Ultrasonic diagnostic apparatus and method for operating the same

Abstract

Disclosed is a method for operating an ultrasonic diagnostic device, the method comprising the following steps: acquiring a first ultrasonic image of an object; detecting a first nerve region corresponding to a first target nerve in the first ultrasonic image; determining whether there is an abnormal region in the first nerve region of the first ultrasonic image based on a determination criterion for determining whether the 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 as abnormal based on a result of determining whether there is an abnormal region in the first nerve region.

Description

Technical Field

[0001] The present invention relates to an ultrasonic diagnostic apparatus and a method for operating an ultrasonic diagnostic apparatus. Background Art

[0002] The ultrasound diagnostic apparatus irradiates ultrasound signals generated from a transducer of a probe onto a subject and receives information about the signals reflected from the subject, thereby obtaining at least one image of an internal portion (eg, soft tissue or blood flow) of the subject. Summary of the Invention

[0003] Technical issues

[0004] The present invention aims to determine whether there is an abnormality in a nerve region detected from an ultrasound image, and based on the determination result, provide information about the abnormal region of the nerve region or basis information about a basis for determining the abnormal region.

[0005] The present invention also aims to detect a nerve region from an ultrasound image acquired in real time, and accurately provide information on whether the nerve is abnormal and basis information on a basis for determining the abnormality.

[0006] Technical Solution

[0007] According to one embodiment, a method for operating an ultrasonic diagnostic device is provided, the method comprising: acquiring a first ultrasonic image of an object; detecting a first nerve region corresponding to a first target nerve in the first ultrasonic image; determining whether there is an abnormal region in the first nerve region of the first ultrasonic image based on a determination criterion for determining whether the 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 there is an abnormal region in the first nerve region.

[0008] According to another embodiment, an ultrasound diagnostic device is provided, which includes: a probe configured to transmit ultrasound signals to an object and receive ultrasound signals 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 executes the instructions to perform the following operations: acquiring a first ultrasound image of the object based on the reflected ultrasound signal; detecting a first nerve area corresponding to a first target nerve in the first ultrasound image; determining whether there is an abnormal area in the first nerve area of ​​the first ultrasound image based on a determination criterion for determining whether the target nerve is abnormal; and displaying at least one of information about the abnormal area and basis information about a basis for determining the abnormal area through the display based on a result of determining whether the abnormal area exists in the first nerve area.

[0009] According to another embodiment, a computer program is provided, which is stored in a medium to execute a method in combination with an ultrasonic diagnostic device, the method comprising: acquiring a first ultrasonic image of an object; detecting a first nerve region corresponding to a first target nerve in the first ultrasonic image; determining whether there is an abnormal region in the first nerve region of the first ultrasonic image based on a determination criterion for determining whether the target nerve is abnormal; and based on a result of determining whether there is the abnormal region in the first nerve region, displaying at least one of information about the abnormal region and basis information about a basis for determining the abnormal region.

[0010] According to another embodiment, a computer-readable recording medium is provided, in which program commands are stored for executing a method for operating an ultrasonic diagnostic device, wherein the method includes: acquiring a first ultrasonic image of an object; detecting a first nerve region corresponding to a first target nerve in the first ultrasonic image; determining whether there is an abnormal region in the first nerve region of the first ultrasonic image based on a determination criterion for determining whether the target nerve is abnormal; and based on a result of determining whether the abnormal region exists in the first neural region, displaying at least one of information about the abnormal region and basis information about a basis for determining the abnormal region.

[0011] Beneficial effects

[0012] Whether or not there is an abnormality in a nerve region detected from an ultrasound image may be determined, and based on the determination result, information on the abnormal region of the nerve region or basis information on a basis for determining the abnormal region may be provided.

[0013] It is possible to detect a nerve region from an ultrasound image acquired in real time, and accurately provide information on whether the nerve is abnormal and information on the basis for determining the abnormality.

[0014] By providing basis information about the basis for determining nerve abnormality, the user can accurately diagnose the nerve. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention can be easily understood by combining the accompanying drawings and the following detailed description, and the accompanying drawings represent structural elements.

[0016] Figure 1 is a block diagram showing the configuration of an ultrasonic diagnostic apparatus according to one embodiment.

[0017] Figures 2a to 2c is a diagram illustrating an ultrasonic diagnostic apparatus according to one embodiment.

[0018] Figure 3 is a diagram for schematically describing a process of detecting a nerve region of a target nerve in an ultrasound image to determine whether an abnormality exists and displaying the determination result according to one embodiment.

[0019] Figure 4 is a diagram for describing a method for operating an ultrasonic diagnostic apparatus according to one embodiment.

[0020] Figure 5 is a diagram for describing a process of detecting a nerve region from an ultrasound image and displaying an abnormal region in the ultrasound image according to one embodiment.

[0021] Figure 6 is a diagram for describing a process of determining whether a nerve is abnormal based on an anatomical structure in a nerve region in an ultrasound image according to one embodiment.

[0022] Figure 7 is a diagram for describing a process of determining whether a nerve is abnormal based on the shape of a nerve region in an ultrasound image according to one embodiment.

[0023] Figure 8 is a diagram for describing a process of determining whether a nerve is abnormal based on the size of a cross-sectional area of ​​a nerve region in an ultrasound image according to one embodiment.

[0024] Figure 9a is a diagram schematically illustrating an artificial neural network for determining whether a nerve in an ultrasound image is abnormal according to one embodiment.

[0025] Figure 9b is a diagram for describing a method of generating a learning model for determining whether a nerve in an ultrasound image is abnormal and an operation of the learning model according to one embodiment.

[0026] Figure 9c is a diagram for describing a honeycomb structure observed in a normal nerve and a honeycomb structure observed in an abnormal nerve according to one embodiment.

[0027] Figure 10 is a diagram for describing a process of determining whether a nerve is abnormal based on corner information in an ultrasound image according to one embodiment.

[0028] Figure 11a is an exemplary diagram showing at least one of information about an abnormal region in a nerve and basis information about a basis for determining the abnormal region in an ultrasonic diagnostic apparatus according to one embodiment.

[0029] Figure 11bis an exemplary diagram showing basis information according to the priority of bases for determining an abnormal region in an ultrasonic diagnostic apparatus according to one embodiment.

[0030] Figure 11c is an exemplary diagram showing trend information of abnormal regions in an ultrasonic diagnostic apparatus according to one embodiment.

[0031] Figure 12 is a block diagram showing the configuration of an ultrasonic diagnostic apparatus according to one embodiment.

[0032] Best Practice

[0033] A method for operating an ultrasonic diagnostic device is disclosed, the method comprising: acquiring a first ultrasonic image of an object; detecting a first nerve region corresponding to a first target nerve in the first ultrasonic image; determining whether there is an abnormal region in the first nerve region of the first ultrasonic image based on a determination criterion for determining whether the 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 there is an abnormal region in the first nerve region. DETAILED DESCRIPTION

[0034] This specification describes the principles of the present invention and discloses embodiments, thereby clarifying the scope of the present invention and enabling those skilled in the art to implement the present invention. The disclosed embodiments can be implemented in various forms.

[0035] Throughout the specification, the same reference numerals represent the same elements. This specification does not describe all components of the embodiment, and the common description in the technical field to which the present invention belongs and the repeated description between the embodiments will be omitted. Terms such as "part" and "section" used herein represent those parts or parts that can be implemented by software or hardware, and depending on the embodiment, multiple parts or parts can be implemented by a single unit or element, or a single part or part can include multiple units or elements. Hereinafter, the operating principle and embodiments of the present invention will be described with reference to the accompanying drawings.

[0036] In this specification, the image may include a medical image acquired by a medical imaging apparatus such as a magnetic resonance imaging (MRI) apparatus, a computed tomography (CT) apparatus, an ultrasound imaging apparatus, and an X-ray imaging apparatus.

[0037] In this specification, the term "subject" refers to an object to be photographed, and may include a person, an animal, or a part thereof. For example, the subject may include a part of the body (ie, an organ), a phantom, or the like.

[0038] Throughout the specification, the term "ultrasound image" refers to an image of an object, which is processed based on ultrasound signals transmitted to and reflected from the object.

[0039] Throughout this specification, the term "target nerve" refers to a nerve that is targeted for determination of abnormality, and the term "target nerve region" refers to a region in an ultrasound image that corresponds to the target nerve. For example, the target nerve is a nerve of the same type as the reference nerve and refers to a nerve to be examined or diagnosed.

