Ultrasound diagnostic apparatus and method for operating same

Patent metadata

Field	Value
Publication number	US-12290406-B2
Application number	US-202017908445-A
Country	US
Kind code	B2
Filing date	Dec 16, 2020
Priority date	Mar 27, 2020
Publication date	May 6, 2025
Grant date	May 6, 2025

Abstract

Disclosed is a method for operating an ultrasound diagnostic apparatus, comprising the steps of: acquiring a first ultrasound image of an object; detecting a first nerve region corresponding to a first target nerve in the first ultrasound image; determining whether an abnormal region is present in the first nerve region of the first ultrasound image, on the basis of a determination standard for determining whether a target nerve is abnormal; and on the basis of a result of determining whether an abnormal region is present in the first nerve region, displaying at least one of information on the abnormal region and basis information regarding the basis for determining the abnormal region as abnormal.

First claim

The invention claimed is:

1. A method for operating an ultrasound diagnostic apparatus, the method comprising:
acquiring an ultrasound image of an object;
detecting a nerve region corresponding to a target nerve in the ultrasound image;
determining whether an abnormal region is present in the nerve region of the ultrasound image based on a determination standard for determining whether a target nerve is abnormal; and
displaying at least one of information about the abnormal region and basis information about a basis for determining the abnormal region, based on a result of determining whether the abnormal region is present in the nerve region,
wherein the determining whether the abnormal region is present in the nerve region of the ultrasound image is performed using at least one of:
a similarity between a reference honeycomb structure in a reference nerve region for a reference nerve and a target honeycomb structure in a target nerve region for the target nerve,
a difference between a reference aspect ratio of the reference nerve region for the reference nerve and an aspect ratio of the target nerve region for the target nerve, and
a difference between a size of a cross-sectional area of the reference nerve region for the reference nerve and a size of a cross-sectional area of the target nerve region for the target nerve.

2. The method of claim 1 , wherein the determining of whether an abnormal region is present in the nerve region based on the determination standard includes:
acquiring a learning model for determining whether the target nerve is abnormal using the similarity between the reference honeycomb structure and the target honeycomb structure; and
detecting a region in which an abnormal honeycomb structure exists in the nerve region by applying the nerve region to the learning model.

3. The method of claim 2 , wherein the learning model is a model in which the reference honeycomb structure is learned based on at least one of a shape and pattern of a honeycomb structure included in a plurality of ultrasound images and a structure of a peripheral region of the honeycomb structure, and a model for determining whether a predetermined target nerve is abnormal when an ultrasound image including the target honeycomb structure in the predetermined target nerve is acquired.

4. The method of claim 1 , wherein the determining of whether an abnormal region is present in the nerve region based on the determination standard includes one of:
acquiring the similarity based on a matching rate between the reference honeycomb structure in the reference nerve region of a reference template for the reference nerve and a target honeycomb structure in the nerve region; and
acquiring the similarity based on at least one of corner information and feature point information for each of the reference honeycomb structure in the reference nerve region for the reference nerve and the target honeycomb structure in the nerve region.

5. The method of claim 1 , wherein the determining of whether an abnormal region is present in the nerve region based on the determination standard for determining whether a target nerve is abnormal includes:
acquiring a reference value of at least one parameter which becomes a reference to determine whether the target nerve is abnormal; and
determining that the abnormal region is present in the nerve region when a difference between a value of the at least one parameter acquired from the ultrasound image and the reference value of the at least one parameter is out of a preset range.

6. The method of claim 1 , wherein the basis information about the basis for determining the abnormal region includes information about at least one parameter, which becomes a reference for determining whether the target nerve is abnormal, and information obtained by comparing a value of the at least one parameter and a reference value of the at least one parameter.

7. The method of claim 1 , wherein the displaying of at least one of the information about the abnormal region and the basis information about the basis for determining the abnormal region includes at least one of:
displaying a boundary of the abnormal region on the ultrasound image; and
displaying the bases for determining whether the abnormal region is present in the nerve region according to a preset priority.

8. The method of claim 7 , wherein the preset priority is determined based on a degree to which values of parameters, which become a reference for determining whether the target nerve is abnormal, are out of a preset range.

9. The method of claim 1 , wherein the displaying of at least one of the information about the abnormal region and the basis information about the basis for determining the abnormal region includes:
displaying the information about the abnormal region on the ultrasound image; and
displaying trend information of the abnormal region for the object by referring to a previous ultrasound image for the object.

10. An ultrasound diagnostic apparatus comprising:
a probe configured to transmit an ultrasound signal to an object and receive an ultrasound signal reflected from the object;
a user interface device;
a display;
a processor; and
a memory configured to store instructions executable by the processor,
wherein, the processor is configured to execute the instructions to:
acquire an ultrasound image of the object based on the reflected ultrasound signal;
detect a nerve region corresponding to a target nerve in the ultrasound image;
determine whether an abnormal region is present in the nerve region of the ultrasound image based on a determination standard for determining whether a target nerve is abnormal; and
display at least one of information about the abnormal region and basis information about a basis for determining the abnormal region through the display based on a result of determining whether the abnormal region is present in the nerve region,

wherein the processor is configured to execute the instructions to determine whether the abnormal region is present in the nerve region of the ultrasound image using at least one of:
a similarity between a reference honeycomb structure in a reference nerve region for a reference nerve and a target honeycomb structure in a target nerve region for the target nerve,
a difference between a reference aspect ratio of the reference nerve region for the reference nerve and an aspect ratio of the target nerve region for the target nerve, and
a difference between a size of a cross-sectional area of the reference nerve region for the reference nerve and a size of a cross-sectional area of the target nerve region for the target nerve.

11. A computer program stored in a medium to perform a method in combination with an ultrasound diagnostic apparatus, wherein the method comprises:
acquiring an ultrasound image of an object;
detecting a nerve region corresponding to a target nerve in the ultrasound image;
determining whether an abnormal region is present in the nerve region of the ultrasound image based on a determination standard for determining whether a target nerve is abnormal; and
displaying at least one of information about the abnormal region and basis information about a basis for determining the abnormal region based on a result of determining whether the abnormal region is present in the nerve region,
wherein the determining whether the abnormal region is present in the nerve region of the ultrasound image is performed using at least one of:
a similarity between a reference honeycomb structure in a reference nerve region for a reference nerve and a target honeycomb structure in a target nerve region for the target nerve,
a differenc

Assignees

• Samsung Medison Co Ltd

Inventors

• Park Moonho
• Son Kihong
• Lee Hojun
• Paul Anjan Kumar
• Ahn Sujin
• Seong Yeongkyeong

Classifications

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10132

  Ultrasound image · CPC title

• G06T7/0014

  using an image reference approach · CPC title

• A61B8/463

  characterised by displaying multiple images or images and diagnostic data on one display · CPC title