Abstract: Disclosed is a method for training a neural network to quantify the vessel calibre of retina fundus images. The method involves receiving a plurality of fundus images; pre-processing the fundus images to normalise images features of the fundus images; and training a multi-layer neural network, the neural network comprising of a convolutional unit, multiple dense blocks alternating with transition units for down-sampling image features determined by the neural network, and a fully-connected unit, wherein each dense block comprises a series of cAdd units packed with multiple convolutions, and each transition layer comprises a convolution with pooling.

Abstract: A method and apparatus for monitoring arid for improving eye health of a user of a device, the method comprising receiving m indication that an event occurred associated with rise of the device; updating data on the device according to the data included in a user profile associated with a user; generating a personalized user interface and displaying said interface on the device; detecting a distance of the user from the device; and providing an indication once the distance exceeds a predefined threshold for a predefined time period.

Abstract: This disclosure provides methods of a method of treating a retinal angiogenic disease in a subject comprising administering an effective amount of an Angio-3 peptide.

Abstract: A computer-aided diagnosis (CAD) system for classification and visualisation of a 3D medical image comprises a classification component comprising a 2D convolutional neural network (CNN) that is configured to generate a prediction of one or more classes for 2D slices of the 3D medical image. The system also comprises a visualisation component that is configured to: determine, for a target class of said one or more classes, which slices belong to the target class; for each identified slice, determine, by back-propagation to an intermediate layer of the CNN, a contribution of each pixel of the identified slice to classification of the identified slice as belonging to the target class; and generate a heatmap that provides a visual indication of the contributions of respective pixels.

Abstract: Disclosed is a method for training a neural network to quantify the vessel calibre of retina fundus images. The method involves receiving a plurality of fundus images; pre-processing the fundus images to normalise images features of the fundus images; and training a multi-layer neural network, the neural network comprising of a convolutional unit, multiple dense blocks alternating with transition units for down-sampling image features determined by the neural network, and a fully-connected unit, wherein each dense block comprises a series of cAdd units packed with multiple convolutions, and each transition layer comprises a convolution with pooling.

Abstract: This disclosure provides methods of a method of treating a retinal angiogenic in a subject comprising administering an effective amount of an Angio-3 peptide.

Abstract: A method of modifying a retina fundus image for a deep learning model is disclosed. In a described embodiment, the method includes converting a retina fundus image to a binary image by converting pixels of the retina fundus image to low intensity modified pixels and high intensity modified pixels of the binary image, and determining a first boundary between the low intensity modified pixels and high intensity modified pixels of the binary image. The method further includes removing outlier boundary values from the first boundary, constructing a second boundary from remaining boundary values, identifying the pixels of the retina fundus image that are within the second boundary, and constructing a modified retina fundus image containing the identified pixels for a deep learning model.

Abstract: This disclosure provides methods of a method of treating a retinal angiogenic in a subject comprising administering an effective amount of an Angio-3 peptide.

Abstract: A method of modifying a retina fundus image for a deep learning model is disclosed. In a described embodiment, the method includes converting a retina fundus image to a binary image by converting pixels of the retina fundus image to low intensity modified pixels and high intensity modified pixels of the binary image, and determining a first boundary between the low intensity modified pixels and high intensity modified pixels of the binary image. The method further includes removing outlier boundary values from the first boundary, constructing a second boundary from remaining boundary values, identifying the pixels of the retina fundus image that are within the second boundary, and constructing a modified retina fundus image containing the identified pixels for a deep learning model.

Abstract: A method and apparatus for monitoring arid for improving eye health of a user of a device, the method comprising receiving m indication that an event occurred associated with rise of the device; updating data on the device according to the data included in a user profile associated with a user; generating a personalized user interface and displaying said interface on the device; detecting a distance of the user from the device; and providing an indication once the distance exceeds a predefined threshold for a predefined time period.

Abstract: A method is proposed for automatically locating the optic disc or the optic cup in an image of the rear of an eye. A portion of the image containing the optic disc or optic cup is divided into sub-regions using a clustering algorithm. Biologically inspired features, and optionally other features, are obtained for each of the sub-regions. An adaptive model uses the features to generate data indicative of whether each sub-region is within or outside the optic disc or optic cup. The result is then smoothed, to form an estimate of the position of the optic disc or optic cup.

Abstract: A non-stereo fundus image is used to obtain a plurality of glaucoma indicators. Additionally, genome data for the subject is used to obtain genetic marker data relating to one or more genes and/or SNPs associated with glaucoma. The glaucoma indicators and genetic marker data are input into an adaptive model operative to generate an output indicative of a risk of glaucoma in the subject. In combination, the genetic indicators and genome data are more informative about the risk of glaucoma than either of the two in isolation. The adaptive model may be a two-stage model, having a first stage in which individual genetic indicators are combined with respective portions of the genome data by first adaptive model modules to form respective first outputs, and a second stage in which the first outputs are combined by a second adaptive mode.

