Ultrasonic Image Acquisition Method, Device, Equipment and Computer Readable Storage Medium

Abstract

An embodiment of the present application provides an ultrasonic image acquisition method, apparatus, device, and computer-readable storage medium. The method includes: performing lesion detection on the acquired ultrasonic image; if there is a lesion in the ultrasonic image, obtaining reference feature information corresponding to the ultrasonic image according to the lesion type corresponding to the ultrasonic image; scanning the lesion position corresponding to the ultrasonic image according to the reference feature information to obtain an ultrasonic image of the lesion position. The ultrasonic image acquisition method provided by the embodiment of the present application performs lesion detection on the acquired ultrasonic image during the scanning process, and after detecting the lesion, uses the reference features corresponding to the lesion to repeatedly scan the lesion position until an ultrasonic image that meets the requirements is obtained. Subsequently, medical practitioners can use the ultrasonic image to provide more accurate diagnostic results.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of ultrasonic image scanning technology, and specifically to an ultrasonic image acquisition method, device, equipment, and computer-readable storage medium. Background Art

[0002] Ultrasound scanning is a relatively common imaging method in medical treatment. The collected ultrasound images can be used for subsequent auxiliary diagnosis of the disease.

[0003] Currently, there are machines that can perform automatic ultrasound scanning, but automatic scanning will be performed according to set parameters. During the scanning process, it is impossible to scan specific areas in a targeted manner, which affects the subsequent auxiliary diagnosis effect of the disease. Summary of the Invention

[0004] The embodiments of the present application provide an ultrasound image acquisition method, apparatus, device, and computer-readable storage medium, which aim to solve the problem in the prior art that automatic scanning cannot scan a specific area in a targeted manner, thereby affecting the subsequent auxiliary diagnosis effect of the disease.

[0005] In one aspect, an embodiment of the present application provides an ultrasound image acquisition method, comprising:

[0006] Perform lesion detection on the acquired ultrasound images;

[0007] If a lesion exists in the ultrasound image, obtaining reference feature information corresponding to the ultrasound image according to the type of lesion corresponding to the ultrasound image;

[0008] The lesion position corresponding to the ultrasound image is scanned according to the reference feature information to obtain an ultrasound image of the lesion position.

[0009] As a feasible embodiment of the present application, scanning the lesion location corresponding to the ultrasound image according to the reference feature information to obtain an ultrasound image of the lesion location includes:

[0010] Analyzing the ultrasound image to obtain lesion feature information of the ultrasound image;

[0011] According to the difference between the lesion characteristic information and the reference characteristic information, the lesion position corresponding to the ultrasound image is scanned to obtain an ultrasound image of the lesion position.

[0012] As a feasible embodiment of the present application, scanning the lesion position corresponding to the ultrasound image according to the difference between the lesion feature information and the reference feature information to obtain an ultrasound image of the lesion position includes:

[0013] Calculate the similarity between the lesion feature information and the reference feature information;

[0014] If the similarity is less than a preset similarity threshold, scan the lesion location corresponding to the ultrasound image to obtain the ultrasound image of the lesion location.

[0015] As a feasible embodiment of the present application, before the step of if the similarity is less than a preset similarity threshold, scan the lesion location corresponding to the ultrasound image to obtain the ultrasound image of the lesion location, the method includes:

[0016] Obtain the part information corresponding to the ultrasound image;

[0017] Set the similarity threshold according to the part information.

[0018] As a feasible embodiment of the present application, the step of obtaining the reference feature information corresponding to the ultrasound image according to the lesion type corresponding to the ultrasound image includes:

[0019] Query a preset database to obtain the associated feature information associated with the lesion type of the ultrasound image;

[0020] Set the associated feature information as the reference feature information corresponding to the ultrasound image.

[0021] As a feasible embodiment of the present application, before the step of querying a preset database to obtain the associated feature information associated with the lesion type of the ultrasound image, the method includes:

[0022] Obtain a sample ultrasound image containing the target lesion type;

[0023] Analyze the sample ultrasound image to obtain the sample feature information of the sample ultrasound image;

[0024] Associate and store the sample feature information with the target lesion type in a preset database.

[0025] As a feasible embodiment of the present application, the step of performing lesion detection on the obtained ultrasound image includes:

[0026] Obtain an ultrasound image and determine the part information corresponding to the ultrasound image;

[0027] Obtain a lesion detection model corresponding to the ultrasound image according to the part information;

[0028] Input the ultrasound image into the lesion detection model for lesion detection to obtain the lesion location and lesion type corresponding to the ultrasound image.

[0029] As a feasible embodiment of the present application, before obtaining the reference feature information corresponding to the ultrasonic image according to the lesion type corresponding to the ultrasonic image, the method further includes:

[0030] Obtain the lesion type corresponding to the ultrasonic image;

[0031] If there are operation parameters associated with the lesion type in the preset database, scan the lesion location corresponding to the ultrasonic image according to the operation parameters to obtain the ultrasonic image of the lesion location;

[0032] If there are no operation parameters associated with the lesion type in the preset database, perform the step of obtaining the reference feature information corresponding to the ultrasonic image according to the lesion type corresponding to the ultrasonic image.

[0033] As a feasible embodiment of the present application, after scanning the lesion location corresponding to the ultrasonic image according to the reference feature information to obtain the ultrasonic image of the lesion location, the method further includes:

[0034] Determine the optimal operation parameter from the candidate operation parameters corresponding to each ultrasonic image in the ultrasonic image according to the quality score of each ultrasonic image in the ultrasonic image;

[0035] Associate and store the optimal operation parameter with the lesion type in the preset database.

