IMAGE PROCESSING APPARATUS, CONTROL METHOD THEREOF, AND COMPUTER PROGRAM

• US 20120063660A1
• Filed: 05/26/2010
• Published: 03/15/2012
• Est. Priority Date: 06/02/2009
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Imamura, Hiroshi, Katayama, Akihiro
• Granted Patent: US 8,861,817 B2
• Time in Patent Office: Days
• US Class Current: 382/131
• CPC Class Codes: A61B 3/102 for optical coherence tomography [OCT]
• CPC Class Codes: A61B 5/0066 Optical coherence imaging
• CPC Class Codes: A61B 5/0073 by tomography, i.e. reconstruction of 3D images from 2D projections A61B5/0066 takes precedence
• CPC Class Codes: G01B 9/02083 characterised by particular signal processing and presentation
• CPC Class Codes: G01B 9/02091 Tomographic interferometers, e.g. based on optical coherence
• CPC Class Codes: G06T 2207/10101 Optical tomography; Optical coherence tomography [OCT]
• CPC Class Codes: G06T 2207/30041 Eye; Retina; Ophthalmic
• CPC Class Codes: G06T 7/12 Edge-based segmentation

Abstract

The present invention an image processing apparatus, which processes an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprises, layer candidate detection means for detecting layer candidates of a retina of the eye to be examined from the tomogram, artifact region determination means for determining an artifact region in the tomogram based on image features obtained using the layer candidates, and image correction means for correcting intensities in the artifact region based on a determination result of the artifact region determination means and image features in the region.

Claims

1. An image processing apparatus, which processes an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprising:

a layer candidate detection unit configured to detect layer candidates of a retina of the eye to be examined from the tomogram;

an artifact region determination unit configured to determine an artifact region in the tomogram based on image features obtained using the layer candidates; and

an image correction unit configured to correct intensities in the artifact region based on a determination result of said artifact region determination unit and image features in the region.

2. The apparatus according to claim 1, further comprising a layer decision unit configured to decide a position of a layer of the retina in the artifact region, based on intensities in the artifact region, which are corrected by said image correction unit.

3. The apparatus according to claim 2, further comprising intensity use judgment unit configured to judge, based on magnitudes of the intensities, whether or not to use the intensities in the artifact region in deciding the position of the layer,

wherein when said intensity use judgment unit judges that the intensities are used, said layer decision unit executes decision processing of the position of the layer using the intensities, and

when said intensity use judgment unit judges that the intensities are not used, said layer decision unit decides the position of the layer by interpolation processing using the layer candidates near the artifact region.

6. The apparatus according to claim 1, wherein the image features obtained using the layer candidates include a continuity between the layer candidates, and

said artifact region determination unit determines the artifact region in the tomogram to have a layer candidate, which has a low continuity and is determined to be discontinuous, as an edge point of the artifact region.

7. The apparatus according to claim 6, wherein said artifact region determination unit uses, as the edge point of the artifact region, a layer candidate having lower intensities in a region deeper than respective layer candidates of two layer candidates which are determined to be discontinuous.

8. The apparatus according to claim 1, wherein the image features obtained using the layer candidates include differences between intensities of pixels in regions specified by the two layer candidates in a direction perpendicular to an A-scan direction of the tomogram, and

said artifact region determination unit determines the artifact region in the tomogram based on a degree of difference between a plurality of intensity profiles in the A-scan direction.

9. The apparatus according to claim 1, further comprising:

a projection image generation unit configured to generate a projection image by adding respective pixels of the tomogram in an A-scan direction of the tomogram corresponding to a depth direction of the retina; and

a feature extraction unit for extracting a feature region including at least one of biological tissue and a morbid portion in the eye to be examined from the projection image,

wherein said artifact region determination unit determines the artifact region in and in the vicinity of the feature region.

10. The apparatus according to claim 9, wherein said feature extraction unit further extracts the feature region from a surface image obtained by capturing an image of the eye to be examined, and

said artifact region determination unit determines the artifact region by further using the feature region extracted from the surface image.

4. An image processing apparatus, which processes an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprising:

a layer candidate detection unit configured to detect layer candidates of a retina of the eye to be examined from the tomogram;

an artifact region determination unit configured to determine an artifact region in the tomogram based on image features obtained using the layer candidates; and

a layer decision unit configured to decide a position of a layer of the retina in the artifact region, based on a determination result of said artifact region determination unit,

wherein said layer decision unit uses a geometric model which is used to specify a layer geometry included in the artifact region and is defined by a plurality of control points, and decides the position of the layer based on evaluation functions associated with a geometry of the geometric model and evaluation functions associated with intensities near the control points.

5. The apparatus according to claim 4, wherein said layer decision unit decides weights of evaluation functions associated with intensities to increase the weights of the evaluation functions associated with the intensities with decreasing intensities of pixels in the artifact region, or decides weights of the evaluation functions in accordance with a ratio between intensities of pixels in the artifact region and intensities of pixels other than the artifact region in the tomogram, and

said layer decision unit decides weights of the evaluation functions associated with the geometry so as to reduce the weights with increasing degree of unevenness in accordance with the degree of unevenness of a geometry of a layer specified by the layer candidates near the artifact region.

11. A control method of an image processing apparatus, which processes an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprising:

a layer candidate detection step of controlling layer candidate detection unit to detect layer candidates of a retina of the eye to be examined from the tomogram;

an artifact region determination step of controlling artifact region determination unit to determine an artifact region in the tomogram based on image features obtained using the layer candidates; and

an image correction step of controlling image correction means to correct intensities in the artifact region based on a determination result in the artifact region determination step and image features in the region.

