical cytoplasm region segmentation method based on deep learning and a conditional diffusion model, and relates to the technical field of artificial intelligence analysis of medical images. According to the method, accurate segmentation of the overlapped cytoplasm region in the cervical cell image is realized through a morphological prior guided conditional diffusion process. The method comprises the following steps: constructing a multi-scale cervical cytoplasm mask pair image; designing a cytoplasm specific data enhancement and preprocessing process; building a multi-branch cervical cell morphology perception condition diffusion network; using a self-adaptive multi-scale combination loss function to optimize training; and a hierarchical classifier is adopted to freely guide sampling for reasoning. According to the method, the frequency domain and space domain features are fused, a cellular morphology and statistics priori knowledge base is established, and a strategy of generating complete cytoplasm by adopting non-overlapped parts is adopted, so that the problem that the traditional method is difficult to segment in complex backgrounds and overlapped regions is successfully solved, and reliable technical support is provided for early screening of cervical cancer.

The invention discloses a cervical cell image intelligent diagnosis system based on a multi-modal visual language large model, belongs to the field of cervical cell image recognition, and particularly relates to the cervical cell image intelligent diagnosis system based on the multi-modal visual language large model. In order to solve the problems of low diagnosis accuracy, strong subjectivity, insufficient efficiency and lack of interpretation in the prior art, the invention provides a cervical cell image intelligent diagnosis system based on a multi-modal visual language large model. The system comprises an image block acquisition module, an image preprocessing and color normalization module, an effective tissue region screening module, a cell region extraction and post-processing module, an image end and text end processing module, a visual language large model acquisition and training module, a cell description text generation module in an inference stage, and a risk judgment and classification module. An interpretability verification and credibility evaluation module; and a structured diagnosis report output module.

The invention discloses a cervical cell segmentation method combining semantic condition diffusion and knowledge verification, which comprises the following steps: S1, constructing a cervical cancer diagnosis vertical field multi-modal large model, and performing fine tuning on an open-source multi-modal large model through a low-rank adaptation supervision fine tuning method to obtain the cervical cancer diagnosis vertical field multi-modal large model; s2, generating a semantic vector for guiding segmentation; s3, performing preliminary segmentation based on a conditional diffusion model, performing iterative denoising on the to-be-segmented image, and generating a preliminary cervical cell segmentation mask; and S4, performing segmentation post-processing based on domain knowledge: performing morphological processing on the preliminary segmentation mask to obtain a final cervical cell segmentation result. According to the method, large-scale text data can be fully utilized and converted into refined semantic information for guiding image segmentation, so that the challenge of scarcity of labeled samples is overcome, the performance, generalization ability and clinical applicability of a cervical cell abnormal region segmentation model are remarkably improved, and finally more accurate and more reliable cervical cell pathological diagnosis assistance is realized.

Disclosed herein is a method for training a network to detect and classify abnormal pathologies in images if cells. Specifically, the network uses a deep framework optimally trained to detect and classify abnormal cervical cells in pap smear images.

The invention relates to a cell morphology feature extraction and prediction analysis method, in particular to a cell morphology feature extraction and prediction analysis method for a high-throughput cervical TCT image. The method aims at solving the problems that in the cell analysis technology of the cervical TCT image, complex morphological characteristics of cells are not fully considered, the characteristic extraction precision is low, and the manual dependence degree is high. The method comprises the following steps: selecting cellular morphology characteristics of cervical TCT image auxiliary diagnosis; obtaining a segmentation result of the cell nucleus and the cytoplasm based on the segmentation network; extracting, measuring and calculating cell morphological characteristics based on a cervical TCT image segmentation result; and analyzing and visualizing the measurement and calculation results of the morphological characteristics of the cells. According to the method, medical priori knowledge and data-driven research methods are fused, and more interpretable quantitative data are provided for subsequent cervical cell research through conjoint analysis of shape features and texture features. The invention belongs to the technical field of medical image analysis and computer vision.