[0036] As a feasible embodiment of the present application, the lesion feature information includes at least one of key sections, contour information, and sign information.

[0037] On the other hand, an embodiment of the present application further provides an ultrasonic image acquisition device, including:

[0038] A detection module for performing lesion detection on the obtained ultrasonic image;

[0039] A determination module for obtaining the reference feature information corresponding to the ultrasonic image according to the lesion type corresponding to the ultrasonic image if there is a lesion in the ultrasonic image;

[0040] A scanning module for scanning the lesion location corresponding to the ultrasonic image according to the reference feature information to obtain the ultrasonic image of the lesion location.

[0041] On the other hand, an embodiment of the present application further provides an ultrasonic image acquisition device. The ultrasonic image acquisition device includes a processor, a memory, and an ultrasonic image acquisition program stored in the memory and executable on the processor. The processor executes the ultrasonic image acquisition program to implement the steps in the above ultrasonic image acquisition method.

[0042] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, on which an ultrasonic image acquisition program is stored, and the ultrasonic image acquisition program is executed by a processor to implement the steps in the above ultrasonic image acquisition method.

[0043] The ultrasonic image acquisition method provided by the embodiment of the present application detects lesions in the acquired ultrasonic images during the scanning process, and after detecting the lesions, uses the reference features corresponding to the lesions to repeatedly scan the lesion positions until an ultrasonic image meeting the requirements is obtained. Subsequently, medical practitioners can use this ultrasonic image to provide more accurate diagnostic results. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 It is a schematic diagram of the implementation scenario of an ultrasonic image acquisition method provided by an embodiment of the present application;

[0046] Figure 2 It is a schematic diagram of the step flow of an ultrasonic image acquisition method provided by an embodiment of the present application;

[0047] Figure 3 It is a schematic diagram of the step flow of scanning the lesion position provided by an embodiment of the present application;

[0048] Figure 4 It is a schematic diagram of the step flow of scanning the lesion position based on the difference in feature information provided by an embodiment of the present application;

[0049] Figure 5 It is a schematic diagram of the step flow of setting the similarity threshold provided by an embodiment of the present application;

[0050] Figure 6 It is a schematic diagram of the step flow of obtaining reference feature information provided by an embodiment of the present application;

[0051] Figure 7 It is a schematic diagram of the step flow of setting reference feature information provided by an embodiment of the present application;

[0052] Figure 8 It is a schematic diagram of the step flow of lesion detection provided by an embodiment of the present application;

[0053] Figure 9Schematic diagram of the steps of another ultrasonic image acquisition method provided by an embodiment of the present application;

[0054] Figure 10 Schematic diagram of the steps of a method for determining optimal operating parameters provided by an embodiment of the present application;

[0055] Figure 11 Schematic diagram of the structure of an ultrasonic image acquisition device provided by an embodiment of the present application;

[0056] Figure 12 Schematic diagram of the structure of an ultrasonic image acquisition device provided by an embodiment of the present application. Detailed implementation manners

[0057] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of the present invention.

[0058] In the embodiments of the present application, the term "exemplary" is used to mean "serving as an example, illustration, or description". Any embodiment described as "exemplary" in the embodiments of the present application is not necessarily construed as being more preferred or more advantageous than other embodiments. In order to enable any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the embodiments of the present application.

[0059] An ultrasonic image acquisition method, device, equipment and computer-readable storage medium are provided in the embodiments of the present application, and the following will be described in detail respectively.

[0060] In the embodiment of the present application, the ultrasonic image acquisition method is deployed in the ultrasonic image acquisition device in the form of a program. The ultrasonic image acquisition device is installed in the ultrasonic image acquisition equipment in the form of a processor. The ultrasonic image acquisition device in the ultrasonic image acquisition equipment executes the following steps by running the program corresponding to the ultrasonic image acquisition method: detecting lesions in the acquired ultrasonic image; if there are lesions in the ultrasonic image, obtaining the reference feature information corresponding to the ultrasonic image according to the lesion type corresponding to the ultrasonic image; scanning the lesion position corresponding to the ultrasonic image according to the reference feature information to obtain the ultrasonic image of the lesion position.

[0061] As Figure 1 shown, Figure 1 FIG. is a schematic diagram of an implementation scenario of an ultrasonic image acquisition method provided by an embodiment of the present application. The implementation scenario provided by the embodiment of the present application includes a scanning device 100 and a processing device 200; the scanning device 100 is mainly used to perform ultrasonic scanning on a patient to obtain an ultrasonic image, and the processing device 200 is mainly used for processing the scanned ultrasonic image and controlling the scanning device 100. Specifically, after the scanning device 100 scans and obtains an ultrasonic image, it will send it to the processing device 200. The processing device 200 will perform real-time lesion detection processing on the received ultrasonic image, and when detecting a lesion, obtain the corresponding reference feature information for controlling the scanning device 100 to perform repeated scanning on the lesion, so that the scanning device 100 obtains the ultrasonic image at the corresponding position.

[0062] It should be noted that Figure 1 the schematic diagram of the scenario of the ultrasonic image acquisition method shown is only an example. The scenario of the ultrasonic image acquisition method described in the embodiment of the present application is for more clearly explaining the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application.

[0063] Based on the above schematic diagram of the implementation scenario of the ultrasonic image acquisition method, a specific embodiment of the ultrasonic image acquisition method is proposed.

