31 results about "Colposcopes" patented technology

The intelligent gynecological flushing system comprises a gynecological flushing platform, a colposcope image guiding system, a self-adaptive flushing execution system and an evaluation feedback optimization system, and the gynecological flushing platform is used for supporting a patient to conduct gynecological flushing; the colposcope image guiding system is used for collecting colposcope image data, identifying lesion characteristics based on an image identification technology, and transmitting an identification result to the self-adaptive flushing execution system; the self-adaptive flushing execution system is used for carrying out self-adaptive gynecological flushing on the focus part by utilizing flushing fluid according to the guidance of the colposcope image guidance system and based on the basic information of the patient; and the evaluation feedback optimization system is used for collecting the components of the flushing fluid after flushing and the reaction of the flushing part, performing quantitative evaluation on the flushing effect, feeding back the evaluation result to the self-adaptive flushing execution system, and optimizing the self-adaptive flushing parameters of the self-adaptive flushing execution system. According to the invention, the stability and accuracy of the flushing process can be ensured.

The invention discloses a vaginal wall mucosa wrinkle degree evaluation method and system based on image processing, and relates to the technical field of medical image processing, and the method comprises the steps: converting a colposcope image from an RGB space to an LAB space, extracting a brightness channel, and extracting a continuous and significant wrinkle contour through an edge detection algorithm; drawing a binary image for a single connected domain, detecting end points by using a sliding window, recording curve coordinates according to an anticlockwise tracking algorithm, and completing boundary extraction by adopting curvature adaptive downsampling; extracting curve characteristics of each fold; based on the curve data set, adopting a support vector machine classifier to carry out model training, and carrying out form classification on the extracted wrinkle curve; extracting comprehensive curve characteristics, and comprehensively describing the richness and the distribution rule of vaginal wall wrinkles; and selecting a typical sample as a centroid, dividing the feature vector of the to-be-evaluated image to the nearest centroid category through iterative calculation, and outputting an evaluation result of the vaginal wall mucosa wrinkle degree.

The invention relates to the technical field of biological detection, and discloses a reagent composition and a kit for detecting cervical cancer and precancerous lesions of cervical cancer and application of the reagent composition and the kit. The reagent composition provided by the invention is used for detecting the methylation degree of a specific marker gene, and the detection sensitivity and specificity of cervical cancer and high-grade cervical cancer precancerous lesions are at a relatively high level. When the reagent composition is used for screening cervical cancer and precancerous lesions of HPV positive people, compared with conventional cytological detection, the colposcope referral rate is greatly reduced, meanwhile, the detection times for definite diagnosis of high-grade cervical lesions or cervical cancer are reduced, and the waste of medical resources and the examination burden of patients are reduced.

The invention relates to the technical field of image processing, and discloses a cervical lesion prediction method and device based on image processing, and the method comprises the steps: carrying out the imaging of a cervical surface through a colposcope, and obtaining a cervical surface image; analyzing the cervical surface image, and positioning a lesion area; configuring pose parameters of an ultrasonic probe according to the position of the lesion area, so that the ultrasonic probe is aligned with the lesion area for scanning, and an ultrasonic image is obtained; the ultrasonic image is analyzed, and the tissue infiltration depth and the blood flow resistance index of the lesion area are obtained; and predicting cervical lesions according to the tissue infiltration depth and the blood flow resistance index. According to the cervical lesion prediction method and device based on image processing, the colposcope and the ultrasound are combined to detect the cervical lesion in the same process, and the detection accuracy and efficiency are improved.

The invention relates to the field of intelligent medical treatment, in particular to a colposcope image-based data processing and segmentation method, equipment and a program product. The method includes: acquiring a vagina vinegar white image; performing mirror surface area detection on the vagina vinegar white image to obtain a mirror surface area; in the mirror surface area detection, a vagina vinegar white image is converted into an HIS color space to obtain a low-saturation S, high-brightness I and gradient GR three-channel vagina vinegar white image, and a mirror surface area is marked based on the three-channel vagina vinegar white image; and performing priority calculation on each pixel point in the mirror surface area, and performing patch repair processing based on a priority sequence to obtain a processed vagina vinegar white image. The application has good clinical value.

