Image processing method, image processing apparatus, and program

Abstract

According to the present invention, image processing performed by a processor comprises: a step for acquiring a choroidal vessel image; a step for detecting a vortex vein position from the choroidal vessel image; a step for identifying a choroidal vessel associated with the vortex vein position; and a step for determining the size of the choroidal vessel.

Description

Technical Field

[0001] The technology of the present disclosure relates to an image processing method, an image processing apparatus, and a program.

Background Art

[0002] Conventionally, a technology for analyzing the blood vessels of the choroid has been proposed (U.S. Patent No. 10136812). It is desired to analyze the choroidal blood vessels around the vortex vein.

Summary of the Invention

[0003] A first aspect of the technology of the present disclosure is image processing performed by a processor, including steps of acquiring a choroidal blood vessel image, detecting a vortex vein position from the choroidal blood vessel image, identifying choroidal blood vessels related to the vortex vein position, and obtaining the size of the choroidal blood vessels.

[0004] An image processing apparatus according to a second aspect of the technology of the present disclosure includes a memory and a processor connected to the memory. The processor executes steps of acquiring a choroidal blood vessel image, detecting a vortex vein position from the choroidal blood vessel image, identifying choroidal blood vessels related to the vortex vein position, and obtaining the size of the choroidal blood vessels.

[0005] A program according to a third aspect of the technology of the present disclosure causes a computer to execute steps of acquiring a choroidal blood vessel image, detecting a vortex vein position from the choroidal blood vessel image, identifying choroidal blood vessels related to the vortex vein position, and obtaining the size of the choroidal blood vessels.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5A

Figure 5B

Figure 5C

Figure 6

Figure 7

Figure 8A

Figure 8B

Figure 9A

Figure 9B

Figure 10

Figure 11

Figure 12A

Figure 12B

Figure 13

Figure 14

Figure 15

Best Mode for Carrying Out the Invention

[0007] Hereinafter, an ophthalmic system 100 according to an embodiment of the present invention will be described with reference to the drawings. FIG. 1 shows a schematic configuration of the ophthalmic system 100. As shown in FIG. 1, the ophthalmic system 100 includes an ophthalmic device 110, a server device (hereinafter referred to as "server") 140, and a display device (hereinafter referred to as "viewer") 150. The ophthalmic device 110 acquires fundus images. The server 140 stores a plurality of fundus images obtained by photographing the fundus of a plurality of patients with the ophthalmic device 110 and the axial length measured by an axial length measuring device (not shown) in correspondence with the patient ID. The viewer 150 displays the fundus images and analysis results acquired by the server 140. The server 140 is an example of the "image processing device" of the technology of the present disclosure.

[0008] The ophthalmic device 110, the server 140, and the viewer 150 are interconnected via a network 130. The viewer 150 is a client in a client-server system, and a plurality of viewers are connected via a network. Also, in order to ensure the redundancy of the system, a plurality of servers 140 may be connected via a network. Alternatively, if the ophthalmic device 110 has an image processing function and an image viewing function of the viewer 150, the ophthalmic device 110 can be in a stand-alone state and can acquire, process, and view fundus images. Also, if the server 140 has an image viewing function of the viewer 150, it is possible to acquire, process, and view fundus images with the configuration of the ophthalmic device 110 and the server 140.

[0009] Note that other ophthalmic devices (examination devices such as visual field measurement and intraocular pressure measurement) and a diagnostic support device that performs image analysis using AI (Artificial Intelligence) may be connected to the ophthalmic device 110, the server 140, and the viewer 150 via the network 130.

[0010] Next, with reference to FIG. 2, the configuration of the ophthalmic apparatus 110 will be described.

[0011] For convenience of explanation, a scanning laser ophthalmoscope is referred to as an "SLO", and an optical coherence tomography is referred to as an "OCT".

[0012] When the ophthalmic apparatus 110 is installed on a horizontal plane, the horizontal direction is the "X direction", the direction perpendicular to the horizontal plane is the "Y direction", and the direction connecting the center of the pupil of the anterior segment of the eye to be examined 12 and the center of the eyeball is the "Z direction". Therefore, the X direction, the Y direction, and the Z direction are perpendicular to each other.

[0013] The ophthalmic apparatus 110 includes an imaging device 14 and a control device 16. The imaging device 14 includes an SLO unit 18 and an OCT unit 20, and acquires a fundus image of the fundus of the eye to be examined 12. Hereinafter, the two-dimensional fundus image acquired by the SLO unit 18 is referred to as an SLO image. Also, a tomographic image or an en-face image of the retina created based on the OCT data acquired by the OCT unit 20 is referred to as an OCT image.

[0014] The control device 16 includes a computer having a CPU (Central Processing Unit) 16A, a RAM (Random Access Memory) 16B, a ROM (Read-Only Memory) 16C, and an input / output (I / O) port 16D.

[0015] The control device 16 includes an input / display device 16E connected to the CPU 16A via the I / O port 16D. The input / display device 16E has a graphic user interface for displaying an image of the eye to be examined 12 and receiving various instructions from the user. Examples of the graphic user interface include a touch panel display.

[0016] The control device 16 also includes an image processing device 17 connected to the I / O port 16D. The image processing device 17 generates an image of the eye to be examined 12 based on the data obtained by the imaging device 14. The control device 16 is connected to the network 130 via the communication interface 16F.

[0017] As described above, in FIG. 2, the control device 16 of the ophthalmic device 110 includes the input / display device 16E, but the technology of the present disclosure is not limited thereto. For example, the control device 16 of the ophthalmic device 110 may not include the input / display device 16E, and may be provided with a separate input / display device physically independent of the ophthalmic device 110. In this case, the display device includes an image processing processor unit that operates under the control of the display control unit 204 of the CPU 16A of the control device 16. The image processing processor unit may display an SLO image or the like based on the image signal output-instructed by the display control unit 204.

[0018] The imaging device 14 operates under the control of the CPU 16A of the control device 16. The imaging device 14 includes an SLO unit 18, an imaging optical system 19, and an OCT unit 20. The imaging optical system 19 includes an optical scanner 22 and a wide-angle optical system 30.

[0019] The optical scanner 22 two-dimensionally scans the light emitted from the SLO unit 18 in the X direction and the Y direction. The optical scanner 22 may be an optical element capable of deflecting a light beam. For example, a polygon mirror, a galvanometer mirror, or the like can be used. Also, a combination thereof may be used.

[0020] The wide-angle optical system 30 combines the light from the SLO unit 18 and the light from the OCT unit 20.

