JP6747617B2 - Ophthalmic image processing device and OCT device - Google Patents

Description

The present disclosure discloses an ophthalmic image processing device that processes an ophthalmic image of an eye to be inspected, an OCT device, an ophthalmic image processing program executed in the ophthalmic image processing device, and a mathematical model construction that constructs a mathematical model used by the ophthalmic image processing device. Regarding the method.

Conventionally, various techniques have been proposed for acquiring a high quality image. For example, the ophthalmologic imaging apparatus described in Patent Document 1 obtains a high-quality tomographic image by performing arithmetic processing on a plurality of tomographic images and suppressing speckle noise.

JP, 2015-9108, A

In the technique of adding and averaging a plurality of images, it is necessary to take a large number of images of the same region repeatedly so as to increase the accuracy of suppressing the influence of noise. Therefore, there is a problem that the shooting time increases in proportion to the number of images to be added.

A typical object of the present disclosure is to provide an ophthalmic image processing device, an OCT device, an ophthalmic image processing program, and a mathematical model building method for appropriately acquiring a high-quality ophthalmic image.

A first aspect of an ophthalmic image processing apparatus provided by an exemplary embodiment of the present disclosure is an ophthalmic image processing apparatus that processes an ophthalmic image that is an image of a tissue of an eye to be inspected, and the ophthalmic image is obtained by an OCT apparatus. An OCT angio image that is a motion contrast image obtained by performing an arithmetic process on at least two OCT signals obtained at different times with respect to the same position, and the control unit of the ophthalmic image processing apparatus is imaged by the OCT apparatus. The obtained OCT angio image or an arithmetic mean image obtained by arithmetically averaging a plurality of OCT angio images obtained by photographing the same part of the tissue by the OCT apparatus is acquired as a base image, and the mathematical model trained by a machine learning algorithm is subjected to the mathematical model described above. By inputting the base image, a target image that is an OCT angio image having a higher image quality than the base image is acquired, and when the timing at which the target image can be displayed has arrived , the target image is previously set according to the timing. At least one of the target image and the basic image is displayed on the display device according to the type of image to be displayed on the display device, and the mathematical model is a plurality of training images of the same site of tissue. Among the ophthalmic images for use, L-based (L≧1) data based on the training ophthalmic images are used as input training data, and H (H>L) the training ophthalmic images are arithmetically averaged. Are trained as output training data.
A second aspect of the ophthalmic image processing apparatus provided by the exemplary embodiment of the present disclosure is an ophthalmic image processing apparatus that processes an ophthalmic image that is an image of a tissue of an eye to be inspected, and the ophthalmic image is obtained by an OCT apparatus. An OCT angio image that is a motion contrast image obtained by performing an arithmetic process on at least two OCT signals obtained at different times with respect to the same position, and the control unit of the ophthalmic image processing apparatus is imaged by the OCT apparatus. The obtained OCT angio image or an arithmetic mean image obtained by arithmetically averaging a plurality of OCT angio images obtained by photographing the same part of the tissue by the OCT apparatus is acquired as a base image, and the mathematical model trained by a machine learning algorithm is subjected to the mathematical model described above. By inputting the base image, a target image that is an OCT angio image having a higher image quality than the base image is acquired, and a two-dimensional tomographic image at a position designated by the user in the tissue included in the imaging range of the target image is acquired. An image is extracted and displayed on a display device, and the mathematical model inputs data based on L (L≧1) of the training ophthalmic images of a plurality of training ophthalmic images of the same region of tissue. The training data is used as training data, and the data of the arithmetic mean image obtained by averaging the H (H>L) training ophthalmic images is used as the training data for output.

The first aspect of the OCT apparatus provided by the exemplary embodiment of the present disclosure is to process the OCT signal by the reference light and the reflected light of the measurement light with which the tissue of the subject's eye is irradiated, thereby treating the tissue ophthalmology. An OCT apparatus for capturing an image, wherein the ophthalmologic image is an OCT angio image which is a motion contrast image obtained by arithmetic processing of at least two OCT signals obtained at different times with respect to the same position, The control unit of the OCT apparatus acquires a captured OCT angio image of the tissue or an arithmetic average image of a plurality of OCT angio images captured of the same site of the tissue as an average, and a machine learning algorithm. By inputting the base image to the mathematical model trained by, the target image which is an OCT angio image having a higher image quality than the base image is acquired, and when it is possible to display the target image In advance, according to the type of image to be displayed on the display device, which is preset according to the timing, at least one of the target image and the basic image is displayed on the display device, and the mathematical model is a tissue. Out of a plurality of training ophthalmic images of the same region, data based on L (L≧1) of the training ophthalmic images is used as input training data, and H (H>L) of the training ophthalmic images. The data of the arithmetic mean image obtained by arithmetic mean of the images is trained as output training data.
A second aspect of the OCT apparatus provided by the exemplary embodiment of the present disclosure is to process the OCT signal by the reference light and the reflected light of the measurement light with which the tissue of the subject's eye is irradiated, thereby treating the tissue ophthalmology. An OCT apparatus for capturing an image, wherein the ophthalmologic image is an OCT angio image which is a motion contrast image obtained by arithmetic processing of at least two OCT signals obtained at different times with respect to the same position, The control unit of the OCT apparatus acquires a captured OCT angio image of the tissue or an arithmetic average image of a plurality of OCT angio images captured of the same part of the tissue as an average, and uses the machine learning algorithm. By inputting the basic image into the mathematical model trained by, a target image that is an OCT angio image having a higher image quality than the basic image is acquired, and the target image is acquired by the user in the tissue included in the imaging range of the target image. The two-dimensional tomographic image at the designated position is extracted and displayed on the display device, and the mathematical model is L (L≧1) of the training images out of a plurality of training ophthalmic images of the same region of the tissue. The data based on the ophthalmic image for training is used as the training data for input, and the data of the arithmetic mean image obtained by arithmetically averaging the H (H>L) training ophthalmic images is used as the training data for output.

Ophthalmologic image processing apparatus according to the present disclosure, and according to the OCT equipment, high quality ophthalmic images are appropriately acquired.

The control unit of the ophthalmic image processing device illustrated in the present disclosure is an ophthalmic image captured by the ophthalmic image capturing device, or an arithmetic mean image obtained by arithmetic mean of a plurality of ophthalmic images obtained by capturing the same region of the tissue by the ophthalmic image capturing device. Is acquired as a base image. The control unit inputs the base image to the mathematical model trained by the machine learning algorithm to acquire a target image of higher quality than the base image. The mathematical model is trained by a training data set, which is a set of input training data and output training data. Data based on L (L≧1) training ophthalmic images among a plurality of training ophthalmic images obtained by photographing the same part of the tissue is used as input training data. In addition, data of an arithmetic mean image obtained by arithmetic mean of H (H>L) training ophthalmic images among a plurality of training ophthalmic images is regarded as output training data (sometimes referred to as correct answer data). It In other words, H is a number larger than the number of training ophthalmic images used for the input training data.

