US 12,387,320 B2
Deep neural network framework for processing oct images to predict treatment intensity
Michael Gregg Kawczynski, San Francisco, CA (US); Jeffrey R. Willis, San Francisco, CA (US); Nils Gustav Thomas Bengtsson, South San Francisco, CA (US); Jian Dai, South San Francisco, CA (US); and Simon Shang Gao, San Francisco, CA (US)
Assigned to Genentech, Inc., South San Francisco, CA (US)
Appl. No. 17/782,497
Filed by Genentech, Inc., South San Francisco, CA (US)
PCT Filed Dec. 4, 2020, PCT No. PCT/US2020/063365
§ 371(c)(1), (2) Date Jun. 3, 2022,
PCT Pub. No. WO2021/113674, PCT Pub. Date Jun. 10, 2021.
Claims priority of provisional application 63/017,898, filed on Apr. 30, 2020.
Claims priority of provisional application 62/944,815, filed on Dec. 6, 2019.
Prior Publication US 2023/0025980 A1, Jan. 26, 2023
Int. Cl. G06V 10/82 (2022.01); G06T 3/067 (2024.01); G06T 7/00 (2017.01); G06T 7/187 (2017.01)
CPC G06T 7/0012 (2013.01) [G06T 3/067 (2024.01); G06T 7/187 (2017.01); G06T 2207/10101 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30041 (2013.01); G06T 2210/22 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
accessing an optical coherence tomography (OCT) image that corresponds to an eye of a subject experiencing age-related macular degeneration;
identifying, within the OCT image, a set of pixels that correspond to a retina layer;
flattening the OCT image based on the set of pixels;
generating a plurality of patches using the flattened OCT image, wherein generating the plurality of patches comprises:
performing one or more cropping processes using the flattened OCT image to produce one or more cropped images; and
extracting the plurality of patches from the one or more cropped images;
wherein the plurality of patches comprises patches having a plurality of sizes;
inputting the plurality of patches into a plurality of a patch-specific neural networks;
wherein each patch-specific neural network has been trained, on training patches having a specific size, to predict an effective characteristic of a treatment schedule; and
wherein the plurality of patches is input, based on the size of each patch, to the plurality of patch-specific neural networks;
generating, by the plurality of a patch-specific neural networks, a plurality of patch-specific outputs;
wherein each plurality of patch-specific outputs corresponds to the respective one of the plurality of patches; and
wherein each output of the plurality of patch-specific outputs predicts an effective characteristic of a proposed treatment schedule for the eye of the subject;
weighting, by an integrating neural network that has learned a weighting relationship, the plurality of patch-specific outputs; and
generating, by the integrating neural network and based on the weighted plurality of patch-specific outputs, a label corresponding to the characteristic of the proposed treatment schedule for the eye of the subject;
and
outputting the label.