Information obtaining method, device, equipment and storage medium

Abstract

The present application discloses an information acquisition method, comprising the following steps: obtaining a target ultrasound image for a target part; performing image recognition on the target ultrasound image to obtain contour measurement information of a target focus area in the target ultrasound image; obtaining relative position information of the target focus area based on marking of the target focus area in a position reference map of the target part; and in the case of detecting an activation operation on the target focus area, associating and displaying the contour measurement information and relative position information of the target focus area. By applying the technical solution provided by the present application, by identifying the target ultrasound image and marking the target focus area in the position reference map, relevant information of the target focus area can be accurately obtained, providing a favorable basis for subsequent further operations. The present application also discloses an information acquisition device, equipment and storage medium, which have corresponding technical effects.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an information acquisition method, device, equipment and storage medium. Background Art

[0002] With the advancement of ultrasound medicine, ultrasound is being used more and more widely, and ultrasound examinations of various parts of the body are gradually increasing. During ultrasound examinations, some lesions such as nodules require special attention. The relevant information obtained from these areas of concern can provide important basis for subsequent diagnosis and treatment, and its value in preventing, diagnosing, and treating diseases is becoming increasingly higher.

[0003] Therefore, how to accurately obtain relevant information of the region of interest is a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0004] The purpose of this application is to provide an information acquisition method, device, equipment and storage medium to accurately obtain relevant information of a region of interest and provide a favorable basis for subsequent further operations.

[0005] In order to solve the above technical problems, this application provides the following technical solutions:

[0006] A method for obtaining information, comprising:

[0007] obtaining a targeted ultrasound image of a target site;

[0008] Performing image recognition on the target ultrasound image to obtain contour measurement information of a target area of ​​interest in the target ultrasound image;

[0009] Obtaining relative position information of the target area of ​​interest according to the marking of the target area of ​​interest in the position reference map of the target part;

[0010] When an activation operation on the target attention area is detected, the contour measurement information and the relative position information of the target attention area are displayed in association with each other.

[0011] In a specific implementation of the present application, performing image recognition on the target ultrasound image to obtain contour measurement information of the target area of ​​interest in the target ultrasound image includes:

[0012] Performing image recognition on the target ultrasound image using a pre-acquired deep neural network model;

[0013] Determine contour measurement information of a target area of ​​interest present in the target ultrasound image according to an output result of the deep neural network model;

[0014] The deep neural network model is obtained by learning a pre-acquired ultrasound image set, wherein the ultrasound image set includes multiple ultrasound images, each of which is marked with the outline of a region of interest.

[0015] In a specific implementation of the present application, it also includes:

[0016] According to the output result of the deep neural network model, the outline of the target area of ​​interest is marked in the target ultrasound image.

[0017] In a specific embodiment of the present application, there are multiple target regions of interest, and the method of performing image recognition on the target ultrasound image using a pre-acquired deep neural network model includes:

[0018] After performing semantic segmentation or instance segmentation on the target ultrasound image using a pre-acquired deep neural network model, image recognition is performed on the segmented images respectively;

[0019] The step of determining contour measurement information of a target area of ​​interest in the target ultrasound image according to an output result of the deep neural network model includes:

[0020] The contour measurement information of each target area of ​​interest present in the target ultrasound image is determined respectively according to the output result of the deep neural network model.

[0021] In a specific implementation of the present application, there are multiple target areas of interest, and the associated display of the contour measurement information and the relative position information of the target areas of interest includes:

[0022] According to the number of the target area of ​​interest, the contour measurement information and the relative position information of the target area of ​​interest are displayed in association.

[0023] In a specific implementation of the present application, the position reference map is a phase map, and the relative position information of the target area of ​​interest includes clock azimuth information of the target area of ​​interest and distance information from a reference point.

[0024] In a specific embodiment of the present application, the target site is the breast.

[0025] In a specific implementation of the present application, it also includes:

[0026] When a click operation on a mark of any area of ​​interest in the position reference map is detected, an ultrasound image corresponding to the area of ​​interest is called back.