That is, the mathematical model building device that builds a mathematical model executes the image set acquisition step and the training step. In the image set acquisition step, a plurality of training ophthalmologic images of the same region of the tissue of the eye to be examined are acquired. In the training step, among a plurality of training ophthalmic images, data based on L (L≧1) training ophthalmic images is used as input training data, and H (H>L) training ophthalmic images are used. The mathematical model is constructed by training the mathematical model by using the data of the arithmetic mean image of the above as the training data for output.

In this case, the constructed mathematical model is similar to the image obtained by adding and averaging a large number of ophthalmic images, even when a small number of ophthalmic images or an adding and averaging image of a small number of ophthalmic images is input as the base image. A target image in which the influence of noise is suppressed can be output. Therefore, it is easy to shorten the photographing time when photographing the basic image. Further, even in the conventional image processing, it was possible to suppress the influence of noise without performing the averaging processing. However, in the conventional image processing, a weak signal and noise cannot be distinguished, and a weak signal that is originally necessary may be erased. On the other hand, the mathematical model illustrated in the present disclosure can output a target image in which a portion in which an image signal is weak due to an influence other than noise is not erased, based on a base image. Therefore, a high quality ophthalmic image is appropriately acquired.

The data used as the training data for input of the training data set (that is, “data based on L training ophthalmic images”) is the data of the captured ophthalmic image itself (that is, the original image that is not averaged). It may be present, or may be data of an arithmetic mean image obtained by arithmetic mean of a plurality of ophthalmic images. Both the original image data and the arithmetic mean image data may be used as the input training data. When the input training data is the original image data, the base image input to the mathematical model is also preferably the original image that is not averaged. Further, when the input training data is data of an arithmetic mean image, it is desirable that the base image is also an arithmetic mean image. Further, the number of images (at least one of the original image and the arithmetic mean image) used for the input training data may be one, or a plurality (for example, about 2 to 5). May be. Further, the number H of training ophthalmic images used when generating the arithmetic mean image used as the output training data is at least larger than the number of training ophthalmic images used for the input training data. For example, when L original images are used as the input training data, H>L. When an image obtained by averaging L′ images is used as the input training data, H>L′. The number of ophthalmic images used for the base image is smaller than the number of H images.

The ophthalmic image may be a two-dimensional tomographic image of the tissue of the eye to be inspected, which is captured by the OCT apparatus. The control unit of the ophthalmic image processing apparatus may acquire a plurality of basic images obtained by photographing a plurality of mutually different positions in the tissue of the eye to be inspected. The control unit may acquire each target image at each of the plurality of positions by inputting each of the plurality of base images into the mathematical model. The control unit generates, based on the plurality of target images, at least one of a three-dimensional tomographic image of the tissue and a two-dimensional front image when the tissue is viewed from the front (that is, the line-of-sight direction of the eye to be inspected). Good. That is, the ophthalmologic image capturing apparatus includes a three-dimensional tomographic image generating step of generating a three-dimensional tomographic image of the tissue based on the plurality of target images, and a front surface generating a two-dimensional front image of the tissue based on the plurality of target images. At least one of the image generation steps may be executed. In this case, the three-dimensional tomographic image or the two-dimensional front image of the tissue in which the influence of noise is suppressed is appropriately generated without capturing a large number of two-dimensional tomographic images.

The two-dimensional front image may be a so-called “Enface image”. The data of the Enface image is, for example, integrated image data in which luminance values are integrated in the depth direction (Z direction) at each position in the XY direction, integrated value of spectrum data at each position in the XY direction, and a certain depth. Data may be brightness data at each position in the XY directions in the directions, brightness data at each position in the XY directions in any layer of the retina (for example, the retina surface layer), and the like.

The ophthalmic image may be a two-dimensional tomographic image of the fundus of the eye to be inspected, which is captured by the OCT apparatus. The control unit of the ophthalmologic image processing device may identify at least one of the plurality of layers included in the fundus by performing an analysis process on the target image that is a two-dimensional tomographic image. That is, the ophthalmologic image processing device may perform a segmentation step of identifying the layer of the fundus from the acquired target image. In this case, a segmentation result in which the influence of noise is suppressed is appropriately acquired without capturing a large number of two-dimensional tomographic images.

An image other than the two-dimensional tomographic image can be used as the ophthalmic image. For example, the ophthalmologic image may not be a two-dimensional tomographic image, but may be a two-dimensional front image of a tissue (for example, the fundus) taken from the front (that is, the line-of-sight direction of the eye to be examined). In this case, the two-dimensional front image may be an OCT angio image. The OCT angio image may be, for example, a motion contrast image acquired by processing at least two OCT signals acquired at different times with respect to the same position. Further, an image (hereinafter, referred to as “FAF image”) obtained by photographing the autofluorescence (FAF) of the fundus of the eye to be inspected by the laser scanning optometry apparatus (SLO) may be used as the ophthalmologic image. Similarly to the OCT two-dimensional tomographic image, the OCT angio image and the FAF image are also subjected to arithmetic averaging of a plurality of images, so that the influence of noise is appropriately suppressed. Moreover, the imaging part of the ophthalmic image may be, for example, the fundus of the eye to be inspected or the anterior segment. As described above, various images that can suppress the influence of noise by adding and averaging a plurality of images can be used as the ophthalmic image in the present disclosure.

Further, the control unit of the ophthalmologic image processing device may execute an analysis process different from the segmentation process for identifying layers on the target image. For example, the control unit acquires, as a target image, a front image of the fundus showing the blood vessel (for example, the above-described OCT angio image), and performs a process of analyzing the blood vessel density of the fundus on the acquired target image. You may. Further, the control unit may perform an analysis process on an image generated based on a plurality of target images (for example, the above-described three-dimensional tomographic image or Enface image).

The control unit of the ophthalmic image processing device may execute at least one of the simultaneous display process and the switching display process. In the simultaneous display process, the control unit causes the display device to simultaneously display the base image and the target image. In the switching display process, the control unit switches between the base image and the target image and displays them on the display device according to an instruction input by the user. In this case, the user can easily confirm both the target image in which the influence of noise is suppressed and the base image (original image or the arithmetic mean image of the original images) that is the basis of the target image. Therefore, the user can perform the diagnosis and the like more appropriately. The base image and the target image may be displayed on the same display device or may be displayed on different display devices.

