69 results about "Eye Surgeon" patented technology

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 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 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.

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.

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.

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.

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.

The invention discloses an artificial intelligence eye disease screening and diagnosis and treatment system based on an ophthalmic robot, the steps of which are: automatically acquiring image data of an examiner's ocular surface, anterior segment and fundus, and synchronously and automatically acquiring multimodal data such as diopter and corneal curvature; With the above data, deep learning algorithms are used to construct an eye disease screening and diagnosis and treatment system to automatically analyze whether there are lesions in each part of the eyeball of the examinee, and to draw corresponding guidance and referral opinions. The invention can replace the ophthalmologist to perform the task of ophthalmology diagnosis and treatment in areas lacking ophthalmologists, assist ophthalmologists in ophthalmology diagnosis and treatment in large hospitals with a large number of patients, improve the efficiency of diagnosis and treatment, and reduce the harm caused by eye diseases to the crowd.