A cervix uteri cell image enhancement method based on a generative adversarial network comprises the following steps: carrying out statistical analysis on a cervix uteri cell image data set, and confirming that a high category imbalance problem exists; according to morphological characteristics and clinical importance of cells of different lesion categories, designing differentiated enhancement strategies and target quantities; for extremely scarce high-risk categories, a StyleGAN2-ADA model constrained by medical knowledge is adopted for generation, and for other categories, a traditional enhancement method combining CLAHE, elastic deformation and the like is adopted; and performing quality control through Masked-SSIM and Med-FID medical image evaluation indexes and pathology expert auditing to obtain a high-quality enhanced image. According to the method, the problem of class imbalance in cervical cell image data is effectively solved, the recognition performance of a deep learning model on high-risk cervical lesions is remarkably improved, and the method has important clinical auxiliary diagnosis value.

The invention discloses a cervical cancer identification method based on a neural network, and the method comprises the following steps: S1, collecting a cervical cell image, marking the types of normal cells and lesion cells of different levels, so as to construct a training data set; S2, carrying out the color enhancement and normalization preprocessing of the image, and improving the subsequent identification effect; s3, designing an improved neural network algorithm, and dynamically optimizing a model training process through multi-scale feature extraction, a second-order attention mechanism and an adaptive regularization strategy for introducing the change rate of a ramp signal in a signal system; S4, training a neural network model by using the preprocessed image; and S5, finally identifying the to-be-detected image based on the trained model, and outputting whether the cervical cancer exists or not and a grading result. According to the method, the image feature readability is enhanced through preprocessing, the regularization intensity is dynamically adjusted by combining an innovative neural network structure and the change rate 0 of a ramp signal in a signal system, the accuracy of cervical cancer recognition and the model generalization ability are effectively improved, and an efficient and reliable technical scheme is provided for automatic screening of cervical cancer.

The invention provides a cervical cell characterization classification method based on a structure constraint network, and the method comprises the following steps: A, carrying out the data enhancement of a cell image, and generating different enhanced views of the same cell; b, performing feature extraction on the enhanced view by adopting a convolutional neural network to obtain cell space structure features; c, introducing a bulldozer distance EMD (Earth Mover's Distance) to apply spatial structure consistency constraint on the enhanced view, and taking the spatial structure consistency constraint as a measurement standard for structure distribution alignment; and D, inputting the features subjected to structure alignment into a classifier to complete cell category identification. According to the method, the EMD measurement is combined to apply the structural consistency constraint in the self-supervised learning framework, so that the network can extract stable and discriminative features under an unsupervised condition, and the problems of cellular morphology diversity, dyeing difference, insufficient labeling and the like are effectively solved. According to the method, excellent accuracy is obtained in an open-source cervical cell data set experiment, good robustness is shown, and an efficient and reliable technical scheme is provided for large-scale automatic analysis of clinical cervical cells.

The invention relates to the technical field of biological medicine, and particularly discloses a targeted nano NK cell exosome gel loaded with lycopene and application thereof, the targeted nano NK cell exosome gel loaded with lycopene is prepared from the following components in percentage by mass: 0.1 to 1 weight percent of lycopene oleoresin, 0.5 to 5 weight percent of NK cell exosome, 60 to 80 weight percent of gel system and the balance of ultrapure water; the lycopene oleoresin is prepared by the following steps: firstly, adding a eutectic solvent into a tomato fermentation extracting solution, carrying out ultrasonic extraction on lycopene, and then uniformly mixing the lycopene, sophorolipid and vegetable oil. According to the application, the NK cell exosome and the lycopene are organically matched, the NK cell exosome directly acts on the local part of the cervix uteri through the NK cell, and meanwhile, the lycopene can repair the damaged cervix uteri cell and restore the damaged cervix uteri cell to a normal structure, so that the purposes of removing viruses and preventing and treating cervical cancer are achieved.