The control unit may acquire a plurality of basic images continuously captured by the ophthalmologic image capturing device. The control unit may acquire a plurality of target images by sequentially inputting the acquired plurality of base images into a mathematical model. The control unit may generate moving image data of the tissue based on the acquired plurality of target images. That is, the ophthalmologic image processing device may execute a moving image generating step of generating moving image data of the tissue based on the plurality of target images. In this case, the user can check the moving image of the tissue displayed with the influence of noise suppressed. That is, even with the conventional technique, it is possible to suppress the influence of noise by averaging a plurality of ophthalmic images. However, according to the conventional technique, one arithmetic mean image is created from a plurality of ophthalmologic images, so that when displaying a moving image of a tissue using the arithmetic mean image, the frame rate is likely to be remarkably reduced. In particular, when the shooting position changes over time, it is difficult to generate a good moving image using the arithmetic mean image. On the other hand, the ophthalmic image processing device of the present disclosure can generate a moving image of a tissue in which the influence of noise is suppressed while suppressing a decrease in the frame rate. Therefore, the user can perform the diagnosis and the like more appropriately.

The control unit may cause the display device to simultaneously display the moving image of the base image and the moving image of the target image. Further, the control unit may switch the moving image of the base image and the moving image of the target image to display them on the display device according to an instruction input by the user. In this case, the user can easily confirm both the moving image of the target image and the moving image of the base image.

FIG. 1 is a block diagram showing a schematic configuration of a mathematical model building device 1, an ophthalmic image processing device 21, and ophthalmic image photographing devices 11A and 11B. 7 is a flowchart of a mathematical model building process executed by the mathematical model building device 1. It is an explanatory view for explaining the 1st acquisition pattern of input training data and output training data. It is an explanatory view for explaining the 2nd acquisition pattern of training data for input and training data for output. It is an explanatory view for explaining the 3rd acquisition pattern of training data for input and training data for output. It is an explanatory view for explaining the 4th acquisition pattern of training data for input and training data for output. 7 is a flowchart of a high-quality moving image generation process executed by the ophthalmologic image processing device 21. 9 is a flowchart of a high-quality three-dimensional image generation process executed by the ophthalmologic image processing device 21. It is a figure which shows an example of the high quality three-dimensional image 40.

(Device configuration)
Hereinafter, one of typical embodiments in the present disclosure will be described with reference to the drawings. As shown in FIG. 1, in the present embodiment, a mathematical model building device 1, an ophthalmic image processing device 21, and ophthalmic image photographing devices 11A and 11B are used. The mathematical model building device 1 builds a mathematical model by training a mathematical model with a machine learning algorithm. The constructed mathematical model outputs a target image of higher image quality (in the present embodiment, the influence of noise is appropriately suppressed) higher than that of the base image, based on the input base image. The ophthalmologic image processing device 21 acquires a target image from the base image using a mathematical model. The ophthalmic image capturing apparatuses 11A and 11B capture an ophthalmic image that is an image of the tissue of the subject's eye.

As an example, a personal computer (hereinafter referred to as “PC”) is used for the mathematical model building device 1 of this embodiment. As will be described later in detail, the mathematical model construction device 1 constructs a mathematical model by training the mathematical model using the ophthalmic image acquired from the ophthalmic image capturing device 11A. However, the device that can function as the mathematical model building device 1 is not limited to the PC. For example, the ophthalmic image capturing apparatus 11A may function as the mathematical model building apparatus 1. In addition, the control units of a plurality of devices (for example, the CPU of the PC and the CPU 13A of the ophthalmic image capturing apparatus 11A) may cooperate to build a mathematical model.

A PC is used as the ophthalmologic image processing device 21 of this embodiment. However, the device that can function as the ophthalmic image processing device 21 is not limited to the PC. For example, the ophthalmic image photographing device 11B or the server may function as the ophthalmic image processing device 21. When the ophthalmic image capturing device (OCT device in this embodiment) 11B functions as the ophthalmic image processing device 21, the ophthalmic image capturing device 11B captures an ophthalmic image and produces an ophthalmic image having a higher image quality than the captured ophthalmic image. You can get it properly. Further, a mobile terminal such as a tablet terminal or a smartphone may function as the ophthalmologic image processing device 21. The control units of the plurality of devices (for example, the CPU of the PC and the CPU 13B of the ophthalmic image capturing apparatus 11B) may cooperate to perform various processes.

Further, in the present embodiment, a case where a CPU is used as an example of a controller that performs various processes will be described. However, it goes without saying that a controller other than the CPU may be used for at least a part of various devices. For example, a GPU may be used as the controller to speed up the process.

The mathematical model building device 1 will be described. The mathematical model building device 1 is arranged, for example, in the ophthalmic image processing device 21 or a manufacturer or the like that provides the ophthalmic image processing program to the user. The mathematical model building device 1 includes a control unit 2 that performs various control processes and a communication I/F 5. The control unit 2 includes a CPU 3 that is a controller that controls the control, and a storage device 4 that can store programs and data. The storage device 4 stores a mathematical model building program for executing a mathematical model building process (see FIG. 2) described later. Further, the communication I/F 5 connects the mathematical model building device 1 to other devices (for example, the ophthalmic image photographing device 11A and the ophthalmic image processing device 21).

The mathematical model building device 1 is connected to the operation unit 7 and the display device 8. The operation unit 7 is operated by the user so that the user inputs various instructions to the mathematical model building apparatus 1. As the operation unit 7, for example, at least one of a keyboard, a mouse, a touch panel, etc. can be used. A microphone or the like for inputting various instructions may be used together with the operation unit 7 or in place of the operation unit 7. The display device 8 displays various images. As the display device 8, various devices capable of displaying an image (for example, at least one of a monitor, a display, a projector, etc.) can be used. It should be noted that the “image” in the present disclosure includes both a still image and a moving image.

The mathematical model building apparatus 1 can acquire ophthalmic image data (hereinafter, also simply referred to as “ophthalmic image”) from the ophthalmic image capturing apparatus 11A. The mathematical model building apparatus 1 may acquire the ophthalmic image data from the ophthalmic image photographing apparatus 11A by, for example, at least one of wired communication, wireless communication, and a removable storage medium (for example, a USB memory).

