34 results about "Fundus photography" patented technology

System and Method pertaining to the modification and integration of an existing consumer digital camera, for example, with an optical imaging module to enable point and shoot fundus photography of the eye. The auto-focus macro capability of existing consumer cameras is adapted to photograph the retina over an extended diopter range, eliminating the need for manual diopter focus adjustment. The thru-the-lens (TTL) auto-exposure flash capability of existing consumer cameras is adapted to photograph the retina with automatic flash exposure eliminating the need for manual flash adjustment. The consumer camera imaging sensor and flash are modified to allow the camera sensor to perform both non-mydriatic focusing of the retina using infrared illumination and standard color flash photography of the retina without the need for additional imaging sensors or mechanical filters. These modifications and integration of existing consumer cameras for fundus photography of the eye significantly improve ease of manufacture and usability over existing fundus cameras.

An ophthalmic photographic apparatus comprises a photographic mask for defining a fundus photography range, a photographic stop for eliminating light reflected from an anterior portion of the eye, and a focusing lens for bringing the fundus into focus. Interlocking means are provided to move the photographic mask and the photographic stop in an interlocked manner relative to the movement of the focusing lens in such a way that with respect to a photographic optical system the photographic mask may be kept at a position substantially conjugate with an imaging plane of a CCD and the photographic stop may be kept at a position substantially conjugate with an anterior portion of the eye. The CCD is located at the image-side focal plane of the image-formation lens, the mask is located on the object-side focal plane of the focusing lens, and the photographic stop is located on the image-side focal plane of the focusing lens. These three components are moved as one unit when the system is adjusted to focus on the fundus.

The invention discloses a detection unit for subject fundus photography. The detection unit for subject fundus photograph comprises an objective lens, a camera, polarizing illuminating beams, a polarizing splitter, a diaphragm, a white light source and an infrared light source. The objective lens is disposed at a first end point of the detection unit and is used for limiting an optical axis and an operating interface of the detection unit. The camera is disposed at a second end point of the detection unit and is used for automatically focusing and photographing subject fundus. The polarizing illuminating beams include a white illuminating beam for subjective fundus photography and an infrared calibrating beam for automatic focusing. The polarizing splitter is slantingly disposed on the optical axis and transmits polarized light from the polarizing illuminating beams. The diaphragm is disposed in front of the camera and is conjugate with the operating interface. The white light source is synchronous with a camera flash light and provides a white beam in the polarizing illuminating beams. The infrared light source provides the infrared calibrating beam in the polarizing illuminating beams to enable the camera to automatically focus. The invention further discloses a detection module for subject fundus photography.

The invention provides a diabetic retinopathy fundus photography standard image generation method, which comprises the following steps: 1) enabling a collected non-standard fundus image to be generated into a new sample image through a generation model; 2) carrying out local feature extraction on the new sample image; and 3) comparing local features of the non-standard image with local features of a standard image in a discrimination model, if the local features are consistent, outputting the new sample image, that is, the generated standard image, and if the local features are not consistent, adjusting the new sample image. The provided method is simple and effective; the definition of the generated standard image reaches requirement of an intelligent aided diagnosis system; and accuracy of diagnosis is improved.

The invention discloses fundus imaging equipment for clinical diagnosis. The fundus imaging equipment for the clinical diagnosis consists of a light source component, a two-dimensional scanning component, a relay lens component, a detector component and a field-of-view target component. According to the fundus imaging equipment for the clinical diagnosis, an observation direction of a patient is fixed by utilizing the field-of-view target component, a retina of a human eye is scanned by using the two-dimensional scanning component, the detector component and an optical amplifier of the detector component optically enlarge a signal reflected by the retina to enhance the signal-to-noise ratio of an image, and a high-resolution image of the retina is acquired through the detection of a confocal signal; according to the fundus imaging equipment for the clinical diagnosis, the influence of field curvature and aberration in an imaging view field is reduced by the special design of a wide-field lens of the relay lens component, and the wide-field imaging of 30 to 60 degrees is realized by adjusting an eyepiece; high-resolution fundus imaging equipment which is compact is design and is applicable to the clinical diagnosis is fulfilled by the schemes of light source fiber input and optical signal fiber output, so that the imaging quality of the traditional fundus photography system is greatly improved, the imaging view field is greatly increased, and the clinical operability of equipment is strengthened; and the fundus imaging equipment for the clinical diagnosis particularly can acquire high-resolution images of retinas of human eyes under the condition that the retinas reflect weak signal light, and is used for the clinical diagnosis of fundus diseases.