The application relates to an intelligent diagnosis method for cervical cell atrophy levels, and relates to the problem that intelligent discrimination of cervical cell atrophy degrees is lacking in automatic pathological diagnosis technology. Cervical vaginal squamous epithelium is divided into surface layer cells, middle layer cells and basal layer cells, and ovarian estrogen affects the growth and maturity of the cells; a decrease in estrogen level can cause symptoms such as atrophic vaginitis and osteoporosis, which need to be treated in time; at present, squamous cell atrophy diagnosis is not clear enough, and there are few reports on atrophy degree diagnosis research, so it is of great significance to establish a systematic and intelligent diagnosis process for cervical cell atrophy degree discrimination. In order to improve the problem, the application provides an intelligent diagnosis method for cervical cell atrophy levels; the method first detects the surface layer cells, the middle layer cells and the basal layer cells by using a target detection model, then segments the cell nucleus of each layer of cells detected by using an instance segmentation model, and finally calculates the cell quantity ratio, the nucleus-cytoplasm ratio and the cell crowding degree index of each layer; the indexes are input into a random forest classification model to grade the atrophy degree; it is known through sufficient experimental verification that good effects are achieved in cervical cell atrophy degree discrimination. The application is applied to cervical cell atrophy degree discrimination.

The application provides a cervical cell nucleus image segmentation method and system based on a residual network and a hollow convolution, a low-layer feature extraction network of sequential convolution is reused, low-layer feature information is added to high-layer information, the low-layer information and the high-layer information are complementary, the utilization rate of a low-layer feature layer with more detailed information is improved, and the learning ability of the network for cells is enhanced.

The application discloses a cervical abnormal cell recognition method and device and electronic equipment, and relates to the technical field of cervical cancer detection. The method comprises the following steps: acquiring a cervical cell slice image; inputting the cervical cell slice image into a pre-trained channel separation module to obtain an H image and a DAB image, wherein the H image is a hematoxylin staining image, and the DAB image is an immunohistochemical staining image; and recognizing cervical abnormal cells by using the H image and the DAB image. The technical scheme of the application can obviously improve the cell detection speed, enhance the recognition accuracy and improve the algorithm execution efficiency in cervical cancer positive cell detection.

The invention discloses a cervical cell image classification method based on dynamic topological optimization and Bayesian reasoning. The method comprises the following steps: constructing and pre-training a basic feature extraction model; training a dynamic topology network; carrying out adaptive Bayesian optimization; performing uncertainty quantification and reasoning; image uploading and model selection are realized through a graphical interface, and confidence distribution and a feature heat map of a classification result are displayed to assist clinical diagnosis; according to the method, through the synergistic effect of the stages, the classification accuracy and robustness are remarkably improved.

The invention relates to a multi-round dialogue type intelligent diagnosis interaction system, in particular to a cervical cell panorama-oriented multi-round dialogue type intelligent diagnosis interaction system. The objective of the invention is to solve the problems that existing diagnostic information is single, insufficient in explanatory property and poor in interaction flexibility, and finer diagnostic information is difficult to obtain; the problems that multi-round interaction and context memory ability are lacked, and continuous and coherent response cannot be made in combination with historical information are solved. Comprising an image block acquisition module used for acquiring a pre-processed full slice image WSI; the image segmentation and effective area screening module is used for obtaining effective image blocks; the image-text pair construction and pathological attribute acquisition module is used for forming attribute vectors; the context-aware multi-round question and answer module is used for obtaining a final answer; and the final diagnosis suggestion generation module is used for obtaining a final diagnosis suggestion based on knowledge graph reasoning and probability model prediction. The method is applied to the field of multi-round dialogue type intelligent diagnosis interaction.

