41 results about "Strabismus" patented technology

The invention discloses a strabismus detection method based on causal feature gating, and the method comprises the steps: carrying out the modeling analysis of a causal relationship between a key point coordinate and a strabismus category through a causal discovery algorithm, obtaining a causal relationship model used for determining the causal relationship, screening the key point coordinate based on the causal relationship model, and obtaining a strabismus detection result. Extracting a plurality of causal variables from a plurality of samples of the training sample set according to the causal variable set; and introducing a causal feature gating module between adjacent network layers of the classification model, training the classification model by using a plurality of causal variables, and performing adaptive adjustment on gating parameters in the training process of the classification model until the classification model converges or reaches a preset training round number, thereby obtaining a final classification model. According to the embodiment of the invention, the accuracy of strabismus classification can be improved, and the interpretability and medical application value of the model can be remarkably enhanced.

The present application discloses a strabismus detection method, apparatus and system based on a display device, a device, and a medium. The method comprises: calibrating a detection position of a user on the basis of a reference marker worn by the user, and determining that the user is at a target detection position; in the detection process, in response to a detection control instruction, controlling a display device to display a target image corresponding to an uncovered eye, wherein the target image works in conjunction with a covering unit to achieve a covering effect on the covered eye and display a target optotype visible to the uncovered eye, and controlling an image collection apparatus to collect the change of the uncovered eye being converted from a covered state to an uncovered state; and on the basis of the change of the uncovered eye being converted from the covered state to the uncovered state, determining deviation data corresponding to the uncovered eye. Widely applicable implementation conditions are provided for strabismus screening, so that the difficulty of strabismus detection is reduced, thereby improving the accuracy and reliability of strabismus detection under the guidance of a non-physician.

The application discloses a strabismus detection method based on a causal feature gate, comprising: modeling and analyzing the causal relationship between key point coordinates and strabismus categories by using a causal discovery algorithm to obtain a causal relationship model for determining the causal relationship, screening the key point coordinates based on the causal relationship model to obtain a causal variable set, and extracting a plurality of causal variables from a plurality of samples in a training sample set according to the causal variable set; introducing a causal feature gate module between adjacent network layers of a classification model, training the classification model by using the plurality of causal variables, and simultaneously adaptively adjusting gate parameters in the training process of the classification model until the classification model converges or a preset training number of rounds is reached to obtain a final classification model. The application embodiment can not only improve the accuracy of strabismus classification, but also significantly enhance the explainability and medical application value of the model.

The invention relates to the technical field of endoscopes, and discloses a strabismus endoscope, an assembling method thereof and an endoscope system.The strabismus endoscope comprises an insertion part, the insertion part comprises a tip part, the tip part comprises a main body part, and the main body part comprises a mounting surface used for mounting a camera shooting unit and a lighting unit; the main body part comprises two mounting cavities, the mounting cavities comprise a first cavity and a second cavity, the first cavity is used for mounting the camera shooting unit or the lighting unit, the first cavity is provided with a first opening, the second cavity is provided with a second opening, and the camera shooting unit or the lighting unit can be mounted in the second cavity through the second opening and continuously mounted in the first cavity through the second cavity. According to the strabismus endoscope, the assembling method of the strabismus endoscope and the endoscope system, the problems that in the prior art, when the camera shooting unit and the lighting unit are installed in the tip part, operation is inconvenient, and the tip part is not prone to being decontaminated can be solved.

The invention relates to the technical field of vision detection, in particular to an eye position image analysis system for measuring a strabismus angle of a child. The strabismus measurement reliability is determined based on the difference of position changes of different types of pupil center areas in eye position images of two steering eye positions in a symmetrical eye position pair and the difference of the position relations between the pupil center areas and cornea light reflecting spots in the eye position images; the strabismus measurement reliability is adjusted through the included angle between the steering eye position and the orthogonal direction in all symmetrical eye position centering, the strabismus deviation angle is determined, and then the overall measurement reliability is determined; determining a strabismus measurement value according to the difference of position changes of different types of pupil center areas in the eye position images of the steering eye position and the positive eye position; and adjusting the strabismus measurement value by using the overall measurement reliability of all the steering eye positions, and determining the final strabismus angle under the positive eye position. According to the method, the final strabismus angle is determined by integrating the information of all the steering eye positions, and the dynamic characteristics of intermittent strabismus are effectively captured.