A solution for optical detection of the eye. Molecular markers are used for high-contrast diagnosis of eye diseases, other diseases, and other vital parameters which can be diagnosed in the eye. For optical detection of the eye, a molecular marker with spectral characteristics of absorption and / or scattering in the visual and infrared spectral region is introduced into the eye and bound to a specific target. The interaction of the molecular marker with the target is detected by means of optical imaging methods, such as fundus photography, confocal laser microscopy, polarisation-optical imaging methods, holographic methods or especially OCT methods. The use of optical methods is strongly preferred for the diagnosis of the eye as a result of the high transparency of the optical system of the eye compared to other body parts.

A fundus photography apparatus is provided that enables optimal adjustment of exposure values according to the color characteristics of the anterior ocular segment of the subject eye. The fundus photography apparatus comprises means for photographing the anterior ocular segment of the eye, means for photographing the eye fundus, and means for detecting the spectral distribution of the iris of the eye based on images of the anterior ocular segment. The photographic exposure value is adjusted in preparation for fudus photography based on the detected spectral distribution of the iris.

The invention discloses a method for detecting glaucoma image based on fundus photography depth learning. The method preprocesses a original fundus image collected and marked from a database to obtaina training sample fundus image and form a training database, performs augmentation to obtain an augmented training database, establish a convolutional neural network comprising a multilayer neural network structure, and inputs the augmented training database into the convolutional neural network for training, and aiming at the fundus image to be detected, inputs the fundus image to be detected into a trained convolutional neural network to obtain an output value of the last layer of neural network structure thereby judging the glaucoma. The method for detecting glaucoma image based on fundusphotography depth learning can continuously optimize the data characteristics and the parameters of the convolutional neural network used for judgment, so that can greatly improve the accuracy, sensitivity and specificity of glaucoma image detection , and save medical resources.

System and Method pertaining to the modification and integration of an existing consumer digital camera, for example, with an optical imaging module to enable point and shoot fundus photography of the eye. The auto-focus macro capability of existing consumer cameras is adapted to photograph the retina over an extended diopter range, eliminating the need for manual diopter focus adjustment. The thru-the-lens (TTL) auto-exposure flash capability of existing consumer cameras is adapted to photograph the retina with automatic flash exposure eliminating the need for manual flash adjustment. The consumer camera imaging sensor and flash are modified to allow the camera sensor to perform both non-mydriatic focusing of the retina using infrared illumination and standard color flash photography of the retina without the need for additional imaging sensors or mechanical filters. These modifications and integration of existing consumer cameras for fundus photography of the eye significantly improve ease of manufacture and usability over existing fundus cameras.

The invention relates to an autonomic fundus photography imaging system and method. The autonomic fundus photography imaging system comprises a fundus photographing device, a pupil auxiliary accurate locating device and a lower jaw supporting system (3), the fundus photographing device comprises a fundus camera (4) and a optical locating sensor (2) which are fixed on a mobile operation platform (7), the pupil auxiliary accurate locating device comprises a controller and a driving mechanism, the controller is separately connected with the driving mechanism, the fundus camera (4) and the optical locating sensor (2), the driving mechanism is connected with the mobile operation platform (7), and the lower jaw supporting device (3) is arranged opposite to the fundus photographing device. Compared with the prior art, the autonomic fundus photography imaging system based on the existing fundus photographing method, is additionally provided with the pupil auxiliary accurate locating device and the optical locating sensor, achieves double-eye searching and optical axis alignment, conducts autonomic accurate fundus photographying, and has the advantages of high efficiency and accuracy.