The invention discloses a rapid classification detection and positioning method for cervical cancer. The method comprises the following steps: step 1, inputting a training sample and performing data enhancement on the sample; 2, training a multi-task learning model; step 3, carrying out rapid target detection based on YOLOv5; and step 4, generating a classification and positioning result of the cervical cancer cell lesion area. According to the method, a multi-task learning model is adopted, the number of training samples is increased by enhancing and optimizing cervical cell image data, and the problems that the number of the samples is insufficient and categories are unbalanced are solved; a multi-task learning framework with shared features is utilized, classification and positioning tasks are considered, and the accuracy and robustness of the model in cervical cancer detection are remarkably improved; by introducing the YOLOv5 network model, the cervical cell lesion area is rapidly detected and positioned, the extracted lesion area features are classified and regressed, and the method has remarkable advantages in the aspects of detection speed and positioning precision.

The application provides a cervical cancer detection method based on a Simsiam Mae self-supervised model, comprising the following steps: S1, acquiring and preprocessing a cervical cell image; S2, data preprocessing; S3, Simsiam Mae self-supervised model training, wherein the Simsiam Mae self-supervised model uses a contrast learning method to train an encoding path, a projection layer and a prediction layer to extract low-frequency information features of the cell image; a masked image modeling method is used to train the encoding path and a decoding path to extract high-frequency information features of the cell image; S4, downstream task training; and S5, using the trained Simsiam Mae self-supervised model to detect cervical cancer. The application greatly reduces the dependence on artificial labeled data, saves time and cost, and improves the classification accuracy of cervical cell images.

The invention discloses a marker and a probe composition for early diagnosis of high-grade cervical lesions and cervical cancer and application of the marker and the probe composition. The marker is a PDE4B gene. According to the present invention, with the application of the marker, the methylation state of the gene can be sensitively and specifically detected so as to be used for the detection of the cervical exfoliated cell DNA, and the composition is used for the screening of the asymptomatic population in the non-invasive manner so as to reduce the harm caused by the invasive detection; the composition has higher sensitivity and accuracy, and can realize real-time monitoring.

The application relates to the technical field of medical image processing, and particularly discloses a cervical cancer screening pathological large model construction method based on DINOv3-TCT. The technical problem to be solved by the application is that when a general visual Transformer model is directly applied to a cervical cell instance segmentation task, there are problems of mismatch between model internal feature representation and instantiation target and high calculation redundancy. Therefore, the application proposes to transform the DINOv3 encoder: inject a learnable query token at a specific layer, and innovatively construct an instance decoupling loss term acting on an attention weight matrix to explicitly guide the encoder to realize instance-level feature separation during training. The method optimizes the internal attention distribution of the model, improves the accuracy of dense cell segmentation, and simultaneously reduces the model parameter quantity and calculation overhead through integrated design, so that the balance between high accuracy and high efficiency is realized.

The invention provides a primer probe composition for detecting Southeast Asia deletion type alpha-thalassemia and application of the primer probe composition, and belongs to the technical field of disease screening. The primer probe composition can be used for detecting samples with the mutation rate as low as 2% and the mutation gene concentration as low as 101 copies / mu L, and is suitable for trace sample analysis. According to the present invention, the Southeast Asia type alpha-thalassemia with the highest carrying rate is adopted as the breakthrough, the total DNA of the non-enriched cervical exfoliated cell sample can be directly extracted, the ddPCR is adopted to perform absolute quantification on the content of the mutant type alpha gene cluster and the wild type alpha gene cluster in the sample, and the ratio is calculated; the purpose of identifying the genotype of fetal thalassemia through an enrichment-free cervical exfoliated cell specimen is achieved by utilizing the proportion. According to the method, indirect inference of the fetal genotype is realized by dynamically analyzing the wild type / deletion type gene proportion and combining the mother genotype.

