Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

82 results about "Colposcopes" patented technology

Instruments inserted into the vagina for examination of the tissues of the vagina and cervix by means of a magnifying lens.

Intelligent cervical cancer screening method based on multi-modal large language model

The invention relates to an intelligent cervical cancer screening method based on a multi-modal large language model, which comprises the following steps: data collection and processing: collecting and processing colposcope images and cervical cancer related medical reports, and pre-training a model for extracting key image and text features and providing input for the multi-modal model to enhance the accuracy and efficiency of cervical cancer screening; setting a multi-modal fusion model; fusing the image features and the text features; model training and tuning: taking the colposcope image and the corresponding text data as input, carrying out joint training on the multi-modal model, and finding an optimal configuration; and model evaluation and verification: carrying out performance evaluation on the model, analyzing the performance of the model on different categories and carrying out clinical verification. According to the method, colposcope images can be efficiently processed and analyzed, cervical cancer screening and diagnosis can be processed, a multi-modal large language model of a medical report can be generated, prognosis prediction, disease progress prediction and risk assessment can be carried out, and doctors can be helped to make more effective diagnosis and treatment plans.
Owner:JIANGYIN MOCHENG MEDICAL TECHNOLOGY CO LTD

Cervical image processing method based on double attention and multi-scale fusion

The invention discloses a cervical image processing method based on double attention and multi-scale fusion, and the method comprises the steps: inputting a pre-obtained cervical image into an optimal cervical image segmentation model obtained through training, and outputting a segmentation mask for obtaining a cervical precancerous lesion and a cervical orifice; and converting the segmented pixel position information of the cervical precancerous lesion and the cervical orifice into relative azimuth information. The precancerous lesion area and cervical orifice segmentation of the colposcope image is realized based on the deep learning algorithm, the cervical precancerous lesion and the cervical orifice can be quickly identified and segmented, the definite diagnosis rate of the precancerous lesion is improved, and the probability of missing detection and false detection in the segmentation process is greatly reduced. Meanwhile, according to the segmentation result of the lesion and the cervical orifice, clinical diagnosis output is simulated, lesion orientation judgment is achieved, and lesion position information is provided for biopsy and subsequent observation and treatment.
Owner:XUZHOU FIRST PEOPLES HOSPITAL

Multi-modal cervical cancer anterior lesion region segmentation method based on Swin Transform

The invention discloses a multi-mode cervical cancer anterior lesion region segmentation method based on a Swin Transform. The invention provides an MSS-Net neural network, and aims to overcome the defects of an existing method and fully utilize the feature extraction capability of Swin Transformer to realize multi-modal fusion of an acetic acid experiment image and an iodine experiment image. The method comprises the following steps: firstly, collecting and marking an HSIL + region in a colposcope image; then, extracting a cervix uteri area by using a target examination algorithm, and eliminating noise of a non-cervix uteri area; then, respectively inputting the pre-processed acetic acid solution image and the pre-processed iodine solution image into a Swin Transform feature extraction network to obtain a multi-level feature map; after the feature maps are subjected to weighted fusion through the multimode attention module, the feature maps are input into the decoder module, and a final segmentation result is generated through cascade up-sampling. And finally, training a neural network MSS-Net by using a Dice coefficient and a cross entropy loss function to obtain a trained model. According to the invention, through multi-modal data fusion and feature extraction capability enhancement, accurate segmentation of the cervical cancer precancerous lesion area is realized.
Owner:HANGZHOU DIANZI UNIV

Intelligent gynecological flushing system and method

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.
Owner:SUZHOU LINATECH MEDICAL SCI & TECH CO LTD

Vagina wall mucosa wrinkle degree evaluation method and system based on image processing

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.
Owner:NANJING MEDLANDER MEDICAL TECH CO LTD

Reagent composition and kit for detecting cervical cancer and precancerous lesions of cervical cancer and application of reagent composition and kit

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.
Owner:CANCER INST & HOSPITAL CHINESE ACADEMY OF MEDICAL SCI +1

Cervical lesion prediction method and device based on image processing

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.
Owner:SUZHOU MUNICIPAL HOSPITAL

Multi-view fusion cervical cancer precancerous lesion image classification method based on self-supervised learning