1. Name of the designed product: disposable colposcope. 2. Use of the designed product: colposcope for gynecological examination. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

The application discloses a colposcope cervical lesion segmentation method, system, device and medium based on an aceto-white attention map, and the method comprises the following steps: acquiring a training data set and a test data set; a cervical lesion segmentation model based on a full convolutional neural network, the model comprising two inputs of an aceto-stained colposcope image and an aceto-white attention map; iteratively training the cervical lesion segmentation model based on the training data set; evaluating the cervical lesion segmentation model after training by using the test data set, and the cervical lesion segmentation model meeting the performance requirement can be used for subsequent colposcope cervical lesion area prediction. The application constructs an aceto-white attention map through a pre-aceto-stained colposcope image and a post-aceto-stained colposcope image, and filters interference information such as background in a convolutional coding block output feature map through a spatial attention mode, so that the precision of the full convolutional neural network segmentation model in the colposcope cervical lesion area segmentation task is effectively improved.

The invention discloses integrated colposcope biopsy forceps capable of adjusting tension, and belongs to the field of medical instruments. The switching assembly is arranged on the second forceps tube, a rotating drum in the switching assembly is used for installing a functional assembly, and the functional assembly is used for sampling, hemostasis and disinfection of a pathological part; the sliding of the first pull rod can drive the second pull rod to synchronously slide in the second clamp tube, and the transmission mode can accurately transmit operating force and provide power for the subsequent action of the clamping piece; a pair of pulling pieces are rotationally installed on a second pull rod, when the second pull rod slides, the pulling pieces can rotate, then the clamping piece far away from one end of the second pull rod is driven to rotate around an installation point on a second forceps tube, opening and closing of the clamping piece are achieved, and surrounding tissue of a pathological part can be stably clamped through opening and closing of the clamping piece; good conditions are created for the work of subsequent functional components, and the accuracy of sampling, hemostasis and other operations is prevented from being affected by tissue movement.

The invention relates to the technical field of medical instruments, in particular to a vaginal lubricant and a preparation method thereof.The vaginal lubricant is prepared from, by mass, 0.05-0.5 part of tremella polysaccharide and 0.1-1.5 parts of soluble proteoglycan, all the ingredients are odorless, mild in property, free of vagina irritation and free of adverse reaction on the human body, and the vaginal lubricant is free of side effects on the human body. The tremella polysaccharide with the molecular weight of 1000000-150000 Da and the soluble proteoglycan with the molecular weight of 400000-600000 Da are adopted for compatibility, so that vaginal secretion can be fully absorbed, and the imaging effect of colposcopy is improved; the vaginal dilator has the advantages that the vaginal dilator is convenient to use, vagina injury caused by cervical forceps and other instruments can be quickly repaired, the elasticity of the dilated vagina can be quickly recovered, good lubricity is achieved, friction force between the instruments and a cavity can be reduced to a great extent, and mechanical injury is effectively avoided.

The invention relates to the technical field of medical instruments, and discloses colposcope biopsy forceps capable of synchronously sampling at multiple points, the inner wall of a forceps tube is fixedly connected with three adjustable biopsy forceps components, the inner wall of a handle sleeve is fixedly connected with a synchronous opening and closing driving component, and three movable forceps clips are driven by a telescopic bracket to respectively approach to corresponding fixed forceps clips, so that the synchronous opening and closing of the forceps is realized. Synchronous closing of jaws of the three groups of movable forceps holders and the fixed forceps holder is realized, so that a plurality of tissue samples can be obtained from different parts at the same time in single operation, the biopsy sampling efficiency is improved, and the pain and bleeding risk of a patient are prevented from being increased; the fixed forceps holder and the movable forceps holder are independently moved and adjusted to a preset depth, so that more accurate tissue sampling depth adjustment is realized, and the sampling positioning accuracy and the subsequent sample detection accuracy are improved; independent and rapid collection of a plurality of samples is realized, cross contamination of the plurality of samples is avoided, and the reliability of subsequent pathological results is ensured.

