37 results about "Retina Layer" patented technology

Methods for analyzing retinal tomography maps to detect patterns of optic nerve diseases such as glaucoma, optic neuritis, anterior ischemic optic neuropathy are disclosed in this invention. The areas of mapping include the macula centered on the fovea, and the region centered on the optic nerve head. The retinal layers that are analyzed include the nerve fiber, ganglion cell, inner plexiform and inner nuclear layers and their combinations. The overall retinal thickness can also be analyzed. Pattern analysis are applied to the maps to create single parameter for diagnosis and progression analysis of glaucoma and optic neuropathy.

An image processing apparatus, which analyzes retina layers of an eye to be examined, comprising, means for extracting a feature amount, which represents an anatomical feature in the eye to be examined, from a projection image obtained from a tomogram of the retina layers and a fundus image of the eye to be examined, means for determining a type of the anatomical feature based on the feature amount, means for deciding layers to be detected from the retina layers according to the determined type of the anatomical feature, and detecting structures of the decided layers in the tomogram, and means for modifying the structure of the layer included in a region having the anatomical feature of the structures of the layers detected by the layer structure detection means.

A tomogram observation apparatus characterized by comprising: detection means for detecting a region in which an optic nerve extends from a retina layer of an eye to be examined to outside the eye to be examined; and generation means for generating a two-dimensional tomogram of a portion around an optic papilla of the eye to be examined, based on a position of the region.

In a tomographic image photographing apparatus, a deformation of a volume image is corrected accurately even if an object to be inspected moves when the volume image is acquired. An image processing apparatus acquires a tomographic image of the object to be inspected from combined light beams of return light beams, which is obtained by irradiating the object to be inspected with a plurality of measuring light beams, and corresponding reference light beams. In the image processing apparatus, a photographing unit obtains a tomographic image of a fundus with the plurality of measuring light beams, and a detection unit detects a retina layer from the tomographic image. Based on the detected retina layer, a fundus shape is estimated. Based on the estimated fundus shape, a positional deviation between tomographic images is corrected.

A model human eye suitable for practicing surgical procedures, comprising a hemispherical-shaped bottom assembly having a bowl-shaped substrate disposed therein, a retinal layer disposed on the bowl-shaped substrate, and a hemispherical-shaped top portion attached to the bottom portion, the top portion comprising a visually transparent cornea portion and a visually opaque sclera portion, wherein the cornea portion and the sclera portion are integrally molded, wherein the cornea portion comprises a posterior corneal surface, wherein a distance from the posterior corneal surface to the retinal layer is an axial length. The model human eye is particularly suited for practicing A-scan ultrasound biometry and optical coherence biometry.

One aspect of embodiments of the present invention relates to an image processing apparatus which specifies one of boundary positions of retina layers in a fundus image showing a retina tomosynthesis, sets a distance transfer function for converting the distance from the specified boundary position to a parameter expressing opacity such that the peak position of the opacity is set to a predetermined position in the retina, sets a luminance transfer function for converting a luminance value of the fundus image to the parameter expressing opacity, and generates a translucent display image by calculating the opacity of respective positions of the tomosynthesis using the distance transfer function and the luminance transfer function, and by volume rendering.

An image processing apparatus comprising, boundary extraction means for detecting boundaries of retina layers from a tomogram of an eye to be examined, exudate extraction means for extracting an exudate region from a fundus image of the eye to be examined, registration means for performing registration between the tomogram and the fundus image, and calculating a spatial correspondence between the tomogram and the fundus image, specifying means for specifying a region where an exudate exists in the tomogram using the boundaries of the retina layers, the exudate region, and the spatial correspondence, likelihood calculation means for calculating likelihoods of existence of the exudate in association with the specified region, and tomogram exudate extraction means for extracting an exudate region in the tomogram from the specified region using the likelihoods.

A tomogram observation apparatus characterized by comprising: detection means for detecting a region in which an optic nerve extends from a retina layer of an eye to be examined to outside the eye to be examined; and generation means for generating a two-dimensional tomogram of a portion around an optic papilla of the eye to be examined, based on a position of the region.