[0040] Throughout this specification, the term "reference nerve" refers to a nerve that becomes a reference for determining whether an abnormality exists in a target nerve, and the term "reference nerve region" refers to a region corresponding to the reference nerve in an ultrasound image.

[0041] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

[0042] Figure 1 1 is a block diagram illustrating a configuration of an ultrasonic diagnostic apparatus 100 according to an embodiment. The ultrasonic diagnostic apparatus 100 according to an embodiment may include a probe 20, an ultrasonic transceiver 110, a controller 120, an image processor 130, a display unit 140, a storage unit 150, a communication unit 160, and an input unit 170.

[0043] The ultrasonic diagnostic apparatus 100 may be implemented not only as a cart type but also as a portable device. Examples of portable ultrasonic diagnostic apparatuses may include smartphones, laptop computers, personal digital assistants (PDAs), tablet personal computers (PCs), etc. that include probes and applications, but the present invention is not limited thereto.

[0044] The probe 20 may include multiple transducers. The multiple transducers may transmit ultrasonic signals toward the object 10 based on the transmission signal applied from the transmitter 113. The multiple transducers may receive the ultrasonic signals reflected from the object 10 and form a received signal. Furthermore, the probe 20 may be integrated with the ultrasonic diagnostic apparatus 100 or may be implemented as a separate type connected to the ultrasonic diagnostic apparatus 100 in a wired or wireless manner. Furthermore, depending on the implementation, the ultrasonic diagnostic apparatus 100 may be provided with one or more probes 20.

[0045] The controller 120 controls the transmitter 113 to form a transmission signal to be applied to each of the plurality of transducers in consideration of the positions and focal points of the plurality of transducers included in the probe 20 .

[0046] The controller 120 converts reception signals received from the probe 20 in an analog-to-digital manner, and controls the receiver 115 to generate ultrasound data by summing the reception signals converted into digital, taking into account positions and focal points of a plurality of transducers.

[0047] The image processor 130 generates an ultrasound image using the ultrasound data generated by the receiver 115 .

[0048] The display unit 140 may display a generated ultrasound image and various information processed by the ultrasound diagnostic apparatus 100. According to implementation, the ultrasound diagnostic apparatus 100 may include one or more display units 140. In addition, the display unit 140 may be implemented as a touch screen combined with a touch panel.

[0049] The controller 120 controls the overall operation of the ultrasonic diagnostic apparatus 100 and the signal flow between its internal components. The controller 120 may include a memory that stores programs or data used to execute the functions of the ultrasonic diagnostic apparatus 100 and a processor that processes the programs or data. Furthermore, the controller 120 controls the operation of the ultrasonic diagnostic apparatus 100 by receiving control signals from the input unit 170 or an external device.

[0050] The ultrasonic diagnostic apparatus 100 includes a communication section 160 and can be connected to an external apparatus (eg, a server, a medical apparatus, a portable apparatus (smartphone, tablet PC, wearable device, etc.)) through the communication section 160 .

[0051] The communication part 160 may include one or more components capable of communicating with an external device, and may include, for example, at least one of a short-range communication module, a wired communication module, and a wireless communication module.

[0052] The communication part 160 may receive a control signal and data from an external device and transmit the received control signal to the controller 120 , so that the controller 120 may control the ultrasonic diagnostic apparatus 100 in response to the received control signal.

[0053] Alternatively, the controller 120 may transmit a control signal to the external device through the communication portion 160 , so that the external device may be controlled in response to the control signal of the controller 120 .

[0054] For example, the external device may process data of the external device in response to a control signal of the controller received through the communication portion.

[0055] A program capable of controlling the ultrasonic diagnostic apparatus 100 may be installed in the external apparatus, and the program may include instructions for executing some or all operations of the controller 120 .

[0056] The program may be pre-installed in the external device, or may be installed by a user of the external device by downloading the program from a server providing the application. The server providing the application may include a recording medium storing the corresponding program.

[0057] The storage part 150 may store various types of data or programs for driving and controlling the ultrasonic diagnostic apparatus 100 , inputting / outputting ultrasonic data, acquired ultrasonic images, and the like.

[0058] The input unit 170 may receive user input for controlling the ultrasonic diagnostic apparatus 100. For example, the user input may include input for manipulating buttons, a keypad, a mouse, a trackball, a toggle switch, a knob, etc., input for touching a touchpad or a touch screen, voice input, motion input, and biometric information input (e.g., iris recognition, fingerprint recognition, etc.), but the present invention is not limited thereto.

[0059] The following will refer to Figures 2a to 2c An example of the ultrasonic diagnostic apparatus 100 according to one embodiment is described.

[0060] Figures 2a to 2c is a diagram illustrating an ultrasonic diagnostic apparatus according to one embodiment.

[0061] Reference Figure 2a and Figure 2b Ultrasonic diagnostic devices 100a and 100b may each include a main display 121 and a sub-display 122. One or more of the main display 121 and the sub-display 122 may be implemented as a touch screen. The main display 121 and the sub-display 122 may display an ultrasonic image or various information processed by the ultrasonic diagnostic devices 100a and 100b. Furthermore, the main display 121 and the sub-display 122 may each be implemented as a touch screen and receive data from a user for controlling the ultrasonic diagnostic devices 100a and 100b by providing a graphical user interface (GUI). For example, the main display 121 may display an ultrasonic image, and the sub-display 122 may display a control panel for controlling the display of the ultrasonic image in the form of a GUI. The sub-display 122 may receive data for controlling the display of the image via the control panel displayed in the form of a GUI. The ultrasonic diagnostic devices 100a and 100b may use the input control data to control the display of the ultrasonic image displayed on the main display 121.

[0062] Reference Figure 2b In addition to the main display unit 121 and the sub-display unit 122, the ultrasonic diagnostic apparatus 100b may further include a control panel 165. The control panel 165 may include buttons, a trackball, a toggle switch, a knob, etc., and may receive data from the user for controlling the ultrasonic diagnostic apparatus 100b. For example, the control panel 165 may include a time gain compensation (TGC) button 171 and a freeze button 172. The TGC button 171 is a button for setting a TGC value for each depth of the ultrasonic image. Furthermore, when an input of the freeze button 172 is detected while scanning an ultrasonic image, the ultrasonic diagnostic apparatus 100b may maintain the display of the frame image at the corresponding time point.

[0063] In addition, buttons, a trackball, a toggle switch, a knob, etc. included in the control panel 165 may be provided for the GUI on the main display portion 121 or the sub-display portion 122 .

[0064] Reference Figure 2c The ultrasonic diagnostic apparatus 100c may be implemented as a portable device. Examples of the portable ultrasonic diagnostic apparatus 100c may include a smartphone, a laptop computer, a PDA, a tablet PC, etc. that includes a probe and an application, but the present invention is not limited thereto.

[0065] The ultrasonic diagnostic apparatus 100c may include a probe 20 and a body 40, and the probe 20 may be connected to one side of the body 40 in a wired or wireless manner. The body 40 may include a touch screen 145. The touch screen 145 may display an ultrasonic image, various information processed by the ultrasonic diagnostic apparatus, a GUI, and the like.

[0066] Figure 3 is a diagram for schematically describing a process of detecting a nerve region of a target nerve in an ultrasound image to determine whether an abnormality exists and displaying the determination result according to one embodiment.

[0067] Reference Figure 3 At block 310, the ultrasound diagnostic apparatus 100 may acquire an ultrasound image of the subject. For example, the ultrasound image may be obtained by scanning a target nerve and may include a nerve region corresponding to the target nerve. As shown in image 311, the ultrasound diagnostic apparatus 100 may display the ultrasound image on its display.

[0068] Reference Figure 3 In block 320 , the ultrasound diagnostic apparatus 100 may detect a nerve region corresponding to a target nerve in the ultrasound image based on an algorithm for detecting a nerve region. As shown in image 321 , the ultrasound diagnostic apparatus 100 may display a nerve region 322 in the ultrasound image.

[0069] Reference Figure 3 At block 330, the ultrasound diagnostic apparatus 100 may determine whether an abnormality exists in the target nerve in the ultrasound image based on criteria for determining whether the target nerve is abnormal. If an abnormality exists in the target nerve, the ultrasound diagnostic apparatus 100 may detect an abnormal region within the nerve. As shown in image 331, the ultrasound diagnostic apparatus 100 may display the abnormal region 332 on the ultrasound image. Furthermore, the ultrasound diagnostic apparatus 100 may display information regarding the abnormal region and basis information 333 regarding the basis for determining the abnormal region.