[0027] An information acquisition device, comprising:

[0028] A target ultrasonic image acquisition module is used to obtain a target ultrasonic image of a target part;

[0029] A contour measurement information acquisition module, used to perform image recognition on the target ultrasound image to obtain contour measurement information of a target area of ​​interest in the target ultrasound image;

[0030] A relative position information obtaining module, used for obtaining the relative position information of the target focus area according to the marking of the target focus area in the position reference map of the target part;

[0031] The related information association display module is used to associate and display the contour measurement information and the relative position information of the target focus area when an activation operation on the target focus area is detected.

[0032] An information acquisition device, comprising:

[0033] Memory for storing computer programs;

[0034] A processor is used to implement the steps of any of the above-mentioned information acquisition methods when executing the computer program.

[0035] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned information obtaining methods are implemented.

[0036] By applying the technical solution provided in the embodiment of the present application, after obtaining the target ultrasound image for the target part, the target ultrasound image can be recognized to obtain the contour measurement information of the target focus area in the target ultrasound image, and the relative position information of the target focus area can be obtained according to the marking of the target focus area in the position reference map of the target part. When the activation operation of the target focus area is detected, the contour measurement information and the relative position information of the target focus area are associated and displayed. By recognizing the target ultrasound image and marking the target focus area in the position reference map, the relevant information of the target focus area can be accurately obtained, providing a favorable basis for subsequent further operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1This is a flowchart of an implementation method of an information acquisition method in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of a breast phase image in an embodiment of the present application;

[0040] Figure 3 Schematic diagram of input and output of the deep neural network model in the embodiment of the present application;

[0041] Figure 4 This is a schematic diagram of the structure of an information acquisition device in an embodiment of the present application;

[0042] Figure 5 This is a schematic diagram of the structure of an information acquisition device in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0044] See also Figure 1 FIG. 1 is a flowchart of an implementation method of an information acquisition method provided in an embodiment of the present application. The method may include the following steps:

[0045] S110: Obtain a target ultrasound image of a target site.

[0046] The target part can be any part of the current ultrasound scan object, such as the breast, thyroid gland, etc. When using the ultrasound scanning device to perform ultrasound scanning on the target part, the operator can observe the ultrasound image in real time. When observing that there may be lesions such as nodules in the ultrasound image, the current ultrasound image can be frozen and the information acquisition operation can be triggered.

[0047] When a frozen ultrasound image is detected, the currently frozen ultrasound image can be determined as a target ultrasound image. After obtaining the target ultrasound image for the target part, the subsequent steps can be further performed.

[0048] S120: Perform image recognition on the target ultrasound image to obtain contour measurement information of the target focus area in the target ultrasound image.

[0049] After obtaining the target ultrasound image for the target part, the target ultrasound image can be subjected to image recognition to determine whether there is a target area of ​​interest in the target ultrasound image. The target area of ​​interest can be a lesion area or other area of ​​interest. If so, the contour of the target area of ​​interest in the target ultrasound image can be determined based on boundary features, etc. Further measurement can obtain contour measurement information of the target area of ​​interest. The contour measurement information of the target area of ​​interest can include the long diameter, wide diameter, distance from the skin, etc. of the target area of ​​interest.

[0050] S130: Obtaining relative position information of the target focus area according to the marking of the target focus area in the position reference map of the target part.

[0051] In an embodiment of the present application, a target ultrasound image for a target part is obtained, image recognition is performed on the target ultrasound image, and contour measurement information of a target area of ​​interest in the target ultrasound image is obtained. The operator can determine whether the obtained contour measurement information of the target area of ​​interest is accurate based on his or her own judgment. If the operator approves the contour measurement information of the target area of ​​interest, he or she can further mark the target area of ​​interest in a position reference map of the target part based on the observed actual position of the target area of ​​interest in the target part.

