54 results about "Cervical tissue" patented technology

The invention relates to the technical field of image classification, in particular to a training method and system of a cervical pathological image classification model based on multiple modes. The method comprises the following steps: acquiring a cervical tissue image and carrying out tissue structure segmentation, forming a nucleus-interstitial-epithelium three-distribution framework, collecting development historical data, confirming a prediction trend of each layer, carrying out environment field simulation through the image, generating a simulated cervical environment field, and carrying out hierarchical evolution prediction on the framework. Evolution mapping images are generated according to the evolution data and classified, finally, a visual basic model is obtained through combined modeling training, image-text fusion is achieved, and a cross-center deployment model system is generated. According to the method, vision-language combined modeling is realized, and the stability and controllability of the whole model structure in image space deformation modeling, semantic cross-modal alignment construction and task-level response flow scheduling are improved.

The invention provides a method and device for directly carrying out HPV prediction by utilizing a cervical cell pathology image, electronic equipment, a storage medium and a program, and relates to the technical field of medical image processing, and the method comprises the following steps: S10, data acquisition: obtaining a same-period cervical cell pathology full-slide image of a detected person which has been subjected to cervical tissue pathology analysis and a conclusion of which is evaluated as ASCUS; and S20, lesion area positioning: determining an abnormal cell area in the cervical cell pathological full-slide image by using the trained target detection model. Compared with the prior art, the method has the following beneficial effects: firstly, suspicious cells are screened out through a target detection method, and an existing method in a tissue pathology all-slide image is migrated into a cell pathology image; secondly, due to application of unsupervised learning and an attention mechanism, the model can automatically learn and emphasize the most important features for HPV detection in the image; and thirdly, the HPV infection state of the ASCUS patient is directly and accurately predicted from the cervical image.

The invention discloses a cervical lesion intercellular relation modeling and analysis system based on a graph neural network, and the system comprises a medical image collection module which is used for collecting a digital image of a cervical tissue pathological section or a cervical TCT slide; the cell detection and segmentation module is used for extracting spatial position information and morphological characteristics of cells; the cell feature extraction module is used for extracting and fusing the spatial position, morphology, texture and biological marker features of the cells; the cell relation graph construction module is used for constructing a heterogeneous cell relation graph with cells as nodes and inter-cell relations as edges; the graph neural network analysis module is used for carrying out feature learning and modeling on the heterogeneous cell relation graph; the intelligent auxiliary diagnosis module is used for generating auxiliary diagnosis suggestions; and the data management and automatic control module is used for realizing automatic control and case data management of the whole process of the data. The intelligent and automatic level of cervical lesion cell analysis can be comprehensively improved, and the accuracy and efficiency of diagnosis are improved.

A testing device for determining a stiffness of a patient's tissue is provided herein that includes a probe housing, an internal probe housed in the probe housing, a load cell connected to the internal probe, and a linear-actuator connected to the load cell. The patient's tissue may be joint tissue, cervical tissue, uterine tissue, muscular tissue, and / or pulmonary tissue. The internal probe may be configured to translate within the probe housing, and the linear-actuator may be configured to move the load cell, causing translation of the internal probe within the probe housing. When the load cell is moved by the linear-actuator, the internal probe may translate within the probe housing, and a tip of the internal probe may cause indentation into a patient's tissue.

The invention discloses a cervical tissue pathology image classification method based on a hybrid CNN-ViT architecture, and relates to the technical field of computer vision and deep learning. According to the method, firstly, on the basis of combining CNN and ViT architectures, a linear angle cross covariance self-attention module (LACCSA) and a novel activation function ExpReLU are provided aiming at the defects of an existing method in feature extraction, classification performance and model adaptability; the LACCSA module is combined with cross covariance attention and linear angle similarity to effectively capture a dynamic relationship between global features, subtle differences between classes can be distinguished, common features in the classes can be extracted, and the precision of complex pathological image classification is remarkably improved; the ExpReLU activation function reduces the influence of data distribution offset on the model performance by enhancing the nonlinear expression ability, and optimizes the calculation efficiency at the same time; in combination with the local feature extraction capability of the CNN and the global feature capture capability of the ViT, the method realizes good balance in detail expression and global relationship modeling.