The invention discloses a diabetic retinopathy screening method and device and a storage medium. The diabetic retinopathy screening method specifically comprises the steps that a deep convolution neural network model is built in advance through a series of methods including construction of a double-vision mydriasis-free fundus photography picture set, picture preprocessing, model design, model training and verification, and result judgment; when diabetic retinopathy results of a patient need to be screened, double-vision mydriasis-free fundus photography pictures of the to-be-screened patientare obtained, and then the pictures meeting quality requirements are input into the pre-constructed convolution neural network model so that diabetic retinopathy results can be easily and convenientlyobtained. Compared with the prior art, the screening method is simple, convenient to use and good in compliance, and also has the advantages of being high in accuracy, sensitivity and specificity.

The invention discloses a blood vessel, artery and vein identification method for fundus photography. Each position in the fundus photography is automatically positioned and measured to achieve an effect on pre-screening diseases, pictures with lesion suspicions can be automatically screened so as to accurately and effectively carry out mark identification on blood vessel contours and blood vesselarteries and veins, then, the diameter ratio of arteries and veins can be calculated to assist in diagnosing diseases, including retina blood vessels and the like, and the workloads of doctors are reduced. In addition, the result of the method does not depend on the experience of doctors and is more objective, doctors can be effectively assisted in diagnosing diseases, and a purpose of remote consultation is realized.

An adaptor for attachment to an image acquisition device, the image acquisition device having one or more camera apertures for enabling capture of one or more images entering the image acquisition device via the one or more camera apertures. The adaptor has a housing defining a passage along which light waves may travel, an objective lens arrangement within the passage, a secondary lens arrangement within the passage positioned such that, when the adaptor is attached to an image acquisition device, the secondary lens arrangement is along a possible light pathway between the objective lens arrangement and one or more camera apertures. The lens arrangements are together configured to magnify an image of a pupil of the eye in proximity to a plane of one or more camera apertures and to focus light waves from a light source at a point external of the adaptor and offset from the optical axis of the objective lens.

The invention relates to a self-timer type shared fundus photography device. The self-timer type shared fundus photography device comprises a lower jaw fixing device for fixing the lower jaw of a self-examiner, a fundus imaging device for taking a fundus image of the self-examiner by adopting a visual target focusing and automatic focusing technology and receiving personal information input of theself-examiner, a fundus image quality evaluation module for judging whether the fundus image meets preset requirements, displaying the fundus image for the self-examiner to choose to submit or retakewhen the fundus image meets the preset requirements, and converting the fundus image into a fundus image with a set file format when a submission instruction is selected, and a fundus image sharing module for storing the personal information of the self-examiner and the corresponding fundus image converted into the set file format for sharing and calling. The self-timer type shared fundus photography device provided by the invention can realize self-photographing of fundus images of patients, avoids operations of medical personnel, realizes digital shared storage and retrieval of fundus imagedata and report information between hospitals, greatly reduces repeated examination, saves medical resources and patient expenses, and is beneficial to rational utilization of medical information.

The invention discloses a retinal fundus image bleeding detection method. A fundus image photographed by a color digital non-mydriatic fundus camera is utilized. The method adopts the following steps that (1) the size of an original image is adjusted; (2) the viewing field of the adjusted image is positioned; (3) bleeding and blood vessel areas based on double-scale background are crudely detected; (4) the blood vessels are detected; (5) a bleeding suspicious area is iteratively positioned; (6) feature extraction is performed on the bleeding suspicious area; and (7) classified detection is performed on the bleeding suspicious area, and the bleeding marked fundus image is generated. According to the method, the fundus image acquired under different acquisition conditions can be processed, the bleeding area can be rapidly and effectively detected and the bleeding site of the processed fundus image is visual and obvious so that further diagnosis is facilitated for ophthalmologists.

