37 results about "Retinal lesion" patented technology

A method, code and system for planning the treatment a lesion on or adjacent to the retina of an eye of a patient are disclosed. There is first established at least two beam paths along which x-radiation is to be directed at the retinal lesion. Based on the known spectral and intensity characteristics of the beam, a total treatment time for irradiation along each beam paths is determined. From the coordinates of the optic nerve in the aligned eye position, there is determined the extent and duration of eye movement away from the aligned patient-eye position in a direction that moves the patient's optic nerve toward the irradiation beam that will be allowed during treatment, while still maintaining the radiation dose at the patient optic nerve below a predetermined dose level.

The invention discloses a method for measuring lesion characteristics of hypertensive retinopathy. The method comprises the following steps: acquiring a fundus image; recognizing an optic disc region of the fundus image and dividing the fundus image into at least three regions including a first region, a second region and a third region based on the optic disc region; performing artery and vein segmentation on the fundus image by using an arteriovenous segmentation model based on deep learning to obtain arteriovenous segmentation results, wherein the arteriovenous blood vessel marking results include an artery marking result, a vein marking result and a small blood vessel marking result; and based on the three regions and the arteriovenous segmentation result, measuring lesion characteristics in the fundus image, wherein the lesion characteristics comprise at least one of arteriovenous cross-indentation characteristics, arteriovenous local stenosis characteristics and arteriovenous general stenosis characteristics. According to the present disclosure, it is possible to provide a measurement method and a measurement system for efficiently and objectively measuring lesion characteristics of hypertensive retinopathy.

The invention relates to the field of medical information intelligent processing, in particular to a convolutional neural network weight optimization method for retinal lesion classification. The method comprises the following steps: firstly, acquiring a fundus image training set and a corresponding multi-lesion label; searching an optimal initial weight value through a single-population leapfrogalgorithm, then constructing a convolution layer, a pooling layer and a full connection layer in the convolutional neural network, and taking the optimal initial weight value as a parameter of first forward propagation calculation; performing cross entropy loss calculation and summation on the four predicted values of the four lesions in the retina and the true value to obtain a loss value, judging whether the loss value is abnormal or not, if the loss value is abnormal, generating a frog group around the weight of the previous forward propagation, and searching an optimal frog updating network weight; otherwise, updating the network weight by adopting a gradient descent algorithm; and finally, optimizing the final weight. According to the method, the accuracy of fundus image multi-lesiondetection can be effectively improved, and the method has high application value for retinal diseases and adjuvant therapy.

A device and method of ophthalmic diagnosis of lesions on retina utilizing a slit lamp apparatus with a pupil reader and at least one visible LED and one Infrared LED to detect a lesion on the retina of an eye.

The invention relates to the technical field of medical image processing, in particular to an artificial intelligence system for identifying high myopia retinopathy, comprising: an image acquisition module for acquiring an optical coherence tomography image and a fundus reference of a patient to be identified; the first recognition module is used for inputting the optical coherence tomography image into a high myopia retinopathy recognition model, judging whether the optical coherence tomography image has lesion or not and obtaining a lesion type result; the second recognition module is used for inputting the fundus color photograph into a high myopia retinal lesion staging model, judging the retinal lesion staging of the fundus color photograph and obtaining a lesion staging judgment result; and the report generation module is used for generating a diagnosis and treatment suggestion report according to the lesion type result and the lesion staging judgment result. According to the method, the optical coherence tomography image and the fundus color photograph of the patient can be quickly and effectively recognized to recognize common retinopathy of high myopia.

The invention provides an inhibitor for autophagy and apoptosis of retinal pigment epithelial cells RPE and application of the inhibitor, and relates to the technical field of biological medicines. The invention relates to an inhibitor for autophagy and apoptosis of retinal pigment epithelial cells RPE. The inhibitor comprises an antagonist Met of a tumor necrosis factor superfamily receptor FAS.It is verified that the tumor necrosis factor superfamily receptor FAS can serve as a receptor of GMFB to activate downstream autophagy and apoptosis pathways, the antagonist Met of the tumor necrosisfactor superfamily receptor FAS can inhibit activation of the FAS and downstream related pathways of the FAS, cell apoptosis and autophagy reactions are reduced, and therefore the morbidity process of diabetic retinopathy is delayed. The inhibitor can be used for preparing medicines for delaying and / or treating diabetic retinopathy in the early stage of disease.

The invention relates to an artificial transcription factor comprising a polydactyl zinc finger protein targeting specifically a receptor gene promoter fused to an inhibitory or activatory protein domain, a nuclear localization sequence, and a protein transduction domain. In particular examples these receptor gene promoters regulate the expression of the endothelin receptor A, the endothelin receptor B, the Toll-like receptor 4 or the high-affinity IgE receptor. Artificial transcription factors directed to the endothelin A or B receptors are useful in the treatment of diseases modulated by endothelin, such as cardiovascular diseases, and, in particular, eye diseases, e.g. retinal vein occlusion, retinal artery occlusion, macular edema, optic neuropathy, central serous chorioretinopathy, retinitis pigmentosa, Leber's hereditary optic neuropathy, and the like. Artificial transcription factors directed to the Toll-like receptor 4 or the IgE receptor are useful for the treatment of autoimmune disorders, and the like, and allergic disorders, respectively.

