Method, device, electronic equipment and storage medium for positioning macular center in fundus images

Patent metadata

Field	Value
Publication number	US-12154381-B2
Application number	US-202017620733-A
Country	US
Kind code	B2
Filing date	May 29, 2020
Priority date	Oct 11, 2019
Publication date	Nov 26, 2024
Grant date	Nov 26, 2024

Abstract

The application relates to the technical field of artificial intelligence, and provides a method, device, electronic equipment and storage medium for positioning macular center in fundus images. The method comprises: acquiring a detection result of the fundus image detection model, wherein the detection result includes an optic disc area, and a first detection block and a first confidence score corresponding to the optic disc area, and a macular area, and a second detection block and a second confidence score corresponding to the macular area; calculating a center point coordinate of the optic disc area according to the first detection block, and calculating a center point coordinate of the macular area according to the second detection block; identifying whether the to-be-detected fundus image is a left eye fundus image or a right eye fundus image, and correcting a center point of the macular area using different correction models.

First claim

What is claimed is:

1. A method for positioning macular center in fundus images, comprising:
inputting a to-be-detected fundus image into a pre-trained fundus image detection model;
acquiring a detection result of the fundus image detection model, wherein the detection result comprises an optic disc area, and a first detection block and a first confidence score corresponding to the optic disc area, and a macular area, and a second detection block and a second confidence score corresponding to the macular area in a fundus image;
calculating a center point coordinate of the optic disc area according to the first detection block, and calculating a center point coordinate of the macular area according to the second detection block;
comparing the second confidence score with a preset first confidence threshold and a preset second confidence threshold, wherein the preset first confidence threshold is greater than the preset second confidence threshold;
if the second confidence score is less than the preset second confidence threshold, identifying whether the to-be-detected fundus image is a left eye fundus image or a right eye fundus image using a pre-trained left and right eye recognition model;
correcting a center point of the macular area using different correction models for the left eye fundus image and the right eye fundus image.

2. The method of claim 1 , wherein the step of correcting a center point of the macular area using different correction models for the left eye fundus image and the right eye fundus image comprises:
correcting the center point of the macular area using a first correction model and the center point coordinate of the optic disc area for the left eye fundus image, and the first correction model is as follows:

x
fovea

=

{

x
oc

+

(

2.42
*
h

)

2

-

(

y
fovea

-

y
oc

)

2

,

⁢
others

x
oc

=

0.39
*

(

W
2

)

,

❘
"\[LeftBracketingBar]"

x
fovea

-

x
oc

❘
"\[RightBracketingBar]"

<

0.3
*
W
⁢

OR

❘
"\[LeftBracketingBar]"

x
fovea

-

x
oc

❘
"\[RightBracketingBar]"

>

0.465
*
W

,

y
fovea

=

0.3
*

y
oc

Assignees

• Ping An Tech Shenzhen Co Ltd

Inventors

• Li Ge
• Wang Rui
• Wang Lilong
• Tang Yijun
• Zhang Meng
• Gao Peng

Classifications

• G06T2207/30041

  Eye; Retina; Ophthalmic · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T7/60

  Analysis of geometric attributes · CPC title

• G06V10/776

  Validation; Performance evaluation · CPC title