72 results about "Eye Surgeon" patented technology

A digital medical diagnostic system according to the present invention enables ophthalmologists to view patient and other images remotely to diagnose various conditions. The system includes at least one modality, one or more viewing stations, and an image server. The modality generates patient images associated with examinations, while the image server retrieves and processes information from the modalities. The image server may accommodate modalities utilizing different interfaces and / or formats. The viewing stations enable remote access to the images via a network (e.g., Internet), where the image server provides the interface for a user in the form of screens or web pages for security and viewing of information. The system enables an ophthalmologist or other medical personnel to view and / or manipulate one or more images to enhance diagnosis of patient examinations.

The present invention provides an improved surgical blade and trocar system for accessing the retina and other parts of the eye while doing vitreo-retinal and cataract surgeries, including surgeries for macular degeneration. The eye surgeon uses an improved surgical blade for vitreo-retinal and cataract surgeries having a generally flat, V-shaped, W-shaped, or “extended W” shaped cross-section. Using the improved surgical blade, the surgeon creates a multi-planar, self-sealing surgical wound, first by directing the surgical blade substantially perpendicular to the eye surface, then redirecting the blade to follow the general curvature of the eye globe, and finally redirecting the blade to enter the interior of the eye. The improved surgical blade is used with an improved trocar system having two main parts-a relatively rigid, wide-mouthed outer segment and a generally thin-walled, collapsible plastic polymer or metal mesh sleeve that spans the surgical wound and substantially molds to its contour. The improved surgical blade and trocar system can be adapted for use in either vitreo-retinal or cataract surgeries.

A method is described for designing and optimizing an individual spectacle lens. The invention is characterized in that a draft design is made by an ophthalmologist on a video workstation by means of a computer program; the design is communicated to a manufacturer or an optical computing office; and that the manufacturer optimizes an individual spectacle lens on the basis of these stipulations.

A reading enhancement device for preventing and / or treating presbyopia of the eye. The enhancement device is sutured to an outer wall of the sclera for buckling and compressing a portion of the sclera and the ciliary body inwardly and perpendicular to the plane of the sclera and exerting a posterior compression force toward the vitreous humor in the rear of the eye. The enhancement device includes a compression body with a front of the body having semi-circular convex surface. The convex surface is used for engaging, buckling and compressing both a portion of the sclera and the ciliary body of the eye. The compression body also includes an enlarged, rounded first and second end portions and an elongated center portion with the convex surface formed thereon. Also, the compression body includes a rear having an outwardly extending rib portion with a pair of grooves at opposite ends of the rib portion. The grooves and the enlarged, rounded first and second end portions are used to aid the eye surgeon in suturing and securing the enhancement device to the side of the eye.

The invention provides a diabetic retinopathy grading method based on a depth map network. The actual diagnosis process of an ophthalmologist on the diabetic retinopathy can be effectively simulated;information transmission and integration of disease characteristics are carried out on a plurality of images of a single eye of a patient to obtain a more accurate diagnosis result. The method is characterized by comprising the following steps of S1, performing preprocessing at least including image quality detection and left and right eye classification and recognition on a plurality of to-be-detected eye fundus images of two eyes of a patient to obtain preprocessed eye fundus images; s2, constructing logic diagram data according to the plurality of preprocessed eye fundus images corresponding to the single eye of the patient, wherein the logic diagram data comprises a full-connection diagram taking the plurality of preprocessed eye fundus images as nodes; and S3, inputting the logic diagram data into a pre-trained diabetic retinopathy grading model so as to obtain diabetic retinopathy grade information of the patient.

Provided is an operative keratometer consisting of a built-in bright LED ring light, which uniquely provides immediate direct preoperative confirmation to the ophthalmologist of the proper meridian for astigmatic cuts and the most advantageous location of cataract incisions to minimize postoperative astigmatism. Also provided are methods for using the operative keratometer device to facilitate evaluation of the amount and direction of astigmatism in a patient. Further provided is a movable fixation / centration device and methods for its use to focus the operative keratometer, particularly for treating astigmatism, permitting the ophthalmologist to qualitatively assess both the amount and direction of the astigmatism; to more accurately conduct surgery near the pupil by providing a patient fixation point that permits the ophthalmologist to more precisely control movement of the patient's eye during an ophthalmic procedure; and to provide monocular centration of the patient's eye.

