Method and system for determining abnormality in medical device

Patent metadata

Field	Value
Publication number	US-11844632-B2
Application number	US-202318177266-A
Country	US
Kind code	B2
Filing date	Mar 2, 2023
Priority date	May 18, 2020
Publication date	Dec 19, 2023
Grant date	Dec 19, 2023

Abstract

A method for determining an abnormality in a medical device from a medical image is provided. The method for determining an abnormality in a medical device comprises receiving a medical image, and detecting information on at least a part of a target medical device included in the received medical image.

First claim

What is claimed is:

1. A computing device, comprising:
a memory storing one or more instructions; and
a processor configured to, by executing the stored one or more instructions,
receive a medical image,
detect information on at least a part of a medical device included in the received medical image,
extract a fiducial marker indicative of an anatomical region associated with the at least the part of medical device from the received medical image, and
determine whether the medical device is abnormal based on the extracted fiducial marker,
wherein at least one of a range indicative of a normal area relative to the fiducial marker or an area corresponding to the at least the part of the medical device relative to the fiducial marker is displayed on the medical image using a distance indicator, and the normal area is indicative of a region where the medical device is properly located.

2. The computing device according to claim 1 , wherein the detected information on the at least the part of the medical device includes information on a type of the medical device, and
wherein the fiducial marker is extracted based on the type of the medical device.

3. The computing device according to claim 1 , wherein the processor is further configured to provide information on whether the medical device is abnormal, in association with the medical image.

4. The computing device according to claim 3 , wherein the providing the information on whether the medical device is abnormal includes outputting a graphical marker indicative of the at least the part of the detected medical device and a graphical marker indicative of the extracted fiducial marker on the medical image.

5. The computing device according to claim 3 , wherein the providing the information on whether the medical device is abnormal includes outputting information on a location of the at least the part of the medical device relative to the extracted fiducial marker on the medical image.

6. The computing device according to claim 3 , wherein the information on whether the medical device is abnormal includes at least one of a position, a shape, a size, a presence or an absence of damage of the medical device, or information about a group to which the medical device belongs.

7. The computing device according to claim 1 , wherein the determining whether the medical device is abnormal includes determining the normal area based on the extracted fiducial marker, and determining whether the medical device is abnormal based on the determined normal area and the extracted fiducial marker.

8. The computing device according to claim 7 , wherein the determining whether the medical device is abnormal based on the determined normal area and the extracted fiducial marker includes, determining whether the medical device is abnormal based on whether the medical device or a tube tip of the medical device in the received medical image is located in the determined normal area.

9. The computing device according to claim 7 , wherein the processor is further configured to output at least one of the determined normal area or the fiducial marker on the medical image, and
wherein the at least one of the normal area or the fiducial marker is displayed on the medical image in a form of at least one of a mask, a region, a contour, a line or a dot.

10. The computing device according to claim 7 , wherein the processor is further configured to generate the determined information on whether the medical device is abnormal based on the normal area and the fiducial marker, and output the generated information on whether the medical device is abnormal in association with the medical image.

11. The computing device according to claim 10 , wherein the outputting the generated information on whether the medical device is abnormal in association with the medical image includes, outputting the information on whether the medical device is abnormal in a form of at least one of text, an image, a guideline or an indicator, in association with the medical image.

12. A method for determining an abnormality in a medical device in a medical image, the method being executed by at least one of processor and comprising:
receiving a medical image,
detecting information on at least a part of a medical device included in the received medical image,
extracting a fiducial marker indicative of an anatomical region associated with the medical device from the received medical image, and
determining whether the medical device is abnormal based on the extracted fiducial marker,
wherein at least one of a range indicative of a normal area relative to the fiducial marker or an area corresponding to the at least the part of the medical device relative to the fiducial marker is displayed on the medical image using a distance indicator, and the normal area is indicative of a region where the medical device is properly located.

13. A non-transitory, computer-readable medium, the computer-readable medium comprising processor-executable code that when executed by a processor, causes the processor to:
receive a medical image,
detect information on at least a part of a medical device included in the received medical image,
extract a fiducial marker indicative of an anatomical region associated with the medical device from the received medical image, and
determine whether the medical device is abnormal based on the extracted fiducial marker,
wherein at least one of a range indicative of a normal area relative to the fiducial marker or an area corresponding to the at least the part of the medical device relative to the fiducial marker is displayed on the medical image using a distance indicator, and the normal area is indicative of a region where the medical device is properly located.

Assignees

• Lunit Inc

Inventors

• Yoo Donggeun
• Lee Sanghyup
• Kim Minchul
• Lee Hanjun
• Park Sunggyun

Classifications

• A61B5/7264 Primary

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title

• A61B6/5217

  extracting a diagnostic or physiological parameter from medical diagnostic data · CPC title

• G06T7/0012

  Biomedical image inspection · CPC title

• A61B6/5211 Primary

  involving processing of medical diagnostic data · CPC title

• G06T7/10

  Segmentation; Edge detection (motion-based segmentation G06T7/215) · CPC title