A method, code and system for planning the treatment a lesion on or adjacent to the retina of an eye of a patient are disclosed. There is first established at least two beam paths along which x-radiation is to be directed at the retinal lesion. Based on the known spectral and intensity characteristics of the beam, a total treatment time for irradiation along each beam paths is determined. From the coordinates of the optic nerve in the aligned eye position, there is determined the extent and duration of eye movement away from the aligned patient-eye position in a direction that moves the patient's optic nerve toward the irradiation beam that will be allowed during treatment, while still maintaining the radiation dose at the patient optic nerve below a predetermined dose level.

The invention belongs to the technical field of computer vision, and discloses a fluorescein fundus angiography image processing system and device, and the system comprises an image preprocessing module which is used for obtaining a to-be-processed fluorescein fundus angiography image, and carrying out the preprocessing of the fluorescein fundus angiography image; the lesion area and lesion area non-perfusion area segmentation module is used for processing the preprocessed fluorescein fundus angiography image through a pre-trained semantic segmentation model, and determining a lesion area in the image and a non-perfusion area in the lesion area; and the ischemic index calculation module is used for acquiring the area value of the lesion region and the area value of the non-perfusion region, and calculating to obtain the clinical ischemic index corresponding to the fluorescein fundus angiography image. According to the method, the lesion area in the fluorescein fundus angiography image and the non-perfusion area in the lesion area can be segmented, lesion quantification is realized, and the method is suitable for various retinopathy effects.

Methods, systems, and devices to improve the assessment of visual function and overcoming limitations of current methods to identify the visual function that potentially could be reached by a given eye. Multiple eye tests including visual stimuli plus optical measurement components, and methods to combine the results, identify and quantify sources of decreased vision resulting from optical sources, such as a lens and cornea as distinguished from retinal sources. By identifying potentially correctable optical sources of decreased vision, and overcoming physiological limitations such as size of the eye's pupil, the visual benefits of treatment such as by cataract or corneal surgery are distinguished from retinal pathology that requires medical intervention. The devices and methods provide metrics that include an expected value of the visual function and sources of variability including both optical and neural components, to guide treatment and improve clinical trials.

The invention discloses a method for grading diabetic retinopathy based on multi-scale cascading, including: a Res2Net basic network for extracting multi-scale information of input images, an attention module for extracting feature maps of the first layer, and integrating feelings with more discriminative feature representations The field module and multi-scale cascaded network; the loss of shallow information is reduced by extracting multi-scale information, and the shallow information and high-level information are fused through cascading. Complementarity to enhance the acquisition of information, combined with multi-scale and cascade can effectively improve the grading effect of DR, which has certain clinical and algorithmic significance.

The invention discloses an optical coherence tomography image retinopathy intelligent detection system and a detection method. Currently obtained retinal images are mainly judged by ophthalmologists relying on naked eye observation, which is not conducive to large-scale promotion. The present invention takes the idea of ​​deep learning as the technical core, combines the migration learning strategy, uses the convolutional neural network algorithm in the deep learning model to construct a classifier, realizes the classification of retinal lesions, and uses the image segmentation algorithm to realize the extraction of lesions and retinal layering , so as to obtain the specific information of the lesion position in the picture and the quantitative information of the morphological parameters, and generate relevant diagnostic reports for further diagnosis by doctors. The present invention can make up for the blank of the current optical coherence tomography system in the field of intelligent identification and precise positioning of lesions, effectively reduce the work intensity of doctors, and further promote the clinical application and technical development of the optical coherence tomography system in the diagnosis of ophthalmic diseases.

The present invention is a type of fundus camera which is one of eye examination and diagnosis equipment. A conventional color fundus camera is equipment for illuminating retinas with light of the visible band (400-640 nm), and then showing retinal lesions and diagnosing retinal diseases. The present invention relates to: a choroidal imaging fundus camera capable of photographing both a choroidal vessel and a choroidal lesion at the back of the retina with near-infrared rays having a wavelength longer than 640 nm; and a device comprising the same. A polarizing fundus camera for effectively suppressing internal reflection, of the present invention, comprises: a lighting part (10) for emitting light; a diffusion lens (20) for diffusing the light incident from the lighting part (10); a lighting lens (30) for emitting, at a predetermined emission angle, the light incident from the diffusion lens (20); a mirror (40) for reflecting the light incident from the lighting lens (30); a polarizing beam splitter (50) allowing a P-polarized light to pass therethrough and an S-polarized light to be reflected in the light incident from the mirror (40); an objective lens (60) for magnifying an image of the fundus of the eye, which has been formed by the light incident from the polarizing beam splitter (50); a short-range eyepiece (70) for reducing the image, of the fundus of the eye, having been magnified by means of the objective lens (60); a linear polarizing filter (80) allowing only the P-polarized light to pass therethrough; a narrow-band optical filter (90) filtering, from the light having passed through linear polarizing filter, the light having a band of 12 nm or less and emitted from the polarizing beam splitter (50); and an imaging device (100) using the light having passed through the narrow-band optical filter (90) so as to convert the same into an electrical signal and acquire an image, wherein the linear polarizing filter (80) respectively has a first linear polarizing filter (81) provided between the lighting part (10) and the polarizing beam splitter (50), and a second linear polarizing filter (82) provided between the polarizing beam splitter (50) and the short-range eyepiece (70).