The utility model relates to the technical field of ultrasonic treatment equipment, in particular to an automatic treatment device with image guidance, which is characterized in that a host is arranged on one side of a control console, a follow-up arm is mounted on the control console, a first mounting hole is formed in the working end of the follow-up arm, a colposcope is mounted in the first mounting hole, a treatment arm is mounted at the working end of the follow-up arm, and the treatment arm is mounted on the control console. A second mounting hole and a third mounting hole are formed in the treatment arm, a treatment gun is mounted in the second mounting hole, a laser head is mounted in the third mounting hole, and the laser head, the treatment gun and the colposcope are all connected with the console. A colposcope image corresponds to coordinate information positioned by a laser head, so that accurate positioning and uniform movement of a treatment position are realized, non-uniform speed and inaccurate position of a treatment gun which is manually moved are avoided, and the treatment efficiency is improved; visualization of a real-time path and an ultrasonic dose when the treatment gun works is achieved, the condition of the treatment process is known in real time, the ultrasonic treatment dose is accurately mastered, the treatment position is accurately positioned, and the treatment mode is optimized.

This invention belongs to the field of medical image processing technology and discloses an automatic annotation method and system for cervical lesion areas in colposcopy. The method includes: converting the cervical RGB image to the CIELAB color space to construct an acetic acid sensitivity index map to enhance color difference contrast; inputting the sensitivity index map and the original image into a dual-stream encoding and decoding segmentation network to accurately segment the conversion area; extracting three complementary features within the conversion area: acetic acid reaction features, vascular morphology features, and iodine staining spatial features; outputting four probabilities (normal, CIN1, CIN2, and CIN3) by a multi-branch hierarchical classifier and adjusting the segmentation threshold accordingly; and marking each level of area with different colored contours and indicating the biopsy location with arrows.

A medical assistance device that assists in performing colposcopy includes one or more processors to: identify, based on a plurality of images obtained by continuous image capturing, the continuous image capturing continuously capturing images of a target region to which acetic acid treatment is applied, a time at which a predetermined change associated with acetic acid treatment occurs in the target region or an image captured at the time; and perform, based on the identified time or the identified image, at least one of image capturing condition control in the continuous image capturing, image recording control in the continuous image capturing, and display control of an image recorded by the continuous image capturing.

A method of quantifying progression of pregnancy, includes a) illuminating a uterine cervix with polarized light having a wavelength comprised between 600 and 1100 nm; b) acquiring a plurality of images of the illuminated uterine cervix through a polarization state analyser in respective analysing states; steps a) and b) being performed either once or a plurality of time using polarized light having different polarization states; c) from the acquired images, computing a depolarization parameter over a region of interest of the uterine cervix; and d) quantifying the progression of the pregnancy from said depolarization parameter. An apparatus, based on a colposcope fitted with a controllable polarization state generator, a controllable polarization state analyser and a suitably-programmed computer, for carrying out such a method. A computer program for carrying out such a method.

The invention relates to the technical field of medical artificial intelligence, in particular to a YOLOv8-based multi-modal colposcope image fusion and classification method, system and medium, and the YOLOv8-based multi-modal colposcope image fusion and classification method comprises the following steps: collecting three modal images from a cervical region of the same patient, size normalization and pixel value normalization preprocessing are respectively carried out on the three modal images; the three modal images comprise a collected original image, an acetic acid white image and an iodine test image; respectively and independently inputting the preprocessed three modal images into a shared YOLOv8 backbone network so as to extract depth feature vectors of corresponding modals; constructing a fusion feature vector by using the three extracted depth feature vectors; and inputting the fusion feature vector into a lightweight full-connection network, and outputting an LSIL / HSIL dichotomy probability through a Softmax activation function to complete cervical lesion classification. The technical scheme has the advantage that the cervical lesion classification accuracy is improved through multi-modal image fusion.

The invention relates to the technical field of colposcopes, and discloses a disposable electronic colposcope which comprises a handle shell, a connecting base, an inspection probe arranged on the side wall of the connecting base and a cleaning unit arranged on the handle shell, and the cleaning unit comprises a wiping part and a control part which are arranged on the handle shell. The wiping part comprises a mounting seat arranged at the lower end of the outer wall of the handle shell, a connecting hose arranged on the side wall of the mounting seat, a variable air box arranged at one end of the connecting hose, and a clamping plate arranged at the upper end of the variable air box; the cleaning unit is arranged on the handle, after a medical worker puts the examination probe into the vagina of a patient, the lens can be cleaned through the cleaning unit, and it is guaranteed that after the examination probe enters the vagina of the patient, a clear picture can be transmitted to the background, and observation and judgment of the medical worker are facilitated.