[0070] Figure 4 is a diagram for describing a method for operating an ultrasonic diagnostic apparatus according to one embodiment.

[0071] Reference Figure 4 In operation S410, the ultrasound diagnostic apparatus 100 may acquire a first ultrasound image of the subject. For example, a probe in the ultrasound diagnostic apparatus 100 may transmit an ultrasound signal toward a region of the subject including a first target nerve, and may receive ultrasound signals reflected from the region including the first target nerve. The ultrasound diagnostic apparatus 100 may acquire the first ultrasound image of the first target nerve based on the reflected ultrasound signal. The first ultrasound image may be acquired in real time. For example, the first ultrasound image may be acquired in units of images or videos.

[0072] In operation S420 , the ultrasound diagnostic apparatus 100 may detect a first nerve region corresponding to a first target nerve in the first ultrasound image.

[0073] For example, the ultrasound diagnostic apparatus 100 may detect a first nerve region corresponding to a first target nerve in the first ultrasound image based on a predetermined automatic detection algorithm or a predetermined automatic segmentation algorithm. The ultrasound diagnostic apparatus 100 may display the detected first nerve region on the first ultrasound image. In addition, the ultrasound diagnostic apparatus 100 may display only the detected first nerve region. Figure 5 A process for detecting nerve regions from ultrasound images is described.

[0074] In operation S430 , the ultrasound diagnostic apparatus 100 may determine whether there is an abnormal region in the first nerve region of the first ultrasound image based on a determination criterion for determining whether the target nerve is abnormal.

[0075] For example, the determination criteria may be obtained based on at least one of the following: the anatomical structure in the reference nerve region for the reference nerve, the shape of the reference nerve region, and the size of the reference nerve region. Here, the anatomical structure may be determined based on the shape, size, and relative positional relationship of the structures constituting the nerve.

[0076] For example, the ultrasound diagnostic apparatus 100 may determine whether there is an abnormality in the first target nerve based on the cellular structure that is the anatomical structure observed in the first target nerve region. Specifically, the ultrasound diagnostic apparatus 100 may determine whether there is an abnormal region in the first nerve region corresponding to the first target nerve based on the similarity between the reference cellular structure in the reference nerve region for the reference nerve and the target cellular structure in the target nerve region for the target nerve. Figure 6 A process is described for determining whether a nerve is abnormal based on honeycomb structures observed in ultrasound images.

[0077] For example, the ultrasound diagnostic apparatus 100 may acquire a learning model for determining whether a target nerve is abnormal using the similarity between a reference cellular structure and a target cellular structure, and may apply the learning model to the first nerve region to detect an area in the first nerve region where an abnormal cellular structure exists.

[0078] Here, the learning model may be a model that learns a reference cellular structure based on at least one of the shape and pattern of the cellular structure included in a plurality of ultrasound images and the structure of the peripheral region of the cellular structure. Furthermore, the learning model may be a model used to determine whether a predetermined target nerve is abnormal when an ultrasound image including a target cellular structure is acquired.

[0079] For example, the ultrasound diagnostic apparatus 100 may obtain similarity based on a matching rate between a reference cellular structure in a reference nerve region of a reference template for a reference nerve and a first target cellular structure in a first nerve region. The ultrasound diagnostic apparatus 100 may determine whether there is an abnormal region in the first nerve region corresponding to the first target nerve based on the obtained similarity. Figure 9a and Figure 9b A learning model is described for obtaining similarity between a reference cellular structure and a target cellular structure and using the similarity to determine whether a target neuron is abnormal.

[0080] For example, the ultrasound diagnostic apparatus 100 may obtain similarity based on at least one of corner information and feature point information of each of a reference cellular structure in a reference nerve region and a first target cellular structure in a first nerve region for the reference nerve. Based on the obtained similarity, the ultrasound diagnostic apparatus 100 may determine whether there is an abnormal area in the first nerve region corresponding to the first target nerve.

[0081] For example, the ultrasound diagnostic apparatus 100 may determine whether there is an abnormal area in the first nerve area corresponding to the first target nerve based on the second determination criterion for determining whether the target nerve is abnormal using a difference between a reference aspect ratio of a reference nerve area for the reference nerve and an aspect ratio of a target nerve area for the target nerve. Figure 7 A process is described for determining whether a target nerve is abnormal based on the aspect ratio of the target nerve region.

[0082] For example, the ultrasound diagnostic apparatus 100 may determine whether an abnormal area exists in the first nerve region corresponding to the first target nerve based on a third determination criterion for determining whether the target nerve is abnormal using a difference between a size of a reference cross-sectional area of ​​a reference nerve region for the reference nerve and a size of a cross-sectional area of ​​a target nerve region for the target nerve. Figure 8 A process for determining whether a target nerve is abnormal based on the size of the cross-sectional area of ​​the target nerve region is described.

[0083] For example, the ultrasound diagnostic apparatus 100 may acquire a baseline value for at least one parameter that serves as a basis for determining whether a target nerve is abnormal. For example, the parameter may include at least one of the validity of the honeycomb structure observed in the nerve region, the similarity of the honeycomb structure, the shape of the nerve region, the aspect ratio of the nerve region, and the size of the cross-sectional area of ​​the nerve region, although the present invention is not limited to the above examples. When the difference between the value of the at least one parameter acquired from the first ultrasound image and the baseline value of the at least one parameter is outside a preset range, the ultrasound diagnostic apparatus 100 may determine that an abnormal area exists in the first nerve region.

[0084] In operation S440 , the ultrasound diagnostic apparatus 100 may display 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 exists in the first nerve region.

[0085] For example, the basis information about the basis for determining the abnormal area may include the following information: information about at least one parameter that serves as a benchmark for determining whether the first target nerve is abnormal, and information obtained by comparing the value of the at least one parameter with a benchmark value of the at least one parameter.

[0086] For example, the ultrasound diagnostic apparatus 100 may display the boundary of an abnormal region on the first ultrasound image. The ultrasound diagnostic apparatus 100 may display the basis for determining whether an abnormal region exists in the first nerve region according to a preset priority. For example, the preset priority may be determined based on the extent to which the value of a parameter serving as a basis for determining whether the first target nerve is abnormal exceeds a preset range.

[0087] For example, the ultrasound diagnostic apparatus 100 may display information about the abnormal region on the first ultrasound image.The ultrasound diagnostic apparatus 100 may display trend information of the abnormal region of the object by referring to previous ultrasound images of the object.

[0088] Figure 5 is a diagram for describing a process of detecting a nerve region from an ultrasound image and displaying an abnormal region in the ultrasound image according to one embodiment.

[0089] The ultrasound diagnostic apparatus 100 may acquire a first ultrasound image with respect to a first target nerve. Figure 5 Image 510 represents a first ultrasound image of a first target nerve.

[0090] For example, the ultrasound diagnostic apparatus 100 may acquire the first ultrasound image in real time using a probe in the ultrasound diagnostic apparatus 100, or acquire the first ultrasound image from ultrasound images stored in the ultrasound diagnostic apparatus 100. In addition, the ultrasound diagnostic apparatus 100 may receive the first ultrasound image from an external apparatus.

[0091] The ultrasound diagnostic apparatus 100 may detect a first nerve region corresponding to a first target nerve in the first ultrasound image. For example, the ultrasound diagnostic apparatus 100 may analyze the entire area of ​​the first ultrasound image and detect the first nerve region corresponding to the first target nerve using a predetermined automatic detection algorithm. For example, the predetermined automatic detection algorithm may be a learning model that detects a nerve region corresponding to a target nerve in an ultrasound image. Figure 5 The image 520 represents an image in which a region 521 detected as a first nerve region is displayed on the first ultrasound image. In addition, when the cross section observed in the first ultrasound image acquired in real time changes according to the movement of the probe, the first nerve region can be automatically tracked according to the changed cross section, and the first nerve region can be displayed. That is, the ultrasound diagnostic apparatus 100 can track and display only the detected first nerve region. For example, the ultrasound diagnostic apparatus 100 can display the first nerve region with a bounding box (such as Figure 5 Here, the strength of the boundary represented by the bounding box can be adjusted.

