US 12,293,830 B2
Image-based detection of ophthalmic and systemic diseases
Kang Zhang, Del Mar, CA (US)
Assigned to ANTINOUS TECHNOLOGY COMPANY LIMITED, Macau (MO)
Filed by ANTINOUS TECHNOLOGY COMPANY LIMITED, Macao (MO)
Filed on Sep. 29, 2021, as Appl. No. 17/488,428.
Application 17/488,428 is a continuation of application No. PCT/CN2020/081663, filed on Mar. 27, 2020.
Application PCT/CN2020/081663 is a continuation in part of application No. PCT/CN2019/080525, filed on Mar. 29, 2019.
Prior Publication US 2022/0165418 A1, May 26, 2022
Int. Cl. G16H 50/20 (2018.01); A61B 3/12 (2006.01); G06T 7/00 (2017.01); G06V 10/774 (2022.01); G16H 15/00 (2018.01)
CPC G16H 50/20 (2018.01) [G06T 7/0012 (2013.01); G06V 10/7747 (2022.01); G16H 15/00 (2018.01); A61B 3/12 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30041 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
a) using at least one hardware processor to:
receive ophthalmic image data;
apply a machine-learning classifier, trained using a domain dataset of ophthalmic images that have been labeled with one or more of a plurality of classifications, to classify the received ophthalmic image data into at least one of the plurality of classifications, wherein the machine-learning classifier comprises a convolutional neural network, wherein the plurality of classifications comprise a normal classification and one or more disorder classifications, wherein the one or more disorder classifications comprise at least one of age-related macular degeneration (AMD), diabetic retinopathy (DR), glaucoma, or retinal vein occlusion (RVO); and
provide a report that indicates the at least one classification of the received ophthalmic image data; and
b) using the at least one hardware processor to train the machine-learning classifier by:
initially training the convolutional neural network to discriminate between objects using a non-domain dataset that contains no ophthalmic images labeled with the one or more disorders; and
subsequently retraining one or more final layers in the convolutional neural network using the domain dataset.