The ophthalmic image processing device 21 will be described. The ophthalmologic image processing device 21 is arranged, for example, in a facility (for example, a hospital or a health examination facility) that diagnoses or inspects a subject. The ophthalmic image processing device 21 includes a control unit 22 that performs various control processes and a communication I/F 25. The control unit 22 includes a CPU 23 that is a controller that controls the control, and a storage device 24 that can store programs and data. The storage device 24 has an ophthalmic image processing program for executing ophthalmic image processing (for example, high-quality moving image generation processing illustrated in FIG. 7 and high-quality three-dimensional image generation processing illustrated in FIG. 8) described below. Remembered The ophthalmologic image processing program includes a program that realizes the mathematical model constructed by the mathematical model constructing apparatus 1. The communication I/F 25 connects the ophthalmic image processing device 21 to another device (for example, the ophthalmic image photographing device 11B and the mathematical model building device 1).

The ophthalmologic image processing device 21 is connected to the operation unit 27 and the display device 28. As the operation unit 27 and the display device 28, various devices can be used as in the operation unit 7 and the display device 8 described above.

The ophthalmic image processing device 21 can acquire an ophthalmic image from the ophthalmic image capturing device 11B. The ophthalmic image processing apparatus 21 may acquire the ophthalmic image from the ophthalmic image capturing apparatus 11B by, for example, at least one of wired communication, wireless communication, and a removable storage medium (for example, USB memory). Further, the ophthalmologic image processing device 21 may acquire a program or the like for realizing the mathematical model constructed by the mathematical model constructing device 1 via communication or the like.

The ophthalmic image capturing apparatuses 11A and 11B will be described. As an example, in the present embodiment, a case will be described in which an ophthalmic image capturing device 11A that provides an ophthalmic image to the mathematical model building device 1 and an ophthalmic image capturing device 11B that provides an ophthalmic image to the ophthalmic image processing device 21 are used. .. However, the number of ophthalmic image capturing devices used is not limited to two. For example, the mathematical model building device 1 and the ophthalmic image processing device 21 may acquire ophthalmic images from a plurality of ophthalmic image capturing devices. Further, the mathematical model building device 1 and the ophthalmic image processing device 21 may acquire the ophthalmic image from one common ophthalmic image photographing device. The two ophthalmic image capturing apparatuses 11A and 11B illustrated in the present embodiment have the same configuration. Therefore, in the following, the two ophthalmic image capturing apparatuses 11A and 11B will be collectively described.

Further, in the present embodiment, an OCT apparatus is exemplified as the ophthalmic image capturing apparatus 11 (11A, 11B). However, an ophthalmic image capturing device other than the OCT device (for example, a laser scanning optometry device (SLO), a fundus camera, a corneal endothelial cell imaging device (CEM), or the like) may be used.

The ophthalmic image capturing device 11 (11A, 11B) includes a control unit 12 (12A, 12B) that performs various control processes, and an ophthalmic image capturing unit 16 (16A, 16B). The control unit 12 includes a CPU 13 (13A, 13B), which is a controller that controls the control, and a storage device 14 (14A, 14B) capable of storing programs, data, and the like.

The ophthalmologic image capturing unit 16 has various configurations necessary for capturing an ophthalmic image of the subject's eye. The ophthalmic image capturing unit 16 of the present embodiment includes an OCT light source, a branching optical element that branches the OCT light emitted from the OCT light source into measurement light and reference light, a scanning unit that scans the measurement light, and a measurement light. An optical system for irradiating the eye to be examined, a light receiving element for receiving the combined light of the light reflected by the tissue of the eye to be examined and the reference light, and the like are included.

The ophthalmologic image capturing apparatus 11 can capture a two-dimensional tomographic image and a three-dimensional tomographic image of the fundus of the eye to be inspected. Specifically, the CPU 13 scans the scan line with OCT light (measurement light) to capture a two-dimensional tomographic image of a cross section intersecting the scan line. Further, the CPU 13 can take a three-dimensional tomographic image of the tissue by two-dimensionally scanning the OCT light. For example, the CPU 13 acquires a plurality of two-dimensional tomographic images by scanning the measurement light on each of a plurality of scan lines whose positions are different from each other in a two-dimensional region when the tissue is viewed from the front. Next, the CPU 13 acquires a three-dimensional tomographic image by combining a plurality of captured two-dimensional tomographic images.

Further, the CPU 13 scans the same site on the tissue (on the same scan line in the present embodiment) with the measurement light a plurality of times to capture a plurality of ophthalmic images of the same site. The CPU 13 can obtain an arithmetic mean image in which the influence of speckle noise is suppressed by performing arithmetic mean processing on a plurality of ophthalmic images of the same part. The averaging process may be performed, for example, by averaging pixel values of pixels at the same position among a plurality of ophthalmic images. The larger the number of images to be subjected to the averaging process, the more easily the effect of speckle noise is suppressed, but the longer the shooting time. The ophthalmic image capturing apparatus 11 executes a tracking process that causes the scanning position of the OCT light to follow the movement of the subject's eye while capturing a plurality of ophthalmic images of the same region.

(Mathematical model construction process)
The mathematical model building process executed by the mathematical model building apparatus 1 will be described with reference to FIGS. The mathematical model building process is executed by the CPU 3 according to the mathematical model building program stored in the storage device 4.

In the mathematical model building process, the mathematical model is trained by the training data set, and thus the mathematical model for outputting a high-quality target image from the base image is built. As will be described in detail later, the training data set includes input training data and output training data. In the present embodiment, data based on one to a plurality of ophthalmic images (two-dimensional tomographic image of the fundus in this embodiment) is used as the input training data. Further, as the output training data, the data of the arithmetic mean image based on the number (H) of ophthalmic images that is larger than the number (L) of the ophthalmic images used for the input training data is used. The input training data and the output training data target the same region of the tissue.

As shown in FIG. 2, the CPU 3 acquires a set 30 (see FIGS. 3 to 6) of a plurality of training ophthalmic images 300A to 300X (X is an arbitrary integer of 2 or more) obtained by imaging the same region of tissue. (S1). Specifically, in the present embodiment, a set of a plurality of two-dimensional tomographic images captured by scanning OCT light on the same scan line on the fundus a plurality of times is used as a set of ophthalmic images for training. It is acquired from the image capturing device 11A. However, the CPU 3 acquires a signal (for example, an OCT signal) that is a basis for generating a two-dimensional tomographic image from the ophthalmologic image capturing apparatus 11A, and generates a two-dimensional tomographic image based on the acquired signal, thereby generating a two-dimensional tomographic image. Images may be acquired.

Next, the CPU 3 acquires input training data from some of the plurality of training ophthalmic images 300A to 300X in the set 30 (S2). A specific acquisition method of the input training data can be selected as appropriate, and details thereof will be described later with reference to FIGS. 3 to 6.

