US 12,482,100 B2
Method and device for assisting heart disease diagnosis
Tae Geun Choi, Seoul (KR); Geun Yeong Lee, Seoul (KR); and Hyung Taek Rim, Seoul (KR)
Assigned to Medi Whale Inc., Seoul (KR)
Filed by MEDI WHALE INC., Seoul (KR)
Filed on Jan. 4, 2024, as Appl. No. 18/404,108.
Application 18/404,108 is a continuation of application No. 17/356,960, filed on Jun. 24, 2021, granted, now 11,869,184.
Application 17/356,960 is a continuation of application No. 16/807,686, filed on Mar. 3, 2020, granted, now 11,164,313, issued on Nov. 2, 2021.
Application 16/807,686 is a continuation of application No. PCT/KR2018/016388, filed on Dec. 20, 2018.
Claims priority of provisional application 62/776,345, filed on Dec. 6, 2018.
Claims priority of provisional application 62/715,729, filed on Aug. 7, 2018.
Claims priority of provisional application 62/694,901, filed on Jul. 6, 2018.
Claims priority of application No. 10-2017-0175865 (KR), filed on Dec. 20, 2017; application No. 10-2018-0157559 (KR), filed on Dec. 7, 2018; application No. 10-2018-0157560 (KR), filed on Dec. 7, 2018; and application No. 10-2018-0157561 (KR), filed on Dec. 7, 2018.
Prior Publication US 2024/0144478 A1, May 2, 2024
Int. Cl. G06T 7/00 (2017.01); A61B 5/00 (2006.01); A61B 5/02 (2006.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/18 (2022.01); G06V 40/14 (2022.01)
CPC G06T 7/0012 (2013.01) [A61B 5/02 (2013.01); A61B 5/4842 (2013.01); A61B 5/7275 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/18 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30041 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30204 (2013.01); G06V 40/14 (2022.01)] 13 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining a model input comprising at least one fundus image, each of which is an image of a fundus of subject's eye;
processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is a neural network model trained with a quantitative imaging biomarker indicating arteriosclerosis and general vessel status as target labels, and is configured to process the model input to generate a model output that characterizes the subject's cardiovascular disease risk with respect to a predicted quantitative imaging biomarker, and wherein the fundus image processing machine learning model is trained to predict the quantitative imaging biomarker by using pairs of fundus images and corresponding quantitative imaging biomarker data as training data; and
processing the model output to generate diagnosis assistance information, wherein the predicted quantitative imaging biomarker is incorporated into the diagnosis assistance information to characterize an aspect of the subject's cardiovascular disease risk.