The invention provides a cataract patient visual impairment degree evaluation system based on an AI technology. The cataract patient visual impairment degree evaluation system comprises an information acquisition module, a fundus image acquisition module, an image identification module, an image classification module, a disease condition evaluation module and a diagnosis and treatment suggestion module. Whether a patient suffers from cataract or not is automatically screened according to the fuzzy degree information in the mydriasis-free fundus image, and then the visual impairment degree of the fundus image marked with cataract is interpreted and graded, so that diagnosis and treatment suggestions are given in a targeted mode for patients with different degrees of visual impairment caused by cataract. According to the method, the relation between the severity of the cataract and the degree of visual impairment can be visually reflected, the accuracy of the evaluation result can be improved, and meanwhile, the process of screening the cataract through fundus photography has the advantages of being simple and rapid.

A wide-field fundus indirect ophthalmoscopy method and apparatus are provided that can be miniaturized to be suitable for employment in a smartphone and that overcome limitations of existing smartphone wide field fundus imaging devices and methods, such as high cost, clinical deployment challenges and limited field of view. The wide-field fundus indirect ophthalmoscopy method and apparatus are also well suited for use in rural and underserved areas where both expensive instruments and skilled operators are typically not available. The wide-field fundus indirect ophthalmoscopy method and apparatus enable wide-field snapshot fundus images to be captured with wide fields of view (FOV) under mydriatic and non-mydriatic conditions and also enables video recordings of the fundus to be captured from which montages can be constructed with even wider FOVs.

The invention discloses a head fixing part for fundus photography examination. The head fixing part comprises a camera base and a handrail, wherein a camera mounting position is arranged at the top of the camera base; a control switch is arranged at one corner of the top of the camera base; a front adjusting hand wheel is arranged on one side wall of the camera base; a head fixing frame is arranged on the other side wall of the camera base; and a rear adjusting hand wheel is arranged on one side wall of the head fixing frame. The head fixing part has the beneficial effects that a sliding rod is arranged between the head fixing frame and the camera base, so that the head fixing frame can be flexibly separated and is suitable for people with different head shapes; and limiting holes and the handrail are arranged on the two sides of the head fixing frame, so that an examiner can hold the head fixing part with two hands and relax the stiff body, and the examination accuracy of the device is improved.

The invention discloses a fundus camera, comprising: an imaging unit, which is used for taking pictures of a patient's ID card and the fundus to obtain image information such as the ID image and the fundus image; and an identification unit, which is used for identifying all identification information recorded on the certificate image; a medical record generating unit, the medical record generating unit generates an electronic medical record according to the identification information. Compared with the prior art, the fundus camera of the present invention can easily associate the fundus image with the patient information without manual input, thereby greatly reducing the workload of the medical staff, so that the medical staff can concentrate on the fundus photography and the fundus image. analyze.

The present disclosure provides a method and a system for recognizing medical image, the present disclosure utilizes the image data with markers of different diseases for calculating and analyzing to build a pre-trained model, the present disclosure has significant improvements to improve the accuracy of image recognition under the general situation of insufficient effective data in the field of medical image recognition technology, the present disclosure can be applied to the field of medical image recognition technology, including X-ray, CT, MRI, ultrasonic, pathological slice photography or fundus photography.

A computer-implemented method and analysis system for performing a COVID-19 test using a deep convolution neural network (DCNN) are provided. The method entails receiving examination data from a user's mobile computing device, which comprises the mobile computing device's identification information and an initial eye image captured by performing a fundus photography or a CCD and CMOS photography via the mobile computing device's optical sensor; pre-processing the initial eye image to create an enhanced processed eye image; assessing the processed eye image by inputting it into a ML model that determines whether the eye image shows characteristics of being COVID-19 positive; and returning the assessment result and the identification information to the original mobile computing device or another electronic device.

