40 results about "Cervical cells" patented technology

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.

The application relates to a kind of mitochondria-based single cell feature extraction and analysis method and system, comprising: obtaining the multiple modal images such as bright field image, nucleus fluorescent image and mitochondria fluorescent image of single cell;Image preprocessing is carried out to the three modal images obtained;For different structures such as mitochondria, morphological and texture features are extracted, and feature analysis is carried out;Further, through the fusion of mitochondria and machine learning technology, the automatic classification of cells is realized.The application is used for the classification of human cervical epithelial cells (H8) and cervical cancer cells (HeLa), and the machine learning analysis of morphological features and texture features shows the potential of mitochondria in the classification of cervical cells.The application has strong applicability, can be combined with machine learning and other analysis methods, and can be applied to various biological cells, has universality, and is easy to popularize.

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 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 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 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 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 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.

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.

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.

The application provides a cervical cell recognition method and system, and the method comprises the following steps: recognizing qualified field regions in a to-be-detected pathological image; extracting contour coordinate information of each to-be-detected cervical cell in the qualified field regions, segmenting and extracting a feature vector of each to-be-detected cervical cell; and based on the feature vector of each to-be-detected cervical cell, querying in a query set to obtain the category of each to-be-detected cervical cell. The application analyzes the image quality of each field region in the to-be-detected pathological image, thereby ensuring the reliability of the final recognition result output and avoiding prediction deviation and errors caused by low-quality data; each cervical cell in the qualified field region is recognized, thereby ensuring that the main to-be-detected target is not missed, learning the underlying common morphological features of various cervical cells, and reducing the workload of labeling; and through the query classification mode, only a small amount of abnormal cell labeling is required compared with the traditional method, and a satisfactory recognition accuracy can be achieved.

The application discloses a cervical cell classification method based on multi-scale attention feature enhancement, comprising the following steps: S1, extracting multi-scale features by using a deep convolutional neural network; S2, constructing a multi-scale feature pyramid according to a feature fusion method in a FPN; S3, respectively calculating spatial attention and channel attention for each layer of features in the pyramid features, and generating a spatial attention pyramid and a channel attention vector; S4, enhancing spatial attention by using masks obtained by threshold segmentation of the spatial attention pyramid; S5, performing attention weighting on the multi-scale pyramid features in S2 by using the enhanced spatial attention pyramid and the channel attention vector of each layer, so as to obtain a multi-scale attention feature pyramid; S6, respectively constructing a classifier for each layer of features in the multi-scale attention feature pyramid; and S7, performing gradient descent optimization training on the whole network and classifying and predicting cervical cells. The application provides a cervical cell classification model with higher classification accuracy.

The application provides a cervical cell nucleus multi-scale accurate segmentation method based on an HSV channel difference feature, the method first converts an image to an HSV space and extracts a saturation S and a brightness V channel; then, adaptive enhanced difference feature channels are constructed by fusing a weighted difference value and a ratio relationship, the discrimination of the cell nucleus and the background is effectively improved, and the method has strong robustness to staining and illumination changes; subsequently, cell density sensing adaptive CLAHE and gradient guided adaptive median filtering are used for multi-scale enhancement and denoising, interference is suppressed while details are retained; in the segmentation stage, a hierarchical strategy of a global threshold value, a local adaptive threshold value and a morphological gradient enhancement is adopted, and adaptive morphological post-processing and screening are combined, so that accurate and complete segmentation of the cell nucleus in a complex scene is finally realized; the whole process of the application is based on clear image processing principles, does not require large-scale training data, has high calculation efficiency and is easy to integrate into an existing pathological information system.

This invention relates to a lightweight cervical cancer image cell detection system based on causal attention. The system constructs sample data through various modules, using the YOLOv5 model as a foundation. By adding deformable convolutional modules guided by causal attention and employing a lightweight convolutional structure design, the system constructs and trains the model to obtain a cervical cancer image abnormal cell region detection model. This model is then used to identify abnormal cells in images from antigen detection kits. The design improves the feature extraction structure of deep networks, enhancing the model's ability to learn complex and irregular morphological features of cervical cell image regions and its generalization ability to complex backgrounds. Furthermore, by using a lightweight convolutional structure to design a finer neck network, the system reduces the number of model parameters and computational load without compromising model accuracy, thereby efficiently and accurately identifying abnormal cells in cervical cancer TCT images.