[0021] Note that the wide-angle optical system 30 may be a reflective optical system using a concave mirror such as an elliptical mirror, a refractive optical system using a wide-angle lens, or a catadioptric optical system combining a concave mirror and a lens. By using a wide-angle optical system using an elliptical mirror or a wide-angle lens, it becomes possible to photograph the retina not only in the central part of the fundus but also in the peripheral part of the fundus.

[0022] When using a system including an elliptical mirror, a configuration using a system with an elliptical mirror described in International Publication WO2016 / 103484 or International Publication WO2016 / 103489 may be adopted. The disclosures of International Publication WO2016 / 103484 and International Publication WO2016 / 103489 are each incorporated herein by reference in their entirety.

[0023] The wide-angle optical system 30 enables observation in a wide field of view (FOV) 12A in the fundus. FOV 12A indicates the range that can be photographed by the imaging device 14. FOV 12A can be expressed as a viewing angle. The viewing angle can be defined by an internal irradiation angle and an external irradiation angle in the present embodiment. The external irradiation angle is the irradiation angle of the light beam irradiated from the ophthalmic device 110 to the eye to be examined 12, defined with respect to the pupil 27. The internal irradiation angle is the irradiation angle of the light beam irradiated to the fundus F, defined with respect to the center O of the eyeball. The external irradiation angle and the internal irradiation angle are in a corresponding relationship. For example, when the external irradiation angle is 120 degrees, the internal irradiation angle corresponds to about 160 degrees. In the present embodiment, the internal irradiation angle is 200 degrees.

[0024] Here, an SLO fundus image obtained by photographing with a photographing angle of 160 degrees or more at the internal irradiation angle is referred to as a UWF-SLO fundus image. Note that UWF refers to the abbreviation of UltraWide Field (ultra-wide angle). With the wide-angle optical system 30 having an ultra-wide angle as the viewing angle (FOV) of the fundus, it is possible to photograph a region from the posterior pole to beyond the equator of the fundus of the eye to be examined 12, and structures existing in the peripheral part of the fundus such as vortex veins can be photographed.

[0025] The SLO system is realized by the control device 16, the SLO unit 18, and the imaging optical system 19 shown in FIG. 2. Since the SLO system includes a wide-angle optical system 30, it enables fundus imaging with a wide FOV 12A.

[0026] The SLO unit 18 includes a light source 40 for B light (blue light), a light source 42 for G light (green light), a light source 44 for R light (red light), and a light source 46 for IR light (infrared light (e.g., near-infrared light)), and optical systems 48, 50, 52, 54, 56 that reflect or transmit the light from the light sources 40, 42, 44, 46 and guide it into one optical path. The optical systems 48, 56 are mirrors, and the optical systems 50, 52, 54 are beam splitters. The B light is reflected by the optical system 48, transmitted through the optical system 50, and reflected by the optical system 54. The G light is reflected by the optical systems 50, 54. The R light is transmitted through the optical systems 52, 54. The IR light is reflected by the optical systems 52, 56 and is respectively guided into one optical path.

[0027] The SLO unit 18 is configured to be able to switch combinations of light sources that emit laser light with different wavelengths, such as a mode that emits R light and G light and a mode that emits infrared light. In the example shown in FIG. 2, it includes four light sources: a light source 40 for B light, a light source 42 for G light, a light source 44 for R light, and a light source 46 for IR light. However, the technology of the present disclosure is not limited to this. For example, the SLO unit 18 may further include a light source for white light and emit light in various modes such as a mode that emits G light, R light, and B light, or a mode that emits only white light.

[0028] The light incident from the SLO unit 18 on the imaging optical system 19 is scanned in the X direction and the Y direction by the optical scanner 22. The scanned light is irradiated onto the fundus via the wide-angle optical system 30 and the pupil 27. The reflected light reflected by the fundus is incident on the SLO unit 18 via the wide-angle optical system 30 and the optical scanner 22.

[0029] The SLO unit 18 includes a beam splitter 64 that reflects B light and transmits light other than B light among the light from the posterior eye segment (fundus) of the eye to be examined 12, and a beam splitter 58 that reflects G light and transmits light other than G light among the light transmitted through the beam splitter 64. The SLO unit 18 includes a beam splitter 60 that reflects R light and transmits light other than R light among the light transmitted through the beam splitter 58. The SLO unit 18 includes a beam splitter 62 that reflects IR light among the light transmitted through the beam splitter 60. The SLO unit 18 includes a B light detection element 70 that detects the B light reflected by the beam splitter 64, a G light detection element 72 that detects the G light reflected by the beam splitter 58, an R light detection element 74 that detects the R light reflected by the beam splitter 60, and an IR light detection element 76 that detects the IR light reflected by the beam splitter 62.

[0030] The light (reflected light reflected by the fundus) incident on the SLO unit 18 via the wide-angle optical system 30 and the optical scanner 22 is reflected by the beam splitter 64 and received by the B light detection element 70 in the case of B light, and is reflected by the beam splitter 58 and received by the G light detection element 72 in the case of G light. The above incident light is transmitted through the beam splitter 58 and reflected by the beam splitter 60 and received by the R light detection element 74 in the case of R light. The above incident light is transmitted through the beam splitters 58 and 60 and reflected by the beam splitter 62 and received by the IR light detection element 76 in the case of IR light. The image processing device 17 operating under the control of the CPU 16A generates a UWF-SLO image using the signals detected by the B light detection element 70, the G light detection element 72, the R light detection element 74, and the IR light detection element 76.

[0031] Further, the control device 16 controls the light sources 40, 42, and 44 to emit light simultaneously. By photographing the fundus of the eye 12 simultaneously with B light, G light, and R light, G-color fundus images, R-color fundus images, and B-color fundus images in which each position corresponds to each other are obtained. An RGB-color fundus image is obtained from the G-color fundus image, the R-color fundus image, and the B-color fundus image. The control device 16 controls the light sources 42 and 44 to emit light simultaneously, and by photographing the fundus of the eye 12 simultaneously with G light and R light, G-color fundus images and R-color fundus images in which each position corresponds to each other are obtained. An RG-color fundus image is obtained from the G-color fundus image and the R-color fundus image.

[0032] The wide-angle optical system 30 can set the field of view (FOV) of the fundus to an ultra-wide angle and photograph a region exceeding the equator from the posterior pole of the fundus of the eye 12.