[0064] As Figure 2 shown, Figure 2 FIG. is a schematic diagram of the step flow of an ultrasonic image acquisition method provided by an embodiment of the present application. The ultrasonic image acquisition method in the embodiment of the present application includes steps 201 to 203:

[0065] 201, Detect lesions in the acquired ultrasonic image.

[0066] In the embodiment of the present application, the acquired ultrasonic image refers to the one obtained by scanning with the scanning device. The acquired ultrasonic image will be transmitted to the processing device for real-time lesion detection processing to obtain the lesion information corresponding to the ultrasonic image.

[0067] Specifically, as a feasible embodiment of the present application, lesion detection of ultrasonic images can be achieved by using a lesion detection network model trained with a large number of training sample images and their corresponding lesion labels based on deep learning technology. For example, relatively common deep network models, convolutional network models, recurrent network models, etc. The specific implementation scheme of training a lesion detection network based on deep learning technology is not elaborated herein in the embodiments of the present application. When detecting an ultrasonic image through the lesion detection network model, it is possible to determine whether there is a lesion in the ultrasonic image, and when there is a lesion, the corresponding lesion type and the position of the lesion in the ultrasonic image.

[0068] Furthermore, considering that the structural differences in different parts are relatively large and the possible lesion types are also different, therefore, in order to improve the detection effect of lesion detection of ultrasonic images in the embodiments of the present application, as an optional embodiment of the present application, the processing device will obtain the corresponding lesion detection network model based on the part information of the ultrasonic image to implement lesion detection of the ultrasonic image. Among them, the corresponding lesion detection network model obtained based on the part information is trained with the training samples of this specific part. The specific implementation scheme can refer to the subsequent Figure 8 and the content of its explanation. It is not elaborated herein in the embodiments of the present application.

[0069] 202. If there is a lesion in the ultrasonic image, obtain the reference feature information corresponding to the ultrasonic image according to the lesion type corresponding to the ultrasonic image.

[0070] In the embodiments of the present application, after completing the lesion detection of the ultrasonic image based on the lesion detection network model, if there is a lesion in the ultrasonic image, it indicates that this may be a potential key area that needs to be carefully scanned. Therefore, it is necessary to perform repeated detection at the lesion position for the subsequent diagnosis by medical practitioners. Specifically, to improve the scanning effect at the lesion, the processing device will obtain the reference feature information corresponding to this lesion type as the reference feature information corresponding to the ultrasonic image according to the lesion type of the lesion existing in the ultrasonic image. Among them, the lesion type and the reference feature information can be pre-analyzed through sample ultrasonic images and stored in a preset database. The specific implementation scheme can refer to the subsequent Figure 6 and the content of its explanation.

[0071] Specifically, as a feasible embodiment of the present application, the reference feature information at least includes at least one of key sections, contour information, and sign information. Based on these reference feature information, it can be used to determine whether the ultrasonic image collected at this lesion reaches the set quality requirements. For example, whether the section and contour are complete, whether the signs are clear, etc.

[0072] To further improve the acquisition effect of subsequent ultrasound images of the corresponding lesion locations, the processing device can also directly find the corresponding optimal operation parameters according to the lesion type corresponding to the ultrasound image to complete the acquisition of the ultrasound image at the lesion location. Among them, the optimal operation parameters are set according to the quality of the ultrasound images obtained by each scan when repeatedly scanning the lesion location. For specific implementation solutions, please refer to the subsequent Figure 9 content and its explanations.

[0073] 203. Scan the lesion location corresponding to the ultrasound image according to the reference feature information to obtain the ultrasound image of the lesion location.

[0074] In the embodiments of the present application, combined with the foregoing related descriptions, it can be seen that the reference feature information can be used to assist in judging whether the acquired ultrasound image meets the set quality requirements. Therefore, by repeatedly scanning the lesion location corresponding to the ultrasound image according to the reference feature information, an ultrasound image that meets the quality requirements can be finally obtained, and medical practitioners can provide more accurate diagnostic results based on this ultrasound image.

[0075] Specifically, during the process of scanning the lesion location corresponding to the ultrasound image according to the reference feature information, the lesion feature information of the acquired ultrasound image will be parsed in real time, and the corresponding lesion location will be scanned based on the difference between the lesion feature information and the reference feature information. For specific implementation solutions, please refer to the subsequent Figure 3 content and its explanations.

[0076] The ultrasound image acquisition method provided by the embodiments of the present application detects lesions in the acquired ultrasound image during the scanning process, and after detecting the lesions, uses the reference features corresponding to the lesions to repeatedly scan the lesion location until an ultrasound image that meets the requirements is obtained. Subsequently, medical practitioners can use this ultrasound image to provide more accurate diagnostic results.

[0077] As Figure 3 shown, Figure 3 is a schematic flowchart of the steps for scanning a lesion location provided by the embodiments of the present application, which is described in detail as follows.

[0078] In the embodiments of the present application, an implementation solution for repeatedly scanning the lesion location based on the difference between feature information is provided. Specifically, it includes steps 301 to 302:

[0079] 301. Parse the ultrasound image to obtain the lesion feature information of the ultrasound image.

[0080] In the embodiments of the present application, the processing device analyzes the ultrasonic image collected by the scanning device to obtain lesion feature information associated with the foregoing reference feature information, that is, key section, contour information, sign information and other feature information in the collected ultrasonic image. Specifically, the analysis of the ultrasonic image can be implemented based on a feature extraction module. For example, the contour information can be extracted by a feature extraction model related to edge detection. Details are not described herein again in the embodiments of the present application.

[0081] 302. According to the difference between the lesion feature information and the reference feature information, scan the lesion position corresponding to the ultrasonic image to obtain the ultrasonic image of the lesion position.