The invention provides a cervical tissue slice lesion diagnosis method and device based on reinforcement learning, and belongs to the technical field of medical diagnosis. The method comprises the following steps: cutting a whole slice image of a standardized cervical tissue slice to be diagnosed according to a preset cutting parameter to obtain an image block, inputting the image block into a visual encoder for feature reasoning analysis to obtain the feature of the whole slice image, calculating the hidden vector of the feature by using a reinforcement learning model, and calculating the hidden vector of the feature. According to the two-dimensional continuous coordinates corresponding to the hidden vectors, indexing of preset iterations is carried out, to-be-diagnosed image block vectors are obtained, an aggregator is used for attention weight distribution, clustering constraint is carried out according to a distribution result, global representation vectors are obtained, the global representation vectors are input into a classification head of the aggregator, and a lesion diagnosis result is output. While high sensitivity is ensured, classification accuracy and focus positioning credibility are remarkably improved, and reliable lesion level judgment is provided for clinicians.

The invention particularly relates to an algorithm based on cervical tissue squamous epithelium lesion diagnosis. The algorithm comprises the following steps of tissue segmentation, region cutting and a classification algorithm. According to the method, multi-step fine processing is carried out on a cervical tissue slice image, for example, in the tissue segmentation stage, gray transformation and Gaussian filtering are adopted to enhance image features, and a cross entropy loss function is used to optimize model parameters; flexible segmentation is carried out according to form contour information during region cutting; in the classification algorithm, image preprocessing and data enhancement are carried out, and a multi-layer neural network is utilized to extract and analyze features, so that squamous epithelium lesion tissues can be identified more accurately, the lesion degree is judged comprehensively, and the diagnosis accuracy is improved.

The present invention proposes a device (100) for collecting cervical tissue samples, comprising: a sample collecting bud (10) connecting to one end of an elongated shaft (21); a holder (20) provided at the other end of the elongated shaft (21); a handle (30) enclosing the elongated shaft (21), wherein the elongated shaft (21) is slidable and rotatable within the handle (30); characterized in that: the sample collecting bud (10) is retractable into the handle (30) and extendable from the handle (30) by moving the holder (20) connected to the sample collecting bud (10) via the elongated shaft (21); wherein the sample collecting bud (10) comprises a star-shaped center cone (11) having a flat tip end, and a plurality of petal-like structures (12) surrounding the center cone (11), each of the petal-like structure (12) having an inner scraping ridge (13) and an outer scraping ridge (14).

This invention discloses a cervical tissue pathology image classification method based on a hybrid CNN-ViT architecture, relating to the fields of computer vision and deep learning. Firstly, based on the combination of CNN and ViT architectures, this invention addresses the shortcomings of existing methods in feature extraction, classification performance, and model adaptability by proposing a Linear Angle Cross-Covariance Self-Attention Module (LACCSA) and a novel activation function, ExpReLU. The LACCSA module, combining cross-covariance attention and linear angle similarity, effectively captures the dynamic relationships between global features, distinguishing subtle differences between categories and extracting common features within categories, significantly improving the accuracy of complex pathology image classification. The ExpReLU activation function enhances nonlinear expressive power, reduces the impact of data distribution shift on model performance, and optimizes computational efficiency. By combining the local feature extraction capabilities of CNNs and the global feature capture capabilities of ViTs, this invention achieves a good balance between detailed representation and global relationship modeling.

The utility model relates to medical instrument technical field discloses a kind of noninvasive cervical cerclage buckles, including flexible kit, one end of flexible kit is provided with upper connecting ring, the other end is provided with lower connecting ring, upper connecting ring inside is provided with the upper annular passage for accommodating first connecting buckle, one end of first connecting buckle enters from the side import of upper annular passage, and it is passed out from the other side export of upper annular passage by the inside of upper annular passage.The utility model is fixed on cervix by setting upper connecting ring and lower connecting ring on the upper and lower ends of flexible kit, and setting the first, second connecting buckle that can be tightened on upper and lower connecting ring, reach the purpose of bundling.Compared with cervical cerclage, it has the superiority of noninvasive, fast, without anesthesia, compared with the cervical support product on market, can provide high-quality individualized product for patient, release the compression to vaginal wall and pelvic tissue, effectively avoid the irritation and harm of operation to cervical tissue.