[0033] The equator 178 will be described with reference to FIG. 5A. The eyeball (the eye to be examined 12) is a spherical structure with a spherical center 170 having a diameter of about 24 mm. The straight line connecting the anterior pole 175 and the posterior pole 176 is called the eye axis 172, the line where the plane orthogonal to the eye axis 172 intersects the eye surface is called a latitude line, and the largest one among them is the equator 174. The portion of the retina and choroid corresponding to the position of the equator 174 is defined as the equatorial region 178.

[0034] The ophthalmic device 110 can photograph a region with an internal irradiation angle of 200° with the center of the eyeball 170 of the eye to be examined 12 as a reference position. The internal irradiation angle of 200° corresponds to an external irradiation angle of 110° with respect to the pupil of the eyeball of the eye to be examined 12. That is, the wide-angle optical system 30 irradiates laser light from the pupil with an angular coverage of an external irradiation angle of 110° and photographs a fundus region with an internal irradiation angle of 200°.

[0035] FIG. 5B shows a UWF-SLO image 179 obtained by photographing with an ophthalmic apparatus 110 that can scan at an internal irradiation angle of 200°. As shown in FIG. 5B, the equator 178 corresponds to 180° at the internal irradiation angle, and in the UWF-SLO image 179, the location indicated by the dotted line 178a corresponds to the equator 178. Thus, the ophthalmic apparatus 110 can photograph the fundus region from the posterior pole to beyond the equator 178.

[0036] FIG. 5C is a diagram showing the positional relationship between the choroid 12M and the vortex veins 12V1, V2 in the eyeball. In FIG. 5C, the reticular pattern indicates the choroidal blood vessels of the choroid 12M. The choroidal blood vessels circulate blood throughout the choroid. Then, blood flows out of the eyeball from a plurality (usually four to six) of vortex veins present in the eye to be examined 12. In FIG. 5C, the upper vortex vein V1 and the lower vortex vein V2 present on one side of the eyeball are shown. The vortex veins often exist in the vicinity of the equator 178. Therefore, in order to photograph the vortex veins present in the eye to be examined 12 and the choroidal blood vessels around the vortex veins, it is performed using the ophthalmic apparatus 110 that can scan at the above-described internal irradiation angle of 200°.

[0037] The OCT system is realized by the control device 16, the OCT unit 20, and the imaging optical system 19 shown in FIG. 2. Since the OCT system includes the wide-angle optical system 30, similar to the photographing of the SLO fundus image described above, it enables OCT imaging of the peripheral fundus. That is, with the wide-angle optical system 30 having an ultra-wide-angle field of view (FOV) of the fundus, OCT imaging of the region from the posterior pole to beyond the equator 178 of the fundus of the eye to be examined 12 can be performed. OCT data of structures present in the peripheral fundus such as the vortex veins can be acquired, and a tomographic image of the vortex veins and a 3D structure of the vortex veins can be obtained by image processing of the OCT data.

[0038] The OCT unit 20 includes a light source 20A, a sensor (detection element) 20B, a first optical coupler 20C, a reference optical system 20D, a collimating lens 20E, and a second optical coupler 20F.

[0039] The light emitted from the light source 20A is branched by the first optical coupler 20C. One of the branched lights is collimated by the collimating lens 20E as measurement light and then incident on the imaging optical system 19. The measurement light is irradiated onto the fundus via the wide-angle optical system 30 and the pupil 27. The measurement light reflected by the fundus is incident on the OCT unit 20 via the wide-angle optical system 30, and is incident on the second optical coupler 20F via the collimating lens 20E and the first optical coupler 20C.

[0040] The other light emitted from the light source 20A and branched by the first optical coupler 20C is incident on the reference optical system 20D as reference light, and is incident on the second optical coupler 20F via the reference optical system 20D.

[0041] These lights incident on the second optical coupler 20F, that is, the measurement light reflected by the fundus and the reference light, are interfered by the second optical coupler 20F to generate interference light. The interference light is received by the sensor 20B. The image processing apparatus 17 operating under the control of the image processing unit 206 generates OCT images such as tomographic images and en-face images based on the OCT data detected by the sensor 20B.

[0042] Here, an OCT image obtained by imaging with an imaging angle of 160 degrees or more at the internal irradiation angle, or an OCT image obtained by scanning the peripheral part of the fundus is referred to as a UWF-OCT image. The OCT image includes a tomographic image of the fundus by B-scan, a three-dimensional image (3D image) based on OCT volume data, and an en-face image (2D image) which is a cross-section of the OCT volume data.

[0043] The image data of the UWF-OCT image is sent from the ophthalmic device 110 to the server 140 via the communication interface 16F and stored in the storage device 254.

[0044] In the present embodiment, the light source 20A is an example of a wavelength-sweeping type SS-OCT (Swept-Source OCT), but OCT systems of various types such as SD-OCT (Spectral-Domain OCT) and TD-OCT (Time-Domain OCT) may also be used.

[0045] Next, with reference to FIG. 3, the electrical configuration of the server 140 will be described. As shown in FIG. 3, the server 140 includes a computer main body 252. The computer main body 252 has a CPU 262, a RAM 266, a ROM 264, and an input / output (I / O) port 268. A storage device 254, a display 256, a mouse 255M, a keyboard 255K, and a communication interface (I / F) 258 are connected to the input / output (I / O) port 268. The storage device 254 is composed of, for example, a non-volatile memory. The input / output (I / O) port 268 is connected to the network 130 via the communication interface (I / F) 258. Therefore, the server 140 can communicate with the ophthalmic device 110 and the viewer 150. An image processing program shown in FIG. 6 is stored in the ROM 264 or the storage device 254. The ROM 264 or the storage device 254 is an example of the "memory" of the technology of the present disclosure. The CPU 262 is an example of the "processor" of the technology of the present disclosure. The image processing program is an example of the "program" of the technology of the present disclosure.

[0046] The server 140 stores each data received from the ophthalmic device 110 in the storage device 254.

[0047] Various functions realized by the CPU 262 of the server 140 executing the image processing program will be described. As shown in FIG. 4, the image processing program includes a display control function, an image processing function, and a processing function. By the CPU 262 executing the image processing program having these functions, the CPU 262 functions as a display control unit 204, an image processing unit 206, and a processing unit 208.

[0048] Next, with reference to FIG. 6, the image processing by the server 140 will be described in detail. When the CPU 262 of the server 140 executes an image processing program, the image processing (image processing method) shown in the flowchart of FIG. 6 is realized.

[0049] In step 600, the image processing unit 206 acquires, as a UWF fundus image, a UWF-SLO image 179 as shown in FIG. 5B from the storage device 254. In step 602, the image processing unit 206 creates (acquires) a choroidal vascular image, which is a binary image, from the acquired UWF-SLO image, and extracts choroidal blood vessels from the created choroidal vascular image.