A method for maintaining anterior chamber intraoperative intraocular pressure (IOP) is provided by receiving and / or detecting variables of a surgical system and utilizing those variables to monitor intraoperative IOP. Determining an IOP in real time during a surgical procedure either provides a notification to an eye surgeon or allows a target IOP of the anterior chamber of a patient's eye to be set and maintained.

The invention relates to an automatic classification method for eye refraction correction multi-source data based on XGBoost, and the method comprises the steps: selecting an attribute feature relatedto eye refraction data classification as the most original feature for training by adopoting a scheme of combining the clinical experience of an ophthalmologist with a statistical strategy; based onthe screened data, utilizing an XGBoost algorithm to further perform feature screening according to the feature importance, and selecting related attribute features most related to the target; and based on the selected training samples, considering the problem of sample imbalance, giving different weights to each sample and avoiding setting corresponding early stop functions by training over-fitting, and training an XGBoost model to classify the samples. According to the method, the accuracy of multi-source data classification can be effectively improved, manual intervention is not needed in the training process, the training time is shortened, and the training efficiency is improved.

The invention provides a multi-modal retina image fusion method and system based on image registration. The method comprises the steps of obtaining a retina image pair; preprocessing, obtaining retina edge image pairs, and extracting a feature point set from each retina edge image pair; combining a plurality of feature descriptors to construct a multi-feature difference descriptor, and guiding feature extraction of the feature point set; updating spatial transformation of the source feature point set according to the corresponding relation matrix; performing image registration, and obtaining an image after spatial transformation in combination with the target image; and fusing the image after spatial transformation and a preset reference image to obtain a fused image. According to the method, the defects of insufficient image registration precision and inaccurate image space transformation in a multi-modal retina image fusion process are overcome, and high-precision and high-stability registration performance can be realized. On the basis of high-precision image registration, effective multi-modal eye fundus image fusion is carried out, so that an ophthalmologist can conveniently observe the change of a lesion area.

The invention belongs to the field of medical image processing, and discloses a method for evaluating fundus image quality. The method comprises the following steps: preprocessing an acquired fundus image, and cutting redundant backgrounds around a retina image to obtain an area only containing a retina; then, respectively extracting color, focusing, contrast and illumination features based on thepreprocessed fundus image, and evaluating the color, focusing, contrast and illumination features; and finally, determining an evaluation result of the fundus image based on the confidence coefficient of the feature weighted evaluation, and analyzing a reason causing low imaging quality. Therefore, the method can be used for guiding the retinal image acquisition process, the workload of ophthalmologists in screening is reduced, and the cost effectiveness is improved.

The invention belongs to the field of medical image classification, and relates to deep learning, in particular to a diabetic retinopathy classification device based on local lesion features, which isused for solving the problems of poor classification effect of a depth model on a fundus image, lack of interpretability of a result and the like. According to the method, the global features and thelocal lesion information of the fundus image are extracted respectively, so that the information in the image with serious lesion degree can be fully utilized, and the problem of poor application effect of deep learning in the field of sugar network lesion classification caused by insufficient and unbalanced data volume is solved; in addition, in the local focus information extraction process, the labeling result of the local focus information in the fundus image is output, the problem that the interpretability degree of a deep learning model result is low is solved, and the auxiliary effecton disease diagnosis of ophthalmologists is improved.

An ophthalmic technician is present with a patient in an exam room to operate eye examination equipment and transmit patient information to remote location. At that remote location, a skilled technician is present to provide the necessary optical care, and may operate the phoropter from the remote location. Using video and / or teleconferencing equipment and a phoropter located in the patient examination room along with management software, the system works to determine the final optical prescription for the patient. That information, coupled with findings from other devices which are integrated with the management software, and that the patient uses locally, are reviewed by a remote-based optometrist or ophthalmologist.

Aspects extend to methods, systems, and computer program products for forecasting eye condition progression for eye patients. When a patient visits an eye practitioner, the patient (or when appropriate their guardian) may be interested in the current eye condition as well as a prediction of eye condition progression in the future and / or as the patient ages. Aspects of the invention can be used to predict the progress of an eye condition for a patient (e.g., a child) at a number of different post-examination times after an examination. Predicting the progress of an eye condition for a patient over time can be used to assist the eye practitioner in tailoring a treatment plan and / or tailoring a subsequent examination schedule for the patient.

