Image processing apparatus, control method, and computer readable storage medium for analyzing retina layers of an eye

Patent metadata

Field	Value
Publication number	US-9430825-B2
Application number	US-201013322905-A
Country	US
Kind code	B2
Filing date	May 13, 2010
Priority date	Jun 2, 2009
Publication date	Aug 30, 2016
Grant date	Aug 30, 2016

Abstract

An image processing apparatus, which analyzes retina layers of an eye to be examined, comprising, means for extracting a feature amount, which represents an anatomical feature in the eye to be examined, from a projection image obtained from a tomogram of the retina layers and a fundus image of the eye to be examined, means for determining a type of the anatomical feature based on the feature amount, means for deciding layers to be detected from the retina layers according to the determined type of the anatomical feature, and detecting structures of the decided layers in the tomogram, and means for modifying the structure of the layer included in a region having the anatomical feature of the structures of the layers detected by the layer structure detection means.

First claim

The invention claimed is:

1. An image processing apparatus, which analyzes retina layers of an eye to be examined, comprising:
one or more processors; and
at least one memory coupled to the one or more processors, the at least one memory having instructions stored thereon which, when executed by the one or more processors, cause the image processing apparatus to:
extract a feature amount, which represents an anatomical feature in the eye to be examined from a fundus image of the eye to be examined;
detect structures of the retina layers in a tomogram of the retina layers, wherein the tomogram corresponds to the fundus image;
extract information of a shape of at least one retina layer based on the detected structures of the retina layers;
determine whether the anatomical feature includes a first morbid portion or a blood vessel based on the feature amount and to determine whether or not the anatomical feature includes an age-related macular degeneration as a second morbid portion based on the information of the shape;
decide at least one layer including a retinal pigment epithelium layer from the retina layers according to the determination of whether the anatomical feature includes the first morbid portion or the blood vessel; and
modify the decided at least one layer and estimate, in a case where the anatomical feature includes the second morbid portion, a normal structure of the retinal pigment epithelium layer.

2. The image processing apparatus according to claim 1 , wherein when the anatomical feature includes a blood vessel, a feature amount of the blood vessel is extracted using a filter which emphasizes a linear structure, and
wherein a structure of a layer, which neighbors the blood vessel, is modified by limiting a search range by interpolation using a boundary of the layer, which neighbors the blood vessel, and re-detecting a layer structure within the search range.

3. The image processing apparatus according to claim 1 , wherein when the anatomical feature includes the first morbid portion, a feature amount of the first morbid portion is extracted based on pixel values, and
wherein the decided at least one layer is modified by interpolation using a boundary of the decided at least one layer.

4. The image processing apparatus according to claim 1 , wherein the feature amount is extracted as a value which reflects an existence likelihood of the anatomical feature in the eye to be examined, and
wherein the decided at least one layer having the likelihood not less than a predetermined value is modified.

5. The image processing apparatus according to claim 1 , wherein the at least one memory has further instructions stored thereon which, when executed by the one or more processors, cause the image processing apparatus to update the decided at least one layer which has been modified,
wherein an energy value is calculated based on at least one of an image energy based on variances of intensities in layers which sandwich detection points and an intensity gradient at the detection points, and a shape energy that represents a smoothness of a shape of the layer formed by connecting the detection points, and
wherein the decided at least one layer is updated based on a specified layer boundary.

6. The image processing apparatus according to claim 1 , wherein the feature amount is extracted from the fundus image of the eye to be examined,
wherein when the anatomical feature includes a blood vessel, a feature amount of the blood vessel is extracted using a filter that emphasizes a linear structure, and
wherein when the anatomical feature includes the first morbid portion, a feature amount of the first morbid portion is extracted based on pixel values.

7. A control method of an image processing apparatus, which analyzes retina layers of an eye to be examined, the control method comprising:
extracting a feature amount, which represents an anatomical feature in the eye to be examined from a fundus image of the eye to be examined;
detecting structures of the retina layers in a tomogram of the retina layers, wherein the tomogram corresponds to the fundus image;
extracting information of a shape of at least one retina layer based on the detected structures of the retina layers;
determining whether the anatomical feature includes a first morbid portion or a blood vessel based on the feature amount and determining whether or not the anatomical feature includes an age-related macular degeneration as a second morbid portion based on the information of the shape;
deciding at least one layer including a retinal pigment epithelium layer from the retina layers according to the determination of whether the anatomical feature includes the first morbid portion or the blood vessel;
modifying the decided at least one layer; and
estimating, in a case where the anatomical feature includes the second morbid portion, a normal structure of the retinal pigment epithelium layer.

8. A non-transitory computer readable storage medium storing a computer program for causing a computer to function as an image processing apparatus, which analyzes retina layers of an eye to be examined, to:
extract a feature amount, which represents an anatomical feature in the eye to be examined from a fundus image of the eye to be examined;
detect structures of the retina layers in a tomogram of the retina layers, wherein the tomogram corresponds to the fundus image;
extract information of a shape of at least one retina layer based on the detected structures of the retina layers;
determine whether the anatomical feature includes a first morbid portion or a blood vessel based on the feature amount and to determine whether or not the anatomical feature includes an age-related macular degeneration as a second morbid portion based on the information of the shape;
decide at least one layer including a retinal pigment epithelium layer from the retina layers according to the determination of whether the anatomical feature includes the first morbid portion or the blood vessel; and
modify the decided at least one layer and estimate, in a case where the anatomical feature includes the second morbid portion, a normal structure of the retinal pigment epithelium layer.

9. The image processing apparatus according to claim 1 , wherein a type of the second morbid portion in the retina layers is further determined.

10. The control method of claim 7 , wherein a type of the second morbid portion in the retina layers is determined.

11. The image processing apparatus according to claim 5 , wherein detection points that form a detected layer are used to specify a layer boundary which minimizes an energy value.

12. An image processing apparatus comprising:
one or more processors; and
at least one memory coupled to the one or more processors, the at least one memory having instructions stored thereon which, when executed by the one or more processors, cause the image processing apparatus to:
extract a first morbid portion from a fundus image of an eye to be examined;
specify a region in a tomogram of a fundus of the eye to be examined onto which the first morbid portion is projected;
determine whether or not an age-related macular degeneration as a second morbid portion in the tomogram is present based on information of a shape of at least one layer including a retinal pigment epithelium layer of the fundus;
estimate, in a case where the second morbid portion is present, a normal structure of the retinal pigment epithelium layer;
decide at least one layer of the fundus according to the specified region onto which the first morbid portion is projected; and
interpolate the decided at least one layer in the tomo

Assignees

• Iwase Yoshihiko
• Imamura Hiroshi
• Furukawa Daisuke
• Canon Kk

Inventors

• Iwase Yoshihiko
• Imamura Hiroshi
• Furukawa Daisuke

Classifications

• G06T2207/10101

  Optical tomography; Optical coherence tomography [OCT] · CPC title

• G01N21/4795

  spatially resolved investigating of object in scattering medium (in vivo A61B) · CPC title

• G06T7/0083

  Physics · mapped topic

• G06T7/602

  Physics · mapped topic

• G06T2207/30041

  Eye; Retina; Ophthalmic · CPC title