The invention provides a strabismus screening system based on multi-dimensional dynamic eye movement tracking. The strabismus screening system comprises a data acquisition module, a data preprocessing module, a data analysis module and a result feedback module. A cartoon experimental normal form is adopted for an experiment through a domestic Pupil.IO AIO eye tracker, so that the eye movement track is monitored, the stability of a fixation point is dynamically quantified, the dynamic change during jump reaction is captured, multi-dimensional eye movement feature calculation such as sight line difference analysis is carried out, and finally dichotomy result judgment is carried out. The problems of inherent limitation, high equipment price, insufficient clinical suitability of a data analysis model and lack of a standardized process of a traditional inspection method are effectively solved.

A fine-grained strabismus diagnosis method and system using a graph neural network based on causal feature selection, and a device and a medium. The method comprises: acquiring nine facial photographs of a patient, and performing image preprocessing on each of the nine facial photographs, in order to construct a nine-gaze-position image; using an object detection algorithm to detect an orbital region in each gaze position in the nine-gaze-position image, in order to extract feature variables of each gaze position that are related to fine-grained strabismus diagnosis; using a causal feature selection algorithm to select from among the feature variables related to each gaze position key feature variables having a direct causal relationship with fine-grained strabismus diagnosis; and inputting the key feature variables of each gaze position into a graph neural convolutional network model, and performing training and optimization with a strabismus disease dataset by means of a propagation formula, in order to output a fine-grained diagnosis result. Unrelated details are removed from entire facial images, and main eye regions are extracted to construct a nine-gaze-position image, thereby reducing the computational cost; and a causal feature algorithm is used to extract key feature variables of each gaze position, and a graph neural convolutional network model is used to learn the key feature variables of each gaze position, thereby making the graph neural convolutional network model more interpretable, and thus realizing fine-grained strabismus diagnosis.

The application relates to the technical field of knowledge graph, and particularly provides a strabismus three-dimensional mapping method and system based on a knowledge graph, which comprises the following steps: taking a starting point space coordinate, a patient corneal reflection point offset and an eyeball rotation center coordinate as attribute values of an entity node, establishing a directed connection edge between nodes according to a fixed attachment relationship between muscles and eyeballs and between muscles and bone walls in anatomy, and constructing an initial heterogeneous graph by all entity nodes and the directed connection edge; weighting and aggregating attribute values of neighborhood nodes connected by the directed connection edge of each node in the obtained initial heterogeneous graph to obtain an aggregated feature vector of the node; and mapping all node coordinates in each obtained sub-graph to a unified three-dimensional coordinate system, and adjusting the relative positions between the sub-graphs so that all positioning base points are located on a plane. The application realizes systematic mapping and pathological posture analysis of three-dimensional space configurations of eye external muscles of a strabismus patient.

The utility model relates to the technical field of ophthalmology examination instruments, and provides a strabismus measuring instrument which comprises a shell, a measuring window and a camera, the measuring window is embedded in the outer surface of the shell and comprises an electrochromic unit and a control unit, and the electrochromic unit is connected with the camera. The electrochromic unit comprises a shielding area which selectively shields one or two eyes of an observer in a power-on state, and the control unit is used for controlling the shielding area to shield the eyes of the observer; the camera is disposed inside the housing for recording a plurality of images of at least one eye of the observer observing the visual stimulation. According to the scheme, the electrochromic unit is used for shielding light to shield the eye area, the influence of the moving process of the baffle on the watching angle of a patient in the matching process of the servo motor and the baffle is avoided, therefore, the visual traction influence is effectively solved, and due to the fact that the servo motor does not need to be used, the visual effect is improved. And the eye shielding process is quiet and rapid.