The application belongs to the field of ophthalmic diagnosis and treatment equipment, specifically a wearable intelligent diagnosis equipment for eye diseases. The wearable intelligent eye disease self-diagnosis device includes an adaptive helmet, a fundus camera system, a control system and a cloud diagnosis system. The adaptive helmet includes a flexible inner layer, a magnetorheological adaptation layer and a rigid outer layer; the fundus photographing system includes a fundus photographing camera and an image recognition system; the cloud diagnosis system includes a cloud database and a disease diagnosis system. The control system adjusts the position of the fundus photographing system by changing the fluidity of the magnetorheological fluid to obtain more accurate fundus photographs. The cloud diagnosis system conducts a preliminary diagnosis of the disease based on the neural convolution network based on the obtained fundus photos, searches the cloud database according to the diagnosis results, conducts cloud consultation, and feeds back the treatment plan to the control system. The self-adaptive helmet is also equipped with a voice interaction system, and the intelligent eye disease diagnosis equipment can enable patients to complete the preliminary detection and diagnosis of eye diseases comfortably and conveniently.

The invention relates to the technical field of hypertension retinopathy evaluation, in particular to a method for evaluating hypertension retinopathy of different traditional Chinese medicine syndromes. The method comprises the steps of traditional Chinese medicine syndrome differentiation; retinal vessel examination; and summarizing and analysis of dynamic and static indexes. According to the method for evaluating hypertension retinopathy of different traditional Chinese medicine syndromes, traditional Chinese medicine syndrome differentiation and typing are conducted on a hypertension patient; then an arteriovenous inner diameter ratio, arteriovenous crossing signs, blood vessel exudation and macular region blood vessel morphology are collected as evaluation indexes; the positive indexdifference of each syndrome is analyzed and used as a standard for traditional Chinese medicine typing, so a basis is provided for guiding traditional Chinese medicine intervention in the next step; retinal angiography is added into the evaluation method to reflect the microcirculation state of retinae and embody a dynamic process, so the defect that fundus imaging only reflects a static state isovercome; and static results obtained through fundus photography and dynamic results obtained through fluorography are integrated for analysis, so the traditional Chinese medicine typing standard of HRP is determined, and later medicine intervention is guided.

The invention discloses a glaucoma image detection method based on deep learning of fundus photography. Preprocessing the original fundus images that have been collected and marked in the database to obtain training example fundus images to form a training database; amplify to obtain an amplified training database; establish a convolutional neural network including a multi-layer neural network structure, The amplified training database is used to input the convolutional neural network for training; for the fundus image to be tested, the fundus image to be tested is input into the trained convolutional neural network to obtain the output value of the last layer of neural network structure, and then the Glaucoma is identified. The invention can continuously optimize the data features used for judgment and the parameters of the convolutional neural network, thereby greatly improving the accuracy, sensitivity and specificity of glaucoma image detection, and saving medical resources.

The invention provides an artificial intelligence cataract screening referral system based on fundus pictures. The artificial intelligence cataract screening referral system comprises a collecting andprocessing module, a model training module, a self-checking and repairing module, a referral output module, a splicing identification module and a memory recovery module. The cataract screening referral system disclosed by the invention is an artificial intelligence system developed by utilizing a deep learning algorithm based on common fundus photography, is used for automatically identifying cataract and automatically grading the severity degree, and is used for realizing automatic screening and referral of the cataract of people in remote areas where ophthalmologists are relatively lack. The system reduces low vision and blinding rate caused by cataract in people, is simple to operate, can be operated by non-medical personnel, can automatically, quickly and accurately screen cataract in real time and determine the severity of cataract, and is suitable for large-scale popularization.

The present disclosure provides a method and a system for recognizing medical image, the present disclosure utilizes the image data with markers of different diseases for calculating and analyzing to build a pre-trained model, the present disclosure has significant improvements to improve the accuracy of image recognition under the general situation of insufficient effective data in the field of medical image recognition technology, the present disclosure can be applied to the field of medical image recognition technology, including X-ray, CT, MRI, ultrasonic, pathological slice photography or fundus photography.