The invention provides an OCT image recommendation method and device based on artificial intelligence, electronic equipment and a storage medium, and the method comprises the steps: obtaining fundus OCT images, and carrying out the preprocessing of all the obtained fundus OCT images, and obtaining an OCT to-be-detected image set; inputting images in the OCT to-be-detected image set into a network detection model for focus detection to obtain a focus image set; constructing a lesion vector, and screening the lesion image set based on the lesion vector to obtain an effective lesion image set; calculating a focus characteristic index of each image in the effective focus image set; and evaluating images in the effective lesion image set based on the lesion feature indexes to obtain an OCT recommended image. According to the method, the focus characteristic indexes of the OCT images are calculated, and the vectors are constructed according to the focus characteristic indexes for operation to quickly recommend similar OCT images, so that the reading and diagnosis efficiency of ophthalmologists is improved.

The invention relates to a retinal vessel segmentation algorithm based on a level set. At present, in medical clinic, fundus images are an important basis for ophthalmologists to diagnose and treat patients with fundus diseases, and the doctors screen the fundus images and judge lesion types by means of subjective experience so as to give diagnosis. This said medical mode consumes a lot of time, has subjectivity and is easy to miss the optimal treatment time. The method of the invention comprises the following steps: preprocessing a retina image, including single-channel color acquisition, region-of-interest extraction and brightness adjustment; performing retinal image enhancement: enhancing a retinal blood vessel image by adopting a method based on combination of Gabor transformation andhigh-low cap transformation; performing retinal vessel segmentation: using an active contour model mainly, using smooth and closed contour lines for covering the edges of sub-pixels, and obtaining anaccurate segmentation target through energy functional minimization of the active contour model. The invention is used for the retinal vessel segmentation algorithm based on the level set.

A nonaqueous ointment for the treatment of persons who are identified by their ophthalmologist to have an infection of common parasites in and around the follicles of the eyelash. The invention is a highly viscous mixture of inert components and antiparasitic powder, as well as a method of application considering the unique composition's qualities. The unique ointment and application method eradicate the pathogens entirely by taking into account their general behavior and lifecycle. Once an infection is identified using instruments readily available to eye doctors in their offices, the ointment is applied once daily to the base of the eye lashes by an ointment tube with an ophthalmic tip. The ointment is applied shortly before bed, over the course of several months. Existing methods of treatment have additional side effects and are largely ineffective, with the parasites often recovering in number after treatment has ceased. The current invention far exceeds these levels of therapeutic effectiveness and offers a permanent solution to the infection of the follicles.

An ophthalmic technician is present with a patient in an exam room to operate eye examination equipment and transmit patient information to remote location. At that remote location, a skilled technician is present to provide the necessary optical care, and may operate the phoropter from the remote location. Using video and / or teleconferencing equipment and a phoropter located in the patient examination room along with management software, the system works to determine the final optical prescription for the patient. That information, coupled with findings from other devices which are integrated with the management software, and that the patient uses locally, are reviewed by a remote-based optometrist or ophthalmologist.

The method and device for detecting retinopathy of prematurity based on a deep neural network provided by the embodiments of the present invention belong to the field of image processing. The method collects a plurality of fundus image data first, and then labels the plurality of fundus image data based on preset rules to generate image data to be processed; then divides the image data to be processed into training sets according to a preset ratio and a test set; then set up a deep neural network model; then train the deep neural network model based on the training set; then process the data in the test set by the trained deep neural network model to obtain processed The output data; finally obtain the ROP lesion diagnosis result based on the output data. Therefore, human resources can be reduced, detection efficiency can be improved, part of the work of ophthalmologists can be saved, and it has important guiding significance for clinical detection of retinopathy of prematurity.

The invention discloses an image classification method and device based on a residual network, equipment and a medium, and the method comprises the steps: obtaining a data set classified according to data features, and compiling a data interface needed by a convolutional neural network according to the data features; making data set labels, wherein each data set with different data features corresponds to one data set label; constructing a training set and a test set, and dividing the data set into a plurality of equal parts; constructing a deep residual unit, constructing a convolutional neural network, and establishing an image classification model; setting training parameters and a loss function strategy for the image classification model, and determining a classification result output by the classifier; performing network training and network testing on the image classification model; and inputting a to-be-classified image into the image classification model to obtain a classification result. According to the method, the image classification model is constructed to assist doctors in diagnosis, so that the burden of ophthalmologists is relieved, the examination time is shortened, and the time and labor cost for screening pictures corresponding to different grades of diseases are reduced.