The present disclosure relates to a head-mounted device and a strabismus detection system, wherein the head-mounted device comprises: a display module configured to sequentially display a set of visual markers in a plurality of set display regions; an image acquisition module configured to acquire a set of eye images corresponding to each eyeball, the eye images being images of a user wearing the head-mounted device when viewing the set of visual markers displayed in the corresponding display region; a gaze position vector determination module configured to determine a corresponding actual gaze position vector based on each eye image; an offset and angle determination module configured to obtain a target point gaze vector corresponding to each eyeball, determine a corresponding eyeball offset and a first angle based on each actual gaze position vector and the corresponding target point gaze vector; and a strabismus determination module configured to determine that the corresponding eyeball has strabismus when viewing the set of visual markers displayed in the corresponding display region, if the corresponding eyeball offset is greater than a first preset threshold and / or the first angle is greater than a first angle threshold.

The utility model relates to the technical field of strabismus measurement and evaluation, in particular to a strabismus measuring instrument. The strabismus measuring instrument comprises an image capturing module, the image capturing module comprises a main camera located in the middle and 2n auxiliary cameras symmetrically distributed on the left side and the right side of the main camera, and n = 1, 2 or 3. According to the strabismus degree measuring method and device, the multiple cameras are arranged so that the eye images can be captured from different angles, eye movement information can be obtained more comprehensively, errors and deviation possibly caused by a single view angle can be reduced, and therefore the strabismus degree measuring accuracy is improved.

The fusion network based on meta learning and image processing is used for few-sample squint detection, and the problem that performance of traditional deep learning is limited under data scarcity is solved. Iris relative offset ratio (IRDR) features are extracted through an image processing algorithm, and precise classification under the condition of few samples is realized in combination with a meta-learning framework. The method comprises the specific steps of obtaining and preprocessing eye image data, and constructing a network model combining image processing and metric learning. The image processing module carries out gray scale and HSV conversion through a double-branch process, and carries out light reflection point detection and pupil area fitting circle calculation to obtain IRDR features. And the IRDR features are combined with meta-learning results, so that the squint classification accuracy is improved. According to the method, the accuracy rate of 86.2% is achieved in a 5-way 1-shot task, the detection performance under the condition of few samples is remarkably improved, and support is provided for clinical strabismus screening.

The invention discloses an intermittent strabismus-oriented eye position control force evaluation method and system, and belongs to the technical field of vision detection.The method comprises the steps that when preset video content is played, a camera device is used for conducting image collection on the left eye and the right eye of a user, and a plurality of frames of eye position images and the physiological offset amount of the user are obtained; according to the eye position image and the physiological offset, calculating the relative position of the iris of the two eyes in the eye socket to obtain the deviation value of the two eyes of each frame of eye position image; based on the two-eye deviation value, performing potential strabismus frame identification on the eye position image, and outputting a strabismus attack event and a strabismus total duration during a playing period; according to the total effective watching duration and the total strabismus duration of the user, the fluctuation condition of the eye position control force of the user is analyzed, and a control force evaluation result is obtained. Therefore, by implementing the method and the device, objective evaluation of the eye position control force can be realized, and data support is provided for evaluating the development trend of intermittent strabismus and surgical decisions.

The invention discloses a synoptophore, and belongs to the technical field of ophthalmology medical instruments. The synoptophore comprises a display system, an image acquisition system, an optical system, a motion measurement system and a control module, wherein the display system at least can display pictures and is observed by a user through the optical system; the image acquisition system can acquire eye images of the user; the motion measurement system can drive the lens cone to rotate and measure the rotation angle of the lens cone. The control module can analyze and process the eye image of the user to determine the position of a light reflecting spot, or determine the position of the light reflecting spot and the center position of a pupil, and determine the Kappa angle number based on the position of the light reflecting spot, or determine the objective strabismus angle number based on the position of the light reflecting spot, the center position of the pupil and the rotation angle of the lens barrel. Or the subjective squint angle number is determined based on the lens barrel rotation angle. According to the invention, the testee can complete measurement independently by himself / herself, operation by related professionals is not needed, the operation difficulty is reduced, and the user experience is improved.

