CN111466948B - Ultrasonic scanning method and ultrasonic scanning device - Google Patents

Abstract

The embodiment of the invention provides an ultrasonic scanning method and an ultrasonic scanning device. The method comprises the following steps: performing an ultrasonic scanning operation on a human body via an ultrasonic scanner to obtain an ultrasonic image; analyzing, via an image recognition module, the ultrasound image to identify an organ pattern in the ultrasound image; and automatically generating guide information according to the recognition result of the organ pattern, wherein the guide information is used for guiding the movement of the ultrasonic scanner to scan the target organ of the human body. Therefore, the efficiency of the traditional manual ultrasonic scanning can be improved.

Description

Ultrasonic scanning method and ultrasonic scanning device

technical field

The invention relates to an ultrasonic scanning technology, in particular to an ultrasonic scanning method and an ultrasonic scanning device.

Background technique

The ultrasound scanning device can scan images of organs in the human body based on ultrasound to evaluate the state of the organs based on the images of the organs. However, traditionally, the ultrasonic scanning device needs to be operated by professionals, and the ultrasonic images obtained through ultrasonic scanning also need to be identified by professionals. It is not easy for an untrained person to identify a specific organ from an ultrasound image. However, in practice, professionals such as doctors or examiners may misinterpret organ patterns due to various conditions (such as lack of professionalism or fatigue) when operating ultrasound scanning devices, resulting in inefficiency in inspections and even lead to inspection failures. The result is inaccurate.

Contents of the invention

The present invention provides an ultrasonic scanning method and an ultrasonic scanning device, which can automatically analyze ultrasonic images and provide guidance information for auxiliary scanning according to the analysis results, thereby improving the above problems.

An embodiment of the present invention provides an ultrasonic scanning method, which is used in an ultrasonic scanning device. The ultrasonic scanning method includes: performing an ultrasonic scanning operation on a human body via an ultrasonic scanner to obtain an ultrasonic image; analyzing the ultrasonic image via an image recognition module to identify an organ pattern in the ultrasonic image; and identifying an organ pattern according to the organ pattern As a result, guide information is automatically generated, wherein the guide information is used to guide the movement of the ultrasonic scanner to scan the target organ of the human body.

An embodiment of the invention further provides an ultrasonic scanning device, which includes an ultrasonic scanner and a processor. The ultrasonic scanner is used to perform ultrasonic scanning operation on the human body to obtain ultrasonic images. The processor is coupled to the ultrasound scanner and configured to analyze the ultrasound image via an image recognition module to identify organ patterns in the ultrasound image. The processor is also used to automatically generate guide information according to the recognition result of the organ pattern, and the guide information is used to guide the movement of the ultrasonic scanner to scan the target organ of the human body.

Based on the above, after the ultrasonic scanning operation is performed on the human body via the ultrasonic scanner to obtain the ultrasonic image, the image recognition module can analyze the ultrasonic image to identify organ patterns in the ultrasonic image. Then, guidance information may be automatically generated according to the recognition result of the organ pattern. In particular, this guidance information can guide the movement of the ultrasonic scanner to scan the target organ of the human body, thereby reducing the burden on professionals to perform ultrasonic scanning and/or people without professional training can also easily operate the ultrasonic scanning device Complete an easy scan.

In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail with reference to the accompanying drawings.

Description of drawings

FIG. 1 is a schematic diagram of an ultrasonic scanning device according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of an ultrasonic scanning operation shown according to an embodiment of the present invention;

Fig. 3 is a schematic diagram of an ultrasonic image and corresponding coordinate information shown according to an embodiment of the present invention;

FIG. 4 and FIG. 5 are schematic diagrams showing guidance information generated according to numerical relationships between areas of predicted frames according to an embodiment of the present invention;

FIG. 6 is a flowchart of an ultrasonic scanning method according to an embodiment of the present invention;

7 and 8 are flowcharts of an ultrasonic scanning method according to an embodiment of the present invention.