A cervical dilator comprises a stem comprising a partially or completely dehydrated hydrogel comprising a water-insoluble synthetic hydrophilic polymer capable of radial expansion due to absorption of water from bodily fluids. The cervical dilator softens and matures cervical tissue and dilates the cervical canal through a combination of radial hydrogel stem expansion and osmotic absorption of water from the tissue. The osmotic absorption is caused by at least one osmotically active compound, such as a water-soluble salt, polyelectrolyte, or mixtures thereof, dispersed within the hydrogel. The cervical dilator may also include a non-toxic plasticizer for the hydrogel, such as water.

A diagnosis system for predicting a preterm birth risk includes an artificial intelligence engine comprising a plurality of first classifiers, each having as first input of complex impedances measured at a plurality of different frequencies from cervical tissues during pregnancy and optionally as a second input at least one of preterm history, pregnancy stage, age, pH level, etc., and a Meta classifier configured to output an indication of the preterm birth risk, with as a third input being the outputs of each of the first classifiers, wherein the first and the second inputs are pre-processed using a plurality of different pre-processing methods, each the same or different for each classifier, and wherein the third inputs are post-processed using a plurality of different post-processing methods, each the same or different for the outputs of each first classifiers.

The utility model discloses an adjustable exercise rehabilitation soft brace which comprises a soft brace body, a supporting soft plate is arranged on one side of the soft brace body, air holes are evenly distributed in the supporting soft plate, bandages are evenly distributed on the supporting soft plate, an adjusting mechanism is arranged in the center of one side of the supporting soft plate, and the adjusting mechanism is arranged on the other side of the supporting soft plate. A neck support is arranged above the adjusting mechanism, the dismounting and mounting mechanism is arranged at the top of the adjusting mechanism, and the bottom end of the neck support is connected with the dismounting and mounting mechanism through a mounting piece. By installing the soft brace body, the binding band, the supporting soft plate, the adjusting mechanism, the neck support, the shell, the lifting sleeve, the micro motor and the lead screw, the soft brace body is worn through the binding band, the neck of a patient is supported on the neck support, the neck support is lifted and supported, and then the cervical vertebra of the patient is pulled and fixed; and the traction degree can be automatically adjusted, so that the cervical traction device is more flexible to use.

The invention relates to the technical field of artificial intelligence, and provides a lesion risk prediction method, a lesion risk patient management system, equipment, a medium and a product, and the method comprises the steps: obtaining a risk depth feature, a risk interaction feature and an original risk feature; and inputting the risk depth feature, the risk interaction feature and the original risk feature into a lesion risk prediction model to obtain a risk prediction result of the histopathologic precancerous lesion. According to the lesion risk prediction method provided by the invention, on the basis of the practical situation that precancerous lesion samples are few, prediction comprehensiveness is enhanced through multi-feature cooperation, hidden deep features and risk interaction features in risk depth feature capture data reveal an inter-variable association mechanism, and original risk features reserve original basic data; the three are combined to break through single feature limitation, more comprehensive feature knowledge is added to the prediction model, the generalization ability and prediction precision of the prediction model are enhanced, and thus the risk prediction accuracy of cervical histopathologic precancerous lesions is improved.

Aspects described herein may include a method of diagnosing cervical cancer and pre-cancer conditions, including: utilizing a computer to extract a numerical value corresponding to an order parameter squared (S2) from image data from at least one image of cervical tissue / cells from a patient, wherein the image data includes at least one region having light regions and dark regions, and wherein S2 includes a numerical value quantifying a degree of order present in the image data, and wherein the extracted numerical value comprises a ratio of an area of the light regions to a total area; comparing the extracted numerical value to one or more predefined diagnosis ranges corresponding to stages of cervical cancer and pre-cancer conditions; and diagnosing the stage of the cervical cancer and pre-cancer conditions if the numerical value of the S2 falls within one of the predefined diagnosis ranges.

