Tomographic image processing device, ophthalmic device comprising the same and non-transitory computer-readable recording medium storing computer-readable instructions for tomographic image processing device

1. A tomographic image processing device comprising:

an input unit configured to input a tomographic image of a subject eye;

a processor; and

a memory storing computer-readable instructions therein,

wherein

the computer-readable instructions, when executed by the processor, cause the processor to execute:

acquiring a tomographic image of a normal eye;

acquiring a tomographic image of an eye having an abnormal portion;

extracting a feature amount of the abnormal portion by using machine learning from the tomographic image of the normal eye and the tomographic image of the eye having the abnormal portion;

acquiring a tomographic image of the subject eye inputted by the input unit;

determining whether the tomographic image of the subject eye includes an abnormal portion based on the feature amount; and

a display unit configured to display an image of the subject eye, wherein when the display unit displays the tomographic image of the subject eye in a case where it is determined that the tomographic image of the subject eye includes the abnormal portion, the display unit is configured to display the abnormal portion and a portion where the abnormal portion does not exist in different manners.

2. The tomographic image processing device of claim 1 , further comprising an image capturing unit configured to capture a tomographic image of a subject eye,

wherein the computer-readable instructions, when executed by the processor cause the processor to execute processing the tomographic image

of the subject eye inputted from the image capturing unit, and

the tomographic image processing device is an ophthalmic device.

3. A tomographic image processing device comprising:

an input unit configured to input a tomographic image of a subject eye;

a processor; and

a memory storing computer-readable instructions therein,

wherein

the computer-readable instructions, when executed by the processor, cause the processor to execute:

acquiring a tomographic image of a normal eye;

acquiring a tomographic image of an eye having an abnormal portion;

extracting a feature amount of the abnormal portion by using machine learning from the tomographic image of the normal eye and the tomographic image of the eye having the abnormal portion;

acquiring a tomographic image of the subject eye inputted by the input unit;

determining whether the tomographic image of the subject eye includes an abnormal portion based on the feature amount;

wherein

the tomographic image of the subject eye comprises a first tomographic image and a second tomographic image, the first tomographic image being captured by irradiating the subject eye with a first polarized wave, the second tomographic image being captured by irradiating the subject eye with a second polarized wave that has a vibration direction different from the first polarized wave, and

the computer-readable instructions, when executed by the processor, further cause the processor to execute:

calculating an entropy based on the first tomographic image and the second tomographic image for a same cross section of the subject eye.

4. The tomographic image processing device of claim 3 , further comprising an image capturing unit configured to capture a tomographic image of a subject eye,

wherein the computer-readable instructions, when executed by the processor, cause the processor to execute processing the tomographic image

of the subject eye inputted from the image capturing unit, and

the tomographic image processing device is an ophthalmic device.

5. A tomographic image processing device comprising:

an input unit configured to input a tomographic image of a subject eye;

a processor; and

a memory storing computer-readable instructions therein,

wherein

the computer-readable instructions, when executed by the processor, cause the processor to execute:

acquiring a tomographic image of a normal eye;

acquiring a tomographic image of an eye having an abnormal portion;

extracting a feature amount of the abnormal portion by using machine learning from the tomographic image of the normal eye and the tomographic image of the eye having the abnormal portion;

acquiring a tomographic image of the subject eye inputted by the input unit;

determining whether the tomographic image of the subject eye includes an abnormal portion based on the feature amount;

wherein

the computer-readable instructions, when executed by the processor, further cause the processor to execute:

acquiring an image for machine learning, the image for machine learning comprising a tomographic image of an eye with a line drawn between tissues in the tomographic image;

extracting a feature amount of inter-tissue boundary by using the machine leaning from the image for the machine learning;

acquiring a tomographic image of the subject eye inputted by the input unit; and

determining an inter-tissue boundary in the tomographic image of the subject eye based on the feature amount.

6. The tomographic image processing device according to claim 5 , further comprising a display unit configured to display an image of the subject eye,

wherein the display unit is configured to display the image of the subject eye with a line that is drawn along the determined inter-tissue boundary superimposed over the image of the subject eye.

7. The tomographic image processing device of claim 5 , further comprising an image capturing unit configured to capture a tomographic image of a subject eye,

wherein the computer-readable instructions, when executed by the processor, cause the processor to execute processing the tomographic image

of the subject eye inputted from the image capturing unit, and

the tomographic image processing device is an ophthalmic device.

8. A non-transitory computer-readable recording medium storing computer-readable instructions for a tomographic image processing device,

wherein the computer-readable instructions, when executed by a processor of the tomographic image processing device, cause the processor to:

acquire a tomographic image of a normal eye;

acquire a tomographic image of an eye having an abnormal portion;

extract a feature amount of the abnormal portion by using machine learning from the tomographic image of the normal eye and the tomographic image of the eye having the abnormal portion;

acquire a tomographic image of a subject eye; and

determine whether the tomographic image of the subject eye includes an abnormal portion based on the feature amount,

wherein the computer-readable instructions, when executed by a processor of the tomographic image processing device, further cause the processor to:

acquire an image for machine learning, the image for machine learning comprising a tomographic image of an eye with a line drawn between tissues in the tomographic image;

extract a feature amount of inter-tissue boundary by using the machine learning from the image for the machine learning;

acquire a tomographic image of a subject eye; and

determine an inter-tissue boundary in the tomographic image of the subject eye based on the feature amount.