[0092] Furthermore, the ultrasound diagnostic apparatus 100 can detect the first nerve region corresponding to the first target nerve by segmenting the first ultrasound image into a plurality of regions using a predetermined automatic segmentation algorithm and analyzing all of the plurality of segmented regions. For example, the predetermined automatic segmentation algorithm can be a learning model for detecting the nerve region corresponding to the target nerve by segmenting the ultrasound image into a plurality of regions and analyzing the segmented regions. Figure 5 The image 530 represents an image in which a region 531 detected as a first nerve region is displayed on the first ultrasound image. Figure 5 The region 521 detected as the first nerve region in the image 520 is used to accurately detect the region 531 in the first nerve region.

[0093] In addition, in the ultrasound diagnostic apparatus 100 , a first nerve region corresponding to the first target nerve may be determined in the first ultrasound image based on a user input.

[0094] The ultrasound diagnostic apparatus 100 may determine whether there is an abnormal area in the first nerve area of ​​the first ultrasound image based on a determination criterion for determining whether the target nerve is abnormal. When it is determined that there is an abnormal area in the first nerve area, the ultrasound diagnostic apparatus 100 may detect the abnormal area in the first nerve area and display the abnormal area. Figure 5 Image 540 represents an image in which an abnormal region 541 in a first nerve region is displayed on a first ultrasound image.

[0095] Figure 6is a diagram for describing a process of determining whether a nerve is abnormal based on an anatomical structure in a nerve region in an ultrasound image according to one embodiment.

[0096] The ultrasound diagnostic apparatus 100 may determine whether there is an abnormal area in the first nerve region of the first ultrasound image based on a determination criterion for determining whether the target nerve is abnormal, which is acquired based on an anatomical structure in the reference nerve region of the reference nerve.

[0097] For example, the ultrasound diagnostic apparatus 100 may determine whether there is an abnormal area in the first nerve area of ​​the first ultrasound image based on a first determination criterion for determining whether the target nerve is abnormal using a honeycomb structure representing a structure observed in the nerve area.

[0098] For example, the first determination criterion may be a benchmark for determining whether the target nerve is abnormal using the similarity between a reference cellular structure in the reference nerve region and a target cellular structure in the target nerve region. Here, the reference cellular structure refers to a structure observed in the reference nerve region. Alternatively, the reference cellular structure may be a structure observed in the nerve region of a normal nerve. For example, the similarity may indicate a matching ratio between the reference cellular structure and the target cellular structure.

[0099] For example, the similarity between the reference cellular structure and the target cellular structure may be acquired based on at least one of a learning model, template matching, information on feature points, and corner information.

[0100] For example, the ultrasound diagnostic apparatus 100 may obtain a learning model for determining whether a target nerve is abnormal using the similarity between the reference cellular structure and the target cellular structure. The ultrasound diagnostic apparatus 100 may obtain the similarity between the reference cellular structure and the first target cellular structure in the first nerve region by applying the learning model to the first nerve region. Figure 9a and Figure 9b A learning model is described for obtaining similarity between a reference cellular structure and a target cellular structure and using the similarity to determine whether a target neuron is abnormal.

[0101] For another example, the ultrasound diagnostic apparatus 100 may obtain similarity based on a matching rate between a reference cellular structure in a reference nerve region of a reference template for a reference nerve and a first target cellular structure in a first nerve region. For a specific example, the ultrasound diagnostic apparatus 100 may store a plurality of reference templates for a reference nerve. The ultrasound diagnostic apparatus 100 may detect a first target cellular structure in a first nerve region of a first ultrasound image. The ultrasound diagnostic apparatus 100 may obtain a first reference cellular structure having a structure most similar to the first target cellular structure by comparing the reference cellular structure of each reference template in a plurality of reference templates with the first target cellular structure. The ultrasound diagnostic apparatus 100 may obtain similarity indicating a matching rate between the first reference cellular structure and the first target cellular structure based on a shape or pattern of the first target cellular structure and the first reference cellular structure.

[0102] For another example, the ultrasound diagnostic device 100 may obtain similarity based on at least one of the following information: corner information and feature point information for each of the baseline honeycomb structure in the baseline neural region and the first target honeycomb structure in the first neural region. For a specific example, the ultrasound diagnostic device 100 may detect a baseline feature point of a specifiable honeycomb structure based on the baseline honeycomb structure. The ultrasound diagnostic device 100 may detect feature points corresponding to the baseline feature points from the first target honeycomb structure in the first neural region. The ultrasound diagnostic device 100 may obtain information about the baseline feature points, and the information about the baseline feature points includes at least one piece of information about the number, position, distribution degree, maximum brightness value, minimum brightness value, and average brightness value of the baseline feature points. In addition, the ultrasound diagnostic device 100 may obtain information about the feature points, and the information about the feature points includes at least one piece of information about the number, position, distribution degree, maximum brightness value, minimum brightness value, and average brightness value of the feature points corresponding to the baseline feature points. The ultrasound diagnostic device 100 may compare the value of at least one parameter based on the information about the baseline feature points and the information about the feature points, and obtain similarity based on the comparison result. Reference will be made to Figure 10 A process is described for obtaining similarity using corner information and determining whether a target nerve is abnormal based on the similarity.

[0103] In addition, when the similarity is greater than or equal to a preset similarity, the ultrasound diagnostic apparatus 100 may determine that the first target nerve is normal. Figure 6 Image 610 is an illustration showing a normal first target cellular structure 611 observed in a first nerve region corresponding to a first target nerve. On the other hand, if the similarity is less than a preset similarity, the ultrasound diagnostic apparatus 100 may determine that an abnormality exists in the first target nerve. For example, the ultrasound diagnostic apparatus 100 may detect an area with an abnormal cellular structure in the first nerve region corresponding to the first target nerve based on the learning model. Figure 6The image 620 is a diagram showing an abnormal first target cellular structure 621 observed in a first nerve region corresponding to a first target nerve. Figure 9c Describe the honeycomb pattern observed in normal nerves and the honeycomb pattern observed in abnormal nerves.

[0104] Figure 7 is a diagram for describing a process of determining whether a nerve is abnormal based on the shape of a nerve region in an ultrasound image according to one embodiment.

[0105] The ultrasound diagnostic equipment 100 can determine whether there is an abnormal area in the first nerve area corresponding to the first target nerve based on a second determination criterion, and the second determination criterion is used to determine whether the target nerve is abnormal using the difference between the baseline aspect ratio of the baseline nerve area for the baseline nerve and the aspect ratio of the target nerve area for the target nerve.

[0106] Reference Figure 7 In the image 710 , the aspect ratio may indicate a ratio of a length of a major axis 712 to a length of a minor axis 713 in the nerve region 711 . Furthermore, the aspect ratio may further indicate a ratio of a length of a minor axis 713 to a length of a major axis 712 in the nerve region 711 .

[0107] Figure 7 Image 720 is a diagram for describing a method of detecting the long axis in a nerve region 721. For example, the ultrasound diagnostic apparatus 100 may detect the center of gravity in the nerve region 721. The ultrasound diagnostic apparatus 100 may detect a line segment 722 as the long axis, which is the longest line segment having an intersection point between a straight line passing through the center of gravity of the nerve region 721 and the nerve region 721 as both end points.

[0108] Figure 7 Image 730 is a diagram for describing a method of detecting a short axis in a nerve region 731. For example, the ultrasound diagnostic apparatus 100 may detect the center of gravity in the nerve region 731. The ultrasound diagnostic apparatus 100 may detect a line segment 732 as the short axis, the line segment 732 being the shortest among line segments each having an intersection point (as two endpoints) between a straight line passing through the center of gravity of the nerve region 731 and the nerve region 731.

[0109] The ultrasound diagnostic apparatus 100 may obtain a baseline aspect ratio of a baseline nerve region for a baseline nerve. For example, the baseline aspect ratio may be set by a user or obtained from an external device. The ultrasound diagnostic apparatus 100 may obtain a first ultrasound image for a first target nerve and detect a first nerve region corresponding to the first target nerve from the first ultrasound image. The ultrasound diagnostic apparatus 100 may obtain the length of the major axis and the length of the minor axis of the first nerve region. The ultrasound diagnostic apparatus 100 may calculate an aspect ratio representing the ratio of the length of the major axis to the length of the minor axis. When the difference between the baseline aspect ratio and the aspect ratio is within a preset range, the ultrasound diagnostic apparatus 100 may determine that the first target nerve is normal. On the other hand, when the difference between the baseline aspect ratio and the aspect ratio is outside the preset range, the ultrasound diagnostic apparatus 100 may determine that an abnormality exists in the first target nerve. That is, the ultrasound diagnostic apparatus 100 may determine the first nerve region for which the aspect ratio is calculated as an abnormal region. When there are multiple nerve regions corresponding to the first target nerve in the first ultrasound image, the ultrasound diagnostic apparatus 100 may calculate an aspect ratio for each of the multiple nerve regions and detect an abnormal nerve region based on a comparison result between the calculated aspect ratio and a reference aspect ratio.