A VR headset, belonging to the field of head-mounted display technology, addresses the issue that in gaming and entertainment scenarios, the 3D movement of the user's head can easily cause the VR headset's headband to slip. Combined with device play and inertial jitter, this can lead to overall device misalignment and loosening, resulting in optical focusing distance misalignment, blurred images, ghosting, and dizziness. Existing lens adjustment solutions cannot solve the device shifting problem, and long-term use can easily induce latent strabismus. Furthermore, significant offline dizziness can occur when switching between virtual and real scenes. This invention includes a display device with a fixed connecting base on its top. This invention can adaptively follow the 3D movement of the head, solving the headband slippage and overall device misalignment problems, maintaining stable optical focusing, avoiding blurring, ghosting, and dizziness, reducing the risk of strabismus, alleviating offline dizziness, improving wearing comfort, reducing component wear, and adapting to high-motion scenarios such as gaming and entertainment.

The invention relates to an automatic processing method for a strabismus inspection image. The method comprises the following steps: acquiring a shot strabismus image; intercepting an eye region in the strabismus image to obtain an eye region image; identifying an eyeball center point and an iris center point in the eye region image to obtain a left eye offset and a right eye offset; generating an offset distribution map based on the obtained left-eye offset and right-eye offset, and marking the left-eye offset and the right-eye offset from the same image as one group; selecting a midpoint between two points with the minimum left eye offset and the minimum right eye offset as an eye center point and taking an image corresponding to the two points as a front bitmap; and according to the offset directions of the left eye offset and the right eye offset in the same group relative to the center point of the eye, obtaining the remaining eight azimuth images. The sudoku image can be automatically screened out from the multiple shot images, manual screening is not needed, the image processing speed is increased, and the diagnosis and treatment efficiency can be improved. A system for implementing the method and a storage medium for performing the method are also included.

The utility model provides a strabismus measuring instrument which comprises a shell, a display module, an image capturing module, a processing module and an automatic light chopper, the display module, the image capturing module and the automatic light chopper are respectively contained in the shell and are respectively connected with the processing module, the display module is used for displaying visual stimulation for observers to observe, and the processing module is used for processing the image capturing module. The image capturing module is used for recording a plurality of images of at least one eye of the observer observing the visual stimulation, the processing module is used for determining the eye misalignment condition of the observer based on the plurality of images recorded by the image capturing module, and the lens group is used for pulling away a nearby object through an optical method. According to the strabismus measuring instrument, an object near the strabismus measuring instrument is pulled away by 6 m through the lens set, and therefore the technical problem that when an existing strabismus measuring device is used for measuring the strabismus degree by 6 m, a mirror needs to be placed in front of human eyes by 3 m, and application and popularization of the measuring instrument are limited is solved.

The application relates to a method for intercepting an effective imaging scene of large-oblique SAR imaging by radar technical indexes, and belongs to the technical field of large-oblique SAR imaging. According to technical index requirements of a radar signal processor, such as a signal bandwidth, a sampling rate, a pulse accumulation time and the like, which are set by a project, the following specific requirements are calculated: an imaging scene center distance, an imaging width and a resolution in a distance direction and an azimuth direction of an imaging scene in a ground plane, and the like; according to a conversion relationship of oblique plane ground plane coordinate axes, the following are calculated: a distance dimension point number and an azimuth direction pulse pressure accumulation point number of a two-dimensional imaging scene in an oblique plane, so that effective data in data recording is retained, redundant data is removed, time consumption of real-time processing of an imaging algorithm is shortened, and design requirements are met.

The utility model relates to the field of image display, and particularly discloses a dynamic image display device and a strabismus measuring instrument. The close-shot display module is arranged in the frame; the distant view display module is arranged on the edge of the frame; and the control module is electrically connected with the close-shot display module and the long-shot display module respectively, and the control module is used for sending a display signal to the close-shot display module or the long-shot display module to display a dynamic image. According to the utility model, the distance between the device and an observer can be flexibly adjusted, and the attention of the observer is improved by displaying rich and colorful dynamic images, so that the diversified requirements of different observers on the display distance and the image are met.