Explanation of reference signs

10: Ultrasonic scanning device

101: Ultrasonic Scanner

102: storage device

103: Image recognition module

104: Processor

105: input/output interface

21: Human body

201: Organs

31: Coordinate table

41, 42, 51, 52: Ultrasound images

410, 420, 510, 520: prediction box

401, 501: Guidance information

S601～S603, S701～S704, S801～S808: steps

Detailed ways

FIG. 1 is a schematic diagram of an ultrasonic scanning device according to an embodiment of the present invention. Referring to FIG. 1 , the ultrasonic scanning device 10 includes an ultrasonic scanner 101 , a storage device 102 , an image recognition module 103 , a processor 104 and an input/output interface 105 . The ultrasonic scanner 101 is used for performing an ultrasonic scanning operation on a human body to obtain ultrasonic images. For example, ultrasound scanner 101 may include a hand-held probe. The ultrasonic scanner 101 can emit ultrasonic waves and receive ultrasonic waves reflected by human organs. Based on the reflected ultrasound waves, ultrasound images can be obtained. In the following embodiments, a two-dimensional ultrasonic image is used as an example for illustration. However, in another embodiment, the ultrasonic image may also include a three-dimensional ultrasonic image, which is not limited in the present invention.

The storage device 102 is used for storing data. For example, the storage device 102 may include volatile storage media and non-volatile storage media. Volatile storage media may include random access memory (random access memory, RAM). The non-volatile memory module may include a flash (flash) memory module, a read only memory (ROM), a solid state drive (SSD) and/or a traditional hard disk (hard disk drive, HDD), etc. In addition, the number of storage devices 102 may be one or more, which is not limited in the present invention.

The image recognition module 103 is configured to perform image recognition on the obtained ultrasonic images. For example, the image recognition module 103 may perform image recognition based on a convolutional neural network (CNN) architecture or other types of image recognition architectures (or algorithms). The image recognition module 103 can be implemented in the form of software or hardware. In one embodiment, the image recognition module 103 includes a software module. For example, the program code of the image recognition module 103 can be stored in the storage device 102 and executed by the processor 104 . In one embodiment, the image recognition module 103 includes hardware circuits. For example, the image recognition module 103 may include a graphics processing unit (GPU) or other programmable general-purpose or special-purpose microprocessors, digital signal processors, programmable controllers, application-specific integrated circuits, programmable Logical devices or other similar devices or combinations of these devices. In addition, the number of image recognition modules 103 may be one or more, which is not limited in the present invention.

The processor 104 is coupled to the ultrasonic scanner 101 , the storage device 102 and the image recognition module 103 . The processor 104 can be used to control the ultrasonic scanner 101 , the storage device 102 and the image recognition module 103 . For example, the processor 104 may include a central processing unit (CPU), a graphics processing unit, or other programmable general-purpose or special-purpose microprocessors, digital signal processors, programmable controllers, application-specific integrated circuits , programmable logic device or other similar devices or combinations of these devices. In one embodiment, the processor 104 can be used to control the whole or part of the operations of the ultrasonic scanning device 10 . In one embodiment, the image recognition module 103 can be implemented in the processor 104 in the form of software, firmware or hardware. In addition, the number of processors 104 may be one or more, which is not limited in the present invention.

The input/output interface 105 is coupled to the processor 104 . The input/output interface 105 is used for receiving signals and/or outputting signals. For example, the input/output interface 105 may include a screen, a touch screen, a touchpad, a mouse, a keyboard, physical buttons, a speaker, a microphone, a wired communication interface and/or a wireless communication interface, and the type of the input/output interface 105 is not limited to this.

FIG. 2 is a schematic diagram of an ultrasonic scanning operation according to an embodiment of the present invention. Referring to FIG. 1 and FIG. 2 , the operator can hold the ultrasonic scanner 101 and move the ultrasonic scanner 101 on the human body 21 to perform an ultrasonic scanning operation. In addition, a gel can be applied between the ultrasonic scanner 101 and the human body 21 to facilitate the ultrasonic scanning operation. Taking FIG. 2 as an example, the ultrasonic image obtained through the ultrasonic scanning operation may present a pattern of an organ 201 (also referred to as an organ pattern). For example, the organ 201 may include various human organs such as heart, liver and/or uterus, which is not limited in the present invention. The obtained ultrasound images may be stored in the storage device 102 .

The processor 104 may analyze the ultrasound image via the image recognition module 103 to identify organ patterns in the ultrasound image. The processor 104 can automatically generate guidance information according to the recognition result of the organ pattern. This guidance information can be used to guide the movement of the ultrasound scanner 101 to scan a specific organ (also referred to as a target organ) of the human body 21 . For example, the guide information may be output in image form through a screen in the input/output interface 105 and/or in the form of sound through a speaker in the input/output interface 105 . Alternatively, the guidance information may also be output in other forms (such as vibration or buzzer), which is not limited by the present invention. In addition, the target organ may be various human organs such as heart, liver and/or uterus, which is not limited in the present invention. The operator can move the ultrasonic scanner 101 according to the guidance information to continuously scan the target organ and/or continuously expand the pattern area of the target organ in the ultrasonic image during the scanning process.