[0110] Figure 8 is a diagram for describing a process of determining whether a nerve is abnormal based on the size of a cross-sectional area of ​​a nerve region in an ultrasound image according to one embodiment.

[0111] The ultrasound diagnostic equipment 100 can determine whether there is an abnormal area in the first nerve area corresponding to the first target nerve based on a third determination criterion, and the third determination criterion is used to determine whether the target nerve is abnormal using the difference between the size of the cross-sectional area of ​​the reference nerve area for the reference nerve and the size of the cross-sectional area of ​​the target nerve area for the target nerve.

[0112] When a nerve is compressed, the cross-sectional area of ​​the nerve may be smaller than the reference cross-sectional area. Here, the reference cross-sectional area may be a threshold used to determine if the nerve is normal. For example, the reference cross-sectional area for the reference nerve may be set by the user or obtained from an external device.

[0113] Reference Figure 8, the ultrasound diagnostic apparatus 100 may acquire a first ultrasound image of the first target nerve, and detect a first nerve region 811 corresponding to the first target nerve from the first ultrasound image. The ultrasound diagnostic apparatus 100 may calculate the size of the cross-sectional area of ​​the first nerve region 811. When the size of the cross-sectional area of ​​the first nerve region 811 is equal to or greater than the size of the reference cross-sectional area, the ultrasound diagnostic apparatus 100 may determine that the first target nerve is normal. On the other hand, when the size of the cross-sectional area of ​​the first nerve region 811 is smaller than the size of the reference cross-sectional area, the ultrasound diagnostic apparatus 100 may determine that an abnormality exists in the first target nerve. That is, the ultrasound diagnostic apparatus 100 may determine the first nerve region 811, for which the size of the cross-sectional area is calculated, as an abnormal region.

[0114] In addition, when there are multiple nerve regions corresponding to the first target nerve in the first ultrasound image, the ultrasound diagnostic equipment 100 can calculate the size of the cross-sectional area of ​​each nerve region in the multiple nerve regions, and detect the abnormal nerve region based on the comparison result between the calculated cross-sectional area size and the baseline cross-sectional area size.

[0115] Reference Figure 8 The ultrasound diagnostic apparatus 100 may detect a first nerve region corresponding to the first target nerve in the first ultrasound image 820. For example, the cross-sectional area of ​​the first nerve region may be the area of ​​the cross section in a direction perpendicular to the length direction. Figure 8 In image 820, the size of the cross-sectional area of ​​the first nerve region decreases from the length direction of the right side to the length direction of the left side. The length of the diameter of the cross section may increase in the order of the first diameter 821, the second diameter 822, and the third diameter 823. The ultrasonic diagnostic apparatus 100 may calculate a first cross-sectional area corresponding to the first diameter 821, a second cross-sectional area corresponding to the second diameter 822, and a third cross-sectional area corresponding to the third diameter 823. Among the first to third cross-sectional areas, the size of the first cross-sectional area may be smaller than the size of the reference cross-sectional area. The ultrasonic diagnostic apparatus 100 may determine that there is an abnormality in the first target nerve. The ultrasonic diagnostic apparatus 100 may determine that a region in the first nerve region whose size is equal to the size of the first cross-sectional area is an abnormal region.

[0116] Figure 9a is a diagram schematically illustrating an artificial neural network for determining whether a nerve in an ultrasound image is abnormal according to one embodiment.

[0117] A learning model may be generated based on the structure of an artificial neural network, the learning model being used to obtain the similarity between the reference cellular structure and the target cellular structure and to use the similarity to determine whether the target nerve is abnormal.

[0118] Reference Figure 9aThe artificial neural network may include an input layer 911, one or more hidden layers 912 and 913, and an output layer 914. Operations performed by the artificial neural network may be performed by a processor in a server or a processor in the ultrasonic diagnostic apparatus 100. Here, the server may be a server that manages software, programs, data, files, etc. used in the ultrasonic diagnostic apparatus 100. The processor in the server may store and manage a program including a learning model for determining whether a target nerve is abnormal. The server may transmit the program including the learning model to the ultrasonic diagnostic apparatus 100.

[0119] In addition, the weights between each layer and the nodes can be trained by learning and training performed in the hidden layers 912 and 913. For example, the processor of the server or the processor of the ultrasonic diagnostic apparatus 100 can obtain the values ​​of the weights between the nodes and the hidden layers 912 and 913, and the hidden layers 912 and 913 are configured to determine the shape or pattern of the honeycomb structure observed in the nerve region or the structure of the peripheral region of the honeycomb structure through repeated learning. The processor of the server or the processor of the ultrasonic diagnostic apparatus 100 can determine whether the nerve is abnormal based on the nerve region included in the ultrasound image, and use the artificial neural network trained by applying the obtained weight values ​​to generate a learning model for detecting abnormal regions.

[0120] Figure 9b is a diagram for describing a method of generating a learning model for determining whether a nerve in an ultrasound image is abnormal and an operation of the learning model according to one embodiment.

[0121] The server or the ultrasound diagnostic apparatus 100 may determine whether the first target nerve observed in the first ultrasound image is abnormal and detect an abnormal area using the learning model 900 for determining whether the target nerve is abnormal.

[0122] At operation 901 of learning the model 900, the server or the ultrasound diagnostic apparatus 100 may acquire a plurality of ultrasound images including a nerve region. Here, the plurality of ultrasound images may include ultrasound images for normal nerves and ultrasound images for abnormal nerves.

[0123] For example, the server or the ultrasound diagnostic apparatus 100 may acquire, as input data, a plurality of ultrasound images and information on whether nerves included in the plurality of ultrasound images are abnormal.

[0124] In addition, the server or ultrasonic diagnostic equipment 100 can obtain the following data as input data: at least one data about the shape and pattern of the honeycomb structure observed in normal nerves and the structure of the peripheral area of ​​the honeycomb structure, and at least one data about the shape and pattern of the honeycomb structure observed in abnormal nerves and the structure of the peripheral area of ​​the honeycomb structure.

[0125] In operation 902 of learning the model 900, the server or ultrasound diagnostic apparatus 100 may learn a reference cellular structure based on at least one of the shape and pattern of the cellular structure in the nerve region included in the plurality of ultrasound images and the structure of the peripheral region of the cellular structure. Furthermore, the server or ultrasound diagnostic apparatus 100 may learn the learning model 900 for determining whether the target nerve is abnormal based on the result of learning the reference cellular structure.

[0126] For example, the server or ultrasound diagnostic equipment 100 may learn the correlation between at least two of the shape and pattern of the honeycomb structure and the structure of the peripheral area of ​​the honeycomb structure based on at least one piece of data about the shape and pattern of the honeycomb structure observed in a normal nerve and the structure of the peripheral area of ​​the honeycomb structure, thereby learning a baseline honeycomb structure and generating a learning model 900 for calculating the similarity between the baseline honeycomb structure and the target honeycomb structure.

[0127] Furthermore, the server or ultrasonic diagnostic apparatus 100 may learn a correlation between at least two of the shape and pattern of the honeycomb structure and the structure of the peripheral region based on at least one piece of data regarding the shape and pattern of the honeycomb structure observed in the abnormal nerve and the structure of the peripheral region of the honeycomb structure. The server or ultrasonic diagnostic apparatus 100 may accurately learn the reference honeycomb structure and improve the accuracy of the learning model 900 for calculating the similarity between the reference honeycomb structure and the target honeycomb structure by learning the learning results of the honeycomb structure observed in the normal nerve and the learning results of the honeycomb structure observed in the abnormal nerve.

[0128] The server or ultrasonic diagnostic device 100 may learn a learning model 900 for determining whether a target nerve is abnormal based on a comparison result between the similarity between the reference cellular structure and the target cellular structure and a preset similarity. Here, the preset similarity may be a threshold similarity that serves as a benchmark for determining that the target cellular structure is a normal cellular structure. As a specific example, the server or ultrasonic diagnostic device 100 may learn and generate a learning model 900 for determining that the target nerve is normal when the similarity between the reference cellular structure and the target cellular structure is greater than or equal to the preset similarity, and for determining that an abnormality exists in the target nerve when the similarity between the reference cellular structure and the target cellular structure is less than the preset similarity.