Next, the CPU 3 acquires, as output training data, the arithmetic mean image 31 (see FIGS. 3 to 6) of the plurality of training ophthalmic images 300A to 300X in the set 30 (S3). As described above, the number H of training ophthalmic images used for the arithmetic mean image 31 which is the training data for output is larger than the number L of training ophthalmic images used for the training data for input. As an example, in the present embodiment, as shown in FIGS. 3 to 6, all (for example, 120) of the plurality of training ophthalmic images 300A to 300X in the set 30 are used for the arithmetic mean image 31. The arithmetic mean image 31 may be generated by the mathematical model construction device 1. The mathematical model construction device 1 may also acquire the arithmetic mean image 31 generated by the ophthalmic image photographing device 11A.

The first acquisition pattern of the input training data will be described with reference to FIG. In the first acquisition pattern, the CPU 3 selects one of the training ophthalmic images 300A to 300X included in the set 30 (that is, the original image that has not been averaged). Data is acquired as training data for input. In this case, the ophthalmologic image processing device 21 preferably inputs one original image to the mathematical model as a basic image when inputting the basic image to the constructed mathematical model to acquire the target image. Since the ophthalmologic image processing device 21 can acquire the target image based on one basic image, it is easy to shorten the photographing time of the basic image. In addition, when generating a moving image of a target image, it is easy to increase the frame rate of the moving image.

The second acquisition pattern of the input training data will be described with reference to FIG. In the second acquisition pattern, the CPU 3 acquires, as input training data, data of original images of a plurality of training ophthalmic images among the plurality of training ophthalmic images 300A to 300X included in the set 30. In the example shown in FIG. 4, the data of two training ophthalmic images 300A and 300B are acquired as the training data for input. However, the number of training ophthalmic images acquired as the input training data can be changed within a range smaller than the number of training ophthalmic images used for the arithmetic mean image 31. When the second acquisition pattern is adopted, the ophthalmologic image processing device 21 inputs the basic image to the constructed mathematical model, and the number of training ophthalmic images used as the input training data is as close as possible. It is preferable to input the original image into the mathematical model as a base image. In this case, the quality of the acquired target image is likely to be improved as compared with the case where one original image is input as a base image into the mathematical model. However, even if the second acquisition pattern is adopted, one original image may be input to the mathematical model as a base image. As described above, when the original image is used as the input training data, the number L of the original images used is 1 or more, and is smaller than the number used for the arithmetic mean image 31.

The third acquisition pattern of the input training data will be described with reference to FIG. In the third acquisition pattern, the CPU 3 obtains the data of the arithmetic mean image 32 obtained by arithmetically averaging L (L≧2) training ophthalmic images out of the plurality of training ophthalmic images 300A to 300X included in the set 30. , As training data for input. In the example shown in FIG. 5, the data of the arithmetic mean image 32 of the two training ophthalmic images 300A and 300B is acquired as the training data for input. However, the number of training ophthalmic images used for the arithmetic mean image 32 can be changed within a range smaller than the number of training ophthalmic images used for the arithmetic mean image 31. When the third acquisition pattern is adopted, the ophthalmologic image processing device 21 preferably inputs the arithmetic mean image as the base image when inputting the base image into the constructed mathematical model. The number of ophthalmic images used for the arithmetic mean of the base images is preferably as close as possible to the number of training ophthalmic images used for the arithmetic mean image 32. In this case, compared with the case where one original image is input to the mathematical model as a base image, the quality of the acquired target image is likely to be improved. However, even when the third acquisition pattern is adopted, one original image may be input to the mathematical model as a base image.

The fourth acquisition pattern of the input training data will be described with reference to FIG. In the fourth acquisition pattern, the CPU 3 acquires a plurality of arithmetic average images 32 obtained by arithmetic mean of L (L≧2) training ophthalmic images, and uses the acquired data of the arithmetic average images 32 for input training. Use as data. In the example shown in FIG. 6, the data of the two arithmetic mean images 32A and 32B are acquired as the input training data. However, it is also possible to change the number of arithmetic mean images 32. When the fourth acquisition pattern is adopted, the ophthalmologic image processing device 21 preferably inputs a plurality of arithmetic mean images as the base image when inputting the base image to the constructed mathematical model. In this case, the quality of the acquired target image is likely to be improved as compared with the case where one original image is input as the base image. However, even when the fourth acquisition pattern is adopted, one original image may be input to the mathematical model as a base image.

The four patterns described above are examples, and the above patterns can be changed. For example, the CPU 3 may use the data of the original images of the P training ophthalmic images and the data of the arithmetic mean image 32 of the P′ training ophthalmic images together as the input training data. In this case, the number of training ophthalmic images used for the arithmetic mean image 31, which is the training data for output, is greater than the number of training ophthalmic images used for the training data for input (for example, the sum of P and P′). There are also many.

It is also possible to acquire a plurality of training data sets from one set 30 of the training ophthalmic images 300A to 300X. For example, in the example shown in FIG. 3, a set of training data sets in which the data of the training ophthalmic image 300A is used as the input training data and the data of the arithmetic mean image 31 is used as the output training data is acquired. Here, the CPU 3 can also acquire a training data set in which the data of the training ophthalmic image 300B is the input training data and the data of the arithmetic mean image 31 is the output training data from the same set 30. ..

Returning to the description of FIG. The CPU 3 executes the training of the mathematical model using the training data set by the machine learning algorithm (S4). As machine learning algorithms, for example, neural networks, random forests, boosting, support vector machines (SVM), etc. are generally known.

The neural network is a method of imitating the behavior of the nerve cell network of an organism. Examples of the neural network include feedforward (forward propagation type) neural network, RBF network (radial basis function), spiking neural network, convolutional neural network, recurrent neural network (recurrent neural network, feedback neural network, etc.), probability. Neural networks (Boltzmann machine, Basian network, etc.).

Random forest is a method of generating a large number of decision trees by performing learning based on training data that is randomly sampled. When using a random forest, the branches of a plurality of decision trees learned in advance as a classifier are traced, and the average (or majority) of the results obtained from each decision tree is taken.

Boosting is a method of generating a strong classifier by combining a plurality of weak classifiers. A strong classifier is constructed by sequentially learning simple and weak classifiers.

SVM is a method of configuring a two-class pattern classifier using a linear input element. The SVM learns the parameters of the linear input element based on, for example, a criterion (hyperplane separation theorem) of finding a margin-maximized hyperplane that maximizes the distance from each data point from the training data.

The mathematical model refers to, for example, a data structure for predicting the relationship between input data and output data. The mathematical model is constructed by being trained with the training data set. The training data set is a set of input training data and output training data. The mathematical model is trained such that when certain input training data is input, the corresponding output training data is output. For example, training updates correlation data (eg, weights) for each input and output.