In one embodiment, the guidance information may include direction information. The operator can move the ultrasonic scanner 101 in a specific direction according to the direction information. In an embodiment, the guide information may include information about whether the current moving direction of the ultrasonic scanner 101 is correct. The operator can decide whether to change the moving direction of the ultrasonic scanner 101 according to the guidance information. In this way, even without professional training in ultrasound scanning and/or analyzing ultrasound images, general users can perform ultrasound scanning of the target organ and/or obtain the complete pattern (or maximum pattern) of the target organ according to the guidance information. ) ultrasound image. In addition, the guidance information can also be used to guide professionals such as doctors or examiners to assist them in completing the ultrasound scan of the target organ.

In one embodiment, the processor 104 may record coordinate information corresponding to a certain ultrasound image. This coordinate information can reflect the position of the ultrasound scanner 101 when the ultrasound image is acquired. For example, a sensor module may be provided in the ultrasonic scanner 101 . For example, the sensor module may include an optical sensor, a gyroscope, and a gravity sensor (such as a G-sensor) to sense the current position, moving direction and/or moving distance of the ultrasonic scanner 101 . The processor 104 can obtain coordinate information corresponding to a certain ultrasonic image according to the information provided by the sensor module.

Fig. 3 is a schematic diagram of an ultrasonic image and corresponding coordinate information according to an embodiment of the present invention. Referring to FIG. 3 , the coordinate table 31 records coordinates (x1, y1)˜(x5, y5) corresponding to a plurality of ultrasonic images numbered 1˜5. Taking the ultrasonic images numbered 1 and 2 as an example, when acquiring the ultrasonic image numbered 1, the position of the ultrasonic scanner 101 is at coordinates (x1, y1); when acquiring the ultrasonic image numbered 2, the position of the ultrasonic scanner 101 The position of 101 is at coordinates (x2, y2), and so on. After performing the image recognition of the organ pattern on a certain ultrasonic image, the processor 104 may generate the guide information according to the recognition result of the organ pattern and the coordinate information corresponding to the ultrasonic image in the coordinate table 31 . In other words, the current location, past location, and/or movement trajectory of the ultrasonic scanner 101 may be considered in the operation of generating the guidance information. It should be noted that the five ultrasound images in the coordinate table 31 are just examples. In another embodiment, more or fewer ultrasound images and corresponding coordinate information may be recorded in the coordinate table 31 . Alternatively, the coordinate table 31 may also record ultrasonic images and corresponding coordinate information in other forms. In addition, more information that can be used to generate the guidance information can also be recorded in the coordinate table 31, depending on practical needs.

In one embodiment, the image recognition module 103 can determine a prediction frame in an ultrasound image. The prediction frame reflects the range of the organ pattern recognized by the image recognition module 103 in the ultrasonic image. Taking an ultrasound image containing a liver pattern as an example, after performing image recognition on the ultrasound image, the image recognition module 103 may determine a prediction frame in the ultrasound image. This prediction box reflects the approximate extent of the liver pattern in this ultrasound image.

In an embodiment, the prediction frame covers the range of the organ pattern of the target organ. For example, assuming that a certain ultrasound image contains multiple organ patterns, the image recognition module 103 can determine the prediction frame according to the organ pattern (also referred to as the target organ pattern) belonging to the target organ among these organ patterns, so that the prediction frame (only ) covers the range of this target organ pattern. From another point of view, after the target organ is determined, the image recognition module 103 can start to track the organ pattern of the target organ, and ignore other organ patterns that do not belong to the target organ. For example, assuming that the determined target organ is the liver, the image recognition module 103 may start to track the liver pattern that may appear in the ultrasound image and ignore the organ patterns of other organs (such as kidney or heart) in the ultrasound image.

In an embodiment, the processor 104 may obtain the area of the predicted frame in a certain ultrasound image. The size of the area may reflect the proportion of the area occupied by the prediction frame in the ultrasonic image. The processor 104 can generate the guide information according to the area. For example, after a plurality of ultrasonic images are obtained continuously, the processor 104 may generate the guide information according to the numerical relationship between the areas of the prediction frames in these ultrasonic images. For example, this numerical relationship may reflect the change in area between such predicted boxes.

