Ophthalmologic image processing device and non-transitory computer-readable storage medium storing computer-readable instructions

An ophthalmologic image processing device that processes an ophthalmologic image of a tissue of a subject eye, the ophthalmologic image processing device comprising a processor, wherein the processor:

• acquires the ophthalmologic image photographed by an ophthalmologic image photographing device;
• inputs the ophthalmologic image into a mathematical model trained by a machine learning algorithm and acquires multiple results of analyses relating to different diseases or structures of a subject eye, the multiple results of analyses being obtained based on ophthalmologic images photographed by the ophthalmic image photographing device that photographs the ophthalmologic image input to the mathematical model;
• acquires a supplemental map, for each of the results of the analyses, that indicates a distribution of weight relating to the analysis by the mathematical model, for which an image area of the ophthalmologic image input into the mathematical model is set as a variable, the supplemental map indicating at least one from among (i) a distribution of a degree of influence that affects the result of the analysis relating to at least one of the specific disease and the specific structure output by the mathematical model, and (ii) a distribution of a degree of certainty of the analysis relating to at least one of the specific disease and the specific structure by the mathematical model;
• generates an integration map in which the supplemental maps are integrated within an identical area;
• and
• displays the integration map on a display unit.

A non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by a processor of an ophthalmologic image processing device, causes the ophthalmologic image processing device to perform processes comprising:

• acquiring an ophthalmologic image photographed by an ophthalmologic image photographing device;
• inputting the ophthalmologic image into a mathematical model trained by a machine learning algorithm and acquiring a result of an analysis relating to at least one of a specific disease and a specific structure of a subject eye;
• acquiring information of a distribution of weight generated by the mathematical model, as supplemental distribution information, for which an image area of the ophthalmologic image input into the mathematical model is set as a variable, the supplemental distribution information including at least one from among (i) information indicating a distribution of a degree of influence that affects the result of the analysis relating to at least one of the specific disease and the specific structure output by the mathematical model, and (ii) information indicating a distribution of a degree of certainty of the analysis relating to at least one of the specific disease and the specific structure by the mathematical model;
• setting a part of the image area of the ophthalmologic image, as an attention area, based on the supplemental distribution information;
• acquiring an image of a tissue including the attention area among a tissue of the subject eye with the ophthalmologic image photographing device that photographs the ophthalmologic image input to the mathematical model;
• and
• displaying the image of the tissue including the attention area on a display unit.