The invention discloses a SD-OCT image retinopathy detection system based on category discrimination and positioning, which includes a data preprocessing module, a neural network prediction module, a heat map calculation module, a lesion area positioning module, and an accurate detection module. Perform enhancement processing, and then classify through the global convolutional neural network. According to the prediction results, obtain the heat map of the category mapping feature. Finally, by obtaining the larger activation value area, generate a mask to obtain the minimum circumscribed rectangle, and determine it according to the coordinates of the minimum circumscribed rectangle The location of the fundus lesion can be used to locate the fundus lesion area in the image. The present invention can effectively improve the accuracy of detection and recognition, and at the same time classify and recognize the retinal images of the fundus, it can locate the location of the corresponding fundus lesion according to the category discrimination information, and has important guidance for the subsequent diagnosis, analysis and treatment of the fundus significance.

The invention discloses a diabetic retinopathy detection system based on serial structure segmentation, comprising: a fundus image acquisition device for acquiring retinal fundus images and a data processing device for analyzing and processing the collected fundus images, and the data processing device includes: a preprocessing function Module, blood vessel segmentation function module, optic disc segmentation function module, fovea determination function module, exudation segmentation function module, statistical calculation function module and doctor diagnosis function module, count the exudation area and calculate the presence of diabetic macular edema in the input fundus image Finally, combined with the results of statistical calculations, the fundus doctor will give the final diagnosis and treatment plan by referring to the segmented exudate area and disease probability, combined with his own specialty. The present invention systematically considers various related physiological structures of the fundus, segments out the lesion area and then gives a diagnosis report by the fundus doctor, which is efficient in detection and more accurate in detecting the lesion, which can greatly reduce the workload of doctors and improve work efficiency.

The invention discloses a vitreous substitute material suitable for proliferative vitreoretinopathy, which is prepared by the following steps: (1) heating a PVA aqueous solution, adding a crosslinking agent to generate a crosslinking reaction, adjusting the pH value to neutral, Prepare PVA hydrogel; (2) Dissolve 5-fluorouracil and PLGA in an organic solvent, then slowly add it dropwise to liquid paraffin containing an emulsifier, heat and stir at a constant temperature to emulsify to obtain an emulsion; (3) Add to step (2 ) Add petroleum ether to the emulsion until all the emulsion forms a precipitate, and centrifuge to obtain microspheres; (4) use petroleum ether to centrifugally wash the microspheres, and obtain 5-fluorouracil microspheres after drying; (5) coagulate the PVA Glue and 5‑fluorouracil microspheres were mixed and stirred under heating to obtain a vitreous substitute material. The material has properties close to those of the natural vitreous, providing an ideal treatment for patients with proliferative vitreoretinopathy.

The present invention contemplates an infant eye model for wide field retinal imaging by implementing nominal physical parameters and optical characteristics found in scientific literature and by simulating retinal features and details found in real eye images. The present invention also contemplates implementing a corneal model with a translucent plastic to mimic image haze and 1st Purkinje reflection. The present invention also contemplates implementing a birefringent layer to the lens posterior surface to simulate 4th Purkinje reflection and its brightness variation. The present invention further contemplates implementing a photo-realistic retinal hemisphere shell to provide retinal details and demonstrate retinopathy associated with retinal diseases.

The invention discloses an adeno-associated virus virion with a mutant capsid and application thereof. The adeno-associated virus virion with a mutant capsid has a mutant AAV6 capsid protein that confers enhanced retinotropic Müller cell infectivity. Wherein, relative to the corresponding parent AAV6 capsid protein, the 663rd serine in the amino acid sequence of the mutant AAV6 capsid protein is mutated to leucine. The pharmaceutical composition comprises the adeno-associated virus virion and a pharmaceutically acceptable excipient. The invention obtains an AAV vector for specifically and efficiently transducing Müller cells by site-directed mutation of the amino acid encoding the AAV6 capsid, and is applicable to a method for carrying an exogenous therapeutic gene to transduce Müller cells to treat retinopathy.

The invention relates to a retina image recognition method, a device, computer equipment and a computer readable storage medium. The method comprises the steps of obtaining a retina image; analyzing retina features of the retina image through a neural network model, wherein the retina features comprise at least one of a blank area of the retina, the number of retina vessels and the width of the retina vessels; and determining a retina category corresponding to the retina image according to the retina features. By adopting the method, category identification can be carried out according to characteristics such as retinal blank areas, the number or width of blood vessels and the like during retinopathy, and the accuracy of retinal category identification is improved.