Image processing apparatus and method for controlling the same

Patent metadata

Field	Value
Publication number	US-9700210-B2
Application number	US-71479810-A
Country	US
Kind code	B2
Filing date	Mar 1, 2010
Priority date	Mar 2, 2009
Publication date	Jul 11, 2017
Grant date	Jul 11, 2017

Abstract

An image processing apparatus includes an image acquisition unit configured to acquire a tomographic image of an object, a layer detection unit configured to detect a layer that constitutes the object from the tomographic image acquired by the image acquisition unit, and a normal structure estimation unit configured to estimate a normal structure of the layer based on the layer detected by the layer detection unit and a feature that is modified by a lesion of the layer.

First claim

What is claimed is:

1. An image processing apparatus, comprising:
at least one processor that acquires a tomographic image of an eye portion; and
at least one memory to store the tomographic image of the eye portion;
wherein the processor is configured to:
detect a layer of the eye portion from the tomographic image stored in the memory,
detect, in the detected layer, a portion of the detected layer located deeper than a threshold in the depth direction of the eye portion,
calculate, as a normal structure of the detected layer, a curve which does not extend across the detected layer and contacts with a part of the detected layer at the portion of the detected layer, such that the detected layer does not protrude below the calculated curve, and
quantify a difference between the detected layer and the calculated curve,
wherein the normal structure represents a boundary of the retinal pigment epithelium in the depth direction of the eye portion before the boundary is deformed into a wavy shape of the detected layer.

2. The image processing apparatus according to claim 1 , wherein
the memory stores the information relating to the wavy shape of the detected layer,
wherein the processor is configured to estimate the normal structure of the layer based on the stored information relating to the wavy shape of the detected layer.

3. The image processing apparatus according to claim 1 , wherein the processor is configured to estimate the normal structure of the layer using a mathematical function based on information relating to the wavy shape of the detected layer.

4. The image processing apparatus according to claim 3 , wherein the mathematical function is variable depending on a surface portion or the detected portion located deeper than the threshold.

5. The image processing apparatus according to claim 1 , wherein the processor is configured to estimate the normal structure of the layer by assuming that a shape of the detected layer is a mixed distribution composed of a mathematical function representing a normal structure and a mathematical function representing the wavy shape.

6. The image processing apparatus according to claim 1 , wherein the processor is configured to determine a normal range of the detected layer, and estimate the normal structure of the detected layer based on the normal range.

7. The image processing apparatus according to claim 1 , further comprising:
a display device,
wherein the processor is further configured to:
cause the display device to display a display form indicating a result of quantification of the difference between the detected layer and the calculated curve.

8. The image processing apparatus according to claim 7 , wherein the processor is configured to quantify the state of the layer according to a feature that reflects a difference between the normal structure estimated and a structure of the detected layer.

9. The image processing apparatus according to claim 8 , wherein the feature that reflects the difference is based on either one of thickness, area, volume, and density of the layer.

10. The image processing apparatus according to claim 1 , wherein the processor acquires the tomographic image of an eyeground of the eye portion, and
wherein the processor detects from the tomographic image the layer of the eyeground.

11. The image processing apparatus according to claim 7 , wherein the processor compares the result of quantification with past quantification data and causes the display device to display the comparison.

12. The image processing apparatus according to claim 7 , wherein the processor superimposes a difference area indicating a difference between the detected layer and the normal structure on the tomographic image and causes the display device to display the superimposed image.

13. The image processing apparatus according to claim 7 , wherein the processor superimposes the display form indicating the normal structure on the tomographic image and causes the display device to display the superimposed image.

14. The image processing apparatus according to claim 1 , wherein the processor estimates, as the normal structure, a boundary of the detected layer before deformation of the boundary into the wavy shape.

15. The image processing apparatus according to claim 1 ,
wherein the processor is further configured to set, in the tomographic image, the threshold with respect to the depth direction of the eye portion.

16. A method accomplished by an image processing apparatus having at least one processor and at least one memory, the method comprising:
acquiring a tomographic image of an eye portion;
storing the tomographic image of the eye portion in the memory;
detecting, with the processor, a layer of the eye portion from the tomographic image stored in the memory;
detecting, with the processor, in the detected layer, a portion of the detected layer located deeper than a threshold in the depth direction of the eye portion,
calculating, with the processor, as a normal structure of the detected layer, a curve which does not extend across the detected layer and contacts with a part of the detected layer at the portion of the detected layer, such that the detected layer does not protrude below the calculated curve; and
quantifying a difference between the detected layer and the calculated curve,
wherein the normal structure represents of a boundary of the retinal pigment epithelium in the depth direction of the eye portion before the boundary is deformed into a wavy shape of the detected layer.

17. The method according to claim 16 , wherein estimating the normal structure includes estimating, with the processor, a boundary of the detected layer before deformation of the boundary into the wavy shape.

18. A non-transitory computer-readable medium storing a program that when executed by at least one processor performs a method for controlling an image processing apparatus, comprising:
computer-executable instructions for acquiring a tomographic image of an eye portion;
computer-executable instructions for storing the tomographic image of the eye portion in at least one memory;
computer-executable instructions for detecting a layer of the eye portion from the tomographic image stored in the memory;
computer-executable instructions for detecting, in the detected layer, a portion of the detected layer located deeper than a threshold in the depth direction of the eye portion,
computer-executable instructions for calculating, as a normal structure of the detected layer, a curve which does not extend across the detected layer and contacts with a part of the detected layer at the portion of the detected layer, such that the detected layer does not protrude below the calculated curve; and
computer-executable instructions for quantifying a difference between the detected layer and the calculated curve,
wherein the normal structure represents a boundary of the retinal pigment epithelium in the depth direction of the eye portion before the boundary is deformed into a wavy shape of the detected layer.

19. An image processing apparatus, comprising:
at least one processor that acquires a tomographic image of an eye portion; and
at least one memory to store the tomographic image of the eye portion,
wherein the processor is configured to:
detect a layer of the eye portion from the tomographic image stored in the memory;
detect, in the detected layer, a portion of the detected layer located deeper than a threshold in the depth direction of the eye portion,
calculate, as a n

Assignees

• Iwase Yoshihiko
• Uchiyama Shinji
• Satoh Kiyohide
• Canon Kk

Inventors

• Iwase Yoshihiko
• Uchiyama Shinji
• Satoh Kiyohide

Classifications

• A61B5/0066 Primary

  Optical coherence imaging · CPC title

• G06T7/0012

  Biomedical image inspection · CPC title

• G06T2207/30041

  Eye; Retina; Ophthalmic · CPC title

• G06T2207/10072

  Tomographic images · CPC title

• A61B5/0073

  by tomography, i.e. reconstruction of 3D images from 2D projections (A61B5/0066 takes precedence) · CPC title