Medical support device, operation method of medical support device, non-transitory computer readable medium, and medical support system
AssigneeFUJIFILM Corporation
InventorNaoki Matsuura
Life of this patent
Estimating the term…
Abstract
A medical support device includes a processor, in which the processor acquires a medical image, acquires correspondence information in which the medical image is associated in advance with presence or absence of a foreign substance image included in the medical image, generates foreign substance estimation information obtained by estimating the presence or absence of the foreign substance image included in the medical image based on the medical image and the correspondence information, and controls a notification based on the foreign substance estimation information.
Claims15
A medical support device comprising:
- a processor configured to:
- acquire a medical image including a subject image;
- acquire correspondence information in which the medical image is associated in advance with presence or absence of a foreign substance image included in the medical image, a type of a foreign substance that forms the foreign substance image, and a position of the foreign substance in a case in which the foreign substance image is present, wherein the correspondence information is a learned model in which the medical image is associated with the presence or absence of the foreign substance image included in the medical image, the type of the foreign substance, and the position of the foreign substance by weighting and the learned model is created by performing learning with machine learning on a plurality of the medical images;
- generate foreign substance estimation information obtained by estimating the presence or absence of the foreign substance image included in the medical image, the type of the foreign substance that forms the foreign substance image, and the position of the foreign substance in a case in which the foreign substance image is present based on the medical image and the correspondence information;
- and
- control a notification based on the foreign substance estimation information.
An operation method of a medical support device, the method comprising:
- an image acquisition step of acquiring a medical image including a subject image;
- an correspondence information acquisition step of acquiring correspondence information in which the medical image is associated in advance with presence or absence of a foreign substance image included in the medical image, a type of a foreign substance that forms the foreign substance image, and a position of the foreign substance in a case in which the foreign substance image is present, wherein the correspondence information is a learned model in which the medical image is associated with the presence or absence of the foreign substance image included in the medical image, the type of the foreign substance, and the position of the foreign substance by weighting and the learned model is created by performing learning with machine learning on a plurality of the medical images;
- a foreign substance estimation information generation step of generating foreign substance estimation information obtained by estimating the presence or absence of the foreign substance image included in the medical image, and the type of the foreign substance that forms the foreign substance image, and the position of the foreign substance in a case in which the foreign substance image is present based on the medical image and the correspondence information;
- and
- a notification control step of controlling a notification based on the foreign substance estimation information.
A non-transitory computer readable medium for storing a computer-executable program causing a computer to function as the medical support device, the computer-executable program causing the computer to execute:
- an image acquisition step of acquiring a medical image including a subject image;
- an correspondence information acquisition step of acquiring correspondence information in which the medical image is associated in advance with presence or absence of a foreign substance image included in the medical image, a type of a foreign substance that forms the foreign substance image, and a position of the foreign substance in a case in which the foreign substance image is present, wherein the correspondence information is a learned model in which the medical image is associated with the presence or absence of the foreign substance image included in the medical image, the type of the foreign substance, and the position of the foreign substance by weighting and the learned model is created by performing learning with machine learning on a plurality of the medical images;
- a foreign substance estimation information generation step of generating foreign substance estimation information obtained by estimating the presence or absence of the foreign substance image included in the medical image, and the type of the foreign substance that forms the foreign substance image, and the position of the foreign substance in a case in which the foreign substance image is present based on the medical image and the correspondence information;
- and
- a notification control step of controlling a notification based on the foreign substance estimation information.
Dependencies are inferred from the claim text.