Agency for Science, Technology and Research

Singapore Health Services Pte Ltd

National University of Singapore

Kent Ridge Digital Labs

Joo Hwee Lim

Jiang Liu

Tien Yin Wong

Huiqi Li

Wing Kee Damon Wong

Ngan Meng Tan

Beng Hai Lee

Zhuo Zhang

Jun Cheng

Tin Aung

Fengshou Yin

Baskaran Mani

Carol Cheung

Ziyang Liang

Wei Xiong

Qi Tian

Wing Kee Wong

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. Texture analysis is performed on the fundus images to classify them based on their quality, and only images which are determined to meet a quality criterion are subjected to an analysis to determine if they exhibit glaucoma indicators. Also, the images are put into a standard format. The system may include estimating the position of the optic cup by combining results from multiple optic cup segmentation techniques. The system may include estimating the position of the optic disc by applying edge detection to the funds image, excluding edge points that are unlikely to be optic disc boundary points, and estimating the position of an optic disc by fitting an ellipse to the remaining edge points.

Obtaining data for automatic glaucoma screening, and screening and diagnostic techniques and systems using the data

A two-dimensional retinal fundus image of the retinal fundus of an eye is processed by optic disc segmentation () followed by cup segmentation. Data derived from the optic disc segmentation (i.e. the output of the disc segmentation () and/or data derived from the output of the optic disc segmentation step, e.g. by a smoothing operation) and data derived from the out-put of the optic cup segmentation (i.e. the output of the cup segmentation () and/or data derived from the output of the optic disc segmentation, e.g. by a smoothing operation) are fed () 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.

Automatic cup-to-disc ratio measurement system

A method for determining the position of an optic cup boundary in a 2D retinal image. The method includes detecting kinks in blood vessels at an estimated boundary of the optic cup and the optic disc, and determining the position of the optic cup boundary in the 2D retinal image based on the detected kinks. The determined optic cup boundary may be used for determining a CDR which may in turn be used for determining a risk of contracting glaucomatous.

Method and system for determining the position of an optic cup boundary

A method and system for generating an entirely well-focused image of a three-dimensional scene. The method comprises the steps of a) learning a prediction model including at least a focal depth probability density function (PDF), h(k), for all depth values k, from historical tiles of the scene; b) predicting the possible focal surfaces in subsequent tiles of the scene by applying the prediction model; c) for each value of k, examining h(k) such that if h(k) is below a first threshold, no image is acquired at the depth k' for said one tile; and if h(k) is above or equal to a first threshold, one or more images are acquired in a depth range around said value of k for said one tile; and d) processing the acquired images to generate a pixel focus map for said one tile.

Method and system for generating an entirely well-focused image of a large three-dimensional scene

A method, an apparatus and a computer program product for indexing and retrieving image data using visual keywords ( ) is disclosed. Visual keywords ( ) are prototypical, visual tokens ( ) and are extracted from samples of visual documents ( ) in a visual-content domain via supervised and/or unsupervised learning processes. An image or a video-shot key frame is described and indexed by a signature ( ) that registers the spatial distribution of the visual keywords ( ) present in its visual content. Visual documents ( ) are retrieved for a sample query ( ) by comparing the similarities between the signature ( ) of the query ( ) and those of visual documents ( ) in the database. The signatures ( ) of visual documents ( ) are generated based on spatial distributions of the visual keywords ( ). Singular-value decomposition ( ) is applied to the signatures ( ) to obtain a coded description ( ).

Method and apparatus for indexing and retrieving images using visual keywords

Growing community of inventors

Singapore, Singapore

Joo Hwee Lim