[0129] In operation 903 of the learning model 900, the server or the ultrasound diagnostic apparatus 100 may acquire a first ultrasound image 921 of a first target nerve as input data of the learning model 900 and determine whether the first target nerve is abnormal. Here, the first ultrasound image 921 of the first target nerve is an ultrasound image including a first nerve region corresponding to the first target nerve.

[0130] Specifically, the server or ultrasonic diagnostic apparatus 100 may detect a first nerve region corresponding to a first target nerve from the first ultrasonic image 921, and apply the first target cellular structure observed in the first nerve region to the learning model 900 to calculate a similarity between the reference cellular structure and the first target cellular structure. The server or ultrasonic diagnostic apparatus 100 may determine whether the first target nerve is abnormal based on a comparison result between the calculated similarity and a preset similarity.

[0131] For example, when the calculated similarity is greater than or equal to a preset similarity, the server or ultrasound diagnostic apparatus 100 may determine that the first target nerve is normal. On the other hand, when the calculated similarity is less than the preset similarity, the server or ultrasound diagnostic apparatus 100 may determine that an abnormality exists in the first target nerve and detect an abnormal region in the first target nerve containing the abnormality. The server or ultrasound diagnostic apparatus 100 may output a result of determining whether the first target nerve is abnormal using the learning model 900.

[0132] For example, referring to block 922 , when it is determined that the first target nerve is normal, the server or the ultrasound diagnostic apparatus 100 may display information indicating that the first target nerve is normal.

[0133] For another example, referring to box 923, when the first target nerve is determined to be abnormal, the server or ultrasound diagnostic apparatus 100 may display one of information about the abnormal area in the first nerve area corresponding to the first target nerve and basis information about the basis for determining the abnormal area.

[0134] In addition, when determining whether the first target nerve is abnormal with respect to the first ultrasound image 921 in the server, the server may transmit information on the result of determining whether the first target nerve is abnormal to the ultrasound diagnostic apparatus 100 .

[0135] Figure 9c is a diagram for describing a honeycomb structure observed in a normal nerve and a honeycomb structure observed in an abnormal nerve according to one embodiment.

[0136] Figure 9c Images 930, 940, and 950 represent honeycomb structures observed in normal nerves. As shown in images 930, 940, and 950, in the honeycomb structures observed in normal nerves, the shapes of one or more unit cells constituting the honeycomb structure may be constant, and the pattern of brightness values ​​of the unit cells may be constant. Furthermore, the honeycomb structures observed in normal nerves can be classified into the honeycomb structure in image 930, the honeycomb structure in image 940, and the honeycomb structure in image 950, depending on the type or location of the nerve. In this case, the structure of the peripheral region of the honeycomb structure may also differ depending on the honeycomb structure.

[0137] in addition, Figure 9c Images 960, 970, and 980 show honeycomb structures observed in abnormal nerves. As shown in images 960, 970, and 980, in the honeycomb structures observed in abnormal nerves, the shapes of one or more unit cells constituting the honeycomb structure may not be constant, and there may not be a pattern in the brightness values ​​of the unit cells.

[0138] Figure 10 is a diagram for describing a process of determining whether a nerve is abnormal based on corner information in an ultrasound image according to one embodiment.

[0139] The ultrasound diagnostic apparatus 100 may acquire the similarity based on at least one of corner information of each of the reference cellular structure in the reference nerve region for the reference nerve and the first target cellular structure in the first nerve region for the first target nerve.

[0140] As a specific example, the ultrasonic diagnostic apparatus 100 may detect corners of a reference unit cell, which may be designated as a reference cell structure, based on the reference cell structure. The ultrasonic diagnostic apparatus 100 may obtain reference corner information, which includes at least one piece of information regarding the number of corner regions corresponding to the reference unit cell, a maximum brightness value, a minimum brightness value, and an average brightness value.

[0141] In addition, refer to Figure 10 The ultrasonic diagnostic apparatus 100 may detect corners of unit cells 1011, 1012, 1013, 1014, 1015, 1016, 1017, 1018, 1019, 1020, and 1021 corresponding to the corners of the reference unit cell in the first target cellular structure in the first nerve region 1010. The ultrasonic diagnostic apparatus 100 may acquire corner information including at least one piece of information regarding the number of corner regions corresponding to the unit cells 1011, 1012, 1013, 1014, 1015, 1016, 1017, 1018, 1019, 1020, and 1021, a maximum brightness value, a minimum brightness value, and an average brightness value.

[0142] The ultrasound diagnostic apparatus 100 may compare the value of at least one parameter based on the baseline corner information and the corner information of the first nerve region 1010, and obtain a similarity based on the comparison result. When the similarity is greater than or equal to a preset similarity, the ultrasound diagnostic apparatus 100 may determine that the first target nerve is normal. On the other hand, when the similarity is less than the preset similarity, the ultrasound diagnostic apparatus 100 may determine that an abnormality exists in the first target nerve. In this case, the ultrasound diagnostic apparatus 100 may detect that the first nerve region 1010 corresponding to the first target nerve is an abnormal region and display the first nerve region 1010.

[0143] Figure 11a is an exemplary diagram showing at least one of information about an abnormal region in a nerve and information about a basis for determining the abnormal region in the ultrasound diagnostic apparatus 100 according to one embodiment.

[0144] The ultrasound diagnostic apparatus 100 may display 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 exists in the first nerve region corresponding to the first target nerve.

[0145] Reference Figure 11a , the ultrasound diagnostic apparatus 100 may determine whether an abnormality exists in the first target nerve scanned in the first ultrasound image 1101, and detect an abnormal region 1102 in the first nerve region corresponding to the first target nerve. The ultrasound diagnostic apparatus 100 may display the abnormal region 1102 in the first nerve region corresponding to the first target nerve on the first ultrasound image 1101. For example, the abnormal region 1102 may be indicated by a solid line or a dotted line and may be displayed by applying a predetermined color. In addition, the ultrasound diagnostic apparatus 100 may also display a normal region in the first nerve region and may display the normal region and the abnormal region 1102 by applying different colors.

[0146] Furthermore, the ultrasound diagnostic apparatus 100 may acquire at least one parameter for determining the presence of an abnormality in the first target nerve. For example, the parameter may include at least one of the validity of the honeycomb structure observed in the nerve region, the similarity of the honeycomb structure, the shape of the nerve region, the aspect ratio of the nerve region, and the size of the cross-sectional area of ​​the nerve region, although the present invention is not limited to the above examples. The ultrasound diagnostic apparatus 100 may acquire information obtained by comparing the value of the at least one parameter with a reference value of the at least one parameter.

[0147] For example, the ultrasound diagnostic apparatus 100 may display at least one of information about a value of at least one parameter, information about a reference value of at least one parameter, and information obtained by comparing the value of at least one parameter with the reference value of at least one parameter.

[0148] For example, refer to Figure 11a The ultrasound diagnostic apparatus 100 may display basis information 1103 regarding the basis for determining the presence of the abnormal region 1102 in the first nerve region based on the similarity of the honeycomb structure, the shape of the nerve region, and the aspect ratio of the nerve region. Specifically, the ultrasound diagnostic apparatus 100 may display basis information 1103 such as "honeycomb structure unclear," "irregular shape, non-elliptical shape," and "aspect ratio lower than a reference value."

[0149] Figure 11b1 is an exemplary diagram showing basis information according to the priority of bases for determining an abnormal region in the ultrasonic diagnostic apparatus 100 according to one embodiment.

[0150] like Figure 11b As shown, the ultrasound diagnostic apparatus 100 may determine whether there is an abnormality in the first target nerve scanned from the first ultrasound image 1111, and detect an abnormal region 1112 in the first nerve region corresponding to the first target nerve. The ultrasound diagnostic apparatus 100 may display the abnormal region 1112 in the first nerve region corresponding to the first target nerve on the first ultrasound image 1111.

[0151] The ultrasound diagnostic apparatus 100 may display basis information 1113 regarding the basis for determining the presence of an abnormal region 1112 in the first nerve region. In this case, the basis for determination may be displayed according to a preset priority. A number, letter, or symbol may be assigned to each basis according to the priority. For example, the preset priority may be determined based on the extent to which the value of a parameter serving as a reference for determining whether the first target nerve is abnormal exceeds a preset range.