The invention discloses a choroidal neovascularization growth protection method combining a constitutive model with a finite element. The method comprises the steps of image preprocessing; area division and partition, specifically including dividing an image into four areas consisting of a CNV area, an outer retina layer, an inner retina layer and a choroids layer; meshing, specifically including performing tetrahedral mesh generation on the four areas; modeling, specifically including modeling by using a hyperelastic biomechanical model and a reaction diffusion equation, and adding quality variation after choroidal neovascularization grows into an equation as a source item, thus causing a deformation gradient tensor to continuously change according to the growth of the new vessel; optimizing the model, computing the best accuracy rate, and performing parameter test; and fitting a parameter curve according to a parameter predicted at each time point, and predicting the growth parameter of the last time point to acquire a prediction result. According to the method provided by the invention, the biomechanical model can be built in a more flexible and personalized mode, the model assumes that organization is orthotropic, the good prediction results can be provided for non-linear large-deformation areas, and the accuracy is high.

The invention discloses a retinal image layering method, device and equipment and a readable storage medium. The method comprises the following steps: carrying out straightening treatment to acquire aregion of interest of retinal layering operation; adaptively selecting the scale of superpixel over-segmentation according to thicknesses of various layers of a retina in the region of interest afterstraightening treatment is implemented so as to carry out initial over-segmentation on retinal images in the region of interest according to a preset clustering rule; and merging superpixel blocks obtained by initial over-segmentation by a preset merging rule so as to acquire a retinal layering result. By the provided method, device, equipment and computer readable storage medium, mistaken layering caused by weak contrast ratio of retina layers can be avoided effectively, and the accuracy of a retinal image layering result is improved.

The invention relates to an OCT image layer segmentation method based on random forest and compound activity curve, which is designed for accurate segmentation of retinal layer and effusion. The OCT image layer segmentation method based on random forest and compound activity curve of the present invention, comprises: obtains OCT image feature training random forest classifier; Composite activity curve algorithm obtains final SF1; Extract 24 features of OCT image, use random forest classifier , the OCT image layer segmentation method based on random forest and compound activity curve in the present invention has simple operation and accurate detection result. It overcomes the problems of low recognition rate and poor segmentation effect of existing OCT image segmentation algorithms for lesions.

The invention relates to an OCT (Optical Coherence Tomography) image layer segmentation method based on a neural network and a constraint graph search algorithm, and is designed for accurately segmenting a retina layer and new vessels. The OCT image layer segmentation method based on the neural network and the constraint graph search algorithm comprises the following steps that: obtaining OCT image features to train a neural network classifier; obtaining a final SF1 through a multi-resolution map search algorithm SF1; extracting 24 features of an OCT image, and using the neural network classifier to find initial surfaces S1, S2,...S8; according to initial boundaries S2 to S8, using the constraint graph search algorithm to find accurate SF2 to SF8 in sequence; and segmenting the new vessels and hydrops between SF7 and SF8. The OCT image layer segmentation method based on the neural network and the constraint graph search algorithm has the advantages of being simple in operation and accurate in detection results. The existing problems of low identification rate, poor segmentation effect and the like of a lesion OCT image segmentation algorithm.

The invention discloses a retina interlayer gray level analysis method based on the 3D-OCT. The method includes the steps that firstly, an input 3D-OCT image is preprocessed; secondly, the multi-layer structure of the retina is segmented out through the image search technology; thirdly, detection is conducted through the texture classification method to find out the RAO area; fourthly, the gray levels of the retina layers are analyzed. According to the retina interlayer gray level analysis method based on the 3D-OCT, the gray levels of the retina layers in an RAO patient are analyzed in a quantitative mode, so that the qualitative judgment that the patient has the RAO disease is expressed in a quantitative mode, and quantitative indexes are provided, so that the severity degree of the RAO is independently and objectively judged. By proving the feasibility of the quantitative method, the foundation is laid for providing the objective basis of the illness state of the RAO patient for a doctor in future.