[0050] First, a method for creating (acquiring) a choroidal vascular image will be described. Note that the choroidal vascular image is a binary image in which pixels corresponding to choroidal blood vessels and vortex veins are white and pixels in other regions are black.

[0051] A case where the choroidal vascular image is generated from an R-color fundus image and a G-color fundus image will be described. First, the information included in the R-color fundus image and the G-color fundus image will be described.

[0052] The structure of the eye is such that the vitreous body is covered by a plurality of layers with different structures. The plurality of layers include, from the innermost to the outermost on the vitreous body side, the retina, the choroid, and the sclera. R light passes through the retina and reaches the choroid. Therefore, the first fundus image (R-color fundus image) includes information on blood vessels (retinal blood vessels) present in the retina and information on blood vessels (choroidal blood vessels) present in the choroid. In contrast, G light reaches only the retina. Therefore, the second fundus image (G-color fundus image) includes only information on blood vessels (retinal blood vessels) present in the retina.

[0053] The image processing unit 206 of the CPU 262 extracts retinal blood vessels from the second fundus image (G-color fundus image) by performing black hat filter processing on the second fundus image (G-color fundus image). Next, the image processing unit 206 removes the retinal blood vessels from the first fundus image (R-color fundus image) by inpainting processing using the retinal blood vessels extracted from the second fundus image (G-color fundus image). That is, a process of filling in the retinal blood vessel structure of the first fundus image (R-color fundus image) with the same value as the surrounding pixels is performed using the position information of the retinal blood vessels extracted from the second fundus image (G-color fundus image). Then, the image processing unit 206 performs adaptive histogram equalization processing (CLAHE, Contrast Limited Adaptive Histogram Equalization) on the image data of the first fundus image (R-color fundus image) from which the retinal blood vessels have been removed, thereby emphasizing the choroidal blood vessels in the first fundus image (R-color fundus image). As a result, a choroidal blood vessel image in which the background is represented by black pixels and the choroidal blood vessels are represented by white pixels is obtained. The generated choroidal blood vessel image is stored in the storage device 254.

[0054] Also, although a choroidal blood vessel image is generated from the first fundus image (R-color fundus image) and the second fundus image (G-color fundus image), the image processing unit 206 may generate a choroidal blood vessel image using the first fundus image (R-color fundus image) or an IR fundus image taken with IR light.

[0055] Regarding the method for generating a choroidal blood vessel image, the disclosure of International Publication WO2019 / 181981 is incorporated herein by reference in its entirety.

[0056] Next, a method for extracting choroidal blood vessels from the choroidal blood vessel image will be described. As described above, since the choroidal blood vessel image is a binarized image in which pixels corresponding to choroidal blood vessels and vortex veins are white and pixels in other regions are black, the image processing unit 206 extracts the choroidal blood vessels including the vortex veins by extracting the white portions from the choroidal blood vessel image. The information on the choroidal blood vessels is stored in the storage device 254. Note that the vortex vein (VV (Vortex Vein)) is an outflow path for the blood flow that has flowed into the choroid.

[0057] In step 604, the position (X, Y) of the vortex vein (VV) is detected as follows. The image processing unit 206 sets the moving direction (blood vessel running direction) of each choroidal blood vessel in the choroidal blood vessel image. Specifically, first, the image processing unit 206 executes the following processing for each pixel of the choroidal blood vessel image. That is, the image processing unit 206 sets a region (cell) centered on the pixel and creates a histogram of the gradient direction of the luminance at each pixel within the cell. Next, the image processing unit 206 sets the gradient direction with the fewest counts in the histogram of each cell as the moving direction of the pixels within each cell. This gradient direction corresponds to the blood vessel running direction. The reason why the gradient direction with the fewest counts is the blood vessel running direction is as follows. The luminance gradient is small in the blood vessel running direction, while the luminance gradient is large in other directions (for example, the luminance difference between blood vessels and other things is large). Therefore, when creating a histogram of the luminance gradient of each pixel, the count for the blood vessel running direction becomes small. Through the above processing, the blood vessel running direction of each pixel in the choroidal blood vessel image is set.

[0058] The image processing unit 206 sets the initial positions of M (natural number) × N (natural number) (= L) particles. Specifically, the image processing unit 206 sets a total of L initial positions at equal intervals on the choroidal blood vessel image, with M positions in the vertical direction and N positions in the horizontal direction.

[0059] The image processing unit 206 estimates (detects) the position of the vortex vein. Specifically, the image processing unit 206 performs the following processing for each of the L positions. That is, the image processing unit 206 acquires the blood vessel running direction at the first position (any of the L positions), moves the particle a predetermined distance along the acquired blood vessel running direction, and at the moved position, acquires the blood vessel running direction again and moves the particle a predetermined distance along the acquired blood vessel running direction. The above process of moving a predetermined distance along the blood vessel running direction is repeated for a preset number of times. The above processing is executed at all L positions. At that time, the point where a certain number or more of particles are gathered is defined as the position of the vortex vein. Further, as another method for detecting a vortex vein, image processing for recognizing a position on the choroidal blood vessel image where the feature amount of the radial pattern is equal to or greater than a predetermined value as the vortex vein, or detecting the position of the vortex vein by detecting the dilated portion of the vortex vein from the choroidal blood vessel image may be performed. Regarding the method for detecting the vortex vein, the disclosure of International Publication WO2019 / 203309 is incorporated herein by reference in its entirety.

[0060] The vortex vein position information (the number of vortex veins, coordinates on the choroidal blood vessel image, etc.) is stored in the storage device 254.

[0061] In step 606, the image processing unit 206 executes a blood vessel area calculation process. FIG. 7 shows a flowchart showing the details of the blood vessel area calculation process in step 606. In step 702 of FIG. 7, the image processing unit 206 reads each data of the choroidal blood vessel image (binary image) and the vortex vein position information from the storage device 254.

[0062] In step 704, the image processing unit 206 classifies each pixel on the choroidal blood vessel by determining which of the plurality of detected vortex veins (hereinafter referred to as "VV") the pixel is related to. Hereinafter, the classification method of each pixel on the choroidal blood vessel will be described.

[0063] There are three classification methods. First, there is a method in which, after determining a boundary line for defining a region related to VV in the choroidal vascular image, classification is performed. Second, there is a method in which, after determining boundary points on the choroidal blood vessels, classification is performed. Third, there is a method of classification without determining a boundary line and boundary points. Note that a choroidal vascular image may be displayed on the display 256 of the server 140, and an operator may set a boundary line or boundary points or associate pixels on the choroidal blood vessels with VV using the mouse 255M or the like. However, in the present embodiment, the image processing unit 206 automatically classifies each of the above pixels by performing image processing.

