EP-4740830-A1 - DIAGNOSTIC IMAGING ASSISTANCE DEVICE, DIAGNOSTIC IMAGING ASSISTANCE SYSTEM, AND DIAGNOSTIC IMAGING ASSISTANCE METHOD

EP4740830A1EP 4740830 A1EP4740830 A1EP 4740830A1EP-4740830-A1

Abstract

An image diagnosis assistance apparatus 5 includes an image selector 511 configured to select, as a diagnosis image, any one of a plurality of images that contain a same subject and on which sets of processing different from one another are executed; and an estimator 512 configured to, by executing an estimation process on the diagnosis image using a trained model, estimate a diagnostic candidate area serving as a diagnostic candidate in the diagnosis image and output reliability of the diagnostic candidate area. The image selector 511 is configured to select any one of the plurality of images as the diagnosis image based on the reliability of the diagnostic candidate area.

Inventors

SUZUKI, HIROSHI
MIYAZAWA, SHINGO
MATSUSHITA, AKIRA

Assignees

Olympus Medical Systems Corp.

Dates

Publication Date: 20260513
Application Date: 20230705

Claims (14)

An image diagnosis assistance apparatus comprising: an image selector configured to select, as a diagnosis image, any one of a plurality of images that contain a same subject and on which sets of processing different from one another are executed; and an estimator configured to, by executing an estimation process on the diagnosis image using a trained model, estimate a diagnostic candidate area serving as a diagnostic candidate in the diagnosis image and output reliability of the diagnostic candidate area, wherein the image selector is configured to select any one of the plurality of images as the diagnosis image based on the reliability of the diagnostic candidate area.
The image diagnosis assistance apparatus according to claim 1, further comprising: a notification unit configured to make a notification of given information; and a notification controller configured to cause a notification of the diagnostic candidate area to be made from the notification unit.
The image diagnosis assistance apparatus according to claim 1, wherein the plurality of images include at least two of a first captured image obtained by capturing feedback light of light of a first wavelength band from the subject to which the light of the first wavelength band is applied, a trimming image obtained by enlarging a part of the first captured image, an image-quality-corrected image obtained by correcting image quality of the trimming image, and a second captured image obtained by capturing a feedback light of light of a second wavelength band different from the first wavelength band from the subject to which the light of the second wavelength band is applied.
The image diagnosis assistance apparatus according to claim 3, wherein the trimming image is an image obtained by enlarging an area containing the diagnostic candidate area in the first captured image.
The image diagnosis assistance apparatus according to claim 1, further comprising an operation receiver configured to receive a user operation of selecting any one of the plurality of images, wherein the image selector is configured to select any one of the plurality of images as the diagnosis image according to the user operation.
The image diagnosis assistance apparatus according to claim 5, further comprising a permission-prohibition setting unit configured to set a permitted state where selecting any one of the plurality of images by the image selector according to the user operation is permitted or a prohibited state where the selecting is prohibited.
The image diagnosis assistance apparatus according to claim 1, wherein the reliability of the diagnostic candidate area is a value representing accuracy of recognition in the diagnostic candidate area, and when the reliability of the diagnostic candidate area is under a first threshold and is at or above a second threshold lower than the first threshold, the image selector is configured to switch the diagnosis image that is selected currently to another image of the plurality of images.
The image diagnosis assistance apparatus according to claim 1, further comprising a display unit configured to display a given image; and a display controller configured to cause the display unit to display the selected diagnosis image.
The image diagnosis assistance apparatus according to claim 1, wherein, when the reliability of the diagnostic candidate area satisfies a given condition for a given number of times or for a given time, the image selector is configured to switch the diagnosis image that is selected currently to another image of the plurality of images.
The image diagnosis assistance apparatus according to claim 1, further comprising a communication unit that is connected to an external device such that communication is enabled; and a communication controller configured to cause the diagnosis image and the reliability of the diagnostic candidate area to be transmitted from the communication unit to the external device.
The image diagnosis assistance apparatus according to claim 1, wherein, when the diagnosis image is switched by the image selector, the estimator is configured to switch a training parameter of the trained model that is used for the estimation process to a training parameter corresponding to the switched diagnosis image.
The image diagnosis assistance apparatus according to claim 1, wherein, when the diagnosis image is switched by the image selector, the estimator is configured to switch the trained model that is used for the estimation process to a trained model corresponding to the switched diagnosis image.
An image diagnosis assistance system comprising: an imaging device configured to generate a captured image by capturing an image of a subject; and an image diagnosis assistance apparatus configured to process the captured image, wherein the image diagnosis assistance apparatus includes: an image selector configured to select, as a diagnosis image, any one of a plurality of images that contain a same subject and that are obtained by executing sets of processing different from one another are executed on the captured image; and an estimator configured to, by executing an estimation process on the diagnosis image using a trained model, estimate a diagnostic candidate area serving as a diagnostic candidate in the diagnosis image and output reliability of the diagnostic candidate area, and the image selector is configured to select any one of the plurality of images as the diagnosis image based on the reliability of the diagnostic candidate area.
An image diagnosis assistance method that an image diagnosis assistance apparatus executes, the method comprising: a step of selecting, as a diagnosis image, any one of a plurality of images that contain a same subject and on which sets of processing different from one another are executed; and a step of, by executing an estimation process on the diagnosis image using a trained model, estimating a diagnostic candidate area serving as a diagnostic candidate in the diagnosis image and outputting reliability of the diagnostic candidate area, wherein the step of selecting the diagnosis image includes selecting any one of the plurality of images as the diagnosis image based on the reliability of the diagnostic candidate area.