[0082] In the embodiments of the present application, after extracting the lesion feature information in the ultrasonic image, the processing device further repeatedly scans the lesion position corresponding to the ultrasonic image according to the difference between the lesion feature information and the reference feature information. Specifically, as an optional embodiment of the present application, for example, when the key section in the reference feature information does not exist in the lesion feature information, the processing device controls the scanning device according to the scanning parameters of the corresponding key section, such as scanning angle and scanning depth, so as to collect the corresponding key section. Or, when the contour information in the lesion feature information is incomplete, the processing device adjusts the pressing force of the scanning device when scanning this position according to the position information of the contour, so as to obtain clear and complete contour information. Details are not described herein again in the embodiments of the present application.

[0083] It should be noted that the foregoing scanning of the corresponding lesion position according to the difference between the lesion feature information and the reference feature information to obtain the ultrasonic image is a process of repeated acquisition and comparison. That is, after determining the difference between the lesion feature information of the obtained ultrasonic image and the reference feature information, the processing device adjusts the scanning device according to this difference to complete the next scan, obtains the adjusted ultrasonic image, and then the processing device further analyzes the adjusted ultrasonic image, and determines the difference between the lesion feature information of the obtained ultrasonic image and the reference feature information again, and then adjusts the scanning parameters of the scanning device again until finally an ultrasonic image meeting the requirements is collected, so as to obtain the complete ultrasonic image at the lesion position.

[0084] Specifically, the finally collected ultrasonic image meeting the requirements should be that the lesion feature information is highly similar to the reference feature information. Therefore, as an optional embodiment of the present application, the similarity between the lesion feature information and the reference feature information can be used as the termination condition for the foregoing repeated image acquisition. The specific implementation solution can refer to the subsequent Figure 4 and its explanatory content.

[0085] As Figure 4 shown, Figure 4This is a schematic diagram of the step process for scanning the lesion location based on the difference in feature information provided by the embodiments of the present application, which is described in detail as follows.

[0086] In the embodiments of the present application, an implementation scheme for scanning the lesion location by using the similarity between the lesion feature information and the reference feature information is provided. Specifically, it includes steps 401 to 402:

[0087] 401. Calculate the similarity between the lesion feature information and the reference feature information.

[0088] In the embodiments of the present application, both the lesion feature information and the reference feature information can be described in the form of vectors. Therefore, the similarity between the lesion feature information and the reference feature information can be calculated by calculating the vector similarity. Specifically, the vector similarity can be calculated by using the calculation formula of cosine similarity, which will not be elaborated in the embodiments of the present application.

[0089] 402. If the similarity is less than the preset similarity threshold, scan the lesion location corresponding to the ultrasonic image to obtain the ultrasonic image of the lesion location.

[0090] In the embodiments of the present application, if the similarity is less than the preset similarity threshold, it indicates that the difference between the lesion feature information of the collected ultrasonic image and the reference feature information is large, that is, the lesion features disclosed in the ultrasonic image are not obvious enough, which is not conducive to the diagnosis of subsequent medical practitioners. Therefore, this lesion location will be scanned again until the similarity between the lesion feature information of the collected ultrasonic image and the reference feature information is greater than or equal to the preset similarity threshold, indicating that the collected ultrasonic image can well represent the lesion information at this time. At this time, the scanning of the lesion location can be ended to obtain a complete ultrasonic image.

[0091] Furthermore, the preset similarity threshold here can be set based on actual needs. However, in order to improve the subsequent diagnosis effect, as a feasible embodiment of the present application, the similarity threshold can be set based on the part information corresponding to the ultrasonic image. The specific implementation scheme can refer to the subsequent Figure 5 and its explanatory content.

[0092] As Figure 5 shown, Figure 5 This is a schematic diagram of the step process for setting the similarity threshold provided by the embodiments of the present application, which is described in detail as follows.

[0093] In the embodiments of the present application, an implementation scheme for setting the similarity threshold based on the part information is provided. Specifically, it includes steps 501 to 502:

[0094] 501. Obtain the part information corresponding to the ultrasonic image.

[0095] In the embodiments of the present application, the location information corresponding to the ultrasonic image can be obtained by input before acquisition. For example, when a medical practitioner clicks on "liver" on the human-machine interaction interface, the processing device can determine that the location information corresponding to the ultrasonic image to be acquired subsequently is the liver. Of course, it is also feasible to obtain the location information by other means. For example, it can also be implemented by using a location detection network model trained with a large number of training sample images and their corresponding location labels, such as common deep network models, convolutional network models, recurrent network models, etc. The embodiments of the present application will not elaborate on this here.

[0096] 502. Set a similarity threshold according to the location information.

[0097] In the embodiments of the present application, after obtaining the location information corresponding to the ultrasonic image, the similarity threshold can be set based on the location information. For example, for some locations where the lesion features are not obvious, such as bones, muscle tissues, etc., the similarity threshold can be set smaller at this time. On the contrary, for locations with obvious lesion features, the similarity threshold can be set larger. Specifically, the association relationship between the location information and the similarity threshold can be pre-stored in the database.

[0098] Such as Figure 6 shown, Figure 6 FIG. is a schematic flowchart of steps for obtaining reference feature information provided by the embodiments of the present application, which is described in detail as follows.

[0099] In the embodiments of the present application, an implementation solution for obtaining reference feature information from a database is provided, specifically including steps 601 to 602:

[0100] 601. Query a preset database to obtain associated feature information associated with the lesion type of the ultrasonic image.