[0064] First, a first classification method of performing classification after determining a boundary line as described above will be described. Specifically, the first classification method includes a method of uniquely (without duplication) determining the boundary of a region related to each VV in the choroidal vascular image, and a method in which an overlapping region is set in a region related to each VV.

[0065] A method of uniquely determining a boundary in the first classification method will be described. The image processing unit 206 determines regions corresponding to each of a plurality of VVs in the choroidal vascular image so as to be adjacent to an adjacent region, that is, so that no overlapping region occurs. FIGS. 8A and 8B show a choroidal vascular image of a portion where adjacent VV1 and VV2 exist. As shown in FIG. 8A, the image processing unit 206 determines one boundary line B11 for defining a region corresponding to VV1 and a region corresponding to VV2.

[0066] As a method of determining one boundary line B12, for example, there is a Graph Cut processing method. There is also the following processing method. As shown in FIG. 8B, the image processing unit 206 calculates the straight-line distance from each VV for each pixel of the choroidal vascular image, determines the VV corresponding to the shortest straight-line distance from the calculated straight-line distances, and associates the determined VV with the pixel. The image processing unit 206 sets each pixel associated with the same VV in the same group. The image processing unit 206 determines one boundary line B12 that divides each group from the positions between pixels whose adjacent pixels belong to different groups.

[0067] In step 704, the image processing unit 206 determines, based on the boundary line B11 or B12, to which one (only one) of the plurality of VVs each pixel on the choroidal blood vessels is related.

[0068] A method of setting an overlapping region in the region related to each VV in the first classification method will be described. FIGS. 9A and 9B show a choroidal blood vessel image of a portion where adjacent VV1 and VV2 exist. As shown in FIG. 9A, the image processing unit 206 determines two boundary lines B21 and B22 by combining dynamic contour processing (Snakes method or Level set processing). In the example shown in FIG. 9A, among the boundary lines B21 and B22, the image processing unit 206 classifies each pixel on the choroidal blood vessels located on the VV2 side from the boundary line B21 close to VV1 as a pixel related to VV2. Among the boundary lines B21 and B22, the image processing unit 206 classifies each pixel on the choroidal blood vessels located on the VV1 side from the boundary line B22 close to VV2 as a pixel related to VV1. The image processing unit 206 classifies each pixel on the choroidal blood vessels located in the region sandwiched between the boundary line B21 and the boundary line B22 as a pixel related to both VV1 and VV2. Also, two boundary lines B21 and B22 can be determined by a method of combining graph cut processing and dynamic contour processing.

[0069] As a method of setting an overlapping region in the region related to each VV, there is also the following method in addition to the above-described method. As shown in FIG. 9B, for each VV, the image processing unit 206 sets circles C1 and C2 with a radius of a predetermined length centered on the VV, and sets the circumferences of the circles C1 and C2 as boundary lines. The image processing unit 206 classifies each pixel on the choroidal blood vessels that does not belong to either circle C1 or circle C2, and when circles C1 and C2 overlap, each pixel on the choroidal blood vessels in the overlapping region, as pixels located in the overlapping region related to both VV1 and VV2. The image processing unit 206 classifies each pixel on the choroidal blood vessels within circle C1 excluding the overlapping region as a pixel related to VV1. The image processing unit 206 classifies each pixel on the choroidal blood vessels within circle C2 excluding the overlapping region as a pixel related to VV2.

[0070] Next, a method of classification after determining boundary points on the choroidal blood vessels in the second classification method will be described. FIG. 10 shows a choroidal blood vessel image of a portion where adjacent VV1 and VV2 exist. The image processing unit 206 thins the choroidal blood vessels. For each pixel on the thinned choroidal blood vessels, the image processing unit 206 counts the number of pixels up to each VV along the thinned choroidal blood vessels. The image processing unit 206 determines the VV corresponding to the pixel number with the fewest number of pixels, and associates the determined VV with the pixel. The image processing unit 206 sets each pixel associated with the same VV in the same group. The image processing unit 206 determines the positions between pixels where adjacent pixels on the thinned choroidal blood vessels belong to different groups as boundary points P1 and P2. The image processing unit 206 classifies each pixel on the choroidal blood vessels by determining to which VV (only one) among a plurality of VVs each pixel is related based on the boundary points P1 and P2.

[0071] Next, a method of classification without determining a boundary line and boundary points in the third classification method will be described. FIG. 11 shows a choroidal blood vessel image of a portion where adjacent VV1 and VV2 exist. The image processing unit 206 thins the choroidal blood vessels. For each pixel on the thinned choroidal blood vessels, the image processing unit 206 counts the number of pixels up to each VV1 and VV2 along the thinned choroidal blood vessels. The image processing unit 206 classifies each pixel for which the number of pixels counted along the thinned choroidal blood vessels from any of VV1 and VV2 is a predetermined number or more as a pixel overlapping with each of VV1 and VV2. The image processing unit 206 classifies each pixel for which the number of pixels counted along the thinned choroidal blood vessels is less than the predetermined number as a pixel corresponding to the VV traced by the pixels less than the predetermined number.

[0072] When any of the above classification processes is completed, the blood vessel area calculation process proceeds to step 706.

[0073] In step 706, the image processing unit 206 initializes a variable n for identifying each of the detected plurality of VVs to 0, and in step 708, the image processing unit 206 increments the variable n by 1.

[0074] In step 710, the image processing unit 206 contacts (connects) with VVn identified by the variable n, that is, extracts the choroidal blood vessels that are connected as VVn connecting blood vessels. FIGS. 12A and 12B show choroidal blood vessel images of the portions where VVn (for example, VV3 (n = 3)) exists. The image processing unit 206 may extract all the pixels of the choroidal blood vessels connected to VVn (= 3), but first, as shown in FIG. 12A, in the choroidal blood vessel image, only the portion of the pixels classified as the pixels corresponding to VVn (= 3) among the pixels of the choroidal blood vessels connected to VVn (= 3) is extracted. As shown in FIG. 12A, the image processing unit 206 extracts the choroidal blood vessels (only the above-classified pixels) connected from the position of VVn (= 3) as VV connecting blood vessels. Alternatively, as shown in FIG. 12B, the image processing unit 206 may extract the choroidal blood vessels (only the above-classified pixels) connected to a certain range (a circle C3 with a radius of a certain length) from the position of VV3 as VVn connecting blood vessels.