[0052] There is a position reference map corresponding to the target part. In the initial stage of ultrasound scanning, the position reference map can be hidden in the information display interface. When the operator needs to mark in the position reference map, a call instruction for the position reference map of the target part can be issued. After receiving the call instruction for the position reference map of the target part, the position reference map of the target part can be output and displayed to the operator in the information display interface. If the target part is the left breast, the position reference map corresponding to the left breast can be output and displayed. Correspondingly, if the target part is the right breast, the position reference map corresponding to the right breast can be output and displayed. The corresponding position reference map can be displayed according to the operator's choice. At the same time, the size of the displayed position reference map can be adjusted according to the operator's adjustment instructions.

[0053] According to the marking of the target focus area in the position reference map of the target part, the relative position information of the target focus area can be obtained.

[0054] In the embodiment of the present application, the position reference map of the target part can be in various forms, such as a phase map, a three-dimensional part model map, etc. When the target part is a breast, the position reference map can be a phase map, and the relative position information of the target focus area can include the clock azimuth information of the target focus area and the distance information from the reference point.

[0055] For example, the phase diagram can be represented by multiple concentric circles. Figure 2The figure shows a breast phase image. The radii of different circles represent different distance ratios. The center of the circle represents the nipple, i.e., the reference point. 1-12 represent 12 clock positions. Among them, the 6 o'clock and 12 o'clock directions can be parallel to the central axis of the body, the 12 o'clock direction points to the head, the 6 o'clock direction points to the feet, and the 3 o'clock and 9 o'clock directions can be parallel to the line connecting the two nipples. When scanning the right breast, the 3 o'clock direction points to the left nipple, and the 9 o'clock direction is away from the left nipple. When scanning the left breast, the 3 o'clock direction is away from the right nipple, and the 9 o'clock direction is towards the right nipple. N1 is a mark for the target area of ​​interest. According to the position of N1 in the breast phase image, the clock position of the target area of ​​interest and the distance from the nipple can be obtained.

[0056] Of course, the breast phase map can also be represented by a circle. For the phase map, other equal parts can also be divided, such as 6 equal parts, or 24 equal parts. It is also possible not to use a clock to represent the orientation, but to use an angle to represent it. This embodiment of the present application will not be repeated.

[0057] S140: When an activation operation on the target attention area is detected, the contour measurement information and the relative position information of the target attention area are associated and displayed.

[0058] In the embodiment of the present application, after obtaining the contour measurement information of the target area of ​​interest and the relative position information of the target area of ​​interest in the target ultrasound image, when an activation operation on the target area of ​​interest is detected, it can be considered that the current operator needs to know the relevant information of the target area of ​​interest, and the contour measurement information and the relative position information of the target area of ​​interest can be displayed in association. Specifically, the contour measurement information and the relative position information can be displayed in different display areas of the information display interface.

[0059] The activation operation for the target area of ​​interest may be triggered by the operator clicking on the target area of ​​interest in the target ultrasound image, or by the operator clicking on the mark of the target area of ​​interest in the position reference map of the target part, or by the operator inputting the number of the target area of ​​interest through information input.

[0060] When there is an activation operation on the target area of ​​interest, the contour measurement information and the relative position information of the target area of ​​interest are displayed in association, so that the operator can view the relevant information of the target area of ​​interest at the same time.

[0061] By applying the method provided in the embodiment of the present application, after obtaining the target ultrasound image for the target part, the target ultrasound image can be recognized to obtain the contour measurement information of the target focus area in the target ultrasound image, and the relative position information of the target focus area can be obtained based on the marking of the target focus area in the position reference map of the target part. When the activation operation of the target focus area is detected, the contour measurement information and the relative position information of the target focus area are associated and displayed. By recognizing the target ultrasound image and marking the target focus area in the position reference map, the relevant information of the target focus area can be accurately obtained, providing a favorable basis for subsequent further operations.

[0062] In one embodiment of the present application, step S120 may include the following steps:

[0063] Step 1: Use the pre-acquired deep neural network model to perform image recognition on the target ultrasound image;

[0064] Step 2: Determine contour measurement information of the target area of ​​interest in the target ultrasound image according to the output result of the deep neural network model;

[0065] The deep neural network model is obtained by learning a pre-acquired ultrasound image set, where the ultrasound image set includes multiple ultrasound images, each of which is marked with the outline of the area of ​​interest.

