Medical image processing apparatus, endoscope system, medical image processing method, and medical image processing program providing a notification in accordance with drawing information
A medical image processing apparatus according to an aspect of the present invention is a medical image processing apparatus including a processor. The processor is configured to execute an image acquisition process for sequentially acquiring time-series medical images; a drawing information acquisition process for acquiring drawing information drawn in the medical images; a drawing information recognition process for recognizing the acquired drawing information; a target object recognition process for recognizing a target object from the medical images; a notification level determination process for determining a notification level for the target object by using the recognized drawing information; and a display process for causing a display device to display the target object at the determined notification level.
1 . A medical image processing apparatus comprising a processor configured to execute:
an image acquisition process for sequentially acquiring time-series medical images;
a drawing information acquisition process for acquiring drawing information drawn in the medical images;
a drawing information recognition process for recognizing the acquired drawing information;
a target object recognition process for recognizing a target object by using a first trained model constructed by machine learning from the medical images, wherein the first trained model is trained by captured images of a living body;
a notification level determination process for determining a notification level the target object by using the recognized drawing information; and
a display process for causing a display device to display the target object at the determined notification level,
wherein the processor is configured to, in response to the drawing information being recognized in the drawing information recognition process, reduce the notification level to be lower than a notification level when the drawing information is not recognized in the notification level determination process.
2 . The medical image processing apparatus according to claim 1 , wherein the processor is configured to, in the drawing information acquisition process, acquire the drawing information from a medical imaging apparatus connected to the medical image processing apparatus.
3 . The medical image processing apparatus according to claim 1 , wherein the processor is configured to, in the drawing information acquisition process, perform image processing on the medical images to acquire the drawing information.
4 . The medical image processing apparatus according to claim 3 , wherein the processor is configured to, in the drawing information acquisition process, acquire the drawing information by using a second trained model constructed by machine learning.
5 . The medical image processing apparatus according to claim 1 , wherein the processor is configured to check the medical images against drawable information that is drawable in the medical images to acquire the drawing information.
6 . The medical image processing apparatus according to claim 1 , wherein the processor is configured to, in the drawing information acquisition process, acquire information related to a geometric shape, a text, or a symbol drawn in the medical images as the drawing information.
7 . The medical image processing apparatus according to claim 6 , wherein the processor is configured to, in the drawing information acquisition process, acquire at least one of a position, a size, a shape, a line type, a color, or a type of at least one of the geometric shape, the text, or the symbol as the drawing information.
8 . The medical image processing apparatus according to claim 1 , wherein the processor is configured to reduce the notification level for the target object to be lower than a notification level when the medical images do not have the drawing information, in accordance with an amount of the drawing information.
9 . The medical image processing apparatus according to claim 8 , wherein the processor is configured to reduce the notification level for a target object for which the amount of the drawing information is recognized to be greater than or equal to a threshold value, such that the notification level is lower than a notification level when the medical images do not have the drawing information.
10 . The medical image processing apparatus according to claim 1 , wherein the processor is configured to, in response to the drawing information being acquired in the drawing information acquisition process, reduce the notification level for the target object to be lower than a notification level when the medical images do not have the drawing information, regardless of an amount of the drawing information.
11 . The medical image processing apparatus according to claim 8 , wherein the processor is configured to determine the amount of the drawing information in accordance with at least one of a position, a size, a shape, a line type, a color, or a type of a geometric shape, a text, or a symbol in the medical images.
12 . The medical image processing apparatus according to claim 1 , wherein the processor is configured to, in the notification level determination process, determine the notification level for the target object on the basis of a positional relationship between the target object and the drawing information in the medical images.
13 . An endoscope system comprising:
the medical image processing apparatus according to claim 1 ;
an endoscope to be inserted into a subject, the endoscope comprising an imaging unit configured to sequentially capture the medical images; and
the display device.
14 . The endoscope system according to claim 13 , wherein the endoscope is an ultrasonic endoscope configured to acquire ultrasound images of the subject as the medical images.
15 . A medical image processing method executed by a medical image processing apparatus comprising a processor, the medical image processing method comprising:
an image acquisition step of sequentially acquiring time-series medical images;
a drawing information acquisition step of acquiring drawing information drawn in the medical images;
a drawing information recognition step of recognizing the acquired drawing information;
a target object recognition step of recognizing a target object by using a first trained model constructed by machine learning from the medical images, wherein the first trained model is trained by captured images of a living body;
a notification level determination step of determining a notification level for the target object by using the recognized drawing information; and
a display step of causing a display device to display the target object at the determined notification level,
wherein in response to the drawing information being recognized in the drawing information recognition step, reduce the notification level to be lower than a notification level when the drawing information is not recognized in the notification level determination step.
16 . A non-transitory, computer-readable tangible recording medium which stores a program for causing, when read by a computer, the computer to execute the medical image processing method according to claim 15 .