FIG. 4 and FIG. 5 are schematic diagrams showing guide information generated according to numerical relationships between areas of prediction frames according to an embodiment of the present invention. Referring to FIG. 4 , it is assumed that after the ultrasonic image 41 is obtained, the ultrasonic image 42 is successively obtained by moving the ultrasonic scanner 101 . The prediction frame 410 in the ultrasound image 41 is determined, and the prediction frame 420 in the ultrasound image 42 is determined. The prediction boxes 410 and 420 may respectively cover at least a part of the organ pattern of the target organ (marked with oblique lines in FIG. 4 ).

The processor 104 can compare the area of the predicted frame 410 with the area of the predicted frame 420 to obtain a numerical relationship between the area of the predicted frame 410 and the area of the predicted frame 420 . In this embodiment, the numerical relationship between the area of the prediction frame 410 and the area of the prediction frame 420 reflects that the area of the prediction frame 410 is smaller than the area of the prediction frame 420 . Therefore, the processor 104 may generate guidance information (also referred to as first guidance information) 401 to remind the operator of the ultrasonic scanner 101 that the current scanning direction is correct and the scanning can continue.

In one embodiment, the area of the prediction frame 410 is smaller than the area of the prediction frame 420 may be regarded as the first numerical relationship between the prediction frames 410 and 420 . The first numerical relationship indicates that as the ultrasound scanner 101 moves, the area of the prediction frame in the ultrasound image gradually increases (equivalent to the gradual increase in the area of the pattern of the target organ in the ultrasound image), as shown in FIG. 4 . Therefore, the guide information 401 can inform the operator to maintain the current moving direction of the ultrasonic scanner 101 to continue scanning without adjusting the moving direction of the ultrasonic scanner 101 . Thereby, the scanning position of the ultrasonic scanner 101 can gradually approach the position of the target organ.

Referring to FIG. 5 , it is assumed that after the ultrasonic image 51 is obtained, the ultrasonic image 52 is successively obtained by moving the ultrasonic scanner 101 . The predicted frame 510 in the ultrasonic image 51 is determined, and the predicted frame 520 in the ultrasonic image 52 is determined. The prediction boxes 510 and 520 may respectively cover at least a portion of the organ pattern of the target organ (marked with oblique lines in FIG. 5 ).

The processor 104 can compare the area of the predicted frame 510 with the area of the predicted frame 520 to obtain a numerical relationship between the area of the predicted frame 510 and the area of the predicted frame 520 . In this embodiment, the numerical relationship between the area of the prediction frame 510 and the area of the prediction frame 520 reflects that the area of the prediction frame 510 is larger than the area of the prediction frame 520 . Therefore, the processor 104 can generate guidance information (also referred to as second guidance information) 501 to remind the operator of the ultrasonic scanner 101 that the current scanning direction is wrong and move the ultrasonic scanner 101 in the opposite direction (or other directions).

In one embodiment, the area 510 of the prediction frame is larger than the area of the prediction frame 520 may be regarded as the second numerical relationship between the prediction frames 510 and 520 . The second numerical relationship indicates that as the ultrasonic scanner 101 moves, the area of the prediction frame in the ultrasonic image gradually decreases (equivalent to the area of the pattern of the target organ in the ultrasonic image gradually decreases), as shown in FIG. 5 . Therefore, the guide information 501 may advise the operator to change the moving direction of the ultrasonic scanner 101 . In this way, the scanning position of the ultrasound scanner 101 can be prevented from being kept away from the position of the target organ. In one embodiment, the guidance information 401 and/or 501 may be generated with reference to the coordinate table 31 of FIG. 3 to obtain the previous moving direction of the ultrasonic scanner 101 and provide a suggested moving direction.

In one embodiment, the processor 104 can continuously record the area of the prediction frame in multiple ultrasound images. According to the comparison result of the areas of multiple predicted frames, the processor 104 can obtain a specific coordinate information (also referred to as target coordinate information). The target coordinate information corresponds to one of the ultrasonic images (also referred to as a target image). The predicted boxes in the target image have the largest coverage relative to the predicted boxes in the rest of the ultrasound images. For example, assuming that the target image is the ultrasonic image numbered 3 in Figure 3, the target coordinate information is (x3, y3), and the area of the predicted frame in the ultrasonic image numbered 3 is larger than that of numbers 1, 2, 4, and 5 The area of the prediction box in any of the ultrasound images.