[0066] In an embodiment of the present application, a deep neural network initial model can be constructed in advance, and multiple ultrasound images can be obtained in advance. The contours of the area of ​​interest in each ultrasound image can be marked manually or using other marking tools to form an ultrasound image set. The ultrasound image set can be studied using the deep neural network initial model to understand the normal tissue structure of the ultrasound image and the tissue structure of the area of ​​interest. When the accuracy is higher than a preset accuracy threshold, a deep neural network model can be obtained.

[0067] The deep neural network model can be, but is not limited to, the following: U-Net (semantic segmentation network), deepLab (semantic image segmentation), HarDNet-MSEG (semantic segmentation model), MaskRCNN (instance segmentation model). You can choose according to the actual situation.

[0068] After obtaining the target ultrasound image of the target part, the pre-acquired deep neural network model can be used to perform image recognition on the target ultrasound image. Through the reasoning of the deep neural network model, the contour of the target area of ​​interest in the target ultrasound image can be automatically identified, and the contour measurement information can be automatically measured and output. Figure 3As shown in the figure, the model input of the deep neural network model is the left picture, the approximately elliptical area in the middle of the left picture is the focus area, and the model output is the right picture, which performs contour recognition and measurement on the focus area. Therefore, the contour measurement information of the target focus area in the target ultrasound image can be determined according to the output result of the deep neural network model.

[0069] The deep neural network model can be used to accurately obtain the contour measurement information of the target area of ​​interest in the target ultrasound image.

[0070] In one embodiment of the present application, the method may further include the following steps:

[0071] Based on the output of the deep neural network model, the outline of the target area of ​​interest is marked in the target ultrasound image.

[0072] In the embodiment of the present application, the target ultrasound image is recognized by using a deep neural network model, and the contour of the target focus area in the target ultrasound image can be automatically recognized. The output result of the deep neural network model can include a contour point set. Based on the output result of the deep neural network model, the contour of the target focus area can be marked in the target ultrasound image according to the contour point set. This facilitates the operator to intuitively view the target focus area.

[0073] In one embodiment of the present application, there may be multiple target regions of interest, and performing image recognition on the target ultrasound image using a pre-acquired deep neural network model may include the following steps:

[0074] After semantic segmentation or instance segmentation of the target ultrasound image using the pre-acquired deep neural network model, image recognition is performed on the segmented images respectively;

[0075] Determining contour measurement information of a target area of ​​interest in a target ultrasound image according to an output result of the deep neural network model may include the following steps:

[0076] The contour measurement information of each target area of ​​interest in the target ultrasound image is determined according to the output results of the deep neural network model.

[0077] In an embodiment of the present application, there may be multiple regions of interest in an ultrasound image. After obtaining a target ultrasound image of a target part, a deep neural network model may be used to perform semantic segmentation or instance segmentation on the target ultrasound image to separate multiple target regions of interest included in the target ultrasound image, and then image recognition is performed on the segmented images respectively, and corresponding output results may be obtained for each target region of interest. According to the output results of the deep neural network model, contour measurement information of each target region of interest in the target ultrasound image may be determined respectively.

[0078] In practical applications, an automatic measurement button and a previous / next button can be provided for the operator. When the operator triggers automatic measurement through the automatic measurement button, the deep neural network model identifies a target area of ​​interest in the target ultrasound image, and determines the contour measurement information of the target area of ​​interest according to the output result. When the operator triggers automatic measurement of the next target area of ​​interest through the previous / next button, the deep neural network model can identify the next target area of ​​interest in the target ultrasound image, and determine the contour measurement information of the target area of ​​interest according to the output result. The previous / next button can be a left / right arrow.

[0079] Of course, when there are multiple target regions of interest, each target region of interest can be marked in the target part position reference map, and the relative position information of each target region of interest can be obtained according to the marking. Each target region of interest can be distinguished by a number, and the number of each target region of interest is unique.

[0080] In one embodiment of the present application, when there are multiple target focus areas, step S140 may include the following steps:

[0081] According to the number of the target area of ​​interest, contour measurement information and relative position information of the target area of ​​interest are displayed in association.