In this embodiment, a multilayer neural network is used as the machine learning algorithm. The neural network includes an input layer for inputting data, an output layer for generating data to be predicted, and one or more hidden layers between the input layer and the output layer. A plurality of nodes (also called units) are arranged in each layer. Specifically, in the present embodiment, a convolutional neural network (CNN), which is a type of multilayer neural network, is used. However, other machine learning algorithms may be used. For example, a hostile generation network (GAN) using two competing neural networks may be adopted as a machine learning algorithm.

The processes of S1 to S4 are repeated until the construction of the mathematical model is completed (S5: NO). When the construction of the mathematical model is completed (S5: YES), the mathematical model construction process ends. The program and data for realizing the constructed mathematical model are incorporated in the ophthalmologic image processing device 21.

(Ophthalmic image processing)
The ophthalmic image processing executed by the ophthalmic image processing device 21 will be described with reference to FIGS. 7 to 9. The ophthalmic image processing is executed by the CPU 23 according to the ophthalmic image processing program stored in the storage device 24.

A high-quality moving image generation process, which is an example of ophthalmic image processing, will be described with reference to FIG. In the high-quality moving image generation processing, a still image of a high-quality target image is acquired using a mathematical model, and a high-quality moving image of the tissue is generated.

First, the CPU 23 acquires a basic image that is an ophthalmologic image (still image) (S11). The base image of the present embodiment is a two-dimensional tomographic image of the fundus, like the above-described training ophthalmic images 300A to 300X. The CPU 23 inputs the base image to the mathematical model described above to acquire a target image having higher image quality than the base image (S12).

In the example illustrated in FIG. 7, the ophthalmologic image capturing apparatus 11B captures a moving image by continuously capturing two-dimensional tomographic images of the fundus. In S11, the CPU 23 sequentially acquires each of the still images that form the moving image captured by the ophthalmic image capturing apparatus 11B. The CPU 23 acquires at least one of the acquired original image of the still image and the arithmetic mean image obtained by arithmetically averaging a plurality of original images as a base image to be input to the mathematical model. The CPU 23 sequentially obtains the target image by sequentially inputting the continuously obtained base images to the mathematical model.

The type of the base image acquired in S11 (at least one of the original image and the arithmetic mean image) and the number of original images used for the base image input to the mathematical model are determined by the acquisition pattern of the input training data described above. It may be appropriately set depending on the situation. When the arithmetic mean image is used as the base image input to the mathematical model, the CPU 23 may acquire the arithmetic mean image by arithmetically averaging a plurality of ophthalmic images of the same imaged region. The CPU 23 may also acquire the arithmetic mean image generated by the ophthalmic image capturing apparatus 11B.

In the high-quality moving image generation process illustrated in FIG. 7, a moving image of the organization is generated. Here, in order to generate a good moving image, it is desirable to maximize the frame rate (the number of still images per unit time). That is, in order to increase the frame rate of the moving image of the target image, it is necessary to maximize the number of target images (still images) acquired per unit time. Therefore, in S11 of FIG. 7, it is preferable that the original image with the smallest possible number is acquired as the base image to be input to the mathematical model. For example, the CPU 23 inputs the acquired one original image into the mathematical model to generate the target image every time one original image is acquired from the ophthalmic image photographing device 11B, so that the ophthalmic image photographing device 11B operates. It is possible to generate a moving image having the same frame rate as the moving image to be captured by using a high quality target image.

Next, the CPU 23 determines whether or not an instruction to display the target image on the display device 28 has been input (S14). In the present embodiment, the user operates the operation unit 27 to instruct which of the target image, the base image, and both the target image and the base image is to be displayed on the display device 28. Can be entered. If the instruction to display the target image is not input (S14: NO), the process proceeds directly to S17. When the instruction to display the target image is input (S14: YES), the CPU 23 causes the display device 28 to display the target image (S15). Specifically, in S15 of the present embodiment, a moving image of the tissue is displayed by sequentially displaying the plurality of target images sequentially acquired in S12 on the display device 28. That is, based on the moving image of the original image captured by the ophthalmologic image capturing apparatus 11B at that time, a high-quality moving image of the tissue being captured is displayed on the display device 28 in real time. Note that the CPU 23 may generate moving image data of the target image based on the plurality of target images continuously acquired in S12 and store the data in the storage device.

Note that the ophthalmologic image processing device 21 can input the target image, the base image, and an instruction to display either the target image or the base image on the display device 28 by various methods. For example, the CPU 23 may cause the display device 28 to display an icon for inputting a display instruction of a target image, an icon for inputting a display instruction of a basic image, and an icon for inputting a display instruction of both images. The user may input a display instruction to the ophthalmic image processing apparatus 21 by selecting a desired icon.

Next, the CPU 23 determines whether or not an instruction to display the basic image on the display device 28 has been input (S17). If not input (S17: NO), the process proceeds directly to S20. When the instruction to display the basic image is input (S17: YES), the CPU 23 causes the display device 28 to display the basic image (S18). Specifically, in S18 of the present embodiment, a plurality of basic images sequentially acquired in S11 are sequentially displayed on the display device 28, thereby displaying a moving image of the tissue. As described above, the CPU 23 can switch between the target image and the base image and display them on the display device 28 according to the instruction input by the user. Therefore, the user can easily confirm both the target image and the base image.

Next, the CPU 23 determines whether or not an instruction to display the target image and the base image on the display device 28 at the same time is input (S20). If not input (S20: NO), the process proceeds directly to S23. When the simultaneous display instruction is input (S20: YES), the CPU 23 causes the display device 28 to simultaneously display the target image and the base image. Specifically, in S20 of the present embodiment, both the moving image of the target image and the moving image of the base image are displayed on the display device 28.

In addition, in S15, S18, and S21, a still image may be displayed instead of a moving image. The CPU 23 may switch the display of the moving image and the display of the still image according to an instruction input by the user. Further, the CPU 23 may store the data of at least one of the moving image and the still image in the storage device 24 without displaying the moving image and the still image on the display device 28.

Further, when displaying the moving image or the still image of the target image on the display device 28, the CPU 23 can cause the display device 28 to display how many ophthalmic images the target image corresponds to. .. For example, when the arithmetic mean image 32 used as the training data for output when constructing the mathematical model is an arithmetic mean image based on H ophthalmic images, the target image acquired in S12 is also H The image corresponds to the arithmetic mean image of the ophthalmic images. Therefore, the CPU 23 causes the display device 28 to display that the target image being displayed corresponds to the arithmetic mean image of the H ophthalmic images. Therefore, the user can appropriately understand the quality of the target image.