The application relates to a sample processing method for cervical exfoliative cell PCR detection, which adopts a sample processing reagent, including a processing liquid, a protection liquid, a conversion liquid, a first purification liquid, a second purification liquid, a third purification liquid and a collection liquid. The processing liquid contains 0.1-0.5N sodium hydroxide and 4-8mol / L urea; the protection liquid contains 1-8mM guanidine isothiocyanate, 0.1-5% SDS, 5-150mM Tris-Hcl and 5-100mM EDTA; and the conversion liquid contains 100-500mM sodium bisulfite, 50-250mM ammonium sulfite, 2-15M ammonium bisulfite, 0.1-3M tetrahydrofurfuryl alcohol, 1-5mM TEPA and 0.1-2M magnesium sulfite. The sample is lysed and protected by the processing liquid and the protection liquid, direct conversion and detection are facilitated, processing time and steps are saved, DNA loss is reduced, cost is saved, the accuracy and reliability of detection results are ensured.

The invention discloses an intelligent labeling method and system for a multi-modal image of a cervical cell, which can realize primary position category labeling and secondary multi-attribute labeling of a multi-target area of a medical image. The system comprises seven modules of image display, prediction assistance, annotation box editing, category label management, attribute label management, annotation storage and annotation recovery, coordinate mapping of an original image and a display image is established through an image scaling factor, loading of pre-training models such as YOLO and the like is supported to automatically generate candidate annotation boxes, and a user can execute operations such as creation and movement on the annotation boxes. According to the scheme, when the image is reloaded, the first-level labeling box and the second-level multi-attribute label can be completely recovered, the cervical cell and pathological image labeling content is effectively expanded, the data reliability is improved, and the method can be directly used for training an interpretable medical image reasoning large model.

This invention relates to the field of sampler technology, specifically to a negative pressure elution cervical exfoliated cell sampler. It includes a sampling rod body, which is a hollow cylindrical structure. One end of the sampling rod body has an operating component, and the other end, away from the operating component, has a sampling head. A piston assembly and a separator are slidably disposed within the inner cavity of the sampling rod body, forming a primary sample mixing chamber for storing irrigation fluid. The operating component has a driving component within its inner cavity. By holding the handle, the sampling rod body and sampling head are inserted into the patient's vagina. Because the diameter of the cylindrical structure of the sampling rod body is significantly smaller than the expansion size of the dilator, it naturally adapts to the human physiological structure without forcibly opening the vaginal cavity. Manually pushing the lever slides within the handle's inner cavity, simultaneously driving the piston rod and piston head to move, causing the irrigation fluid from the primary sample mixing chamber to be sprayed out in a scattering pattern through the sampling hole of the sampling head.

The application discloses a cervical cell detection method based on multi-scale space information and relates to the technical field of medical images. The application combines the advantages of high speed and high precision of Sparse R-CNN, the extraction ability of a multi-scale space information extraction branch and a channel attention module for space features and channel features, and better detection performance is obtained, so that the problem of insufficient detection precision of existing cervical lesion cells is solved.

The application relates to a visual attention-based unsupervised cervical cell instance segmentation method, and relates to the problems of missing labeled data and accurate segmentation of cervical cells in intelligent auxiliary diagnosis technology of cervical cancer. Computer intelligent auxiliary diagnosis technology is widely applied, and cell segmentation technology is the basis of various downstream tasks. A deep learning model needs a large amount of labeled data for training, pixel-level labeling is time-consuming and labor-consuming, and there are impurities such as bacteria, white blood cells and bubbles caused by physiological reasons and film reasons, in addition, there are problems such as overlapping adhesion and visual inseparability of cervical cell images. In order to improve these problems, a visual attention-based unsupervised cervical cell instance segmentation method is provided. Experiments show that the method can effectively improve the accuracy of segmentation and reduce the missing detection problems caused by the interference of impurities and incomplete labels. The application is applied to accurate segmentation of cervical cells under the condition of no label.