Description

Field The present invention relates to an image diagnosis assistance apparatus, and an image diagnosis assistance method. Background In recent years, in the field of medicine, image recognition techniques based on AI (Artificial Intelligence) have been proposed (for example, refer to Patent Literature 1). The technique described in Patent Literature 1 executes an estimation process using a trained model on a captured image that is captured with an endoscope, thereby estimating a diagnostic candidate area, such as a lesion, or the like, in the captured image. Citation List Patent Literature Patent Literature 1: Japanese Patent No. 6952214 Summary Technical Problem With image recognition techniques based on AI, however, sufficient performance is not delivered depending on the definition of a captured image that is input and it is not possible to accurately estimate a diagnostic candidate area, such as a lesion, in some cases. In other words, it is not possible to provide an image suitable for diagnosis in some cases. The present invention was made in view of the above-described circumstances and an object of the present invention is to provide an image diagnosis assistance apparatus, an image diagnosis assistance system, and an image diagnosis assistance method that make it possible to provide an image suitable for diagnosis. Solution to Problem To solve the problem described above and to achieve the object, an image diagnosis assistance apparatus according to the present invention includes: an image selector configured to select, as a diagnosis image, any one of a plurality of images that contain a same subject and on which sets of processing different from one another are executed; and an estimator configured to, by executing an estimation process on the diagnosis image using a trained model, estimate a diagnostic candidate area serving as a diagnostic candidate in the diagnosis image and output reliability of the diagnostic candidate area. The image selector is configured to select any one of the plurality of images as the diagnosis image based on the reliability of the diagnostic candidate area. An image diagnosis assistance system according to the present invention includes: an imaging device configured to generate a captured image by capturing an image of a subject; and an image diagnosis assistance apparatus configured to process the captured image. The image diagnosis assistance apparatus includes: an image selector configured to select, as a diagnosis image, any one of a plurality of images that contain a same subject and that are obtained by executing sets of processing different from one another are executed on the captured image; and an estimator configured to, by executing an estimation process on the diagnosis image using a trained model, estimate a diagnostic candidate area serving as a diagnostic candidate in the diagnosis image and output reliability of the diagnostic candidate area. The image selector is configured to select any one of the plurality of images as the diagnosis image based on the reliability of the diagnostic candidate area. An image diagnosis assistance method according to the present invention is an image diagnosis assistance method that an image diagnosis assistance apparatus executes. The method includes: a step of selecting, as a diagnosis image, any one of a plurality of images that contain a same subject and on which sets of processing different from one another are executed; and a step of, by executing an estimation process on the diagnosis image using a trained model, estimating a diagnostic candidate area serving as a diagnostic candidate in the diagnosis image and outputting reliability of the diagnostic candidate area. The step of selecting the diagnosis image includes selecting any one of the plurality of images as the diagnosis image based on the reliability of the diagnostic candidate area. Advantageous Effects of Invention According to the image diagnosis apparatus, the image diagnosis assistance system, and the image diagnosis assistance method, it is possible to provide an image suitable for diagnosis. Brief Description of Drawings FIG. 1 is a diagram illustrating a configuration of an endoscope system according to an embodiment.FIG. 2 is a diagram illustrating the configuration of the endoscope system according to the embodiment.FIG. 3 is a diagram schematically illustrating a function of a controller.FIG. 4 is a flowchart illustrating an image diagnosis assistance method.FIG. 5 is a diagram illustrating a specific example of a display image.FIG. 6 is a diagram illustrating a specific example of the display image.FIG. 7 is a diagram illustrating a specific example of the display image.FIG. 8 is a diagram illustrating a specific example of the display image.FIG. 9 is a diagram illustrating Modification 1 of the embodiment.FIG. 10 is a diagram illustrating Modification 2 of the embodiment.FIG. 11 is a diagram illustrating Modification 3 of the embodiment. Desc