Image processing system, endoscope system, and image processing method

Patent metadata

Field	Value
Publication number	US-12249071-B2
Application number	US-202217886698-A
Country	US
Kind code	B2
Filing date	Aug 12, 2022
Priority date	Feb 21, 2020
Publication date	Mar 11, 2025
Grant date	Mar 11, 2025

Abstract

An image processing system includes at least one processor including hardware. The processor performs a process that acquires, as a processing target image sequence, images captured in a time series manner with an inside of a living body by an endoscope imaging device, a process based on a database generated by using a plurality of in-vivo images captured at earlier timings than timings at which the processing target image sequence is captured, and a process that determines, when a bleeding has been occurring inside the living body, a kind of a desirable bleeding stopping treatment for a blood vessel on which the bleeding has been occurring based on the processing target image sequence and the database to present, to a user, the determined type of the bleeding stopping treatment.

First claim

What is claimed is:

1. An image processing system, comprising:
at least one processor including hardware, wherein
the processor being configured to perform
a process that acquires, as a processing target image sequence, images captured in a time series manner with an inside of a living body by an endoscope imaging device, and
a process based on the processing target image sequence and a database generated by using a plurality of in-vivo images captured at earlier timings than timings at which the processing target image sequence is captured, and
a process that determines, when a bleeding has been occurring inside the living body, a kind of a bleeding stopping treatment desirable for a blood vessel on which the bleeding has been occurring based on the processing target image sequence and the database to present, to a user, the determined type of the bleeding stopping treatment.

2. The image processing system as defined in claim 1 , wherein
the processor
identifies a type of the blood vessel on which the bleeding has been occurring, based on the processing target image sequence and the database, and
determines the kind of the bleeding stopping treatment based on the identified type.

3. The image processing system as defined in claim 2 , wherein
the database includes a plurality of datasets in each of which an in-vivo image sequence representing the in-vivo images captured in a time series manner is associated with blood vessel type information, the blood vessel type information indicating the type of the blood vessel on which the bleeding being occurring is captured in the in-vivo image sequence, and
the processor
performs a process that identifies the type of the blood vessel on which the bleeding has been occurring based on the processing target image sequence and a trained model, the trained model having machine-learned a relationship between the in-vivo image sequence and the blood vessel type information based on the plurality of datasets, and
determines the kind of the bleeding stopping treatment based on the identified type.

4. The image processing system as defined in claim 1 , wherein
the database includes a plurality of datasets in which an in-vivo image sequence representing the in-vivo images captured in a time series manner is associated with bleeding stopping treatment information, the bleeding stopping treatment information indicating a recommended kind of the bleeding stopping treatment for the bleeding captured in the in-vivo image sequence, and
the processor
performs a process that determines the kind of the bleeding stopping treatment based on the processing target image sequence and a trained model, the trained model having machine-learned a relationship between the in-vivo image sequence and the bleeding stopping treatment information based on the plurality of datasets.

5. The image processing system as defined in claim 1 , wherein
the processor performs a process that adds, to the database, a dataset in which the processing target image sequence used for determination of the bleeding stopping treatment and the kind of the bleeding stopping treatment for the bleeding detected in the processing target image sequence are associated with each other.

6. The image processing system as defined in claim 1 , wherein
the processor
performs a bleeding detection process that detects whether or not the bleeding has been occurring inside the living body based on the processing target image sequence, and
performs, when the bleeding is detected, a bleeding point detection process that identifies a bleeding point serving as an occurrence position of the bleeding.

7. The image processing system as defined in claim 6 , wherein
the processor performs a bleeding notification process that notifies the user of information regarding at least one of occurrence of the bleeding detected by the bleeding detection process or the bleeding point identified by the bleeding point detection process.

8. The image processing system as defined in claim 1 , wherein
the processor performs, when determining that the user has executed an emergency bleeding stopping treatment for the bleeding, a process that determines a treatment that has higher bleeding stopping capability than a kind of the emergency bleeding stopping treatment as the kind of the bleeding stopping treatment, based on the processing target image sequence and the database.

9. The image processing system as defined in claim 8 , wherein
the processor performs the process that determines the kind of the bleeding stopping treatment based on the processing target image sequence including images captured during execution of the emergency bleeding stopping treatment by the user or after the execution of the emergency bleeding stopping treatment.

10. The image processing system as defined in claim 1 , wherein
the processing target image sequence and the in-vivo images are images captured with a liver,
the processor performs the process that determines the kind of the bleeding stopping treatment for a blood vessel that is any one of a hepatic artery, a hepatic vein, and a portal vein, based on the processing target image sequence and the database.

11. The image processing system as defined in claim 10 , wherein
the processor performs a process that identifies whether or not a Pringle maneuver that interrupts bloodstream of the hepatic artery and the portal vein is being performed to determine the kind of the bleeding stopping treatment based on a result of the identification.

12. The image processing system as defined in claim 10 , wherein
the processor determines, based on the processing target image sequence and the database, a kind of a first bleeding stopping treatment when a Pringle maneuver that interrupts bloodstream of the hepatic artery and the portal vein is being performed and a kind of a second bleeding stopping treatment when the Pringle maneuver is not being performed.

13. An endoscope system, comprising:
an imaging device that captures images of an inside of a living body; and
at least one processor including hardware,
wherein
the processor being configured to perform
a process that acquires, as a processing target image sequence, the images captured in a time series manner by the imaging device,
a process based on the processing target image sequence and a database generated by using a plurality of in-vivo images captured at earlier timings than timings at which the processing target image sequence is captured, and
a process that determines, when a bleeding has been occurring inside the living body, a kind of a bleeding stopping treatment desirable for a blood vessel on which the bleeding has been occurring based on the processing target image sequence and the database to present, to a user, the determined type of the bleeding stopping treatment.

14. An image processing method, comprising:
performing a process that acquires, as a processing target image sequence, images captured in a time series manner with an inside of a living body by an endoscope imaging device;
performing a process that determines, when a bleeding has been occurring inside the living body, a kind of a bleeding stopping treatment desirable for a blood vessel on which the bleeding has been occurring based on the processing target image sequence and a database generated by using a plurality of in-vivo images captured at earlier timings than timings at which the processing target image sequence is captured; and
performing a process that presents, to a user, the determined type of the bleeding stopping treatment.

Assignees

• Olympus Corp

Inventors

• Kimura Masato

Classifications

• G06T2207/30101

  Blood vessel; Artery; Vein; Vascular · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10068

  Endoscopic image · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• A61B5/02042

  Determining blood loss or bleeding, e.g. during a surgical procedure · CPC title