[0152] For example, when the similarity between the target cellular structure and the reference cellular structure is less than 70%, it can be determined that there is an abnormality in the target nerve where the target cellular structure is observed. Figure 11b As shown, the calculated similarity between the first target cellular structure and the reference cellular structure is 40%. Therefore, the ultrasonic diagnostic apparatus 100 can determine that an abnormality exists in the first target nerve where the first target cellular structure is observed. Furthermore, when the degree of similarity between the first target cellular structure and the reference cellular structure deviates from a preset similarity by a greater degree than the degree to which the values ​​of different parameters deviate from a preset range, the similarity between the first target cellular structure and the reference cellular structure can be the primary basis for determining the presence of an abnormality in the first target nerve, and can be set to the first priority.

[0153] In addition, even when the value of the predetermined parameter is within the normal range, the ultrasonic diagnostic apparatus 100 may display information about the predetermined parameter in the basis information. Figure 11b As shown, the ultrasound diagnostic apparatus 100 may display a phrase indicating information related to the size of the cross-sectional area, such as, “the size of the cross-sectional area is within a normal range”, in the basis information 1113 .

[0154] In addition, the ultrasound diagnostic apparatus 100 may display information obtained by comparing a value of at least one parameter with a reference value of the at least one parameter having a specific value.

[0155] Figure 11c 1 is an exemplary diagram showing trend information of abnormal regions in the ultrasonic diagnostic apparatus 100 according to one embodiment.

[0156] The ultrasound diagnostic apparatus 100 may display the abnormal region 1122 on the first ultrasound image 1121 , and may display basis information 1123 regarding a basis for determining the abnormal region 1122 .

[0157] The ultrasound diagnostic apparatus 100 may display trend information of the abnormal region with respect to the first target nerve by referring to the previous ultrasound image 1111 that has been acquired before the first ultrasound image 1121 is acquired.

[0158] For example, the ultrasound diagnostic apparatus 100 may display basis information 1123 regarding a basis for determining the abnormal region 1122 in the first ultrasound image 1121 and basis information 1113 regarding a basis for determining the abnormal region 1112 in the previous ultrasound image 1111 .

[0159] Figure 12 is a block diagram showing the configuration of an ultrasonic diagnostic apparatus according to one embodiment.

[0160] like Figure 12 As shown, the ultrasonic diagnostic apparatus 100 may include a probe 1210, a user interface device 1220, a display 1230, a memory 1250, and a processor 1240. However, not all components shown in the drawings are essential. The ultrasonic diagnostic apparatus 100 may be implemented with more or fewer components than those shown in the drawings. The above components will be described below. Figure 12 The ultrasonic diagnostic apparatus 100 shown can be used with reference to Figure 1 and Figures 2a-2c The same as the ultrasonic diagnostic apparatus 100 described above. Figure 12 The ultrasonic diagnostic apparatus 100 may perform a reference Figures 3 to 11c A method for operating the ultrasonic diagnostic apparatus 100 is described.

[0161] The probe 1210 may include a plurality of transducer elements for performing conversion between ultrasonic signals and electrical signals. That is, the probe 1210 may include a transducer array composed of a plurality of transducer elements, and the plurality of transducer elements may be arranged in one dimension or two dimensions. Each of the plurality of transducer elements may generate an ultrasonic signal individually, or the plurality of transducer elements may generate ultrasonic signals simultaneously. The ultrasonic signal emitted from each of the plurality of transducer elements is reflected by an impedance discontinuity surface in the object. Each of the plurality of transducer elements may convert the reflected ultrasonic signal into an electrical receive signal.

[0162] The user interface device 1220 refers to a device for receiving data or signals from a user for controlling the ultrasound diagnostic apparatus 100. The processor 1240 may control the display 1230 to generate and output a user interface screen for predetermined commands or data received from the user.

[0163] The display 1230 displays a predetermined screen. Specifically, the display 1230 displays a predetermined screen according to the control of the processor 1240. The display 1230 includes a display panel and can display an ultrasound image, etc. on the display panel.

[0164] In addition, the ultrasound diagnostic apparatus 100 may further include a memory 1250. The memory 1250 may store a program for executing the method for operating the ultrasound diagnostic apparatus 100. In addition, the memory 1250 may store a code representing the method for operating the ultrasound diagnostic apparatus 100.

[0165] Processor 1240 may acquire a first ultrasound image of the subject. For example, probe 1210 in the ultrasound diagnostic apparatus may transmit an ultrasound signal toward a region of the subject including a first target nerve, and may receive an ultrasound signal reflected from the region including the first target nerve. Processor 1240 may acquire a first ultrasound image of the first target nerve based on the reflected ultrasound signal. The first ultrasound image may be acquired in real time.

[0166] The processor 1240 may detect a first nerve region corresponding to the first target nerve in the first ultrasound image.

[0167] For example, the processor 1240 may detect a first nerve region corresponding to the first target nerve in the first ultrasound image based on a predetermined automatic detection algorithm or a predetermined automatic segmentation algorithm, and may display the detected first nerve region on the first ultrasound image through the display 1230 .

[0168] The processor 1240 may determine whether there is an abnormal region in the first nerve region of the first ultrasound image based on a determination criterion for determining whether the target nerve is abnormal.

[0169] For example, the determination criteria may be acquired based on at least one of the anatomical structure, shape, and size of the reference nerve region for the reference nerve. Here, the anatomical structure may be determined based on the shape, size, and relative positional relationship of the structures constituting the nerve.

[0170] For example, the processor 1240 may determine whether an abnormality exists in the first target nerve based on the cellular structure that is the anatomical structure observed in the first target nerve region. Specifically, the processor 1240 may determine whether an abnormal region exists in the first nerve region corresponding to the first target nerve based on the similarity between the reference cellular structure in the reference nerve region for the reference nerve and the target cellular structure in the target nerve region for the target nerve.

[0171] For example, the processor 1240 may acquire a learning model for determining whether the target nerve is abnormal using the similarity between the reference cellular structure and the target cellular structure, and may apply the learning model to the first nerve region to detect an area in the first nerve region having an abnormal cellular structure.

[0172] Here, the learning model may be a model for learning a reference cellular structure based on at least one of the shape and pattern of the cellular structure included in a plurality of ultrasound images and the structure of the peripheral region of the cellular structure. Furthermore, the learning model may be a model for determining whether a predetermined target nerve is abnormal when acquiring an ultrasound image including a target cellular structure in the predetermined target nerve.

[0173] For example, processor 1240 may obtain similarity based on a matching ratio between a reference cellular structure in a reference nerve region of a reference template for a reference nerve and a first target cellular structure in a first nerve region. Processor 1240 may determine whether an abnormal region exists in the first nerve region corresponding to the first target nerve based on the obtained similarity.

[0174] For example, processor 1240 may obtain similarity based on at least one of the following information: corner information and feature point information about each of the reference cellular structure in the reference nerve region for the reference nerve and the first target cellular structure in the first nerve region. Processor 1240 may determine whether there is an abnormal region in the first nerve region corresponding to the first target nerve based on the obtained similarity.

[0175] For example, processor 1240 may determine whether there is an abnormal area in the first nerve area corresponding to the first target nerve based on a second determination criterion, wherein the second determination criterion is used to determine whether the target nerve is abnormal using the difference between the baseline aspect ratio of the baseline nerve area for the baseline nerve and the aspect ratio of the target nerve area for the target nerve.

[0176] For example, processor 1240 may determine whether there is an abnormal area in the first nerve area corresponding to the first target nerve based on a third determination criterion, which is used to determine whether the target nerve is abnormal using the difference between the size of the baseline cross-sectional area of ​​the baseline nerve area for the baseline nerve and the size of the cross-sectional area of ​​the target nerve area for the target nerve.

[0177] For example, processor 1240 may obtain a reference value for at least one parameter that serves as a benchmark for determining whether a target nerve is abnormal. For example, the parameter may include at least one of the validity of a honeycomb structure observed in the nerve region, the similarity of the honeycomb structure, the shape of the nerve region, the aspect ratio of the nerve region, and the size of the cross-sectional area of ​​the nerve region, although the present invention is not limited to the above examples. When the difference between the value of at least one parameter obtained from the first ultrasound image and the reference value of at least one parameter is outside a preset range, processor 1240 may determine that an abnormal region exists in the first nerve region.