The invention relates to a multi-view fusion cervical cancer precancerous lesion image classification method based on self-supervised learning, and the method comprises the steps: collecting video screenshot data of a prostate endoscopic resection operation, and carrying out the preprocessing, and obtaining an optimized model weight; a second visual Transform model and a third visual Transform model which are optimized are obtained, and the second visual Transform model and the third visual Transform model which are optimized are obtained; and carrying out weighted fusion on the classification result of the colposcope acetic acid picture of the precancerous lesion and the classification result of the colposcope iodine picture of the precancerous lesion to obtain a final classification result. According to the method, a self-supervised learning method is introduced, and a large amount of label-free medical picture data is utilized, so that the generalization ability and classification accuracy of a ViT model, namely a visual Transform model, in cervical cancer precancerous lesion classification are improved; according to the method, efficient auxiliary diagnosis of CIN grading is achieved, especially in areas with limited medical resources, an efficient and low-cost solution is provided for automatic screening, doctors are helped to improve the diagnosis accuracy, the missed diagnosis rate is reduced, and important technical support is provided for early cervical cancer prevention.
Owner:ANHUI UNIV

Electronic colposcope control method and device, electronic colposcope, medium and equipment

The invention relates to the field of medical instruments, and particularly provides a control method and device of an electronic colposcope, the electronic colposcope, a medium and equipment, and the electronic colposcope comprises a multi-direction trigger function key; the control method comprises the steps of obtaining direction trigger instruction information; the direction triggering instruction information is sent to a vagina lens and / or a colposcope workstation; and controlling a vaginal lens and / or a colposcope workstation based on the trigger instruction information. According to the control method of the electronic colposcope provided by the invention, the electronic colposcope is controlled by triggering the function key in multiple directions, so that the shaking and deviation degree of the lens when the electronic colposcope uses the lens to observe and examine can be reduced. According to the embodiment of the invention, the probability of mistakenly touching the key can be reduced, and the workflow checking efficiency and flexibility are improved.
Owner:EDAN INSTR

Artificial intelligence-based colposcope collection image comparison method and system

The invention provides a colposcope collection image comparison method and system based on artificial intelligence, and the method comprises the steps: carrying out the mixed noise reduction and multi-scale enhancement processing of a 4K original image collected by a colposcope, and obtaining an enhanced noise reduction image; adaptively adjusting the scaling of the enhanced and denoised image based on image feature distribution, and focusing columnar epithelium and squamous epithelium cell features by using an attention convolutional network to obtain a feature focusing image; cross-modal feature fusion segmentation processing is carried out on the feature focusing image, columnar epithelium and squamous epithelium regions are segmented, and segmented region images are obtained; image convolution and topological feature extraction are carried out on the segmented region image, an image adjacent image is constructed, and an image feature vector is obtained; and performing fuzzy similarity measurement and comparison decision processing on the image feature vector to obtain a colposcope acquisition image comparison result. According to the invention, the defect that the consistency and the accuracy are difficult to guarantee when the colposcope collection image is identified manually at present is overcome.
Owner:SHENZHEN LIANAN MEDICAL TECHNOLOGY CO LTD

Specimen collecting and storing device for colposcope cervical biopsy

ActiveCN119700209ASurgical furnitureSurgical needlesCervical biopsyColposcopes
The invention relates to a biopsy specimen storage device, in particular to a specimen collection and storage device for colposcope cervical biopsy, which comprises a turntable mechanism at the bottom and tube body loading modules arranged in the circumferential direction, the tube body loading modules are arranged above the turntable mechanism in an annular array, and the tube body loading modules are used for inserting sample tubes; the upper portion of the tube body loading module is sealed, a large tube used for containing tissue is fixedly installed in the middle of the rotating disc mechanism in a suspended mode, a net bag is arranged in the large tube, a dismounting box is arranged on the front portion of the device, a middle dismounting groove is formed in the dismounting box, the dismounting groove is used for sealing and dismounting sample tubes, and the dismounting box is provided with an electronic display window, a left key and a right key. Sampling positions are indicated through colors, after multi-point sampling, additional handwriting marking on samples is not needed, different sample positions are in different colors, loading and closed storage are correspondingly carried out after sampling, continuous operation can be continuously carried out on samples in different common positions, and confusion of samples of different patients is avoided.
Owner:JILIN UNIVERSITY

Data processing and segmentation method, equipment and program product based on colposcope image

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.
Owner:THE NAVAL MEDICAL UNIV OF PLA