[0101] In the embodiments of the present application, by pre-analyzing and statistically processing sample ultrasonic images containing specific lesion types, the feature information corresponding to the specific lesion type can be obtained. After associating and storing the feature information and this specific lesion type in the preset database, the subsequent processing device can directly obtain the associated feature information associated with the lesion type of the ultrasonic image by querying the preset database. Among them, the implementation solution for pre-analyzing and statistically processing the sample ultrasonic images to determine the association relationship between the lesion type and the feature information can refer to the subsequent Figure 7 and its explanatory content.

[0102] 602. Set the associated feature information as the reference feature information corresponding to the ultrasonic image.

[0103] In an embodiment of the present application, after obtaining the associated feature information associated with the lesion type of the ultrasonic image, the associated feature information is the reference feature information corresponding to the ultrasonic image.

[0104] As Figure 7 shown, Figure 7 FIG. is a schematic flow chart of steps for setting reference feature information provided by an embodiment of the present application, which is described in detail below.

[0105] In an embodiment of the present application, an implementation solution for setting reference feature information based on a sample ultrasonic image is provided, specifically including steps 701 to 703:

[0106] 701. Obtain a sample ultrasonic image containing a target lesion type.

[0107] In an embodiment of the present application, by performing lesion detection on the sample ultrasonic image and classifying the sample ultrasonic image based on the result of the lesion detection, several image sets can be obtained. Among them, each sample ultrasonic image contained in a set is an ultrasonic image containing the same specific target lesion type.

[0108] 702. Analyze the sample ultrasonic image to obtain the sample feature information of the sample ultrasonic image.

[0109] In an embodiment of the present application, by analyzing the ultrasonic images containing the same specific target lesion type, the sample feature information of each ultrasonic image can be obtained. The implementation solution for analyzing the ultrasonic image to obtain the feature information can refer to the content of the foregoing step 301 and its explanatory description, which will not be elaborated in this embodiment of the present application.

[0110] In an embodiment of the present application, after determining the sample feature information of each sample ultrasonic image, based on the statistics of the sample feature information of each sample ultrasonic image, the sample feature information of the sample ultrasonic image can be obtained. Specifically, the statistics of the feature information here can be obtained by calculating the vector mean, and of course, other statistical methods can also be used, such as weighted average, which will not be elaborated in this embodiment of the present application.

[0111] 703. Store the sample feature information and the target lesion type in a preset database in an associated manner.

[0112] In an embodiment of the present application, after extracting the sample feature information by the foregoing method, the sample feature information and the corresponding target lesion type are stored in a preset database in an associated manner, and then the subsequent processing device can directly query and obtain the corresponding reference feature information based on the lesion type.

[0113] As Figure 8 shown, Figure 8A schematic flow chart of the steps for lesion detection provided in an embodiment of the present application is described in detail as follows.

[0114] In an embodiment of the present application, a solution is provided for obtaining a corresponding lesion detection model based on location information, specifically including steps 801 to 803:

[0115] 801 : Acquire an ultrasound image and determine location information corresponding to the ultrasound image.

[0116] In the embodiment of the present application, the part information corresponding to the ultrasound image is similar to the part information obtained in the aforementioned step 501, and can be obtained by input before acquisition. For example, when a medical practitioner clicks "liver" on the human-computer interaction interface, the processing device can then determine that the part information corresponding to the subsequently acquired ultrasound image is the liver. Of course, it is also feasible to obtain part information by other means. For example, it can also be implemented by using a part detection network model trained using a large number of training sample images and their corresponding part labels based on deep learning technology, such as the more common deep network models, convolutional network models, recurrent network models, etc., which will not be further described in the embodiment of the present application.

[0117] 802. Acquire a lesion detection model corresponding to the ultrasound image according to the location information.

[0118] In the embodiment of the present application, after obtaining the site information corresponding to the ultrasound image, the processing device further obtains a lesion detection model corresponding to the ultrasound image. For example, when the site information corresponding to the ultrasound image is the liver, the obtained lesion detection model is a specific lesion detection model trained based on training samples of the liver site and specifically used for detecting lesions in the liver.

[0119] 803 : Input the ultrasound image into the lesion detection model to perform lesion detection, and obtain the lesion location and lesion type corresponding to the ultrasound image.

[0120] In an embodiment of the present application, the ultrasound image is input into a lesion detection model for lesion detection processing, and the lesion detection model will ultimately output the lesion location and lesion type corresponding to the ultrasound image.

[0121] like Figure 9 As shown, Figure 9 A schematic flow chart of the steps of another ultrasound image acquisition method provided in an embodiment of the present application is described in detail as follows.

[0122] In an embodiment of the present application, a solution is provided for scanning the lesion location based on the operation parameters corresponding to the lesion type after obtaining the lesion type, specifically including steps 901 to 903:

[0123] 901. Obtain the lesion type corresponding to the ultrasound image, and determine whether there are operation parameters associated with the lesion type in the preset database. If so, execute step 902; if not, execute step 903.

[0124] In the embodiment of the present application, when the processing device scans the ultrasound image of the lesion, it will determine the optimal operation parameters based on the quality of the acquired ultrasound image and store them in association with the lesion type. Thus, after obtaining the lesion type corresponding to the ultrasound image, the processing device will determine whether there are operation parameters associated with the lesion type in the preset database, so as to determine whether to scan this lesion position based on the operation parameters or based on the reference feature information.

[0125] 902. Scan the lesion position corresponding to the ultrasound image according to the operation parameters to obtain the ultrasound image of the lesion position.