The invention relates to the technical field of image recognition model algorithms, in particular to a construction method of a colposcope intelligent auxiliary diagnosis decision-making system, which comprises the following steps of: S1, widely collecting colposcope image data covering different lesion degrees on the basis of a multi-modal cervical special disease database, marking the image data one by one by a qualified doctor, accurately delimiting a high-risk area of high-level cervical lesions to form a target detection annotation data set; s2, performing data preprocessing on the data obtained in the step S1, including performing systematic cleaning and enhancement processing on an original image, and performing focus area detection processing on the preprocessed data; and S3, inputting the candidate region detected in the step S2 into a feature learning network. According to the method, spatial distribution characteristics of lesion severity are fully considered, and an area with the most likely existence of HSIL is preferentially recommended and covered, so that biopsy targeting and diagnosis efficiency are improved.

The present application relates to the technical field of image recognition model algorithm, in particular to a kind of colposcope intelligent auxiliary diagnosis decision system construction method, step S1, with multi-modal cervical disease database as the basis, the image data of different lesion degrees is widely collected, the image data is annotated by experienced doctor, and the high-risk area of high-grade cervical lesion is accurately demarcated to form target detection annotation dataset;Step S2, data preprocessing is carried out to the data obtained in step S1, including systematic cleaning and enhancement processing to the original image, and lesion area detection processing is carried out to the preprocessed data;Step S3, the candidate area detected in step S2 is input into feature learning network.The method of the present application fully considers the spatial distribution characteristics of lesion severity, preferentially recommends the area most likely to exist HSIL, thereby improving the targeting and diagnostic efficiency of biopsy.

This invention discloses a multimodal cervical precancerous lesion region segmentation method based on the Swin Transformer. The invention proposes the MSS-Net neural network to overcome the shortcomings of existing methods, fully utilizing the feature extraction capabilities of the Swin Transformer to achieve multimodal fusion of acetic acid and iodine test images. First, HSIL+ regions in colposcopy images are collected and labeled. Then, a target inspection algorithm is used to extract the cervical region, removing noise from non-cervical regions. Next, the preprocessed acetic acid and iodine solution images are input into the Swin Transformer feature extraction network to obtain multi-level feature maps. After weighted fusion of the feature maps through a multimodal attention module, the data is input into a decoder module, where cascaded upsampling generates the final segmentation result. Finally, the MSS-Net neural network is trained using the Dice coefficient and cross-entropy loss function to obtain the trained model. This invention achieves relatively accurate segmentation of cervical precancerous lesion regions through multimodal data fusion and enhanced feature extraction capabilities.

This invention discloses a portable colposcope device for cervical lesion screening, belonging to the field of medical device technology. It includes a multi-axis support assembly, a colposcope assembly, a support assembly, and a mobile PC platform. The multi-axis support assembly achieves precise positioning of the colposcope assembly throughout space through five-axis coordination. The support assembly achieves stable fixation through a combination of mechanical limiting and vacuum adsorption. The colposcope assembly is equipped with an electric telescopic rod for fine-tuning the focus. The mobile PC platform features a centralized control device and uses an AI analysis module combined with a case database to assist in diagnosis. This device features a modular design for easy assembly and disassembly, good portability, simple operation, and high diagnostic efficiency and accuracy, making it suitable for various scenarios such as primary healthcare and portable screening.

The invention relates to the technical field of medical instruments. In order to solve the problem of dilatation discomfort in the prior art, the invention provides a colposcope diagnostic system based on air bag self-adaptive dilatation and dual-optical-path cooperative positioning. The system comprises a host, an air bag assembly, a dual-optical-path imaging assembly and a control module. The control module is connected with the air bag assembly, the double-light-path imaging assembly and the main machine and used for coordinating work of all the assemblies. The air bag assembly is used for realizing self-adaptive expansion of the vagina; the double-light-path imaging assembly is used for acquiring images in the vagina; and the host is used for processing, analyzing and displaying the image. According to the colposcope diagnostic system based on air bag self-adaptive expansion and double-light-path cooperative positioning, self-adaptive expansion of the vagina is achieved through the air bag assembly, and the comfort level and adaptability of a patient are improved; the dual-optical-path imaging assembly can synchronously obtain multi-dimensional images, and the lesion positioning and imaging definition is improved; the control module coordinates all the components to work efficiently, the host machine achieves comprehensive image processing, and the diagnosis accuracy and efficiency are remarkably improved.