In an embodiment, the processor 104 may generate guidance information (also referred to as third guidance information) according to the target coordinate information. For example, the processor 104 may generate third guidance information according to the target coordinate information and the current position of the ultrasonic scanner 101 . The third guide information can be used to assist the operator to move the ultrasonic scanner 101 to the scanning position corresponding to the target coordinate information. After the ultrasonic scanner 101 is moved to the scanning position corresponding to the target coordinate information, the ultrasonic image with the largest prediction frame (equivalent to the organ pattern of the largest target organ) (for example, the ultrasonic image 42 or FIG. 5 Ultrasound image 51). In other words, in one embodiment, the third guide information can be used to guide the ultrasound scanner 101 to a scanning position where the maximum organ pattern of the target organ can be obtained.

Fig. 6 is a flowchart of an ultrasonic scanning method according to an embodiment of the present invention. Referring to FIG. 6 , in step S601 , an ultrasonic scanning operation is performed on the human body via an ultrasonic scanner to obtain an ultrasonic image. In step S602, the ultrasound image is analyzed via an image recognition module to identify organ patterns in the ultrasound image. In step S603, guide information is automatically generated according to the recognition result of the organ pattern. The guidance information is used to guide the movement of the ultrasonic scanner to scan the target organ of the human body.

7 and 8 are flowcharts of an ultrasonic scanning method according to an embodiment of the present invention. Referring to FIG. 7 , in step S701 , an ultrasonic scanning operation is performed on the human body via an ultrasonic scanner to obtain an ultrasonic image. In step S702, the ultrasound image is analyzed via an image recognition module to identify organ patterns in the ultrasound image. In step S703, it is determined whether an organ pattern appears in the ultrasonic image. If there is no organ pattern in the ultrasonic image, go back to step S701. If there is an organ pattern in the ultrasonic image, in step S704, it is determined whether to track the organ pattern. For example, in step S704, it may be determined according to user operation whether to track the organ pattern. If it is determined to track the organ pattern, it means that the organ pattern is the organ pattern of the target organ and the method can enter step S801 in FIG. 8 to start tracking. On the contrary, if the organ pattern is not tracked, it means that the operator may not have moved the ultrasonic scanner to the scanning position of the organ pattern covering the target organ, so step S701 can be repeated.

Referring to FIG. 8 , in step S801 , the area of the predicted frame in the ultrasound image and the coordinate information of the ultrasound image are recorded. In step S802, the recorded areas of the plurality of prediction frames are compared. In step S803, it is determined whether the area of the prediction frame in the ultrasonic images gradually increases. If the areas of the predicted frames in the ultrasound images gradually increase, in step S804 , first guidance information indicating to maintain the scanning path (or the correct scanning direction) is generated. Alternatively, if the area of the prediction frame in the ultrasonic images does not gradually increase (for example, gradually decrease), then in step S805 , generate second guidance information indicating to change the scanning path (or to scan in the wrong direction). After steps S804 and S805, step S806 may be executed. In addition, in another embodiment, step S806 may also be executed at any point in time, which is not limited by the present invention.

In step S806, it is judged according to the user operation whether the operator intends to return to the scanning position of the measured largest organ pattern. If no user operation reflecting the desire to return to the scanning position of the measured largest organ pattern is received, return to step S701 in FIG. 7 to continue scanning. In addition, if the received user operation reflects that the operator intends to return to the measured scanning position of the largest organ pattern, in step S807, query the comparison result of the area of the previously recorded prediction frame to obtain the target corresponding to the target image. coordinate information. In step S808, third guidance information is generated according to the target coordinate information and the current coordinate position of the ultrasonic scanner.

However, each step in FIG. 6 to FIG. 8 has been described in detail above, and will not be repeated here. It should be noted that each step in FIG. 6 to FIG. 8 can be implemented as a plurality of program codes or circuits, which is not limited in the present invention. In addition, the methods shown in FIG. 6 to FIG. 8 can be used together with the above embodiments, or can be used alone, which is not limited by the present invention.

To sum up, after the ultrasonic scanning operation is performed on the human body via the ultrasonic scanner to obtain the ultrasonic image, the image recognition module may analyze the ultrasonic image to identify organ patterns in the ultrasonic image. Then, guidance information may be automatically generated according to the recognition result of the organ pattern. In particular, this guidance information can be used to guide the movement of the ultrasound scanner to scan the target organ of the human body, thereby reducing the burden on professionals to perform ultrasound scanning and/or making it easy for untrained personnel to perform ultrasound scanning The device completes a simple scan.

