An image processing method, including: by a processor: acquiring a fundus image; performing a first enhancement processing on an image of at least a central region of the fundus image, and performing a second enhancement processing, which is different from the first enhancement processing, on an image of at least a peripheral region of the fundus image that is at a periphery of the central region; and generating an enhanced image of the fundus image on the basis of a first image obtained as a result of the first enhancement processing having been performed and a second image obtained as a result of the second enhancement processing having been performed.

An image processing method, including: by a processor: acquiring a fundus image; performing a first enhancement processing on an image of at least a central region of the fundus image, and performing a second enhancement processing, which is different from the first enhancement processing, on an image of at least a peripheral region of the fundus image that is at a periphery of the central region; and generating an enhanced image of the fundus image on the basis of a first image obtained as a result of the first enhancement processing having been performed and a second image obtained as a result of the second enhancement processing having been performed.

This application discloses an image feature recognition method performed at a computing device. The computing device obtains a first neural network model by training parameters in a second neural network model using a first training set and a second training set consecutively, image features of training pictures in the first training set being marked and image features of training pictures in the second training set being not marked. After obtaining a first neural network model, the computing device obtains a recognition request for recognizing an image feature in a target picture. The computing device then recognizes the image feature in the target picture by applying the target picture to the first neural network model. Finally the computing device returns a first recognition result of the first neural network model, the first recognition result indicating an image feature (for example, a pathological feature) recognized in the target picture.

Systems and methods are provided for performing optical coherence tomography angiography for the rapid generation of en face images. According to one example embodiment, differential interferograms obtained using a spectral domain or swept source optical coherence tomography system are convolved with a Gabor filter, where the Gabor filter is computed according to an estimated surface depth of the tissue surface. The Gabor-convolved differential interferogram is processed to produce an en face image, without requiring the performing of a fast Fourier transform and k-space resampling. In another example embodiment, two interferograms are separately convolved with a Gabor filter, and the amplitudes of the Gabor-convolved interferograms are subtracted to generate a differential Gabor-convolved interferogram amplitude frame, which is then further processed to generate an en face image in the absence of performing a fast Fourier transform and k-space resampling. The example OCTA methods disclosed herein are shown to achieve faster data processing speeds compared to conventional OCTA algorithms.

An information processing method includes deducing a diagnosis name derived from a medical image on the basis of an image feature amount corresponding to a value indicating a feature of a medical image, deducing an image finding representing a feature of the medical image on the basis of the image feature amount, and presenting the image finding deduced in the deducing the image finding which is affected by an image feature amount common to the image feature amount that has affected the deduction of the diagnosis name in the deducing the diagnosis name and the diagnosis name to a user.

A feature value related to a positional relationship between a vortex vein position and a characteristic point on a fundus image is computed. The image processing method provided includes a step of analyzing a choroidal vascular image and estimating a vortex vein position, and a step of computing a feature value indicating a positional relationship between the vortex vein position and a position of a particular site on a fundus.

Systems and methods are provided for imaging and characterizing objects including the eye using non-uniform or speckle illumination patterns. According to the present technology, a method for characterizing at least a portion of an object may include generating, using at least one light source, one or multiple non-uniform illumination patterns on an object. The method may also include detecting, using a detector, backscattered light from the object in response to the generating. The method may further include extracting, using the detector, data representative of the backscattered light. The method may also include processing, using a processing unit, the data representative of the backscattered light to create one or more images of at least a portion of the object.

In the ophthalmic apparatus 1 of an aspect example, the image acquiring unit (the fundus camera unit 2, the OCT unit 100, the image data constructing unit 220) acquires an anterior segment image constructed based on data collected from an anterior segment of a subject's eye by OCT scanning. The part image identifying processor 231 performs identification of two or more part images respectively corresponding to two or more parts of the anterior segment from the anterior segment image acquired. The part image assessing processor 232 performs image quality assessment of each of the two or more part images. The anterior segment image assessing processor 233 performs image quality assessment of the anterior segment image based on two or more pieces of assessment data respectively obtained for the two or more part images.

In the ophthalmic apparatus 1 of an aspect example, the image acquiring unit (the fundus camera unit 2, the OCT unit 100, the image data constructing unit 220) acquires an anterior segment image constructed based on data collected from an anterior segment of a subject's eye by OCT scanning. The part image identifying processor 231 performs identification of two or more part images respectively corresponding to two or more parts of the anterior segment from the anterior segment image acquired. The part image assessing processor 232 performs image quality assessment of each of the two or more part images. The anterior segment image assessing processor 233 performs image quality assessment of the anterior segment image based on two or more pieces of assessment data respectively obtained for the two or more part images.

An apparatus for predicting a cardiovascular risk factor according to an embodiment includes a target cardiovascular risk factor predicting module for producing an initial prediction value for a target cardiovascular risk factor from a fundus image, at least one related cardiovascular risk factor predicting module for producing respective prediction values for at least one related cardiovascular risk factor from the fundus image, and a combining module for producing a final prediction value for the target cardiovascular risk factor on the basis of the initial prediction value for the target cardiovascular risk factor and the respective prediction values for the at least one related cardiovascular risk factor.