[0126] In the embodiment of the present application, if there are operation parameters associated with the lesion type in the preset database, the processing device will directly control the scanning device to complete the scanning of the lesion position according to the operation parameters, so as to directly obtain an ultrasound image with better quality effect.

[0127] 903. Obtain the reference feature information corresponding to the ultrasound image according to the lesion type corresponding to the ultrasound image.

[0128] In the embodiment of the present application, if there are no operation parameters associated with the lesion type in the preset database, the processing device will directly control the scanning device to complete the scanning of the lesion position according to the reference feature information, so as to directly obtain an ultrasound image with better quality effect.

[0129] Further, after subsequently scanning the lesion position corresponding to the ultrasound image according to the reference feature information to obtain the ultrasound image of the lesion position, the processing device will determine the optimal operation parameters according to the quality scores of each ultrasound image and store them in association with the lesion type. Subsequently, when scanning the same lesion, the image acquisition of the lesion position can be directly completed according to this operation parameter, without using the reference feature information to complete the image acquisition of the lesion position.

[0130] As Figure 10 shown, Figure 10 is a schematic flow chart of the steps for determining the optimal operation parameters provided by the embodiment of the present application. Specifically, it includes steps 1001 to 1002:

[0131] 1001. Determine the optimal operation parameter from the candidate operation parameters corresponding to each ultrasound image in the ultrasound image according to the quality scores of each ultrasound image in the ultrasound image.

[0132] In an embodiment of the present application, after finally acquiring an ultrasound image, the processing device will perform quality detection on each ultrasound image in the ultrasound image to obtain the quality scores of each ultrasound image, and then determine the ultrasound image with the optimal quality based on the magnitude relationship of the quality scores of each ultrasound image, and use the candidate operation parameters corresponding to the ultrasound image with the optimal quality as the optimal operation parameters.

[0133] 1002, store the optimal operation parameters and the lesion type in a preset database in an associated manner.

[0134] In an embodiment of the present application, the processing device will store the optimal operation parameters and the lesion type in a preset database in an associated manner, so that when the same lesion is detected subsequently, the acquisition of the ultrasound image can be directly completed based on the optimal operation parameters, thereby improving the scanning efficiency of the ultrasound image.

[0135] To more clearly understand the implementation solution of ultrasound image acquisition provided in the embodiments of the present application, the following will combine Figures 1 to 10 specific embodiments provided to provide a complete implementation step of ultrasound image acquisition, as follows:

[0136] 1) Obtain the ultrasound image;

[0137] 2) Perform part detection on the ultrasound image to obtain part information;

[0138] 3) Obtain the corresponding lesion detection model according to the part information, and perform lesion detection on the ultrasound image to determine whether there is a lesion, and the lesion type and lesion location corresponding to the lesion;

[0139] 4) If there is a lesion in the ultrasound image, determine whether there are operation parameters corresponding to the lesion type in the preset database;

[0140] 5) If so, control the scanning device to complete repeated scanning at the lesion location according to the operation parameters to obtain an ultrasound image, and then return to step 1 to continue obtaining the ultrasound image of the next area or the next part;

[0141] 6) If not, obtain the reference feature information corresponding to the ultrasound image according to the lesion type;

[0142] 7) Analyze the ultrasound image to obtain the lesion feature information of the ultrasound image, and calculate the similarity between the lesion feature information and the reference feature information;

[0143] 8) Determine the similarity threshold according to the part information, and compare the similarity and the magnitude relationship of the similarity threshold;

[0144] 9) If the similarity is less than the similarity threshold, scan the lesion location corresponding to the ultrasound image according to the difference between the lesion feature information and the reference feature information to obtain a new ultrasound image, re-parse to obtain new lesion feature information, determine the new similarity, and continue scanning the lesion location until the new similarity is greater than the similarity threshold, then end the scanning of the lesion location to obtain the ultrasound image;

[0145] 10) According to the quality scores of the ultrasound images in the ultrasound image, determine the optimal operation parameters from the candidate operation parameters corresponding to the ultrasound images in the ultrasound image, and store the optimal operation parameters associated with the lesion type in the preset database, and then return to step 1 to continue obtaining the ultrasound image of the next region or the next part.

[0146] To better implement the ultrasound image acquisition method provided by the embodiments of the present application, based on the ultrasound image acquisition method, an ultrasound image acquisition device is further provided in the embodiments of the present application. As Figure 11 shown, Figure 11 is a schematic structural diagram of an ultrasound image acquisition device provided by an embodiment of the present application. The ultrasound image acquisition device includes:

[0147] A detection module 1101, configured to perform lesion detection on the acquired ultrasound image;

[0148] A determination module 1102, configured to, if there is a lesion in the ultrasound image, obtain the reference feature information corresponding to the ultrasound image according to the lesion type corresponding to the ultrasound image;

[0149] A scanning module 1103, configured to scan the lesion location corresponding to the ultrasound image according to the reference feature information to obtain the ultrasound image of the lesion location.

[0150] In some embodiments of the present application, the scanning module includes:

[0151] An analysis sub-module, configured to analyze the ultrasound image to obtain the lesion feature information of the ultrasound image;

[0152] A scanning sub-module, configured to scan the lesion location corresponding to the ultrasound image according to the difference between the lesion feature information and the reference feature information to obtain the ultrasound image of the lesion location.

[0153] In some embodiments of the present application, the scanning sub-module includes:

[0154] A similarity calculation unit, configured to calculate the similarity between the lesion feature information and the reference feature information;

[0155] A scanning unit, configured to scan a lesion position corresponding to the ultrasonic image to obtain an ultrasonic image of the lesion position if the similarity is less than a preset similarity threshold.

