KR20170098480A

KR20170098480A - Reference image providing for portable ultrasound device

Info

Publication number: KR20170098480A
Application number: KR1020160020436A
Authority: KR
Inventors: 류정원; 정유찬
Original assignee: 주식회사 힐세리온
Priority date: 2016-02-22
Filing date: 2016-02-22
Publication date: 2017-08-30

Abstract

The present invention relates to provision of a reference image for a portable ultrasonic device, capable of allowing a non-expert to make a diagnosis and facilitating a diagnosis in training. According to the present invention, a method and a system to provide a reference image for a portable ultrasonic device comprise the following processes of: accumulating an ultrasonic image as big data; using machine learning to search for the images closest to the current diagnosis image from a database wherein the big data is stored and to suggest the searched images; and comparing the reference image with a scanned image in real time as a user scans the ultrasonic image while viewing the reference image, and putting a mark on the corresponding image and informing the user of the closest image when the closest image is scanned.

Description

[0001] The present invention relates to a reference image for a portable ultrasound device,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a portable ultrasound apparatus, and more particularly, to a method and system for automatically extracting and displaying a reference image during diagnosis through a portable ultrasound apparatus.

Ultrasonic diagnosis has non-invasive and non-destructive properties and is widely used in the medical field to obtain information inside the object. Ultrasonic diagnosis is very important in the medical field because it can provide the doctor with high-resolution images of the internal tissue of the subject without the need of a surgical operation to directly examine the subject.

The ultrasound diagnostic system is a system for irradiating ultrasound signals from a body surface of a subject to a target portion in the body and extracting information from the reflected ultrasound signals to obtain an image of a tomography or a blood flow of the soft tissue.

Such an ultrasound diagnostic system is small, inexpensive, and displays in real time when compared with other imaging devices such as an X-ray examination apparatus, a CT scanner (Magnetic Resonance Image Scanner), a MRI (Magnetic Resonance Image Scanner) And it is widely used for diagnosis of heart, abdomen, urinary and reproductive system because it has high safety because it does not have exposure such as X-ray.

In recent years, an attempt has been made to implement an ultrasonic diagnostic apparatus in a portable manner, and to perform ultrasonic diagnosis by connecting a portable terminal such as a smart phone or a tablet with an ultrasonic diagnostic apparatus through wireless communication. Such portable ultrasonic diagnostic apparatuses are generally used to be used in various clinic rooms or ward rooms because of the freedom of movement, and they are commonly used by a plurality of users.

Portable ultrasound devices can expand the opportunity for ultrasound diagnosis not only for the physicians who are experts but also for the non-specialists, and it is highly applicable to the ultrasound diagnosis education than the existing ultrasound diagnosis system.

However, it is not easy to use these portable ultrasound devices properly in non-specialists or curriculum. That is, when diagnosing using a portable ultrasound device, it is difficult to obtain a proper ultrasound image by scanning at an accurate angle at an accurate position.

Accordingly, it is an object of the present invention to provide a reference image providing method and system capable of diagnosing a non-specialist or facilitating diagnosis at the time of education by providing a reference image when diagnosing using a portable ultrasound device.

According to an aspect of the present invention, there is provided a reference image providing method and system for a portable ultrasound system, the method comprising: accumulating ultrasound images as big data in a server; Comparing the reference image with the scanned image in real time in the process of scanning the ultrasound image while the user views the reference image, and if the image is a close image, marking the image and notifying the user of the image.

In the reference image providing method and system for a portable ultrasound system, when a user scans and stops the image, the image of the scanned images, which is closest to the reference image, is searched using machine learning and then marked, So that it can be stored.

According to the present invention, a reference image is provided at the time of diagnosis using a portable ultrasound device, and a recommendation of a screen shot that best matches the reference image is provided, thereby making it possible to diagnose an unprofessional or facilitate diagnosis at the time of education .

1 is a conceptual diagram of a parameter automatic setting method and system for a portable ultrasound system according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. In the following description and the accompanying drawings, substantially the same components are denoted by the same reference numerals, and redundant description will be omitted. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

In the embodiment of the present invention, a best-fit image of the currently diagnosed screen is displayed among the set ultrasound image data, and a screen shot that best matches the reference image is recommended.

① The ultrasound image is stored in the server as big data.

Usually, when you are diagnosing an ultrasound, you end up recording a few images. For example, when ultrasonographic diagnosis of pregnant women is performed, the ultrasonic images of three or four sheets are stored in order to measure the body length up to 13 weeks, followed by the head, leg length, and optionally trunk circumference. In other words, the images that are stored in this way are well-parameterized and well-named images. The accumulated data includes various parts, body shape, clinical condition, and the like.

② Use machine learning (neural network) to find the images closest to the current diagnostic image from the accumulated database. This can be extracted as a set of reference images, and multiple images can be presented in priority order.

On the other hand, the data accumulated in the server is stored together with tag information such as position data such as GPS, and storage time. These reference data can be used together when searching for the closest image. For example, abdominal ultrasound can make a difference between obese and thin people, or between Koreans and Europeans. Therefore, it is possible to find the nearest image through machine learning with reference data such as race, region, etc. as well as image data.

③ When the reference image is presented, the user scans the ultrasound image to be the most similar image while viewing the reference image.

④ While scanning the ultrasound image, machine learning (neural network) is used to compare the reference image with the scanned image in real time. When the image is the closest to the reference image, it informs the user through screen display and sound. That is, when an image close to the reference image is displayed among the scanned images, the corresponding frame is marked and informs the user through sound or the like.

In addition, if the user stops scanning while the scanner is stopped, about 150 scanned images (still images) are generated until then, and a slide is displayed so that the scanned image can be searched. Among these images, And then mark it to allow the user to browse and save the marked image (via the slide), or to view the nearest of the marked image and save the appropriate image.

The above-described embodiments of the present invention can be embodied in a general-purpose digital computer that can be embodied as a program that can be executed by a computer and operates the program using a computer-readable recording medium. The computer-readable recording medium includes a storage medium such as a magnetic storage medium (e.g., ROM, floppy disk, hard disk, etc.), optical reading medium (e.g., CD ROM,

The present invention has been described with reference to the preferred embodiments. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

Claims

A process of storing the ultrasound image as big data in a server, a process of finding and presenting the images closest to the diagnostic image from the accumulated database by using machine learning, a process of browsing the ultrasound image while the user views the reference image, And a step of comparing the scanned image with the scanned image in real time to mark the image and informing the user when the image is close to the reference image.

The method according to claim 1,
Further comprising the steps of: if the user scans and stops the image scanning, searching for the images closest to the reference image among the scanned images by using machine learning and then marking the images so that the user can browse and store the images; A method and system for providing reference images.