Multifunctional cart

ActiveCN309141199SColposcopesTesting Methods
1. The name of the product under this design: Multifunctional cart. 2. Purpose of the product of this design: used to support and place a handheld colposcope and a display terminal, and provide a certain storage space. 3. The design key point of this appearance design product lies in the shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.
Owner:NANJING MEDLANDER MEDICAL TECH CO LTD

Disposable colposcope

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.
Owner:HUIZHOU LITTLE GOOSE MEDICAL TECH CO LTD

An integrated colposcope biopsy forceps with adjustable tension

ActiveCN121154217BColposcopesBiopsy forceps
The application discloses an integrated colposcope biopsy forceps with adjustable tension and belongs to the field of medical devices, which comprises a first forceps body, a switching assembly arranged on a second forceps pipe, a rotating drum arranged in the switching assembly and used for mounting a functional assembly, the functional assembly being used for sampling, hemostasis and disinfection of pathological parts, a first pull rod, the sliding of the first pull rod being able to drive the synchronous sliding of a second pull rod in the second forceps pipe, the transmission mode being able to accurately transmit operating force and provide power for the action of a subsequent clamping piece, a pair of pull tabs rotatably mounted on the second pull rod, the pull tabs being rotated when the second pull rod slides, and then driving the clamping piece away from one end of the second pull rod to rotate around a mounting point on the second forceps pipe, so that the opening and closing of the clamping piece is realized, the surrounding tissue of the pathological part is stably clamped through the opening and closing of the clamping piece, good conditions are created for the work of the subsequent functional assembly, and the accuracy of sampling, hemostasis and other operations is avoided from being affected by the movement of the tissue.
Owner:THE SEVENTH MEDICAL CENTER OF PLA GENERAL HOSPITAL

Medical adjustable colposcope

The utility model relates to the technical field of medical instruments, and particularly discloses a medical adjustable colposcope which comprises a supporting rod, a sliding rod connected with the supporting rod in an up-down sliding mode, a cube fixed to the top of the sliding rod, a telescopic arm rotationally arranged on the side edge of the cube, and a positioning mechanism arranged in the cube and used for positioning the telescopic arm. A mounting plate is fixed to one end of the telescopic arm, a microscopic colposcope body is arranged on the mounting plate, and a dustproof box capable of containing the microscopic colposcope body is fixed to the side edge of the sliding rod. According to the utility model, the microscopic colposcope body can be conveniently and flexibly adjusted, the efficiency and the accuracy of irradiation detection are improved, and the microscopic colposcope body can be well prevented from dust and protected.
Owner:NANJING GENERAL HOSPITAL NANJING MILLITARY COMMAND P L A

HSIL postoperative cutting edge state prediction method, system, equipment and medium

The invention belongs to the technical field of image processing, and discloses an HSIL postoperative cutting edge state prediction method, system and device and a medium, and the method comprises the steps: obtaining a data set which comprises clinical data of a plurality of patients, colposcope images and corresponding diagnosis labels; inputting the colposcope image of each patient into the risk prediction model for classification prediction to obtain an incisal edge prediction score; screening final features in the clinical data and the cutting edge prediction score based on a feature screening method; constructing a combined model, wherein the combined model is composed of a plurality of machine learning models; training the combined model based on the selected final features, performing verification evaluation, and selecting an optimal machine learning model as a cutting edge state prediction model based on an evaluation result; and executing an incisal edge state prediction task of the patient based on the incisal edge state prediction model. According to the method, the accuracy and effectiveness of preoperative evaluation of the HSIL patient by a doctor can be improved.
Owner:THE SECOND HOSPITAL OF SHANDONG UNIV

A colposcope cervical lesion segmentation method, system, device and medium

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.
Owner:THE OBSTETRICS & GYNECOLOGY HOSPITAL OF FUDAN UNIV +1

A lightweight colposcopy image classification algorithm based on EffiCervNet

The present invention relates to the field of medical image technology, and in particular to a lightweight colposcopy image classification algorithm based on EffiCervNet. The steps are as follows: obtaining cervical colposcopy images as input training data sets; preprocessing the colposcopy image data sets in the training data sets; building a classification model based on EffiCervNet; learning and training the EfficientNet classification model; inputting the cervical colposcopy images in the training data sets into the EfficientNet classification model for training, and saving the trained model. The lightweight colposcopy image classification algorithm based on EffiCervNet provided by the present invention combines the advantages of EfficientNet's high speed and high precision, Cerv‑MBConv's ability to extract spatial features and channel features, and Triplet Attention and ECA's high feature extraction capabilities, while reducing model parameters, better classifies different types of cervix under colposcopy, has higher classification accuracy, and can better classify cervical types, meeting existing medical actual needs.
Owner:CHONGQING UNIV OF TECH +2