[0178] The processor 1240 may display at least one of information about the abnormal region and basis information about a basis for the abnormal region through the display 1230 based on the result of determining whether the abnormal region exists in the first nerve region.

[0179] For example, the basis information about the basis for determining the abnormal area may include the following information: information about at least one parameter that serves as a benchmark for determining whether the first target nerve is abnormal, and information obtained by comparing the value of at least one parameter with a benchmark value of at least one parameter.

[0180] For example, the display 1230 may display the boundary of the abnormal region on the first ultrasound image. The processor 1240 may display, via the display 1230, the basis for determining whether an abnormal region exists in the first nerve region according to a preset priority. For example, the preset priority may be determined based on the extent to which the value of a parameter serving as a basis for determining whether the first target nerve is abnormal exceeds a preset range.

[0181] For example, the display 1230 may display information about the abnormal region on the first ultrasound image. The processor 1240 may display trend information of the abnormal region of the subject through the display 1230 by referring to a previous ultrasound image of the subject.

[0182] The ultrasonic diagnostic apparatus 100 described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers (such as processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable arrays (FPAs), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions).

[0183] The processing device may execute an operating system (OS) and one or more software applications executed on the OS. In addition, the processing device may access, store, operate, process, and generate data in response to the execution of the software.

[0184] For ease of understanding, the processing device may be described as being used alone, but one skilled in the art will appreciate that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, the processing device may include multiple processors or a processor and a controller. In addition, different processing configurations (such as parallel processors) are also possible.

[0185] Software may include computer programs, codes, instructions, or a combination of one or more thereof, and may configure a processing device to operate as desired, or may independently or collectively instruct a processing device.

[0186] Software and / or data may be embodied permanently or temporarily in any type of machine, component, physical device, virtual device, computer storage medium or device, or in a transmitted signal wave for the purpose of being interpreted by a processing device or providing commands or data to a processing device. Software may be distributed across networked computer systems to be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0187] The method according to the embodiment can be implemented in the form of program commands that can be executed by various computer devices, and the program commands can be recorded on a computer-readable recording medium. The computer-readable recording medium may include a single one or a combination of program commands, data files, and data structures. The program commands recorded on the computer-readable recording medium may be program commands specifically designed and configured for the embodiment, or may be program commands known and available to those skilled in the art.

[0188] Examples of computer-readable recording media may include magnetic recording media (such as hard disks, floppy disks, and magnetic tapes), optical recording media (such as compact disk read-only memories (CD-ROMs) and digital versatile disks (DCDs)), magneto-optical recording media (such as floppy disks), and hardware devices specially configured to store and execute program commands (such as ROM, random access memory (RAM), and flash memory).

[0189] Examples of the program commands may include machine language codes that can be generated by a compiler and high-level language codes that can be executed by a computer using an interpreter.

[0190] The hardware devices may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

[0191] Although the embodiments have been described with reference to the accompanying drawings, those skilled in the art may make various changes and modifications to the embodiments without departing from the spirit and scope of the present invention. For example, the described techniques may be performed in a different order than described, and / or the components of the described systems, structures, devices, and circuits may be combined or combined in a different manner than described, or may be replaced or substituted with other components or their equivalents.

[0192] Accordingly, other implementations, other embodiments, and equivalents of the appended claims are within the scope of the appended claims.

Claims

1. A method for operating an ultrasonic diagnostic device, the method comprising: acquiring a plurality of ultrasound images; learning a reference cellular structure within a reference neural region based on the cellular structure within the neural region included in the plurality of ultrasound images; generating a learning model that calculates the similarity between the learned baseline cellular structure and the target cellular structure; acquiring a first ultrasound image of the object; detecting a first nerve region corresponding to a first target nerve in the first ultrasound image; determining whether an abnormal area exists in the first nerve area of ​​the first ultrasound image based on a determination criterion for determining whether the target nerve is abnormal; as well as displaying, based on a result of determining whether an abnormal region exists in the first nerve region, at least one of information about the abnormal region and basis information about a basis for determining the abnormal region; The step of determining whether the abnormal region exists in the first nerve region of the first ultrasound image is performed using a similarity between the reference cellular structure and the target cellular structure in the target nerve region for the first target nerve.

2. The method according to claim 1, wherein The step of determining whether there is an abnormal area in the first neural area comprises: A region in the first neural region where abnormal honeycomb structure exists is detected by applying the first neural region to the learned model.

3. The method according to claim 2, wherein: The learning model is a model that learns the baseline honeycomb structure based on the shape and pattern of the honeycomb structure and at least one of the structures of the peripheral area of ​​the honeycomb structure in the multiple ultrasound images, and a model for determining whether the predetermined target nerve is abnormal when acquiring an ultrasound image including the target honeycomb structure in the predetermined target nerve.

4. The method according to claim 1, wherein The step of determining whether an abnormal area exists in the first neural region comprises one of the following: obtaining the similarity based on a matching rate between the reference cellular structure in the reference nerve region of the reference template for the reference nerve and a first target cellular structure in the first nerve region; as well as The similarity is acquired based on at least one of corner information and feature point information of each of the reference cell structure in the reference nerve region and the first target cell structure in the first nerve region for the reference nerve.

5. The method according to claim 1, wherein The step of determining whether there is an abnormal area in the first neural area comprises: acquiring a reference value of at least one parameter that serves as a reference for determining whether the target nerve is abnormal; and When a difference between the value of the at least one parameter acquired from the first ultrasound image and a reference value of the at least one parameter is outside a preset range, it is determined that an abnormal region exists in the first nerve region.

6. The method according to claim 1, wherein The basis information regarding the basis for determining the abnormal area includes information regarding at least one parameter that serves as a benchmark for determining whether the first target nerve is abnormal, and information obtained by comparing a value of the at least one parameter with a benchmark value of the at least one parameter.

7. The method according to claim 1, wherein The step of displaying at least one of information about the abnormal region and basis information about a basis for determining the abnormal region comprises at least one of the following: displaying a boundary of the abnormal area on the first ultrasound image; and The basis for determining whether there is an abnormal area in the first neural area is displayed according to the preset priority.

8. The method according to claim 7, wherein: The preset priority is determined based on the extent to which a value of a parameter serving as a reference for determining whether the first target nerve is abnormal exceeds a preset range.

9. The method according to claim 1, wherein The step of displaying at least one of information about the abnormal area and basis information about a basis for determining the abnormal area includes: displaying information about the abnormal area on the first ultrasound image; and Trend information of the abnormal region of the object is displayed by referring to previous ultrasound images of the object.

10. An ultrasonic diagnostic device comprising: a probe configured to transmit an ultrasonic signal toward an object and receive an ultrasonic signal reflected from the object; user interface device; monitor; processor; as well as a memory configured to store instructions executable by the processor, The processor is configured to execute the instructions to perform the following operations: acquiring a plurality of ultrasound images; learning a reference cellular structure within a reference neural region based on the cellular structure within the neural region included in the plurality of ultrasound images; generating a learning model that calculates the similarity between the learned baseline cellular structure and the target cellular structure; acquiring a first ultrasound image of the object based on the reflected ultrasound signal; detecting a first nerve region corresponding to a first target nerve in the first ultrasound image; determining whether an abnormal area exists in the first nerve area of ​​the first ultrasound image based on a determination criterion for determining whether a target nerve is abnormal; and displaying, on the display, 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 exists in the first nerve region; The processor is configured to execute commands to determine whether the abnormal area exists in the first nerve area of ​​the first ultrasound image using a similarity between the reference cellular structure and the target cellular structure in the target nerve area for the first target nerve.

11. A computer-readable recording medium having stored therein program commands for executing a method for operating an ultrasonic diagnostic apparatus, in, The method comprises: acquiring a plurality of ultrasound images; learning a reference cellular structure within a reference neural region based on the cellular structure within the neural region included in the plurality of ultrasound images; generating a learning model that calculates the similarity between the learned baseline cellular structure and the target cellular structure; acquiring a first ultrasound image of the object; detecting a first nerve region corresponding to a first target nerve in the first ultrasound image; determining whether an abnormal area exists in the first nerve area of ​​the first ultrasound image based on a determination criterion 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 exists in the first nerve region, The step of determining whether the abnormal region exists in the first nerve region of the first ultrasound image is performed using a similarity between the reference cellular structure and the target cellular structure in the target nerve region for the first target nerve.

Images