[0075] In step 712, the image processing unit 206 extracts (identifies) only the choroidal blood vessels around VVn among the VVn connecting blood vessels as VVn surrounding blood vessels. FIG. 13 shows a choroidal blood vessel image of the portion where VVn (for example, VV4 (n = 4)) exists. The image processing unit 206 extracts the remaining blood vessel portion as VVn surrounding blood vessels by eliminating the blood vessel portion exceeding a certain range (a circle C4 with a radius of a certain length) from VVn in the VVn connecting blood vessels. The choroidal blood vessels around VVn (VVn surrounding blood vessels) are an example of the "choroidal blood vessels related to the position of the vortex vein" of the technology of the present disclosure. The choroidal blood vessels around VVn (VVn surrounding blood vessels) are connected to VVn and are an example of the "choroidal blood vessels connected to the vortex vein" of the technology of the present disclosure.

[0076] In step 714, the image processing unit 206 calculates the area of the VVn surrounding blood vessels. For example, For each pixel of the VVn peripheral blood vessels, the image processing unit 206 reads out the area of the fundus corresponding to the pixel, and calculates the area of the VVn peripheral blood vessels by adding the read areas for each pixel of the VVn peripheral blood vessels. Note that the following value is used for the area of the fundus corresponding to the pixel. A patient's eyeball model is created in advance by correcting the standard eyeball model based on the patient's axial length. In the storage device 254, the area on the patient's eyeball model is stored corresponding to each pixel of the choroidal blood vessel image. In step 714, the image processing unit 206 reads out and uses the area corresponding to the pixel stored in the storage device 254.

[0077] In step 716, the image processing unit 206 determines whether the variable n is equal to the total number N of detected VVs. If it is not determined that the variable n is equal to the total number N, there is a VV for which the area of the peripheral blood vessels has not been calculated, so the blood vessel area calculation process returns to step 708 and repeats the above process (steps 708 to 716).

[0078] If it is determined that the variable n is equal to the total number N, the area of the peripheral blood vessels has been calculated for all VVs, so the blood vessel area calculation process (step 606 in FIG. 6) ends and the image processing proceeds to step 608.

[0079] In step 608, the image processing unit 206 executes an analysis process. The analysis process will be described below.

[0080] The image processing unit 206 calculates statistical values of the blood vessel areas calculated for all VVs. Examples of the statistical values include the average value and standard deviation of the blood vessel areas calculated for all VVs, and the maximum value and minimum value among the blood vessel areas calculated for all VVs.

[0081] The statistical values include the average value, standard deviation, maximum value, and minimum value of the calculated vascular area for each quadrant. Note that the image processing unit 206 detects the watershed of the choroidal vascular network and determines the quadrants based on the detected watershed. The watershed is an area in the choroidal vascular image where the density of the choroidal vessels is lower than other areas (for example, curves LX and LY, see also the choroidal vascular image display field 544 in FIG. 14).

[0082] The statistical values include the values obtained by comparing the average value, standard deviation, maximum value, and minimum value of the vascular area between quadrants. The compared values are the differences, standard deviation, maximum value, and minimum value of the above values (average value, standard deviation, maximum value, and minimum value) between each quadrant. The statistical values include the following VV center distance and VV center angle. Specifically, these values are obtained as follows. A graph representing each position of the choroidal vascular image in polar coordinates (distance and angle from the center of the choroidal vascular image) is created, and at least one of the centroid position of VV (from VV1 to VV4) and the weighted centroid position is used as the center position to obtain the distance from the center of the above graph to the center position (VV center distance) and the angle of the center position (VV center angle).

[0083] The image processing unit 206 calculates the difference between the calculated statistical value and the corresponding statistical value stored in the normal eye database previously stored in the storage device 254.

[0084] The image processing unit 206 detects the positions of the optic nerve head and the macula from the UWF fundus image. The image processing unit 206 calculates the distance between the optic nerve head and each VV, the distance between the macula and each VV, the angle between the line connecting the optic nerve head and the macula and the line connecting the macula and each VV, and the angle between the line connecting the optic nerve head and the macula and the line connecting the optic nerve head and each VV.

[0085] The image processing unit 206 calculates the centroid position and the centroid position weighted by the vascular area for each VV as the center position for all VVs.

[0086] In step 608, the image processing unit 206 creates data for the display screen for displaying the calculated value. FIG. 14 shows a first display screen 500A. As shown in FIG. 14, the first display screen 500A has an information area 502 and an image display area 504A. The information area 502 has a patient ID display field 512, a patient name display field 514, an age display field 516, a visual acuity display field 518, a right eye / left eye display field 520, and an axial length display field 522. In each display area from the patient ID display field 512 to the axial length display field 522, the viewer 150 displays each piece of information based on the information received from the server 140.

[0087] The image display area 504A is an area for displaying a fundus image or the like. The following display fields are provided in the image display area 504A. Specifically, there are a comment field 530, a UWF fundus image display field 542, a choroidal vascular image display field 544, a first vascular area display field 526, and a second vascular area display field 528.

[0088] The comment field 530 is a remarks column where an ophthalmologist who is a user can arbitrarily input the observed result or the diagnosis result.

[0089] In the UWF fundus image display field 542, a circle (〇) centered on the position of each VV (from VV1 to VV4) and at least one of the centroid position and the weighted centroid position as the center position are displayed on the UWF fundus image. In the example shown in FIG. 14, a circular area (●) centered on the weighted centroid position is displayed.

[0090] In the choroidal vascular image display field 544, curves LX, LY indicating each watershed, VV connecting vessels, and circles C4 (from C41 to C44) for setting the vessels around VVn are displayed on the choroidal vascular image.

[0091] In the first vascular area display field 526, a bar graph showing the vascular area corresponding to each VV, the average value of the vascular area: ○○ [μm], and the standard deviation: ●● [μm] are displayed. In "○○", the specific value of the average value of the vascular area is displayed. In "●●", the specific value of the standard deviation is displayed.

[0092] In the second vascular area display field 528, on a graph representing each position of the choroidal vascular image in polar coordinates (distance and angle from the center of the choroidal vascular image), a circle centered on the position of each VV and having an area corresponding to the vascular area, and at least one of the centroid position and the weighted centroid position as the center position are displayed. In the example shown in FIG. 14, a circular area (●) centered on the weighted centroid position is displayed. In the second vascular area display field 528, the distance from the center of the graph at the center position (for example, the weighted centroid position) (VV center distance): △△ [μm], and the angle of the center position (VV center angle): ▲▲ [deg] are displayed. In △△ [μm], the specific value of the VV center distance is displayed. In ▲▲ [deg], the specific value of the VV center angle is displayed.