The present disclosure describes clinical workflows, methods, and systems used to perform an indirect to direct subjective refraction to a patient with a mobile smartphone application that works as a encrypted remote administration tool in any portable electronic device and interconnect both systems via by 4G, 5G, 6G, or Wifi. According to various embodiments, an eye doctor may utilize a remote administration tool (RAT) or (RAS) remote access software application on a portable electronic device (PED) (smartphone, tablet, or laptop) to view and control the main control base (MCB) anywhere in the world to interconnect both systems. The eye doctor can perform an on-demand live subjective vision refraction via RAT technology. Furthermore, the eye doctor can control the (MCB) that can control, exam chair, digital phoropter, vision chart software, robotic phoropter arm, exam chair height, exam room lights, and near robotic chart arm anywhere in the world.

The invention discloses a diabetic retinopathy image classification method based on an improved ResNeSt convolutional neural network model. The method comprises the following steps: acquiring a lesion image from a hospital; preprocessing the image, manually marking the image by an ophthalmologist, and dividing a data set; establishing a deep learning server platform required by the experiment then, and then writing a python code; introducing two lightweight and efficient convolution operations of OctConv and SPConv into a ResNeSt convolutional neural network, and introducing a learning rate mediation mechanism of Warm Restart and cosine annealing; pre-training the improved ResNeSt network by adopting an ILSVRC2012 data set, and migrating the obtained model to the preprocessed data set for fine tuning; and loading a test set, testing the trained ResNeSt convolutional neural network classification model to obtain a classification result, and judging whether each classification index meets the requirement or not. The diabetic retinopathy image classification method is realized, the improved ResNeSt model is utilized, the operation efficiency and the classification accuracy are high, and the application value is very high.

The invention discloses an eye fundus image optic cup and optic disk segmentation method under a unified framework, and the method comprises the steps: obtaining an eye fundus image before segmentation, and carrying out the image preprocessing operation, such as cutting and rotating; generating a corresponding mask image according to an optic cup and optic disk area marked on the fundus color photo by an ophthalmologist; constructing a deep network for segmenting an optic cup and an optic disk; iteratively training the deep segmentation network by using the mask image and the fundus image, and optimizing network parameters; and segmenting the optic cup and the optic disc, and obtaining the segmentation results of the optic cup and the optic disc by using the trained segmentation network model. The invention provides a deep neural network for optic cup and optic disc segmentation. The deep neural network comprises a multi-scale feature extractor, a multi-scale feature transition and an attention pyramid structure. According to the method, the optic cup and the optic disc can be effectively segmented, the segmentation precision is high, and meanwhile, a new thought is provided for segmentation of fundus images and segmentation of other medical images.

The invention provides a diabetic retinopathy lesion image recognition method based on an attention model, and the method is characterized in that the method comprises the steps: firstly, carrying out the preprocessing suitable for a medical image for an original fundus image in a data set; secondly, constructing an attention network model based on semantic segmentation to perform feature extraction; then, constructing a lesion sensing module, a feature keeping module, a feature fusion module and a head attention module, extracting lesion related information from the extracted features, and generating a lesion detection probability graph; and finally, guiding eye disease screening by using the focus detection probability graph obtained by the attention model according to the input fundus photo, and obtaining a fundus photo recognition result with diabetic retinopathy focus information. According to the method, related focus information in the fundus photo can be effectively obtained, the interpretable focus detection probability graph is generated while the diabetic retinopathy is automatically screened, ophthalmologists can be well assisted in diagnosis, and the method has wide clinical application prospects.

Systems and methods are provided for obtaining sight screenings, optical prescriptions and fittings for eyeglasses and contact lenses. A system can be self-operated through a voice-activated response system that enables an individual to determine one's own refraction, or can be operated with the assistance of a technician. A plurality of customer diagnostic locations can include digital equipment and optical instruments to conduct the sight screening. The data generated at these locations can be transferred to a remotely located eye doctor who interacts with a customer via a live audio-video connection to assist with interpreting the data, diagnosing the customer and operating the instruments at the locations. The eye doctor diagnoses, consults and authorizes the prescriptions for the customer. The customer's data can be sent to a lens laboratory to enable the fabrication, purchasing, and delivery of eyeglasses or contact lenses.

