US 12,293,512 B2
Ophthalmic image processing device and ophthalmic image processing method
Ryosuke Shiba, Aichi (JP); and Yoshiki Kumagai, Aichi (JP)
Assigned to NIDEK CO., LTD., Aichi (JP)
Filed by NIDEK CO., LTD., Aichi (JP)
Filed on Nov. 17, 2021, as Appl. No. 17/528,848.
Claims priority of application No. 2020-193429 (JP), filed on Nov. 20, 2020.
Prior Publication US 2022/0164949 A1, May 26, 2022
Int. Cl. G06T 7/00 (2017.01); A61B 3/10 (2006.01); G06N 20/00 (2019.01); G06T 11/00 (2006.01)
CPC G06T 7/0012 (2013.01) [A61B 3/102 (2013.01); G06N 20/00 (2019.01); G06T 11/00 (2013.01); G06T 2207/10101 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30041 (2013.01); G06T 2207/30101 (2013.01); G06T 2210/41 (2013.01)] 10 Claims
OG exemplary drawing
 
1. An ophthalmic image processing device that processes an ophthalmic image of a subject eye, comprising:
a controller comprising a processor and programming configured to:
acquire an ophthalmic image including a tomographic image of a plurality of tomographic planes in a fundus of the subject eye, wherein the tomographic image is an optical coherence Tomography (OCT) image;
acquire a probability distribution for identifying two or more layers in the fundus and/or boundaries of the layers included in a plurality of layers and/or layer boundaries in the tomographic image, by inputting the ophthalmic image into a mathematical model trained with using a machine learning algorithm;
generate a structural abnormality degree map showing a two-dimensional distribution of a degree of abnormality of a structure in the fundus, for each of the two or more layers and/or layer boundaries, based on the probability distribution; and
simultaneously display two or more structural abnormality degree maps generated for each of the two or more layers and/or layer boundaries side by side on a display device,
wherein a correspondence relationship between a gradation value of each pixel and the degree of abnormality of the structure in the structural abnormality degree map is variable for each structural abnormality degree map generated for each layer and/or layer boundary, or the correspondence relationship differs according to the structural abnormality degree map generated for each layer and/or layer boundary.