[0082] In the embodiment of the present application, each target area of ​​interest has its own number. When an activation operation is detected for any target area of ​​interest, the contour measurement information and relative position information of the corresponding target area of ​​interest can be displayed in association with the number of the target area of ​​interest targeted by the activation operation, so that the operator can accurately obtain relevant information of the target area of ​​interest.

[0083] In one embodiment of the present application, the method may further include the following steps:

[0084] When a click operation on a mark of any area of ​​interest in the position reference map is detected, an ultrasound image corresponding to the area of ​​interest is called back.

[0085] In an embodiment of the present application, the ultrasonic scanning of the target part is a continuous process. In this process, multiple target ultrasonic images of the target part can be obtained. For each target ultrasonic image, the contour measurement information and relative position information of the target area of ​​interest in the corresponding target ultrasonic image can be obtained according to the operation of steps S120 and S130. At the same time, each target ultrasonic image can be saved in a database to provide a basis for clinical treatment. After a period of ultrasonic scanning or after the end of the ultrasonic scanning, there can be multiple marks of the area of ​​interest in the position reference map of the target part, each mark has a corresponding ultrasonic image, and the multiple areas of interest in the same position reference map have a logical connection, which can effectively reduce the risk of missed marks and missed detections, facilitate backtracking, and facilitate surgical navigation. When a click operation on a mark of any area of ​​interest in the position reference map is detected, the ultrasonic image corresponding to the area of ​​interest can be searched in the database, and the ultrasonic image corresponding to the area of ​​interest can be called back to facilitate the operator to view.

[0086] In addition, if the ultrasound image is directly recalled in the database, the region of interest in the ultrasound image will be activated and adjustable. The mark of the region of interest in the corresponding position reference map and the marks of other regions of interest can be displayed by color. At the same time, the contour measurement information and relative position information of each region of interest in the ultrasound image can also be displayed in association.

[0087] In one embodiment of the present application, after the ultrasonic scanning of the target part is completed, the contour measurement information and relative position information of each target area of ​​interest of the target part can be output in the form of a report, etc., so that the operator can view the distribution of all target areas of interest of the target part.

[0088] The embodiment of the present application realizes automatic recognition and measurement of the area of ​​interest in the ultrasound image, accurately obtains the long diameter, wide diameter, distance from the skin, etc. of the area of ​​interest, helps the operator quickly obtain the contour measurement information of the area of ​​interest, and uses the position reference map to facilitate the operator to record the relative position information of the area of ​​interest. It can simply and quickly complete the ultrasound scan of the target part, facilitate the operator to intuitively understand the relevant information of the area of ​​interest of the target part, improve work efficiency, reduce the risk of missed detection, and facilitate clinical treatment and diagnosis and treatment tracking.

[0089] Corresponding to the above method embodiment, the embodiment of the present application further provides an information obtaining device. The information obtaining device described below and the information obtaining method described above can refer to each other.

[0090] See also Figure 4 As shown, the device may include the following modules:

[0091] A target ultrasound image acquisition module 410 is used to acquire a target ultrasound image for a target part;

[0092] The contour measurement information obtaining module 420 is used to perform image recognition on the target ultrasound image to obtain contour measurement information of the target focus area in the target ultrasound image;

[0093] A relative position information obtaining module 430 is used to obtain relative position information of the target focus area according to the marking of the target focus area in the position reference map of the target part;

[0094] The related information association display module 440 is used to associate and display the contour measurement information and relative position information of the target focus area when an activation operation on the target focus area is detected.

[0095] By using the device provided in the embodiment of the present application, after obtaining the target ultrasound image for the target part, the target ultrasound image can be recognized to obtain the contour measurement information of the target focus area in the target ultrasound image, and the relative position information of the target focus area can be obtained according to the marking of the target focus area in the position reference map of the target part. When the activation operation of the target focus area is detected, the contour measurement information and the relative position information of the target focus area are associated and displayed. By recognizing the target ultrasound image and marking the target focus area in the position reference map, the relevant information of the target focus area can be accurately obtained, providing a favorable basis for subsequent further operations.