A semi-supervised learning method and system for classifying the degree of cervical intraepithelial neoplasia by combining generative adversarial networks

The present invention discloses a semi-supervised learning method and system for classifying the degree of cervical intraepithelial neoplasia by combining generative adversarial networks. The method includes: generating realistic colposcopy acetic acid images based on an improved generative adversarial network GAN, and optimizing the realistic colposcopy acetic acid images through a super-resolution generative adversarial network SRGAN; generating pseudo-labels for the optimized realistic colposcopy acetic acid images based on a deep residual network ResNet, and training the ResNet network based on the optimized realistic colposcopy acetic acid images and images with real labels until the pseudo-labels no longer change, and retaining the trained ResNet network; inputting independent vaginal acetic acid images into the trained ResNet network to classify the degree of cervical intraepithelial neoplasia. The present invention can better adapt to the situation where the coverage of colposcopy image samples is insufficient and reduce the influence of data deviation.
Owner:ANHUI UNIV

Integrated colposcope biopsy forceps capable of adjusting tension

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.
Owner:THE SEVENTH MEDICAL CENTER OF PLA GENERAL HOSPITAL

Vagina lubricant and preparation method thereof

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.
Owner:南京中科拜尔医药集团有限公司

Construction method for predicting lesion model based on HPV infection rate

PendingCN119943153AData visualisationBiostatisticsCervical biopsyColposcopes
The invention belongs to the field of biological information, particularly relates to a construction method for predicting a lesion model based on an HPV infection rate, and more particularly relates to a construction method, device and equipment for predicting a lesion model based on a single infection rate and a co-infection rate of an HPV. The invention provides a construction method for predicting a lesion model based on an HPV infection rate, and the method comprises the steps: obtaining training data, which comprises an HPV typing detection result and a detection result; determining a single infection rate and a co-infection rate according to an HPV typing detection result; according to the HPV typing detection result and the detection result, determining the relationship between the single infection rate and the detection result as well as between the co-infection rate and the detection result; and constructing a model for predicting lesion based on the HPV infection rate according to the relationship with the detection result. By means of the model building method, a prediction model can be built, and lesions such as TCT detection, colposcope detection results and cervical biopsy results can be predicted through the single infection rate and the co-infection rate.
Owner:HUNAN SANWAY CLINICAL LABORATORIES INC

Colposcope biopsy forceps capable of synchronously sampling materials at multiple points

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.
Owner:GENERAL HOSPITAL OF NUCLEAR IND

Automatic treatment device with image guidance

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.
Owner:HAIYING ELECTRONIC MEDICAL SYST CO LTD

Colposcope cervical lesion area automatic labeling method and system thereof

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.
Owner:GENERAL HOSPITAL OF THE NORTHERN WAR ZONE OF THE CHINESE PEOPLES LIBERATION ARMY

Medical assistance device, medical assistance method, and non-transitory recording medium

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.
Owner:CASIO COMPUTER CO LTD

Intelligent cervical cancer screening method based on Unet3 +-Repvg model

The invention relates to an intelligent cervical cancer screening method based on a Unet3 +-Repvang model, which comprises the following steps: collecting colposcope image data, and marking disease positions and categories of images; performing fine tuning and segmentation training by using the pre-trained Unet3 network, and segmenting the image; restoring the segmented binary image corresponding to the original image; performing classification training by utilizing a Repvg model to obtain a symptom to which the colposcope belongs; and extracting features of a newly shot colposcope image through the segmentation model, and finally obtaining final disease prediction through the classification model. According to the method, a reasonable judgment basis is provided for helping a doctor to accurately judge the cervical symptom, relieving the pressure of the doctor and judging whether the patient needs to be further treated and diagnosed or not.
Owner:JIANGYIN MOCHENG MEDICAL TECHNOLOGY CO LTD

Method and apparatus for quantifying the progression of a pregnancy

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.
Owner:CENT NAT DE LA RECH SCI (C N R S) +2