In addition, as the timing of displaying the target image, for example, the timing of displaying in real time during photographing by the ophthalmologic image photographing apparatus 11B, the timing of confirming whether or not the photographed image is good, the analysis result after photographing. Alternatively, there are a plurality of timings such as the timing of displaying the report. The CPU 23 separately gives, for each of a plurality of timings at which the target image can be displayed, a target image, a base image, and which of the target image and the base image is to be displayed on the display device 28. Can be entered. That is, the user presets which of the target image, the base image, or both the target image and the base image is to be displayed on the display device 28 in accordance with the timing at which the target image can be displayed. Can be set. As a result, user convenience is further improved.

Next, the CPU 23 determines whether or not an instruction to end the display has been input (S23). If not input (S23: NO), the process returns to S11 and the processes of S11 to S23 are repeated. When the instruction to end the display is input (S23: YES), the CPU 23 executes the segmentation process on the target image (in the present embodiment, at least one of the plurality of target images continuously acquired) (S24). ). The segmentation process is a process of identifying at least one of a plurality of layers of the tissue shown in the image. The layer identification may be performed, for example, by image processing on the target image, or a mathematical model trained by a machine learning algorithm may be used. By performing the segmentation process on the target image, the segmentation result in which the influence of noise is suppressed is appropriately acquired. The user may operate the operation unit 27 to manually perform the segmentation process. Also in this case, the CPU 23 may display the target image on the display device 28 as an image to be subjected to the segmentation process.

A high-quality three-dimensional tomographic image generation process, which is an example of ophthalmic image processing, will be described with reference to FIGS. 8 and 9. In the high-quality three-dimensional tomographic image generation processing, high-quality two-dimensional tomographic images and three-dimensional tomographic images are acquired using a mathematical model. When the high-quality three-dimensional tomographic image generation process is executed, the OCT image capturing apparatus 11B two-dimensionally scans the OCT light (measurement light) to capture a three-dimensional tomographic image of the tissue. .. Specifically, the ophthalmologic image capturing apparatus 11B scans a plurality of scan lines on a plurality of scan lines whose positions are different from each other in a two-dimensional region when the tissue is viewed from the front, and thereby a plurality of (first ~Zth) two-dimensional tomographic image is acquired. A three-dimensional tomographic image is acquired by combining a plurality of two-dimensional tomographic images.

The CPU 23 uses, as a base image, an N-th (two-dimensional tomographic) two-dimensional tomographic image captured by the ophthalmologic image-capturing apparatus 1B, which is the N-th (two-dimensional tomographic) two-dimensional tomographic image. It is acquired (S31). The CPU 23 acquires the Nth target image by inputting the acquired base image into the mathematical model (S32). Next, the CPU 23 determines whether or not the processing for all of the plurality of (first to Zth) basic images has been completed (S33). If not completed (S33: NO), "1" is added to the value of N (S34), and the process returns to S31. The processes of S31 to S33 are repeated until the processes for all the base images are completed.

When the processing for all the base images is completed (S33: YES), the acquired plurality of target images are combined to generate the three-dimensional tomographic image 40 (see FIG. 9) of the tissue (S35). According to the high-quality three-dimensional tomographic image generation process illustrated in FIG. 8, even if the arithmetic mean image is not used as each of the two-dimensional tomographic images forming the three-dimensional tomographic image, the influence of noise is equal to that of the arithmetic mean image. A three-dimensional tomographic image is generated by the suppressed target image.

Note that the CPU 23 can also generate an image other than the three-dimensional tomographic image based on the plurality of target images. For example, the CPU 23 may generate a two-dimensional front image (so-called “Enface image”) when the tissue is viewed from the front, based on the plurality of target images acquired in S32.

Further, the CPU 23 can also perform an analysis process on the three-dimensional tomographic image 40 generated based on the plurality of target images. For example, the CPU 23 may perform a segmentation process on the three-dimensional tomographic image 40 to extract at least one of the plurality of layers included in the fundus. The CPU 23 may generate a thickness map that two-dimensionally shows the thickness distribution of at least one of the layers based on the result of the segmentation processing. In this case, the thickness map is appropriately generated based on the three-dimensional tomographic image 40 in which the influence of noise is suppressed.

Further, the CPU 23 may generate a two-dimensional tomographic image at an arbitrary position in the tissue included in the imaging range of the three-dimensional tomographic image 40 based on the three-dimensional tomographic image 40 generated based on the plurality of target images. Good. The CPU 23 may display the generated two-dimensional tomographic image on the display device 28. As an example, the CPU 23 of the present embodiment inputs an instruction from the user for designating the position where the tomographic image is generated. For example, the user may operate the operation unit 27 to specify the generation position of the tomographic image on the two-dimensional front image or the three-dimensional tomographic image 40 displayed on the display device 28. The generation position of the tomographic image may be specified by lines of various shapes (straight lines, circular lines, etc.), for example. The CPU 23 may generate (extract) a two-dimensional tomographic image at a position designated by the user from the three-dimensional tomographic image 40. In this case, a tomographic image at an arbitrary position desired by the user is appropriately generated based on the three-dimensional tomographic image 40 in which the influence of noise is suppressed.

Further, the CPU 23 may determine whether or not the ophthalmic image captured by the ophthalmic image capturing apparatus 11B is good every time one or more ophthalmic images are captured. When determining that the captured ophthalmic image is good, the CPU 23 may input the good ophthalmic image as a base image into the mathematical model. Further, when the CPU 23 determines that the captured ophthalmic image is not good, the CPU 23 may output an instruction to re-capture the ophthalmic image at the same position to the ophthalmic image capturing device 11B. In this case, the target image is acquired based on a good base image. Note that a specific method for determining whether or not the captured ophthalmic image is good can be appropriately selected. For example, the CPU 23 uses a signal strength of the photographed ophthalmic image or an index indicating goodness of the signal (for example, SSI (Signal Strength Index) or QI (Quality Index)) to obtain a good ophthalmic image. May be determined. Further, the CPU 23 may determine whether or not the ophthalmic image is good by comparing the captured ophthalmic image with the template.

Further, when performing analysis processing (for example, segmentation processing or the like) on any of the plurality of target images, the CPU 23 determines whether the plurality of target images or the plurality of base images that are the basis of the plurality of target images are good. Images may be extracted. The CPU 23 may perform an analysis process on the extracted good target image or the target image based on the good basic image. In this case, the accuracy of the analysis process is improved. As a method of extracting a good image, various methods such as the above-described method using SSI or the like can be adopted.