12. A control method of an image processing apparatus, which processes an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprising:

a layer candidate detection step of controlling layer candidate detection unit to detect layer candidates of a retina of the eye to be examined from the tomogram;

an artifact region determination step of controlling artifact region determination unit to determine an artifact region in the tomogram based on image features obtained using the layer candidates; and

a layer decision step of controlling layer decision unit to decide a position of a layer of the retina in the artifact region, based on a determination result in the artifact region determination step,

wherein in the layer decision step, a geometric model which is used to specify a layer geometry included in the artifact region and is defined by a plurality of control points is used, and the position of the layer is decided based on evaluation functions associated with a geometry of the geometric model and evaluation functions associated with intensities near the control points.

13. A non-transitory computer readable storage medium storing a computer program for making a computer function as respective units of an image processing apparatus which processes an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, said apparatus comprising:

a layer candidate detection unit configured to detect layer candidates of a retina of the eye to be examined from the tomogram;

an artifact region determination unit configured to determining an artifact region in the tomogram based on image features obtained using the layer candidates; and

an image correction unit configured to correct intensities in the artifact region based on a determination result of said artifact region determination unit and image features in the region.

14. A non-transitory computer readable storage medium storing a computer program for making a computer function as respective units of an image processing apparatus which processes an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, said apparatus comprising:

a layer candidate detection unit configured to detect layer candidates of a retina of the eye to be examined from the tomogram;

an artifact region determination unit configured to determine an artifact region in the tomogram based on image features obtained using the layer candidates; and

a layer decision unit configured to decide a position of a layer of the retina in the artifact region, based on a determination result of said artifact region determination unit,

wherein said layer decision unit uses a geometric model which is used to specify a layer geometry included in the artifact region and is defined by a plurality of control points, and decides the position of the layer based on evaluation functions associated with a geometry of the geometric model and evaluation functions associated with intensities near the control points.

15. A method for processing an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprising:

an identifying step for identifying an artifact region in the tomogram;

a first detection step for detecting, by a first method, boundaries of layers constituting a retina of the eye to be examined in a region other than the artifact region;

a second detection step for detecting, by a second method different from the first method based on an intensity of the artifact region, boundaries of layers constituting the retina of the eye to be examined in the artifact region of the tomogram; and

a display step for displaying lines indicating the detected boundaries of the layers by superimposing them on the tomogram.

16. The method according to claim 15, wherein the first method is different from the second method in that an algorism to be used to detect the layers and/or a threshold to be used to detect the boundaries of the layers.

17. The method according to claim 15, wherein in said second detection step, the boundaries of the layers in the artifact region are detected based on the intensity of the artifact region and positions of the boundaries of the layers detected by the first method.

18. The method according to claim 15, wherein in said identifying step, a blood vessel region and/or an exudates region is extracted using the tomogram and/or a fundus image of the eye to be examined and, a region corresponding to the extracted region in the tomogram is identified as the artifact region.

19. The method according to claim 15, wherein in said identifying step, it is determined whether the artifact region having an attenuated intensity exists or not in a region of the tomogram corresponding to the blood vessel region or the exudates region.

20. The method according to claim 15, wherein in said identifying step, the artifact region is identified based on a continuity of candidate points of a predetermined layer boundary detected in the tomogram.

21. The method according to claim 15, wherein in said identifying step, a region, located on the rear side of a blood vessel region of the retina when viewed from the front side of the eye to be examined, is identified as the artifact region.

22. An image processing apparatus which performs a method according to claim 15, the apparatus comprising:

identifying means for performing said identifying step;

detection means for performing said first detection step and said second detection step; and

display means for performing said display step.

23. A tomography system comprising:

an image processing apparatus according to claim 22; and

a tomography apparatus.

24. An image processing apparatus for processing an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprising:

identifying means for identifying an artifact region in the tomogram;

detection means for detecting, by a first method, boundaries of layers constituting a retina of the eye to be examined in a region other than the artifact region, and for detecting, by a second method different from the first method based on an intensity of the artifact region, boundaries of layers constituting the retina of the eye to be examined in the artifact region of the tomogram; and

display means for displaying lines indicating the detected boundaries of the layers by superimposing them on the tomogram.

25. A non-transitory computer readable storage medium storing a computer program causing an image processing apparatus to perform a method for processing an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, said method comprising:

an identifying step for identifying an artifact region in the tomogram;

a first detection step for detecting, by a first method, boundaries of layers constituting a retina of the eye to be examined in a region other than the artifact region;

a second detection step for detecting, by a second method different from the first method based on an intensity of the artifact region, boundaries of layers constituting the retina of the eye to be examined in the artifact region of the tomogram; and

a display step for displaying lines indicating the detected boundaries of the layers by superimposing them on the tomogram.

26. A method for processing an image of a tomogram obtained by capturing an image of an eye to be examined by a tomography apparatus, comprising:

a first detection step for detecting, by a first method, boundaries of layers constituting a retina of the eye to be examined in the tomogram based on respective intensities of the layers;

an identifying step for identifying a region where the boundary detected in said first detecting step is discontinuous;

a second detection step for detecting, by a second method different from the first method based on an intensity of the artifact region, boundaries of layers in the identified region based on an intensity of the identified region; and

a display step for displaying lines indicating the detected boundaries of the layers by superimposing them on the tomogram.