The invention discloses an intelligent automatic eye disease screening robot which comprises a main body used for providing energy and data analysis, a positioning module used for automatically locating eyeballs, a shooting module used for face shooting and eye shooting and a head fixing frame used for fixing the head of a patient. A focusing cylinder is arranged on the rear upper part of the body; The positioning module is embedded in the focusing cylinder, the positioning module comprises a turntable used for rotating and switching the cameras and a positioning block used for locating the cameras, and the shooting module comprises an inner camera used for automatically shooting the ocular surface, the anterior segment of the eye and the fundus and an outer camera used for shooting the human face. Eyeballs of a patient can be automatically located, corneas, irises and retinas of the examined eye are focused, corresponding ocular surfaces, anterior segments and fundus photos are automatically shot; meanwhile, the corneal curvature and diopter of the examined eye are automatically obtained, professional ophthalmologists can be replaced to complete large-scale ophthalmologic comprehensive examination of the patient, and manpower and material resources are saved. The robot popularization is promoted.

The invention belongs to the technical field of surgery cleaning and particularly relates to a postoperative cleaning device for doctors in the ophthalmology department. In order to solve the problemthat since the areas around eyes are sensitive, it is inappropriate to directly use brushes or gauze for binding up and cleaning, a scheme is disclosed. According to the scheme, the postoperative cleaning device includes a cleaning fluid, a supporting rack and a fixing platform welded to the top of the supporting rack; a water storage tank is fixed to the middle of the bottom of the fixing platform through bolts, a flange is fixed to the top of the fixing platform through bolts, and a hydraulic jacking rod is fixed to the fixing platform through the flange; a second thrust ball bearing is welded to the top of an extending rod body of the hydraulic jacking rod, a first fixing plate is fixed to the top of the second thrust ball bearing through bolts, and two steel channel slide rails are welded to the portions, close to the two ends, of the upper surface of the first fixing plate, wherein the openings of the two steel channel slide rails are opposite and parallel to each other. A turntable at the bottom can be automatically rotated to achieve nursing of the eyes according to procedures, and the nursing quality and the nursing scientificity are improved.

The invention provides an ophthalmologic operation head fixing and anti-disturbance device which comprises head fixing and anti-disturbance units which are fixed to the two sides of a head respectively and used in pairs, and each head fixing and anti-disturbance unit comprises a main telescopic device, an upper auxiliary telescopic device, a lower auxiliary telescopic device, a telescopic clamping device and a main controller. A main telescopic device piston in the main telescopic device is controlled by the main controller to move, and auxiliary telescopic device pistons in the upper auxiliary telescopic device and the lower auxiliary telescopic device are controlled by the main controller to move, so that the telescopic clamping device makes contact with the head of the patient, and the head of the patient is clamped. According to the technical scheme, optimal clamping force can be provided for the head of a patient, optimal posture control is provided for implementation of an ophthalmic operation, and operation errors caused by slight vibration and disturbance of the head of the patient during the ophthalmic operation are eliminated, so that the operation quality and speed of an ophthalmologist are improved, the time of the patient in an operating room is shortened, and the pain time is reduced.

A method for adjusting prescription eyeglasses at a remote location based on measured data of a user of the eyeglasses is disclosed. With measurement decals adhered to lenses of the prescription glasses customized for a patient, an optometrist, optician, ophthalmologist, online optical merchant, or supplying lab will be able to have a physical measurement of the patient's segment height and monocular and binocular pupillary distance for improved fitting, thereby providing more comfortable single vision, bifocal and progressive prescription glasses, all without the need for an office visit or additional fees.

The invention provides a deep learning-based human eye parameter measuring method and system. The method comprises the steps: acquiring a human face picture, and extracting a left and right eye imagein the picture; identifying different positions in the left and right eye image by employing a deep neural network, including positions of cornea, scleras and inner and outer canthi; and calculating multiple eye parameters at different positions in the left and right eye image. Meanwhile, equipment realized based on the human eye parameter measuring method and system is provided. The deep learning-based human eye parameter measuring method and system and the equipment provided by the invention can realize automatic recognition and positioning of different parts of human eyes; automatic measurement of eye parameters that an ophthalmologist often needs to measure is realized; and the parameter assistance and support are provided for the ophthalmologist to realize analysis of eye disease conditions.