US 12,380,558 B2
Method for differentiating retinal layers in oct image
Hyoung Uk Kim, Anyang-si (KR); and Seong Yeol Park, Anyang-si (KR)
Assigned to HUVITZ CO., LTD., Anyang-si (KR)
Filed by HUVITZ CO., LTD., Anyang-si (KR)
Filed on Oct. 14, 2022, as Appl. No. 17/966,628.
Claims priority of application No. 10-2021-0146595 (KR), filed on Oct. 29, 2021.
Prior Publication US 2023/0137102 A1, May 4, 2023
Int. Cl. G06T 7/00 (2017.01); G06T 7/13 (2017.01)
CPC G06T 7/0012 (2013.01) [G06T 7/13 (2017.01); G06T 2207/10101 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30041 (2013.01)] 4 Claims
OG exemplary drawing
 
1. A method of determining boundary lines between retinal layers, comprising:
step S20 of obtaining an optical coherence tomography (OCT) retinal layer image of an eye to be examined and inputting it into a deep neural network;
step S22 of calculating a probability P that each pixel is included in each layer from the inputted layer image;
step S24 of calculating a probability P1(x, y) that a pixel at the coordinate (x, y) is in or above (k−1)-th layer and a probability P2(x, y) that the pixel is in or below k-th layer from probabilities P (x, y) that the pixel at the coordinate (x, y) is included in each layer, wherein the probability P1(x, y) and the probability P2(x, y) are calculated by steps of:
calculating a likelihood L1 that the pixel at position (x, y) is located above a boundary line between the (k−1)-th layer and the k-th layer, the likelihood L1 being determined by summing probabilities, output by the deep neural network, that the pixel is classified as belonging to one of retinal layers Cuppers above the boundary line, and a likelihood L2 that the pixel is located below the boundary line, the likelihood L2 being determined by summing probabilities, output by the deep neural network, that the pixel is classified as belonging to one of retinal layers Clowers below the boundary line, using Equation 1 below:
L1(x,y)Σi∈cuppersPl(x,y),L2(x,y)=Σi∈clowerspl(x,y)  Equation 1:
obtaining the probability P1 and the probability P2 from the likelihood L1 and the likelihood L2 using Equation 2 below:

OG Complex Work Unit Math
step S26 of calculating a probability Fk−1,k(x, y) that the pixel becomes a boundary line between the (k−1)-th layer and the k-th layer from the probability P1(x, y) that the pixel is in or above the (k−1)-th layer and the probability P2(x, y) that the pixel is in or below the k-th layer;
step S28 of obtaining a node cost Ck−1,k(x, y) of the pixel by multiplying the probability Fk−1,k(x, y) that the pixel at the position (x, y) becomes the boundary line between the (k−1)-th layer and the k-th layer with an image brightness change ΔI at the pixel; and
step S30 of determining the boundary line between the (k−1)-th layer and the k-th layer by connecting the coordinates (x, y) of the pixels where the node cost Ck−1,k(x, y) calculated for each position x is the maximum.