The application provides a strabismus nine-orientation image classification method and system, which comprises the following steps: based on a preset recognition algorithm and a pre-constructed coordinate system, boundary recognition is performed on a pre-acquired eye image to obtain initial left eye boundary box coordinates and initial right eye boundary box coordinates, a deviation angle is calculated and the eye image is corrected according to the deviation angle to obtain target left eye boundary box coordinates and target right eye boundary box coordinates; based on a preset centroid algorithm and the corrected eye image, target left eye iris centroid coordinates and target right eye iris centroid coordinates are calculated; a preset prediction model is used to obtain a nine-orientation distribution probability of the eye image; based on preset nine-orientation mutual exclusion requirements and the nine-orientation distribution probability of the eye image, the eye image is classified to obtain a strabismus nine-orientation image classification result. The application realizes accurate positioning of the iris position of the eye image, reduces irrelevant information interference, and classifies the iris by combining the mutual exclusion characteristics among the nine orientations, thereby improving the reliability of the eye image classification.

1. The name of the design product: automatic training instrument for strabismus and amblyopia. 2. The use of the design product: vision correction training for strabismus and amblyopia. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective drawing.

To provide a filter, filter set, or apparatus for strabismus examination that enables a more visually understandable examination. [Solution] A transmission-type Fourier transform hologram filter that projects a virtual image by transmitting light from a light source in a straight line, and is brought close to the eye of a subject to cover their field of view, and is used as a filter for strabismus testing to determine the presence or degree of strabismus symptoms based on how the subject perceives the virtual image.

The invention discloses an intelligent vision fixation training instrument and a training method. The method comprises the following steps: generating two point light sources on a screen; automatically identifying pupils of the user, and judging the interpupillary distance; automatically tracking and correcting pupil positions of the user to enable the user to look at the point light source; automatically focusing and synchronously timing; if strabismus or blinking occurs after focusing, stopping the training, and refocusing and timing; if timing reaches a set value after focusing, stopping the training; three groups are trained each time, if the timing of the three groups of training reaches a set value, the three groups of training are judged to be qualified, otherwise, the three groups of training are judged to be unqualified, and the user is prompted to carry out the next fixation training after a period of time. The training instrument comprises a display, a front camera, a voice system, a focusing recognition system, an interpupillary distance calculation system, a timing system, a logic control system and an evaluation system which are connected through a bus. Training can be carried out under the prompt of intelligent voice, and the training result can be intelligently evaluated.

1. The name of the design product: therapeutic instrument (strabismus amblyopia). 2. The use of the design product: the design product is used for the treatment of amblyopia and strabismus. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

The invention relates to the technical field of medical instruments, in particular to a child strabismus postoperative eyeball movement rehabilitation training device and a matched training method.The child strabismus postoperative eyeball movement rehabilitation training device comprises a base provided with a table top, a displayer is arranged on the table top, a moving assembly is installed at the position, corresponding to the displayer, of the table top, and the moving assembly comprises a moving frame; the adjusting frame is installed at one end of the table top, a training instrument is arranged on the adjusting frame, and a fixing assembly is arranged at the position, corresponding to the training instrument, of the adjusting frame; the chin supporting plate is arranged below the training instrument, and an adjusting assembly is arranged between the chin supporting plate and the training instrument; the chin of a patient is lifted through the chin supporting plate, the pressure of the neck of the patient is reduced, the position of the chin supporting plate relative to the adjusting frame can be adjusted through cooperation of the adjusting nut and the adjusting block, the height of the chin supporting plate can adapt to most patients, and the distance between the training instrument and the chin supporting plate can be adjusted through the adjusting threaded hole and the adjusting threaded rod; and the through groove on the training instrument can be more accurately aligned with the eyes of the patient.