[0093] When the creation of the data on the display screen is completed as described above, the process of step 608 in FIG. 6 is completed. In step 610, the image processing unit 206 outputs (stores) each value calculated in step 608 and the data on the display screen to the storage device 254 corresponding to the patient ID.

[0094] When an ophthalmologist diagnoses a patient, according to the operation of the ophthalmologist, the viewer 150 instructs the server 140 to specify the patient ID and transmit each data stored in the storage device 254 corresponding to the patient ID. The server 140 transmits each data stored in the storage device 254 corresponding to the patient ID to the viewer 150. The viewer 150 displays the first display screen 500A shown in FIG. 14 on the display based on the received each data.

[0095] As described above, in the present embodiment, the blood vessel area is calculated. When there is a disease in the choroidal blood vessels, the blood vessel area calculated for the VV corresponding to the choroidal blood vessels increases. Therefore, an ophthalmologist or the like can determine whether there is a disease in the choroidal blood vessels of the VV from the blood vessel area of the VV. For example, in the example shown in FIG. 14, the blood vessel area of VV3 is larger than the blood vessel areas of other VVs. Therefore, an ophthalmologist or the like can determine whether there is a disease in the choroidal blood vessels of VV3.

[0096] Also, in the present embodiment, the centroid position without weighting is calculated, and the centroid position with weighting is calculated as the center position. For example, when a disease occurs in which blood flow is biased to one location, the corresponding VV expands, the blood vessel area increases, and when the center point of the VV is calculated using the blood vessel area as a weight, the weighted centroid position shifts from the unweighted centroid position to the side of the VV where the blood vessel area has increased. Therefore, an ophthalmologist or the like can determine whether a disease has occurred in which blood flow is biased to one location from the weighted centroid position and the unweighted centroid position.

[0097] In the embodiment described above, the position of the vortex vein (VV) is detected as the position (X, Y) on the choroidal blood vessel image. The technology of the present disclosure is not limited to this. For example, a standard eyeball model is corrected with the axial length of the eyeball stored corresponding to the patient ID to obtain a corrected eyeball model, the choroidal blood vessel image is mapped onto the obtained eyeball model, and the position of the vortex vein (VV) is detected as the position (X, Y, Z) on the eyeball model onto which the choroidal blood vessel image is mapped. In step 608 of FIG. 6, each value is calculated using the eyeball model onto which the choroidal blood vessel image is mapped.

[0098] For example, the position vn=(xn, yn, zn) of each VV is calculated.

[0099] The center position vcenter for all VVs is represented by a vector indicated by vcenter = Rx(xcenter, ycenter, zcenter). R is the radius of the eyeball model corrected with the axial length of the eye to be examined.

[0100] Here, xcenter is calculated by the formula indicated by Equation 1.

[0101]

Equation

[0102] xcenter is the normalization of xc, and xc is calculated by the weighted average of x.

[0103] wn is the weight related to the vascular area. It is not limited to obtaining the weighted average value in this way, and the m-th power average or the like may be used.

[0104] yc and zc are also calculated in the same way as xc. ycenter and zcenter are also calculated in the same way as xcenter.

[0105] For each vector from the center of the eyeball model to VV, the weight of the vascular area integral is attached, and by synthesizing the weighted vectors, the vector from the center of the eyeball model to the VV center point is calculated.

[0106] FIG. 15 shows the second display screen 500B when each value is calculated using the eyeball model in step 608 of FIG. 6. As shown in FIG. 15, since the second display screen 500B is substantially the same as the first display screen 500A, the different parts will be described.

[0107] The second display screen 500B is provided with an eyeball model display field 532 instead of at least one of the first blood vessel area display field 526 and the second blood vessel area display field 528 in the first display screen 500A. In the example shown in FIG. 15, the eyeball model display field 532 is provided instead of the second blood vessel area display field 528. In the eyeball model display field 532, vectors to each VV (VV1 to VV4) and vectors to at least one of the centroid position and the weighted centroid position are displayed. In the example shown in FIG. 15, a vector to the weighted centroid position is displayed.

[0108] Also, in the above-described embodiments, the blood vessel area is calculated using the choroidal blood vessel image obtained from the UWF fundus image. The technology of the present disclosure is not limited to this. For example, a three-dimensional image (3D image) based on OCT volume data may be used to calculate the blood vessel volume. In this case, in step 608, instead of the blood vessel area, the blood vessel volume is used. For example, the above weighting uses the blood vessel volume.

[0109] In each of the examples described above, the case where image processing is realized by a software configuration using a computer is exemplified, but the technology of the present disclosure is not limited to this. For example, instead of a software configuration using a computer, image processing may be executed only by a hardware configuration such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). Part of the image processing may be executed by a software configuration and the remaining processing may be executed by a hardware configuration.

[0110] As described above, since the technology of the present disclosure includes cases where image processing is realized by a software configuration using a computer and cases where it is not, it includes the following technologies.

[0111] (First technology) An acquisition unit that acquires a choroidal vascular image, A detection unit that detects the position of the vortex vein from the choroidal vascular image, An identification unit that identifies the choroidal blood vessels related to the position of the vortex vein, A calculation unit that calculates the size of the choroidal blood vessels, An image processing apparatus comprising the same.

[0112] (Second technology) A step in which the acquisition unit acquires a choroidal vascular image, A step in which the detection unit detects the position of the vortex vein from the choroidal vascular image, A step in which the identification unit identifies the choroidal blood vessels related to the position of the vortex vein, A step in which the calculation unit calculates the size of the choroidal blood vessels, An image processing method.

[0113] The image processing unit 206 is an example of the "acquisition unit", "detection unit", "identification unit", and "calculation unit" of the technology of the present disclosure.

[0114] The following technology is proposed from the above disclosure content. (Third technology) A computer program product for image processing, The computer program product includes a computer-readable storage medium that is not itself a transient signal, A program is stored in the computer-readable storage medium, The program is To cause a computer to Acquire a choroidal vascular image, Detect the position of the vortex vein from the choroidal vascular image, Identify the choroidal blood vessels related to the position of the vortex vein, Determine the size of the choroidal blood vessels, And execute A computer program product.

[0115] Server 140 is an example of the "computer program product" of the technology of the present disclosure.

[0116] Each of the image processes described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be changed within the scope of not departing from the gist.