Although the present invention has been disclosed above with the embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the present invention The scope of protection shall prevail as defined by the claims.

Claims (6)

1. An ultrasonic scanning method for an ultrasonic scanning apparatus, comprising:

performing an ultrasonic scanning operation on a human body via an ultrasonic scanner to obtain an ultrasonic image;

analyzing, via an image recognition module, the ultrasound image to identify an organ pattern in the ultrasound image; and

automatically generating guide information according to the recognition result of the organ pattern, wherein the guide information is used to guide the movement of the ultrasonic scanner to scan a target organ of the human body,

wherein the step of automatically generating the guide information according to the recognition result of the organ pattern comprises:

generating the guide information according to an area of a prediction box in the ultrasound image,

wherein the prediction box reflects a range of the organ pattern identified by the image identification module in the ultrasound image,

wherein the ultrasound image includes a first image and a second image, the prediction box includes a first prediction box in the first image and a second prediction box in the second image, and the step of automatically generating the guide information according to the recognition result of the organ pattern includes:

generating the guide information according to a numerical relationship between an area of the first prediction box and an area of the second prediction box,

wherein the numerical relationship comprises a first numerical relationship and a second numerical relationship, wherein the first numerical relationship reflects that the area of the first prediction box is smaller than the area of the second prediction box, and wherein the second numerical relationship reflects that the area of the first prediction box is larger than the area of the second prediction box.

2. The ultrasonic scanning method according to claim 1, wherein the step of automatically generating the guide information according to the recognition result of the organ pattern includes:

generating the guide information according to the recognition result of the organ pattern and coordinate information,

wherein the coordinate information reflects a position of the ultrasound scanner at a time of acquiring the ultrasound image.

3. The ultrasound scanning method of claim 1, wherein the step of generating the guidance information according to the numerical relationship between the area of the first prediction box and the area of the second prediction box comprises:

obtaining target coordinate information according to the numerical relationship, wherein the target coordinate information corresponds to a target image in the ultrasonic image, and when the numerical relationship between the area of the first prediction frame and the area of the second prediction frame is the first numerical relationship, the target image is the second image; and

and generating the guide information according to the target coordinate information.

4. An ultrasonic scanning device comprising:

an ultrasonic scanner for performing an ultrasonic scanning operation on a human body to obtain an ultrasonic image;

a processor coupled to the ultrasound scanner and configured to analyze the ultrasound image via an image recognition module to identify an organ pattern in the ultrasound image,

wherein the processor is further configured to automatically generate guidance information according to a recognition result of the organ pattern, and the guidance information is configured to guide movement of the ultrasonic scanner to scan a target organ of the human body,

wherein the operation of the processor automatically generating the guidance information according to the recognition result of the organ pattern comprises:

generating the guide information according to an area of a prediction box in the ultrasound image,

wherein the prediction box reflects a range of the organ pattern identified by the image identification module in the ultrasound image,

wherein the ultrasound image comprises a first image and a second image, the prediction box comprises a first prediction box in the first image and a second prediction box in the second image, and the operation of the processor automatically generating the guidance information according to the recognition result of the organ pattern comprises:

generating the guide information according to a numerical relationship between an area of the first prediction box and an area of the second prediction box,

wherein the numerical relationship comprises a first numerical relationship and a second numerical relationship, wherein the first numerical relationship reflects that the area of the first prediction box is smaller than the area of the second prediction box, and wherein the second numerical relationship reflects that the area of the first prediction box is larger than the area of the second prediction box.

5. The ultrasound scanning device of claim 4, wherein the operation of the processor automatically generating the guidance information from the recognition of the organ pattern comprises:

generating the guide information according to the recognition result of the organ pattern and coordinate information,

wherein the coordinate information reflects a position of the ultrasound scanner at a time of acquiring the ultrasound image.

6. The ultrasound scanning device of claim 4, wherein the operation of the processor generating the guidance information according to the numerical relationship between the area of the first prediction box and the area of the second prediction box comprises:

obtaining target coordinate information according to the numerical relationship, wherein the target coordinate information corresponds to a target image in the ultrasonic image, and when the numerical relationship between the area of the first prediction frame and the area of the second prediction frame is the first numerical relationship, the target image is the second image; and

and generating the guide information according to the target coordinate information.

Images