The invention relates to the technical field of hysteroscopes, and discloses a disposable hysteroscope which comprises a grab handle, a mirror rod is arranged on the grab handle, and a guide head is arranged at the end of the mirror rod; the guide head comprises an abduction lip part and a convergent neck part, a guide hole is formed in the center of the abduction lip part, the mirror rod penetrates through the guide hole, the convergent neck part is arranged on the mirror rod in a sleeving mode, the abduction lip part is in a horn shape, the narrow end of the abduction lip part is connected with the convergent neck part, and the convergent neck part makes friction contact with the mirror rod; the mirror rod is close to the guide hole, so that the open end of the abduction lip part is enlarged. According to the disposable hysteroscope, accurate centering of the disposable hysteroscope and a cervical opening can be automatically completed. When the abduction lip is in contact with the cervix uteri, the elastic petal structure can automatically adjust the angle under the interaction of the propulsive force of the mirror rod and the counter-acting force of the cervix uteri tissue until the center of the guide hole coincides with the center of the cervix uteri opening.

The invention relates to CNF-C / PVA composite hydrogel, a cervical support as well as preparation and application of the CNF-C / PVA composite hydrogel and the cervical support, the composite hydrogel is prepared from raw materials containing carboxylated nanocellulose fibers CNF-C and polyvinyl alcohol PVA through freezing and thawing cycle treatment, and the carboxyl content in the carboxylated nanocellulose fibers CNF-C is 1.7-2.5 mmol / g; the alcoholysis degree of the polyvinyl alcohol PVA is more than 98 mol%, and the polymerization degree of the polyvinyl alcohol PVA is 2200-2500. The cervical support comprises a main body part and a cavity, and the main body part is composed of CNF-C / PVA composite hydrogel. According to the invention, through a nanocellulose fiber compounding and dynamic cross-linking strategy, the mechanical property of the composite material is regulated and controlled, so that the composite material is dynamically matched with the cervical tissue of a human body, reliable supporting force can be provided, and mechanical damage to mucous membranes can be reduced.

The invention belongs to the technical field of biological medicines, and aims to solve the problems of low popularization rate, poor diagnosis sensitivity and specificity, low prediction efficiency and the like of current cervical cancer screening means. The invention provides a cervical cancer biomarker FCGR3B and an application thereof, and further provides an application of the FCGR3B as a cervical cancer diagnosis biomarker in diagnosis of cervical cancer. The biomarker is FCGR3B, and the specific expression level of the FCGR3B in cancer tissues of a cervical cancer patient is up-regulated. The fact that FCGR3B has a good diagnostic value in cervical cancer is evaluated by drawing an ROC curve, and the correlation between SELL and immune cells is analyzed by using a CIBERSORT technology. According to the research, the expression of FCGR3B in cervical cancer is obviously higher than that in normal cervical tissues. FCGR3B may become a biomarker for diagnosis of cervical cancer and a key target for treatment, and provides a new idea and reference for prevention and treatment of cervical cancer.

The invention relates to an early diagnosis reagent for cervical and gastric adenocarcinoma based on multi-marker combination and application thereof, PGC can be used as a new marker for detecting cervical and gastric adenocarcinoma, and PGC is not expressed in other cervical adenocarcinoma and tumors except cervical and gastric adenocarcinoma and normal cervical tissues, and has extremely high specificity; furthermore, the PGC can be combined with the CLDN18.2 and the HIK1083, so that the positive predicted value can be obviously improved.

The invention belongs to the technical field of biological medicines, particularly relates to tumor inhibitory escherichia coli 18 and application thereof, and more particularly relates to escherichia coli HZEc18 and application thereof. According to the present invention, the bacteria in the cervical tissue and the vaginal swab of the cervical cancer patient are subjected to in vitro culture and purification to obtain a plurality of strains having potential influence on the tumor microenvironment, and the Escherichia coli HZEc18 has strong tumor cell inhibition activity and host cell interaction, and can be used for the development of antitumor drugs.