[0096] In a specific implementation of the present application, the profile measurement information obtaining module 420 is used to:

[0097] Perform image recognition on the target ultrasound image using a pre-acquired deep neural network model;

[0098] Determine contour measurement information of a target area of ​​interest in a target ultrasound image according to an output result of the deep neural network model;

[0099] The deep neural network model is obtained by learning a pre-acquired ultrasound image set, where the ultrasound image set includes multiple ultrasound images, each of which is marked with the outline of the area of ​​interest.

[0100] In a specific embodiment of the present application, a contour marking module is also included, which is used to:

[0101] Based on the output of the deep neural network model, the outline of the target area of ​​interest is marked in the target ultrasound image.

[0102] In a specific implementation of the present application, there are multiple target focus areas, and the contour measurement information acquisition module 420 is used to:

[0103] After semantic segmentation or instance segmentation of the target ultrasound image using the pre-acquired deep neural network model, image recognition is performed on the segmented images respectively;

[0104] Determine contour measurement information of a target area of ​​interest in a target ultrasound image according to an output result of the deep neural network model, including:

[0105] The contour measurement information of each target area of ​​interest in the target ultrasound image is determined according to the output results of the deep neural network model.

[0106] In a specific implementation of the present application, there are multiple target focus areas, and the related information association display module 440 is used to:

[0107] According to the number of the target area of ​​interest, contour measurement information and relative position information of the target area of ​​interest are displayed in association.

[0108] In a specific implementation of the present application, the position reference map is a phase map, and the relative position information of the target area of ​​interest includes the clock azimuth information of the target area of ​​interest and the distance information from the reference point.

[0109] In a specific embodiment of the present application, the target site is the breast.

[0110] In a specific implementation of the present application, an ultrasound image callback module is also included, which is used to:

[0111] When a click operation on a mark of any area of ​​interest in the position reference map is detected, an ultrasound image corresponding to the area of ​​interest is called back.

[0112] Corresponding to the above method embodiment, the embodiment of the present application further provides an information obtaining device, including:

[0113] Memory for storing computer programs;

[0114] A processor is used to implement the steps of the above-mentioned information obtaining method when executing a computer program.

[0115] In the embodiment of the present application, the information acquisition device may specifically be an ultrasonic scanning device, and the ultrasonic scanning device may further include an ultrasonic probe for performing ultrasonic scanning on the target part to obtain a target ultrasonic image of the target part.

[0116] like Figure 5 , which is a schematic diagram of the structure of the information acquisition device, the information acquisition device may include: a processor 10, a memory 11, a communication interface 12 and a communication bus 13. The processor 10, the memory 11 and the communication interface 12 all communicate with each other through the communication bus 13.

[0117] In the embodiment of the present application, the processor 10 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic devices, etc.

[0118] The processor 10 may call a program stored in the memory 11. Specifically, the processor 10 may execute operations in the embodiment of the information obtaining method.

[0119] The memory 11 is used to store one or more programs, which may include program codes, and the program codes include computer operation instructions. In the embodiment of the present application, the memory 11 at least stores programs for implementing the following functions:

[0120] obtaining a targeted ultrasound image of a target site;

[0121] Performing image recognition on the target ultrasound image to obtain contour measurement information of the target focus area in the target ultrasound image;

[0122] Obtaining relative position information of the target focus area according to the marking of the target focus area in the position reference map of the target part;

[0123] When an activation operation on the target attention area is detected, contour measurement information and relative position information of the target attention area are associated and displayed.

[0124] In one possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required for at least one function (such as an image processing function, an information processing function), etc.; the data storage area can store data created during use, such as ultrasound image data, area of ​​interest data, etc.

[0125] In addition, the memory 11 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0126] The communication interface 12 may be an interface of a communication module, and is used to connect to other devices or systems.

[0127] Of course, it should be noted that Figure 5 The structure shown does not constitute a limitation on the information acquisition device in the embodiment of the present application. In actual applications, the information acquisition device may include Figure 5 More or fewer components than shown, or combinations of certain components.