The invention discloses a high squint SAR error estimation method and device, electronic equipment and a storage medium, and belongs to the technical field of radar signal processing, and the method comprises the steps: carrying out the distance spectrum division of a frequency domain echo signal of a to-be-measured target, and obtaining the steering vectors of a plurality of sub-spectrum echo signals; carrying out characteristic decomposition on the covariance matrix between the channels to obtain a noise subspace of each sub-spectrum segment; based on a local error estimation model, according to the noise subspace of the sub-spectrum segment and the steering vector of the echo signal of the sub-spectrum segment, solving an inter-channel error of each sub-spectrum segment; and fusing the inter-channel errors of the sub-spectrum segments to obtain a globally optimal channel error estimation value. According to the method, the frequency spectrum is divided in the distance spectrum section, so that the frequency spectrum broadening degree in each sub-spectrum section is effectively constrained, and the problem of estimation misalignment caused by frequency spectrum broadening in a satellite-borne large squint scene can be solved.

The utility model relates to the technical field of medical instruments, and particularly discloses a novel strabismus operation hook which comprises a holding rod, a telescopic sliding block is connected into the holding rod in a sliding mode, a first through hole and a second through hole are formed in the surface of the telescopic sliding block, a first hook body is rotationally connected to the bottom of the first through hole, and a second hook body is rotationally connected to the bottom of the second through hole. An angle adjusting rotating rod penetrates through the second through hole and is in sliding connection with the second hook body, a length adjusting rotating rod penetrates through the first through hole and is meshed with the first through hole, the two hook bodies are arranged at the bottom of the telescopic sliding block and synchronously rotate through a gear meshing structure, and transmission is conducted through the angle adjusting rotating rod; an internal thread in a first through hole of the telescopic sliding block is meshed with an external thread of a length adjusting rotating rod, the holding rod is held by a single hand, a thumb and an index finger are used for rotating corresponding rotary knobs, and therefore when one hand conducts shearing or suturing operation, the other hand independently completes stretching and retracting and angle adjusting of traction and a hook. The independent operation capability of doctors is improved, and the dependence on assistants is reduced.

The application discloses a large squint SAR error estimation method and device, electronic equipment and a storage medium, and belongs to the technical field of radar signal processing, and the method comprises the steps of: performing distance spectrum segmentation on a frequency domain echo signal of a to-be-measured target to obtain a steering vector of a plurality of sub-spectrum echo signals; performing eigenvalue decomposition on a covariance matrix between channels to obtain a noise subspace of each sub-spectrum; based on a local error estimation model, solving a channel error of each sub-spectrum according to the noise subspace of the sub-spectrum and the steering vector of the sub-spectrum echo signal; and fusing the channel error of the sub-spectrum to obtain a globally optimal channel error estimation value. The application effectively constrains the spectrum widening degree in each sub-spectrum by performing spectrum segmentation on the distance spectrum, and can solve the estimation misalignment problem caused by spectrum widening in the spaceborne large squint scene.

1. The name of the design product: conjugate prism. 2. The use of the design product: conjugate prism for strabismus correction training. 3. The design points of the design product: in the combination of shape and pattern. 4. The picture or photo that best indicates the design points: perspective view 1.

The invention discloses a dynamic weighting method for face quality evaluation based on task semantic driving, which comprises the following steps: performing multi-dimensional quality analysis on a to-be-evaluated face image, and extracting nine original scores including the number of faces, secondary copying, overexposure / too dark, blurring, occlusion / incomplete, non-crown-free, posture, eye closing and strabismus; the method comprises the following steps of: mapping a category label or a natural language description of an application scene (such as identification photo auditing, face payment and the like) into a high-dimensional semantic vector through a task semantic encoder; inputting the vector into a dynamic weight generation network, and adaptively outputting a weight coefficient corresponding to each quality dimension to realize sensitivity adjustment of alignment with a service target; and calculating a comprehensive quality score through weighted fusion and applying the score to business decision. According to the method, an end-to-end driving mechanism from task semantics to quality evaluation weight is constructed for the first time, so that a single universal model can flexibly adapt to various heterogeneous scenes, and manual weight configuration or repeated training of a special model is not needed.