This invention discloses a cervical image classification method and system based on wavelet transform multimodal fusion, comprising: 1) constructing a multi-branch feature encoding network to process cervical OCT images, colposcopy saline images, iodine smear images, and acetic acid whitening images respectively; 2) introducing wavelet transform to perform frequency domain decomposition on the multimodal images, obtaining high-frequency and low-frequency components, and designing a cross-frequency interaction mechanism to more effectively capture the structural and detailed information of the images, and extracting the features of each modality through a ResNet-18 backbone network; 3) designing a feature fusion module to stack and compress the three colposcopy features, and then concatenate them with the OCT features to form fused features; 4) achieving feature dimensionality reduction through a double fully connected layer, adopting a weighted voting multimodal decision classification strategy, and employing a five-fold cross-validation strategy, combined with a weighted cross-entropy loss function to solve the data imbalance problem; 5) finally classifying using Softmax. This invention can achieve accurate classification of cervical images.

This invention relates to the technical field of vaginal examination and discloses a handheld built-in colposcope, including a handheld casing, an outer tube fixedly connected to one end of the handheld casing, a circular tube rotatably connected inside the outer tube, an energy storage device and a controller fixedly connected inside the handheld casing, a conductive collar fixedly connected to one side of the controller, and a drive wheel mounted on the handheld casing. One end of the circular tube is rotatably connected to the conductive collar, and the drive wheel is connected to a force-distributing component. When the drive wheel rotates, the force-distributing component controls the synchronous rotation of the outer tube. When the pressure device is pressed, the force-distributing component drives the outer tube to rotate at a set angle. The continuous rotation of the casing shaft via the rotating shaft and transmission belt allows for rapid and continuous adjustment of the camera's field of view, facilitating quick positioning of the approximate cervical region by medical personnel. It also assists in observing areas prone to blind spots, such as the cervical lateral wall and posterior fornix. The colposcope can flexibly adapt to differences in cervical displacement and elevation among different patients, eliminating blind spots.

The utility model provides an electronic colposcope supporting frame. Relates to the technical field of medical instruments. The electronic colposcope supporting frame comprises a circular base arranged below a colposcope, a hollow bearing column is fixedly installed at the top of the circular base, an adjusting column is slidably installed in the hollow bearing column, and the top end of the adjusting column extends to the position above the hollow bearing column and is fixedly provided with a concave support. A concave support is fixedly arranged on the outer wall of the hollow bearing column, a connecting rotating shaft is rotatably arranged in the concave support, an adapter is fixedly arranged on the connecting rotating shaft in a sleeving manner, the top of the adapter is fixedly connected with the colposcope, a cable is inserted below the colposcope, a [-shaped connecting frame is fixedly arranged on the outer wall of the hollow bearing column, and a winding roller is rotatably arranged in the [-shaped connecting frame; the winding roller is fixedly provided with a simulation socket. According to the cable winding device, cables can be wound, the cables are convenient to arrange, and the cables are prevented from being lost.

Described herein, the disclosure, in one aspect, relates to simulated cervical tissues composed of a gel and red-toned pigment, wherein the cervical tissue has a first face, wherein the first face includes one or more simulated lesions. Methods for constructing the simulated cervical tissue are also disclosed. Additionally, disclosed are kits composed of two or more simulated cervical tissues as described herein, wherein the simulated cervical tissues are different from each based on (1) the number of simulated lesions on each first face of each simulated cervical tissue, (2) the position of the simulated lesions on each first face of each simulated cervical tissue, or a combination thereof. The simulated cervical tissues and kits described herein are useful training tool for performing colposcopies and cam be incorporated into cervical trainers.