Abstract: A non-stereo fundus image is used to obtain a plurality of glaucoma indicators. Additionally, genome data for the subject is used to obtain genetic marker data relating to one or more genes and/or SNPs associated with glaucoma. The glaucoma indicators and genetic marker data are input into an adaptive model operative to generate an output indicative of a risk of glaucoma in the subject. In combination, the genetic indicators and genome data are more informative about the risk of glaucoma than either of the two in isolation. The adaptive model may be a two-stage model, having a first stage in which individual genetic indicators are combined with respective portions of the genome data by first adaptive model modules to form respective first outputs, and a second stage in which the first outputs are combined by a second adaptive mode.

Abstract: A non-stereo fundus image is used to obtain a plurality of glaucoma indicators. Additionally, genome data for the subject is used to obtain genetic marker data relating to one or more genes and/or SNPs associated with glaucoma. The glaucoma indicators and genetic marker data are input into an adaptive model operative to generate an output indicative of a risk of glaucoma in the subject. In combination, the genetic indicators and genome data are more informative about the risk of glaucoma than either of the two in isolation. The adaptive model may be a two-stage model, having a first stage in which individual genetic indicators are combined with respective portions of the genome data by first adaptive model modules to form respective first outputs, and a second stage in which the first outputs are combined by a second adaptive mode.

Abstract: A method is proposed for automatically locating the optic disc or the optic cup in an image of the rear of an eye. A portion of the image containing the optic disc or optic cup is divided into sub-regions using a clustering algorithm. Biologically inspired features, and optionally other features, are obtained for each of the sub-regions. An adaptive model uses the features to generate data indicative of whether each sub-region is within or outside the optic disc or optic cup. The result is then smoothed, to form an estimate of the position of the optic disc or optic cup.

Abstract: A method is proposed for automatically analysing a retina image, to identify the presence of drusen which is indicative of age-related macular degeneration. The method proposes dividing a region of interest including the macula centre into patches, obtaining a local descriptor of each of the patches, reducing the dimensionality of the local descriptor by comparing the local descriptor to a tree-like clustering model and obtaining transformed data indicating the identity of the cluster. The transformed data is fed into an adaptive model which generates data indicative of the presence of drusen in the retinal image. Furthermore, the trans formed data can be used to obtain the location of the drusen within the image.

Abstract: An OCT image of an eye which has been subject to a DSAEK corneal transplant, in which a Descement's membrane in the cornea has been replaced by a graft, is processed to identify the outline of the graft. The process includes the steps of: computationally extracting the boundary of the cornea including the graft; computationally detecting the corners of the graft; computationally extracting points on the boundary between the graft and the original cornea; and computationally fitting the points on the boundary between the graft and the original cornea smoothly into a curve. The outline of the graft is then displayed. A graft profile may be generated, indicating the thickness of the graft at each point along its length.

Abstract: There is provided a method of monitoring retinopathy in a subject. The method involves measuring autofluorescence of a retina in response to high intensity blue light and infra-red reflectance of the anterior region of an eye in response to high intensity infra-red light of the subject over a total time period to obtain an autofluorescence intensity profile and an infra-red reflectance intensity profile. The autofluorescence intensity profile and infra-red reflectance intensity profile are processed to obtain a pupillary light reflex measurement that is used to assess the retinopathy status of the retina.

Abstract: A two-dimensional retinal fundus image of the retinal fundus of an eye is processed by optic disc segmentation (2) followed by cup segmentation 4. Data derived from the optic disc segmentation (i.e. the output of the disc segmentation (2) and/or data derived from the output of the optic disc segmentation step, e.g. by a smoothing operation 3) and data derived from the out-put of the optic cup segmentation (i.e. the output of the cup segmentation (4) and/or data derived from the output of the optic disc segmentation, e.g. by a smoothing operation 5) are fed (6) to an adaptive model which has been trained to generate from such inputs a value indicative of cup-to-disc ratio (CDR) of the eye. The CDR is indicative of glaucoma. Thus, the method can be used to screen patients for glaucoma.

Abstract: A platform is proposed for automated analysis of retinal images, for obtaining from them information characterizing retinal blood vessels which may be useful in forming a diagnosis of a medical condition. A first aspect of the invention proposes that a plurality of characteristics of the retina are extracted, in order to provide data which is useful for enabling an evaluation of cardiovascular risk prediction, or even diagnosis of a cardiovascular condition. A second aspect uses fractal analysis of retinal images to provide vascular disease risk prediction, such as, but not limited to, diabetes and hypertension.