[0156] In some embodiments of the present application, the scanning sub-module further includes:

[0157] A part obtaining unit, configured to obtain part information corresponding to the ultrasonic image;

[0158] A threshold setting unit, configured to set a similarity threshold according to the part information.

[0159] In some embodiments of the present application, the determination module includes:

[0160] A query sub-module, configured to query a preset database to obtain associated feature information associated with the lesion type of the ultrasonic image;

[0161] A determination sub-module, configured to set the associated feature information as reference feature information corresponding to the ultrasonic image.

[0162] In some embodiments of the present application, the determination module further includes:

[0163] A sample obtaining sub-module, configured to obtain a sample ultrasonic image including a target lesion type;

[0164] A sample analysis sub-module, configured to analyze the sample ultrasonic image to obtain sample feature information of the sample ultrasonic image;

[0165] A storage sub-module, configured to store the sample feature information and the target lesion type in association in a preset database.

[0166] In some embodiments of the present application, the detection module includes:

[0167] A part determination sub-module, configured to obtain an ultrasonic image and determine part information corresponding to the ultrasonic image;

[0168] A model obtaining sub-module, configured to obtain a lesion detection model corresponding to the ultrasonic image according to the part information;

[0169] A model detection sub-module, configured to input the ultrasonic image into the lesion detection model for lesion detection to obtain a lesion position and a lesion type corresponding to the ultrasonic image.

[0170] In some embodiments of the present application, the ultrasonic image acquisition device further includes:

[0171] A type obtaining module, configured to obtain a lesion type corresponding to the ultrasonic image;

[0172] A parameter scanning module, configured to scan the lesion location corresponding to the ultrasonic image according to the operation parameters if there are operation parameters associated with the lesion type in a preset database, so as to obtain an ultrasonic image of the lesion location;

[0173] A determination module, configured to obtain reference feature information corresponding to the ultrasonic image according to the lesion type corresponding to the ultrasonic image if there are no operation parameters associated with the lesion type in the preset database.

[0174] In some embodiments of the present application, the ultrasonic image acquisition device further includes:

[0175] A screening module, configured to determine an optimal operation parameter from candidate operation parameters corresponding to each ultrasonic image in the ultrasonic image according to the quality score of each ultrasonic image in the ultrasonic image;

[0176] A storage module, configured to store the optimal operation parameter and the lesion type in association in a preset database.

[0177] An embodiment of the present application further provides an ultrasonic image acquisition device, as Figure 12 shown, Figure 12 which is a schematic structural diagram of an ultrasonic image acquisition device provided by an embodiment of the present application.

[0178] The ultrasonic image acquisition device includes a memory, a processor, and an ultrasonic image acquisition program stored in the memory and executable on the processor. When the processor executes the ultrasonic image acquisition program, the steps in the ultrasonic image acquisition method provided by any embodiment of the present application are implemented.

[0179] Specifically: The ultrasonic image acquisition device may include a processor 1201 with one or more processing cores, a memory 1202 with one or more storage media, a power supply 1203, an input unit 1204, and other components. Those skilled in the art can understand that Figure 12 the structure of the ultrasonic image acquisition device shown in

[0180] The processor 1201 is the control center of the ultrasonic image acquisition device, connecting various parts of the entire ultrasonic image acquisition device through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 1202, and invoking data stored in the memory 1202, it executes various functions of the ultrasonic image acquisition device and processes data, thereby monitoring the entire ultrasonic image acquisition device. Optionally, the processor 1201 may include one or more processing cores; preferably, the processor 1201 may integrate an application processor and a modulation / demodulation processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modulation / demodulation processor mainly processes wireless communication. It can be understood that the above modulation / demodulation processor may not be integrated into the processor 1201 either.

[0181] The memory 1202 can be used to store software programs and modules. The processor 1201 executes various functional applications and data processing by running the software programs and modules stored in the memory 1202. The memory 1202 mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, image playback function, etc.), etc.; the data storage area can store data created according to the use of the ultrasonic image acquisition device, etc. In addition, the memory 1202 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage devices. Correspondingly, the memory 1202 may also include a memory controller to provide the processor 1201 with access to the memory 1202.

[0182] The ultrasonic image acquisition device further includes a power supply 1203 that supplies power to each component. Preferably, the power supply 1203 can be logically connected to the processor 1201 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 1203 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0183] The ultrasonic image acquisition device may further include an input unit 1204, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0184] Although not shown, the ultrasonic image acquisition device may further include a display unit and the like, which will not be elaborated herein. Specifically, in this embodiment, the processor 1201 in the ultrasonic image acquisition device will load the executable files corresponding to the processes of one or more application programs into the memory 1202 according to the following instructions, and the processor 1201 will run the application programs stored in the memory 1202, so as to implement the steps in the ultrasonic image acquisition method provided in any embodiment of the present application.

[0185] For this reason, an embodiment of the present application provides a computer-readable storage medium, which may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc. An ultrasonic image acquisition program is stored on the computer-readable storage medium, and when the ultrasonic image acquisition program is executed by the processor, the steps in the ultrasonic image acquisition method provided in any embodiment of the present application are implemented.

[0186] In the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not elaborated in a certain embodiment, reference may be made to the detailed descriptions of other embodiments above, which will not be elaborated herein.

[0187] Specifically in implementation, the above units or structures can be implemented as independent entities, or can be combined arbitrarily to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the method embodiments above, which will not be elaborated herein.