Further, when generating the motion contrast image, the CPU 23 may acquire the target image using the mathematical model exemplified in the present disclosure, and may generate the motion contrast image based on the acquired target image. As described above, when a motion contrast image is generated, a plurality of OCT signals are acquired at different times with respect to the same position, and arithmetic processing is performed on the plurality of OCT signals. The CPU 23 may acquire a target image based on each of a plurality of OCT signals (two-dimensional tomographic images) and perform a calculation process on the acquired plurality of target images to acquire a motion contrast image. In this case, the motion contrast image in which the influence of noise is suppressed is appropriately generated.

The technology disclosed in the above embodiments is merely an example. Therefore, it is possible to change the technique exemplified in the above embodiment. First, it is possible to execute only a part of the plurality of techniques exemplified in the above embodiment. For example, the ophthalmologic image processing device 21 may execute only one of the high-quality moving image generation processing (see FIG. 7) and the high-quality three-dimensional tomographic image generation processing (see FIG. 8).

The process of acquiring the base image in S11 of FIG. 7 and S31 of FIG. 8 is an example of the “base image acquisition step”. The process of acquiring the target image in S12 of FIG. 7 and S32 of FIG. 8 is an example of the “target image acquisition step”. The process of generating the three-dimensional tomographic image in S35 of FIG. 8 is an example of the “three-dimensional tomographic image generating step”. The segmentation process shown in S24 of FIG. 7 is an example of a “segmentation step”. The process of switching between the target image and the base image for display in S14 to S18 of FIG. 7 is an example of the “switching display process” and the “switching display step”. The process of simultaneously displaying the target image and the base image in S21 of FIG. 7 is an example of “simultaneous display process” and “simultaneous display step”. The process of generating the moving image data of the target image in S15 of FIG. 7 is an example of a “moving image generating step”. The process of acquiring the training ophthalmic image set 30 in S1 of FIG. 2 is an example of an “image set acquisition step”. The process of constructing the mathematical model in S2 to S4 of FIG. 2 is an example of “training step”.

1 Mathematical model building device 3 CPU
4 Storage device 11 Ophthalmic image photographing device 21 Ophthalmic image processing device 23 CPU
24 storage device 28 display device 30 set 31 arithmetic mean image 32 arithmetic mean image 300 training ophthalmic image

Claims (4)

An ophthalmic image processing apparatus for processing an ophthalmic image that is an image of the tissue of an eye to be inspected,
The ophthalmic image is an OCT angio image that is a motion contrast image obtained by performing an arithmetic process on at least two OCT signals obtained at different times for the same position by the OCT apparatus,
The control unit of the ophthalmic image processing device,
An OCT angio image photographed by the OCT device, or an arithmetic mean image obtained by arithmetic mean of a plurality of OCT angio images obtained by photographing the same part of the tissue by the OCT device is acquired as a base image,
By inputting the base image to a mathematical model trained by a machine learning algorithm, a target image that is an OCT angio image having a higher image quality than the base image is acquired,
When the timing at which the target image can be displayed has arrived, at least one of the target image and the base image is preset according to the timing, depending on the type of image displayed on the display device. Is displayed on the display device,
In the mathematical model, data based on L (L≧1) of the training ophthalmic images of the plurality of training ophthalmic images of the same region of the tissue is used as input training data, and H (H) >L) The ophthalmic image processing device is trained as output training data using data of an arithmetic mean image obtained by arithmetic mean of the training ophthalmic images. An ophthalmic image processing apparatus for processing an ophthalmic image that is an image of the tissue of an eye to be inspected,
The ophthalmic image is an OCT angio image that is a motion contrast image obtained by performing an arithmetic process on at least two OCT signals obtained at different times for the same position by the OCT apparatus,
The control unit of the ophthalmic image processing device,
An OCT angio image photographed by the OCT device, or an arithmetic mean image obtained by arithmetic mean of a plurality of OCT angio images obtained by photographing the same part of the tissue by the OCT device is acquired as a base image,
By inputting the base image to a mathematical model trained by a machine learning algorithm, a target image that is an OCT angio image having a higher image quality than the base image is acquired,
In the tissue included in the imaging range of the target image, the two-dimensional tomographic image at the position designated by the user is extracted and displayed on the display device,
In the mathematical model, data based on L (L≧1) of the training ophthalmic images of the plurality of training ophthalmic images of the same region of the tissue is used as input training data, and H (H) >L) The ophthalmic image processing device is trained as output training data using data of an arithmetic mean image obtained by arithmetic mean of the training ophthalmic images. An OCT apparatus for capturing an ophthalmic image of the tissue by processing an OCT signal by the reference light and the reflected light of the measurement light with which the tissue of the subject's eye is irradiated,
The ophthalmic image is an OCT angio image that is a motion contrast image acquired by performing an arithmetic process on at least two OCT signals acquired at different times for the same position,
The control unit of the OCT device is
An OCT angio image of the imaged tissue, or an arithmetic mean image obtained by arithmetically averaging a plurality of OCT angio images of the same site of the tissue is acquired as a base image,
By inputting the base image to a mathematical model trained by a machine learning algorithm, a target image that is an OCT angio image having a higher image quality than the base image is acquired,
When the timing at which the target image can be displayed has arrived, at least one of the target image and the base image is preset according to the timing, depending on the type of image displayed on the display device. Is displayed on the display device,
In the mathematical model, data based on L (L≧1) of the training ophthalmic images of the plurality of training ophthalmic images of the same region of the tissue is used as input training data, and H (H) >L) The OCT apparatus is trained as output training data using data of an arithmetic mean image obtained by arithmetic mean of the training ophthalmic images. An OCT apparatus for capturing an ophthalmic image of the tissue by processing an OCT signal by the reference light and the reflected light of the measurement light with which the tissue of the subject's eye is irradiated,
The ophthalmic image is an OCT angio image that is a motion contrast image acquired by performing an arithmetic process on at least two OCT signals acquired at different times for the same position,
The control unit of the OCT device is
An OCT angio image of the imaged tissue, or an arithmetic mean image obtained by arithmetically averaging a plurality of OCT angio images of the same site of the tissue is acquired as a base image,
By inputting the base image to a mathematical model trained by a machine learning algorithm, a target image that is an OCT angio image having a higher image quality than the base image is acquired,
In the tissue included in the imaging range of the target image, the two-dimensional tomographic image at the position designated by the user is extracted and displayed on the display device,
In the mathematical model, data based on L (L≧1) of the training ophthalmic images of the plurality of training ophthalmic images of the same region of the tissue is used as input training data, and H (H) >L) The OCT apparatus is trained as output training data using data of an arithmetic mean image obtained by arithmetic mean of the training ophthalmic images.