The invention provides a cervical cancer prognosis evaluation kit based on ITM2A mRNA expression level and application of the cervical cancer prognosis evaluation kit, and belongs to the technical field of molecular detection. The kit disclosed by the invention comprises a primer pair capable of specifically amplifying a human ITM2A gene sequence; through detection of expression levels of ITM2A genes and encoded proteins in normal cervical tissues and tumor tissues, it is found that expression of ITM2A in the tumor tissues of cervical cancer patients is remarkably reduced, and a kit for prognosis judgment of cervical cancer is developed based on the discovery. The method has extremely important significance on risk assessment and prognosis prediction of cervical cancer patients.

This invention belongs to the field of biomedical technology, specifically relating to a tumor-suppressive *Escherichia coli* 18 and its uses, and more specifically to *Escherichia coli* HZ_Ec_18 and its applications. This invention obtains multiple strains with potential to influence the tumor microenvironment through in vitro culture and purification of bacteria from cervical tissue and vaginal swabs of cervical cancer patients. Among them, *Escherichia coli* HZ_Ec_18 exhibits stronger tumor cell inhibitory activity and interaction with host cells, and can be used for the development of anti-tumor drugs.

The present invention discloses a postpartum cervical clamp hemostat, comprising two forceps necks and two forceps handles correspondingly assembled with the two forceps necks. A locking rack is respectively arranged on each of the two forceps necks; a plugging groove is arranged on the forceps neck, and the plugging groove is plugged and assembled with a plugging column, and the plugging column is arranged on the forceps handle; a rotating shaft connecting rod is further arranged on the plugging column, and the rotating shaft connecting rod is respectively fixedly assembled with one ends of a first elastic sheet and a second elastic sheet, and the other ends of the first elastic sheet and the second elastic sheet are open ends; forceps blades are arranged on the clamping ends of the forceps necks for clamping an object. The forceps blades of the present invention have a larger area and are provided with a grid, and can clamp the longitudinal blood vessels just entering the uterus and the transverse blood vessels walking in the cervix, and can achieve the effect of clamping the bilateral cervical tissues for hemostasis; the forceps necks have sufficient length to facilitate the operation in the vagina; the forceps handle is detachable, and no discomfort is observed after clamping for a long time.

The invention provides a cervical lesion thermodynamic diagram prediction method and system based on pathological base model fine tuning, a storage medium and a program, and relates to the technical field of medical pathological diagnos.The method comprises the steps that S10, a pre-trained Prov-GigaPath tissue pathological base model is adopted to extract pathological feature vectors of a cervical tissue panoramic digital slice image; s20, executing dichotomy mapping according to the pathological feature vectors, and generating positive probabilities of the sub-regions; s30, generating a highly suspicious sub-region set according to the positive probability of each sub-region; and S40, executing five-classification prediction according to the height suspicious sub-region set, and generating lesion level probability distribution corresponding to each height suspicious sub-region. Compared with the prior art, the method has the following beneficial effects: 1, two-classification and five-classification tasks are decoupled, so that the model complexity is reduced; secondly, fine-grained distinguishing of CINI-III and canceration is achieved through a five-classification grading framework; thirdly, by embedding an uncertainty quantification mechanism, a lesion grading result and model confidence degree evaluation are synchronously output.

The utility model discloses a cervical contractor which comprises an elastic constriction piece which is suitable for being hooped on a cervical canal so as to seal a cervical opening. The elastic contraction piece comprises a lantern ring part and a holding structure, and the lantern ring part is suitable for being arranged on the cervical canal in a sleeving mode; the enclasping structure is arranged in the circumferential direction of the lantern ring part in a surrounding mode and can tighten the cervical canal. According to the cervical contractor provided by the embodiment of the utility model, the cervical contractor can be flexibly hooped on a cervical canal to realize effective sealing of a cervical orifice, so that premature delivery of a fetus is prevented. Compared with a traditional method, the operation process is greatly simplified through the design, complex suture and suture removing processes are not needed, and the infection risk and the complication occurrence rate are remarkably reduced. Meanwhile, due to the elastic characteristic, appropriate adjustment can be conducted according to natural changes of the cervix uteri, the comfort level of the pregnant woman is improved, and discomfort is reduced. In addition, by means of the non-invasive design, damage to cervical tissue is greatly reduced, and psychological burden is relieved.

