17 results about "Colposcopes" patented technology

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 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.

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 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 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 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.

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.

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 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.