The application discloses a kind of based on watershed cervical liquid-based cell segmentation method and system, it is related to cell segmentation technical field.The steps of including image pre-processing, preliminary rough segmentation of watershed, Kmeans target classification and the target optimization of over-segmentation and under-segmentation, solve the problem that threshold segmentation method is relatively inflexible and the segmentation ability of limited and deep learning segmentation method needs a lot of annotation data.For under-segmentation problem of watershed method, the method of secondary thresholding solves the problem of concave point detection and ellipse fitting;For over-segmentation problem, the method of inflation is used to judge again to reduce the rate of missed detection.The cervical liquid-based cell segmentation method of the application can obtain good segmentation effect for cells in cervical cell image.

The present application provides a methylation detection reagent for human cervical cells and a cell type determination method. The present application uses 20 nucleotide sequences specific to methylation abnormalities of human cervical cancer cells as positive and negative reference reagents, respectively, thereby improving the sensitivity and accuracy of methylation detection. The present application uses the average value of the methylation levels of multiple sequences in the 10 specific sequences related to the abnormal increase in the methylation level of cervical cancer cells and / or the 10 specific sequences related to the abnormal decrease in the methylation level of cervical cancer cells to determine whether the methylation level of the test cervical cells is abnormal, thereby determining whether the test cervical cells have differentiated into cervical cancer cells, which has the beneficial effects of high sensitivity, good specificity, and less false positives.

The present invention pertains to the technical field of biomedical testing, and more specifically pertains to a kit and method for detecting methylation of genes in cervical cells. The present invention is used to determine whether a precancerous lesion occurs in a sample by detecting a methylation level of promoter regions of three genes MTHFR, PAX1 and SGSH in the sample, which is easy and convenient to operate, has high detection sensitivity and good specificity, and has a very positive significance for the detection of cervical cancer.

The application discloses a cervical cell seven-classification method and system based on hierarchical routing and boundary expert fusion, and belongs to the technical field of image processing. In order to solve the technical problem that the existing technology directly adopts a single multi-classification model for cell classification, resulting in unreliable gray area boundary discrimination and finally leading to unstable cell classification result discrimination, the application utilizes multi-dimensional morphological indexes and detection confidence to calculate quality points; single cells and cell groups and halo cells are shunted for processing, the cell groups and the halo cells are directly outputted in types, the single cells enter subsequent processes, different morphological cells are avoided from being mixed into the same classifier, the single model training target inconsistency and feature deviation problem is solved; the single cell five-classification basic probability is acquired firstly, target areas of ASC-US and LSIL and ASC-H and HSIL are screened out through boundary uncertainty comprehensive points and quality points, finally probability is obtained through fusion of morphological indexes, bias probability and fusion strength, and the class with the maximum probability is selected as the seven-classification result. The application is used for cervical cell classification.

Embodiments of the present disclosure disclose a slide image processing method, device and equipment based on dynamic consensus. A specific embodiment of the method comprises: generating a multi-modal instruction package according to an obtained original cervical cell image and a pre-trained visual language model; generating an image processing result data package according to an image processing agent group, the multi-modal instruction package and cervical cell retrieval knowledge information; generating a first image processing result according to the image processing result data package and historical weight information; determining a category number mapping relationship according to the obtained first image processing results; dynamically dividing a preset storage space according to the category number mapping relationship to obtain a storage space corresponding to the original cervical cell image; and storing and processing the original cervical cell image according to the storage space and the first image processing result. This embodiment reduces the storage resources consumed, shortens the time consumed for overall classified storage, and reduces the computing resources consumed.

This invention belongs to the field of image classification technology, specifically involving a cervical cell pathology slide classification method based on weakly supervised learning. First, key image patches are screened using a dual index of feature entropy and activation heat, and mapped to instance feature sets. The teacher branch calculates instance attention weights based on package-level labels, outputs package-level predictions after weighted aggregation, and generates soft pseudo-labels by normalizing the weights. The student branch fits the distribution of soft pseudo-labels through knowledge distillation and generates hard pseudo-labels. After fusing distillation and cross-entropy loss, the shared encoder parameters are updated. Finally, the updated encoder parameters are synchronized to the feature extraction stage. The model is iteratively optimized through alternating training by the teacher and student branches and a difficult instance mining mechanism, outputting classification results and generating a heatmap of positive instance location. This invention achieves high-precision instance-level classification and positive region location under weak supervision using only slide-level labels, effectively improving the identification ability of difficult positive instances.