[0188] The specific implementation of each of the above operations can refer to the previous embodiments, which will not be elaborated herein.

[0189] The above has introduced in detail an ultrasonic image acquisition method provided by an embodiment of the present application. Specific examples are used herein to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for acquiring ultrasonic images, characterized in that: include: Perform lesion detection on the acquired ultrasound images; If a lesion is present in the ultrasound image, obtaining reference feature information corresponding to the ultrasound image based on the type of lesion corresponding to the ultrasound image; wherein the reference feature information includes at least one of key sections, contour information, and sign information; and determining whether the acquired ultrasound image of the lesion location meets set quality requirements based on the reference feature information; Analyzing the ultrasound image to obtain lesion feature information of the ultrasound image; Scanning the lesion location corresponding to the ultrasound image according to the difference between the lesion characteristic information and the reference characteristic information to obtain an ultrasound image of the lesion location; Among them, according to the difference between the lesion characteristic information and the reference characteristic information, the corresponding lesion position is scanned to obtain the ultrasound image, which is a process of repeated acquisition and comparison. After determining the difference between the lesion characteristic information of the acquired ultrasound image and the reference characteristic information, the scanning device is adjusted according to the difference to complete the next scan to obtain the adjusted ultrasound image, and then the adjusted ultrasound image is further analyzed, and the scanning parameters of the scanning device are adjusted again according to the difference between the lesion characteristic information of the acquired ultrasound image and the reference characteristic information, until the ultrasound image that meets the requirements is finally acquired.

2. The ultrasonic image acquisition method according to claim 1, characterized in that: Scanning the lesion position corresponding to the ultrasound image according to the difference between the lesion feature information and the reference feature information to obtain an ultrasound image of the lesion position includes: Calculating the similarity between the lesion feature information and the reference feature information; If the similarity is less than a preset similarity threshold, the lesion position corresponding to the ultrasound image is scanned to obtain an ultrasound image of the lesion position.

3. The ultrasonic image acquisition method according to claim 2, characterized in that: If the similarity is less than a preset similarity threshold, scanning the lesion location corresponding to the ultrasound image to obtain an ultrasound image of the lesion location, the method includes: Acquiring location information corresponding to the ultrasound image; A similarity threshold is set according to the part information.

4. The ultrasonic image acquisition method according to claim 1, wherein: The acquiring, according to the lesion type corresponding to the ultrasound image, reference feature information corresponding to the ultrasound image includes: Querying a preset database to obtain associated feature information associated with the lesion type of the ultrasound image; The associated feature information is set as reference feature information corresponding to the ultrasound image.

5. The ultrasonic image acquisition method according to claim 4, characterized in that: Before querying a preset database to obtain associated feature information associated with the lesion type of the ultrasound image, the method includes: acquiring a sample ultrasound image containing the target lesion type; Analyzing the sample ultrasound image to obtain sample feature information of the sample ultrasound image; The sample characteristic information is associated with the target lesion type and stored in a preset database.

6. The ultrasonic image acquisition method according to claim 1, characterized in that: The step of performing lesion detection on the acquired ultrasound image includes: Acquire an ultrasound image and determine location information corresponding to the ultrasound image; acquiring a lesion detection model corresponding to the ultrasound image according to the location information; The ultrasound image is input into the lesion detection model to perform lesion detection, and the lesion location and lesion type corresponding to the ultrasound image are obtained.

7. The ultrasonic image acquisition method according to any one of claims 1 to 6, characterized in that: Before obtaining reference feature information corresponding to the ultrasound image according to the lesion type corresponding to the ultrasound image, the method further includes: Acquiring a lesion type corresponding to the ultrasound image; If there is an operation parameter associated with the lesion type in the preset database, scanning the lesion position corresponding to the ultrasound image according to the operation parameter to obtain an ultrasound image of the lesion position; If the preset database does not contain the operation parameter associated with the lesion type, the step of acquiring reference feature information corresponding to the ultrasound image according to the lesion type corresponding to the ultrasound image is performed.

8. The ultrasonic image acquisition method according to claim 7, characterized in that: After scanning the lesion location corresponding to the ultrasound image based on the difference between the lesion feature information and the reference feature information to obtain an ultrasound image of the lesion location, the method further includes: determining an optimal operating parameter from candidate operating parameters corresponding to each ultrasound image in the ultrasound images according to a quality score of each ultrasound image in the ultrasound images; The optimal operating parameters are associated with the lesion type and stored in a preset database.

9. An ultrasonic image acquisition device, characterized in that: Applied to the method according to any one of claims 1 to 8, the device comprises: A detection module, used for performing lesion detection on the acquired ultrasound image; a determination module, configured to, if a lesion is present in the ultrasound image, obtain reference feature information corresponding to the ultrasound image based on the type of lesion corresponding to the ultrasound image; wherein the reference feature information includes at least one of key sections, contour information, and sign information; and determine whether the acquired ultrasound image of the lesion location meets set quality requirements based on the reference feature information; A scanning module is used to scan the lesion position corresponding to the ultrasound image according to the reference feature information to obtain an ultrasound image of the lesion position.

10. An ultrasonic image acquisition device, characterized in that: The ultrasonic image acquisition device includes a processor, a memory, and an ultrasonic image acquisition program stored in the memory and executable on the processor. The processor executes the ultrasonic image acquisition program to implement the steps of the ultrasonic image acquisition method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that An ultrasound image acquisition program is stored on the computer-readable storage medium, and the ultrasound image acquisition program is executed by the processor to implement the steps in the ultrasound image acquisition method according to any one of claims 1 to 8.

Images