[0128] Corresponding to the above method embodiment, the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above information obtaining method are implemented.

[0129] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0130] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0131] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0132] Specific examples are used herein to illustrate the principles and implementation methods of the present application, and the description of the above embodiments is only used to help understand the technical solution and core ideas of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A method for obtaining information, characterized in that: include: obtaining a targeted ultrasound image of a target site; Performing image recognition on the target ultrasound image to obtain contour measurement information of a target area of ​​interest in the target ultrasound image; Obtaining relative position information of the target area of ​​interest according to the marking of the target area of ​​interest in the position reference map of the target part; When an activation operation on the target area of ​​interest is detected, the contour measurement information and the relative position information of the target area of ​​interest are displayed in association; Correspondingly, after the target part is ultrasonically scanned for a period of time or after the ultrasonic scan is completed, if a click operation on the mark of any area of ​​interest in the position reference map is detected, the ultrasonic image corresponding to the any area of ​​interest is called back for visual display; wherein, the same position reference map of the target part includes marks of multiple areas of interest, and each mark corresponds to an ultrasonic image.

2. The information acquisition method according to claim 1, characterized in that: The performing image recognition on the target ultrasound image to obtain contour measurement information of a target area of ​​interest in the target ultrasound image includes: Performing image recognition on the target ultrasound image using a pre-acquired deep neural network model; Determine contour measurement information of a target area of ​​interest present in the target ultrasound image according to an output result of the deep neural network model; The deep neural network model is obtained by learning a pre-acquired ultrasound image set, wherein the ultrasound image set includes multiple ultrasound images, each of which is marked with the outline of a region of interest.

3. The information acquisition method according to claim 2, characterized in that: Also includes: According to the output result of the deep neural network model, the outline of the target area of ​​interest is marked in the target ultrasound image.

4. The information acquisition method according to claim 2, characterized in that: There are multiple target areas of interest, and using a pre-acquired deep neural network model to perform image recognition on the target ultrasound image includes: After performing semantic segmentation or instance segmentation on the target ultrasound image using a pre-acquired deep neural network model, image recognition is performed on the segmented images respectively; The step of determining contour measurement information of a target area of ​​interest in the target ultrasound image according to an output result of the deep neural network model includes: The contour measurement information of each target area of ​​interest present in the target ultrasound image is determined respectively according to the output result of the deep neural network model.

5. The information acquisition method according to claim 1, characterized in that: There are multiple target areas of interest, and the associated display of the contour measurement information and the relative position information of the target areas of interest includes: According to the number of the target area of ​​interest, the contour measurement information and the relative position information of the target area of ​​interest are displayed in association.

6. The information obtaining method according to claim 1, characterized in that: The position reference map is a phase map, and the relative position information of the target area of ​​interest includes clock azimuth information of the target area of ​​interest and distance information from a reference point.

7. The information obtaining method according to claim 6, characterized in that: The target site is the breast.

8. An information acquisition device, characterized in that: include: A target ultrasonic image acquisition module is used to obtain a target ultrasonic image of a target part; A contour measurement information acquisition module, used to perform image recognition on the target ultrasound image to obtain contour measurement information of a target area of ​​interest in the target ultrasound image; A relative position information obtaining module, used for obtaining the relative position information of the target focus area according to the marking of the target focus area in the position reference map of the target part; A related information association display module, configured to associate and display the contour measurement information and the relative position information of the target focus area when an activation operation on the target focus area is detected; Correspondingly, the information acquisition device is also used for: after a period of time of ultrasonic scanning of the target part or after the ultrasonic scanning is completed, if a click operation on the mark of any area of ​​interest in the position reference map is detected, the ultrasonic image corresponding to the any area of ​​interest is called back for visual display; wherein, the same position reference map of the target part includes marks of multiple areas of interest, and each mark corresponds to an ultrasonic image.

9. An information acquisition device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the information obtaining method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the information obtaining method according to any one of claims 1 to 7 are implemented.

Images