The invention relates to the technical field of gynecological clinical diagnosis, and discloses an intelligent colposcope system based on multi-modal data fusion and AR real-time labeling, and the system comprises an image collection module which is used for obtaining real-time video stream data of a cervical region; the data processing server is in communication connection with the image acquisition module; and the augmented reality display module is in communication connection with the data processing server, the data processing server is configured to execute a first analysis algorithm and a second fusion algorithm, and the first analysis algorithm is used for processing real-time video stream data. A cervix uteri real-time image feature analysis result is deeply fused with HPV typing detection data and patient medical history information, and a quantitative risk score is generated through a linear weighting algorithm, so that evaluation deviation caused by single dependence on images or clinical data is avoided, doctors can be assisted to more comprehensively judge lesion risks, and the risk assessment efficiency is improved. Especially, reliable reference is provided for clinical personnel with insufficient experience, and missed diagnosis and misdiagnosis caused by one-sided information are reduced.

The present application relates to biopsy specimen storage device, specifically relates to a kind of specimen collection storage device for colposcope cervical biopsy, including the bottom rotating disc mechanism and the pipe body loading module of circumferential arrangement, rotating disc mechanism top annular array arrangement is installed with pipe body loading module, the pipe body loading module is used to insert sample tube, the pipe body loading module top is sealed, rotating disc mechanism middle part is fixedly suspended and is installed with for containing tissue large pipe, the large pipe inside is equipped with net dipper, the front of device is equipped with dismounting box, the dismounting box is equipped with middle part dismounting slot, the dismounting slot is used to close dismounting sample tube, the dismounting box is equipped with electronic display window and left and right button.The present application is indicated sampling position by color, after multi-point sampling, without additional handwritten mark to sample, different sample position is different color, corresponding after sampling is loaded closed storage, different common position sample can be continuously operated, avoid the confusion of different patient samples.

The invention discloses a cervical cancer colposcope image cancerous tissue discrimination system based on a subregion. The system comprises a data preprocessing module used for preprocessing a collected cervical cancer colposcope image; the sub-region processing module is used for dividing the preprocessed image into a plurality of sub-regions; the distinguishing and classifying module is used for distinguishing and classifying each input sub-region picture by using a cervical cancer pathological image distinguishing network; the model training module is used for training the cervical cancer pathological image discrimination network and selecting a sub-region with optimal performance; and the result output module is used for discriminating by using the trained cervical cancer pathological image discrimination network based on the sub-region part with the optimal performance and outputting a final discrimination result of the cancerous tissue. By extracting the features of the subregions of the image, the accuracy of cervical cancer lesion classification is effectively improved, and the method has huge potential in clinical application.

The invention discloses a colposcope image processing algorithm based on multi-modal feature fusion. The algorithm comprises the following steps: data acquisition: acquiring a colposcope image acquired by medical equipment; labeling the collected colposcope image, wherein the collected colposcope image comprises a marker of a lesion area and an image category; data preprocessing: carrying out image preprocessing on the colposcope image, carrying out preprocessing on text data, and aligning multi-modal data; dividing the preprocessed data into a training set and a test set; establishing and training a neural network model, wherein the model is used for performing feature extraction and feature fusion to obtain a colposcope image after multi-modal feature fusion; the feature fusion comprises the step of fusing the extracted image features, text features, physiological signal features and laboratory examination result features. Richer and more comprehensive input is provided for the model, so that the diagnosis performance is remarkably improved.

The present application relates to a kind of multi-view fusion cervical precancerous lesion image classification methods based on self-supervised learning, comprising: the video screenshot data of prostate endoscope resection surgery is collected, and pretreatment is carried out, and the optimized model weight is obtained;Second visual Transformer model, third visual Transformer model are obtained after optimization;Cervical precancerous lesion colposcope acetic acid picture classification result and cervical precancerous lesion colposcope iodine picture classification result are weighted fusion, and final classification result is obtained.The present application introduces self-supervised learning method, utilizes a large number of unlabeled medical picture data, improves the generalization ability and classification accuracy of ViT model, i.e., visual Transformer model in cervical precancerous lesion grading;Realize the efficient auxiliary diagnosis of CIN grading, especially in the area of limited medical resources, provide efficient, low-cost solution for automated screening, help doctors improve diagnostic accuracy, and reduce the rate of missed diagnosis, provide important technical support for early cervical cancer prevention.