1. The name of the design product: brush head for collecting cervical cells. 2. The use of the design product: the product is a device for collecting cervical exfoliative cells of women, mainly used for Papanicolaou smear (PAP) test. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

This invention provides an automated method for evaluating the image quality of LD CytoMatrix 20 slide scans. The algorithm obtains digital images of cervical cells by scanning the entire slide, calculates the information content of each image, and filters out images with acceptable information content. Then, it calculates the sum of the G, R, and B values ​​of the top five images based on their information entropy. The staining condition of the image is determined according to the RGB threshold of a standard image. All images with an information content greater than 2.0 are then input into a three-class focusing model to determine if the image is in focus. Finally, the staining and focusing results are combined to determine the overall image quality of the sample, and a quality score is assigned to each sample image. The LD CytoMatrix 20 slide scan image quality automated evaluation method can efficiently and accurately check the quality of cervical cytology slide images, reducing human error and improving the speed and accuracy of pathological diagnosis. This method is not only applicable to cervical cytology but also widely used in other types of cytopathology and histopathology research.

The utility model discloses a TCT intelligent primary screening device. The device comprises a shell, control buttons are arranged on the two sides of the top of the shell and the middle positions of the two ends of the shell, direction buttons are installed at the two ends of one side of the top of the shell, plugging structures are installed on the two sides and the two ends of the top end in the shell, motors are arranged on the two sides and the two ends of the top end in the shell, and the two ends of the top end in the shell are connected with the control buttons. Servo motors are arranged on the two sides and the two ends of the bottom end in the shell, a connecting rod is arranged in the middle of the bottom end in the shell, a rotating piece is rotationally installed on the top of the connecting rod, and motors are arranged on the two ends and the two sides of the top of the rotating piece. According to the cervical cell detection device, the plurality of carrying pieces are arranged on the rotating piece, a user can detect cervical cells in batches, the detected cervical cells are more, the detection efficiency of the cervical cells is improved, the motor and the lead screw are arranged, and the motor rotates to drive the lead screw to rotate, so that the carrying pieces can be stably lifted, and a kit is convenient to take.

The application discloses a kind of based on position perception and feature modulation cell image multi-task classification method and system, belong to medical image analysis field.The method first utilizes the global visual feature of cervical cell image extracted by depth backbone network, and predicts its hierarchical position (surface layer / middle layer / base layer).On this basis, introduce position perception hybrid expert module, utilize position information by two paths: one will position label be mapped into semantic embedding feature;Another generates channel level modulation parameter according to position label, carries out dynamic affine transformation to global feature, and the feature after modulation is sent into multiple expert networks.At the same time, based on the routing network of image content generates dynamic weight, weights the fusion of expert feature, obtains enhanced feature.Finally, enhanced feature and position semantic embedding feature are fused, and lesion type classification and position classification tasks are collaboratively trained.The application guides feature modulation and expert fusion by position information, effectively improves the accuracy and explainability of cervical cell image classification, and can be used for computer-aided screening of cervical cancer.

The present invention provides a pharmaceutical composition containing a selenium-containing compound and a pharmaceutically acceptable acid selected from citric acid, acetic acid, malic acid, carbonic acid, sulfuric acid, nitric acid, hydrochloric acid, fruit acids, and mixtures thereof for use in reducing the progression of cervical cell abnormalities in a female patient, wherein the patient is p16-positive and Ki-67-positive in at least the cervical region. The composition is applied intravaginally.

The present application belongs to the technical field of slice image recognition, and particularly relates to a cervical cell pathological slice recognition method based on multi-modal learning, which comprises the following steps: acquiring cervical pathological slice images and clinical text data of a patient, extracting image modal feature vectors and text modal feature vectors through an image encoder and a text encoder respectively; inputting the two modal features into a cross-modal fusion network constructed based on an asymmetric attention mechanism, guiding image feature enhancement with the text feature as a query, guiding text feature enhancement with the image feature as a query, and fusing to generate multi-modal joint feature representation; and outputting classification results such as normal cells, low-grade lesions, high-grade lesions or squamous cell carcinoma based on the joint feature representation. Through bidirectional cross-modal attention interaction, the present application realizes effective fusion of pathological image morphological features and clinical text information, and makes up for the limitations of single-modal data.