[0117] The disclosure of Japanese Patent Application No. 2020-073123 is incorporated herein by reference in its entirety. All documents, patent applications, and technical standards described in this specification are incorporated herein by reference in the same manner as if each individual document, patent application, and technical standard were specifically and individually described as being incorporated by reference.

Claims

1. An image processing method performed by a processor, comprising: obtaining a choroidal vascular image; detecting a first vortex vein and a second vortex vein from the choroidal vascular image; classifying each of all the choroidal blood vessels in the choroidal vascular image into a first choroidal blood vessel group associated with the first vortex vein or a second choroidal blood vessel group associated with the second vortex vein based on the position information of the first vortex vein and the second vortex vein; and an image processing method including the above steps.

2. The classifying step includes: dividing the choroidal blood vessels connecting both the first vortex vein and the second vortex vein and connecting between the first vortex vein and the second vortex vein into the first choroidal blood vessel group associated with the first vortex vein or the second choroidal blood vessel group associated with the second vortex vein by dividing the choroidal blood vessels connecting between the first vortex vein and the second vortex vein based on the position information with respect to the first vortex vein and the second vortex vein. The image processing method according to Claim 1.

3. The classifying step classifies the choroidal blood vessels in the choroidal vascular image into the first choroidal blood vessel group or the second choroidal blood vessel group by classifying the pixels on the choroidal blood vessels as pixels of the first choroidal blood vessel group or the second choroidal blood vessel group. The image processing method according to Claim 1 or Claim 2.

4. The classifying step classifies the choroidal blood vessels into the first choroidal blood vessel group or the second choroidal blood vessel group based on the straight-line distances between each pixel on the choroidal blood vessels in the choroidal vascular image and the first vortex vein and the second vortex vein. The image processing method according to Claim 3.

5. The classifying step sets a boundary line based on the straight-line distances between each pixel on the choroidal blood vessels and the first vortex vein and the second vortex vein, and classifies the choroidal blood vessels in the choroidal vascular image into the first choroidal blood vessel group or the second choroidal blood vessel group based on the boundary line. The image processing method according to Claim 3.

6. The classifying step sets a boundary line between the first vortex vein and the second vortex vein based on the running direction of the choroidal blood vessels, and classifies the choroidal blood vessels in the choroidal vascular image into the first choroidal blood vessel group or the second choroidal blood vessel group based on the boundary line. The image processing method according to Claim 3.

7. The step of classifying measures, for each pixel on the choroidal blood vessels, the number of pixels from the choroidal blood vessels along to the first vorticose vein and the second vorticose vein, and classifies the choroidal blood vessels into the first choroidal blood vessel group or the second choroidal blood vessel group based on the measured number of pixels. The image processing method according to claim 3.

8. The step of classifying identifies, as the first choroidal blood vessel group, pixels among the pixels on the choroidal blood vessels where the measurement result up to the first vorticose vein is less than the measurement result up to the second vorticose vein. The image processing method according to claim 7.

9. The step of classifying extracts pixels on the choroidal blood vessels connecting from the first choroidal blood vessel group to the first vorticose vein, and extracts pixels on the choroidal blood vessels connecting from the second choroidal blood vessel group to the second vorticose vein. The image processing method according to any one of claims 1 to 8.

10. The method further includes a step of obtaining the area or volume of the choroidal blood vessels related to the first vorticose vein based on the first choroidal blood vessel group. The image processing method according to any one of claims 1 to 9.

11. The step of obtaining the area or volume obtains the area or volume of the choroidal blood vessels related to the first vorticose vein based on the pixels on the choroidal blood vessels located within a certain range including the position of the first vorticose vein among the first choroidal blood vessel group. The image processing method according to claim 10.

12. The method further includes a display step of superimposing and displaying the area or volume of the choroidal blood vessels related to the first vorticose vein obtained in the step of obtaining the area or volume and the choroidal blood vessels related to the first vorticose vein used for calculating the area or volume. The image processing method according to claim 10 or claim 11.

13. The step of obtaining the choroidal blood vessel image obtains a three-dimensional image of the choroidal blood vessels composed of OCT volume data. The step of obtaining the area or volume obtains the volume of the choroidal blood vessels. The image processing method according to any one of claims 10 to 12.

14. The step of classifying measures, for each pixel on the choroidal blood vessels, the number of pixels from the choroidal blood vessels along to the first vorticose vein and the second vorticose vein, and classifies the pixels on the choroidal blood vessels where the number of pixels up to the first vorticose vein and the second vorticose vein is less than a predetermined number as pixels of the first choroidal blood vessel group and the second choroidal blood vessel group in duplicate. The image processing method according to any one of claims 3 to 13.

15. A step of obtaining the area or volume of the choroidal blood vessels related to the second vortex vein based on the second choroidal blood vessel group; A step of calculating the central position between the first vortex vein and the second vortex vein, which is weighted based on the area or volume of the choroidal blood vessels related to the first vortex vein and the second vortex vein; The image processing method according to any one of claims 10 to 14, further comprising:

16. An image acquisition unit that acquires a choroidal blood vessel image; A detection unit that detects a first vortex vein and a second vortex vein from the choroidal blood vessel image; A classification unit that classifies each of all the choroidal blood vessels in the choroidal blood vessel image into a first choroidal blood vessel group related to the first vortex vein or a second choroidal blood vessel group related to the second vortex vein based on the position information of the first vortex vein and the second vortex vein; An image processing apparatus comprising:

17. The classification unit is connected to both the first vortex vein and the second vortex vein, and divides the choroidal blood vessels connecting between the first vortex vein and the second vortex vein based on the position information with respect to the first vortex vein and the second vortex vein, thereby classifying the choroidal blood vessels connecting between them into a first choroidal blood vessel group related to the first vortex vein or a second choroidal blood vessel group related to the second vortex vein, The image processing apparatus according to claim 16.

18. A program for causing a computer to execute a procedure for acquiring a choroidal blood vessel image, a procedure for detecting a first vortex vein and a second vortex vein from the choroidal blood vessel image, and a procedure for classifying each of all the choroidal blood vessels in the choroidal blood vessel image into a first choroidal blood vessel group related to the first vortex vein or a second choroidal blood vessel group related to the second vortex vein based on the position information of the first vortex vein and the second vortex vein.

19. The classifying procedure is connected to both the first vortex vein and the second vortex vein, and divides the choroidal blood vessels connecting between the first vortex vein and the second vortex vein based on the position information with respect to the first vortex vein and the second vortex vein, thereby classifying the choroidal blood vessels connecting between them into a first choroidal blood vessel group related to the first vortex vein or a second choroidal blood vessel group related to the second vortex vein, The program according to claim 18.

Images