University of Michigan

Kanishka T Jayasundera

Matthew K Johnson-Roberson

Nathan T Patel

Christopher R Ranella

Daniel L Albertus

Ira H Schachar

Victor M Elner

Jillian T Huang

Naheed W Khan

Sarwar Zahid

Amani Al-Tarouti

Zhao Huang

Andrew M Lynch

Carla S Kaspar

Gail Hohner

Adnan Tahir

A method for automatically measuring changes in retinal, retinal pigment epithelial, or choroidal disease includes retrieving a set of images of a fundus and selecting a plurality of images from the set of images. The plurality of images are co-registered and pre-processed such that the quality, contrast, and gain of each of the plurality of images is made similar. Then, a comparison is made between the plurality of images to determine a change in retinal, retinal pigment epithelial, or choroidal disease, wherein the change in retinal, retinal pigment epithelial, or choroidal disease is determined based on various disease metrics. Finally, an indication of the change in retinal, retinal pigment epithelial, or choroidal disease is generated for display to a user on a computing device.

Automated measurement of changes in retinal, retinal pigment epithelial, or choroidal disease

The invention relates to methods and systems for automatically detecting an optic disc in a retinal fundus autofluorescence image. A monochromatic image of a retina is obtained by stimulated autofluorescence. The image is processed using filters and machine learning to identify blood vessel segments and to identify pixels as possible optic disc pixels. The possible optic disc pixels are grouped into clusters, and a best fit circle (or portion thereof lying within the image) is fitted to each cluster. The circle may be enlarged to improve image contrast at the circumference of the circle. Blood vessel segments that intersect the circle are identified, and metrics are derived from such intersecting blood vessel segments. These metrics are assessed by machine learning processes to determine the probability that each cluster contains the optic disc, and the contours of the optic disc are further determined by analysis of the possible optic disc pixels.

Optic disc detection in retinal autofluorescence images

A method for automatically diagnosing inherited retinal disease includes receiving a plurality of dissimilar types of data and pre-processing at least one of the plurality of dissimilar types of data to generate a feature vector descriptive of a patient. Further, the method includes, for each of the plurality of dissimilar types of data: (i) comparing portions of the respective type of data or a corresponding feature vector to data in a mutation proven database; (ii) generating a ranked list of matches between the patient and the plurality of patients with known diagnoses; and (iii) storing the ranked list of matches in an output database. A diagnosis routine then aggregates a plurality of ranked lists of matches in the output database to generate a ranked list of genetic diagnoses corresponding to the patient and sends an indication of the ranked list of genetic diagnoses to the end user device.

Systems and methods for diagnosing inherited retinal diseases

Growing community of inventors

Ann Arbor, MI, United States of America

Kanishka T Jayasundera