The invention discloses a lactic acid bacteria bacteriostatic composition, bacteriostatic gel and application. The lactic acid bacteria bacteriostatic composition is prepared from the following raw materials in parts by weight: 15 to 30 parts of lactic acid bacteria powder, 6 to 10 parts of rhizoma bletillae extract, 2 to 6 parts of herba centellae extract, 3 to 5 parts of fructus cnidii extract, 0.8 to 1 part of polyhexamethylene biguanide hydrochloride, 8 to 16 parts of stabilizer and 8 to 14 parts of additive. The lactic acid bacteria bacteriostatic composition has obvious anti-inflammatory and bacteriostatic effects, has a remarkable treatment effect on vaginitis and cervicitis, can effectively improve pathological injuries caused by vaginitis and cervicitis and promote repair of tissue mucosa, and can also promote expression of MKP-1 in cervical tissue, so that inflammatory response is improved, and the anti-inflammatory effect is achieved. Meanwhile, inflammation infiltration of the vagina of the rat is reduced to relieve the symptom of red and swollen vulva, the vaginal flora is protected, a favorable vaginal environment is created, the lactobacillus level is recovered to be normal, and harmful pathogenic bacteria can be inhibited in a targeted manner.

A cervical dilator including a stem comprising a partly or fully dehydrated hydrogel comprising a water-insoluble synthetic hydrophilic polymer capable of radial expansion due to absorption of water from a bodily fluid. The cervical dilator softens and ripens the cervical tissue and expands the cervical canal by a combined action of radial hydrogel stem expansion and osmotic withdrawal of water from the tissue. The osmotic withdrawal is caused by at least one osmotically active compound, such as a water-soluble salt, a polyelectrolyte, or a mixture thereof, wherein the at least one osmotically active compound is dispersed in the hydrogel. The cervical dilator may also include a non-toxic plasticizer of the hydrogel, such as water.

The utility model relates to a cervical hemostatic clip, relates to the technical field of medical instruments, and is used for solving the problems that the clamping force of oval forceps in the prior art is not easy to control, the hemostatic effect cannot be achieved if the clamping force is not enough, and the cervical is damaged and even cervical tissue necrosis is caused if the clamping force is too large. Comprising an upper arc-shaped clamping plate, an upper clamping short handle, a lower arc-shaped clamping plate, a lower clamping short handle and a torsion assembly, the upper clamping short handle is fixedly connected to one end of the upper arc-shaped clamping plate, the lower clamping short handle is fixedly connected to one end of the lower arc-shaped clamping plate, and the upper clamping short handle and the lower clamping short handle are rotationally connected through the torsion assembly. A limiting plate is rotationally installed on the upper clamp short handle, a first limiting block is fixedly installed on the lower clamp short handle, a plurality of second limiting blocks are fixedly installed on the side, close to the first limiting block, of the limiting plate, and the bottom of the first limiting block abuts against the top of one second limiting block.

The present application relates to the technical field of image classification, and more particularly to a training method and system for a cervical pathological image classification model based on multi-modal. The method comprises the following steps: obtaining cervical tissue images and performing tissue structure segmentation to form a three-distribution framework of nucleus-stroma-epithelium, collecting development history data, confirming the prediction trend of each layer, simulating an environment field through images, generating a simulated cervical environment field, and performing layered evolution prediction on the framework, generating an evolution mapping image according to the evolution data and performing classification, and finally obtaining a visual basic model through joint modeling training, realizing image-text fusion and generating a cross-center deployment model system. The present application realizes visual-language joint modeling, improves the stability and controllability of the overall model structure in image space deformation modeling, semantic cross-modal alignment construction and task-level response flow scheduling.

The cervical vertebra tissue retractor with the endoscope channel comprises a drag hook supporting arm and a drag hook piece hung on the drag hook supporting arm, the front face of the drag hook piece is sunken to form the endoscope channel, and a wire clamping part is arranged on the drag hook supporting arm. The retractor adopts the structural design that the retractor and the endoscope channel are integrated, has the advantages of being simple in structure, light and handy, and convenient and fast to use, occupies small space in the area where surgical instruments are located when being placed into a soft electronic endoscope, and can effectively avoid or reduce interference on the surgical instruments.