US 12,367,966 B2
Predicting geographic atrophy growth rate from fundus autofluorescence images using deep neural networks
Simon Shang Gao, San Francisco, CA (US); and Neha Sutheekshna Anegondi, Fremont, CA (US)
Assigned to Genentech, Inc., South San Francisco, CA (US)
Filed by Genentech, Inc., South San Francisco, CA (US)
Filed on Jan. 12, 2023, as Appl. No. 18/153,762.
Application 18/153,762 is a continuation of application No. PCT/US2021/041697, filed on Jul. 14, 2021.
Claims priority of provisional application 63/149,073, filed on Feb. 12, 2021.
Claims priority of provisional application 63/052,292, filed on Jul. 15, 2020.
Prior Publication US 2023/0154595 A1, May 18, 2023
Int. Cl. G16H 50/20 (2018.01); G16H 30/40 (2018.01); G06T 3/4046 (2024.01)
CPC G16H 30/40 (2018.01) [G16H 50/20 (2018.01); G06T 3/4046 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for evaluating geographic atrophy in a retina, the method comprising:
receiving a set of fundus autofluorescence (FAF) images of the retina;
generating an input for a machine learning system using the set of fundus autofluorescence images;
predicting, via the machine learning system, a lesion area for a geographic atrophy lesion in the retina using the set of fundus autofluorescence images; and
predicting, via the machine learning system, a lesion growth rate for the geographic atrophy lesion in the retina using the input.