Focus observation positioning method based on scanned image, ultrasonic scanning equipment and medium
By comparing key metric parameters of lesion images during ultrasound scanning, the lesion feature observation area is automatically determined, solving the problem that the lesion observation location depends on human experience and improving the accuracy of lesion observation and scanning efficiency.
Patent Information
- Application Number
- CN202510981136.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-15
- Publication Date
- 2025-12-09
AI Technical Summary
In existing ultrasound scanning technologies, the degree of automation in determining the location of lesions is low, requiring doctors to have extensive scanning and image interpretation experience.
By obtaining the first key metric parameter of the current frame image in the pre-scan operation, comparing it with the second key metric parameter of the new image, caching the optimal key metric parameter, and prompting the user that the current retrace position is the target observation position during the retrace operation.
It enables the automated determination of lesion feature observation areas, improving accuracy and reducing the number of scans, thus increasing scanning efficiency.
Smart Images
Figure CN121081024A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of ultrasound scanning technology, and particularly relates to a lesion observation and localization method based on scanned images, a lesion observation and localization device based on scanned images, an ultrasound scanning device, and a computer-readable storage medium. Background Technology
[0002] Ultrasound scanning is a common method for scanning lesions in physiological tissues. Through ultrasound scanning, complete video images can be obtained, allowing for the examination and analysis of lesions in the target area of the patient.
[0003] However, ultrasound scans produce black-and-white images, requiring doctors to have extensive scanning and image interpretation experience to identify the optimal location for lesion observation. Therefore, current methods for determining lesion locations suffer from a low degree of automation. Summary of the Invention
[0004] The purpose of this application is to provide a lesion observation and localization method based on scanned images, a lesion observation and localization device based on scanned images, an ultrasound scanning device, and a computer-readable storage medium, which can improve the automation level of determining the lesion feature observation area.
[0005] The first aspect of this application provides a method for lesion observation and localization based on scanned images, including:
[0006] Obtain the first key metric parameter of the current frame image in the pre-scan operation;
[0007] When a new image is acquired during the pre-scanning operation, the second key metric parameter of the new image is compared with the first key metric parameter to obtain a comparison result;
[0008] Based on the comparison results, at least one set of key metrics parameters should be cached as target key metrics parameters.
[0009] During the user's retrace operation, when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters, the user is prompted that the current retrace position is the target observation position.
[0010] This application provides a method for lesion observation and localization based on scanned images. It acquires the first key metric parameter of the current frame image during a pre-scan operation. When a new image is acquired during the pre-scan operation, the second key metric parameter of the new image is compared with the first key metric parameter to obtain a comparison result. Since key metric parameters can assist in lesion observation location, by comparing key metric parameters of different frames in the pre-scan operation, a better comparison result can be selected, which is the optimal key metric parameter. Based on the comparison result, at least one set of key metric parameters is cached as target key metric parameters. Then, during the user's retracement operation, when the key metric parameter of the retracement image matches the target key metric parameter, the user is prompted that the current retracement position is the target observation position. Thus, it achieves automated determination of lesion feature observation areas, which not only improves the accuracy of lesion feature observation area determination but also reduces the number of scans and improves scanning efficiency.
[0011] A second aspect of this application provides a lesion observation and localization device based on scanned images, comprising:
[0012] The acquisition module is used to acquire the first key metric parameters of the current frame image in the pre-scan operation;
[0013] The matching module is used to compare the second key metric parameter of the new image with the first key metric parameter when the pre-scan operation acquires a new image, and obtain a comparison result;
[0014] The storage module is used to cache at least one set of key metric parameters as target key metric parameters based on the comparison results;
[0015] The prompting module is used to prompt the user that the current retrace position is the target observation position when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters during the user's retrace operation.
[0016] A third aspect of this application provides an ultrasound scanning device, including: a memory, a processor, and a computer program stored in the memory and executable on the ultrasound scanning device. When the processor executes the computer program, it implements the steps of the lesion observation and localization method based on scanned images provided in the first aspect above.
[0017] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the lesion observation and localization method based on scanned images provided in the first aspect above.
[0018] It is understood that the beneficial effects of the second, third, and fourth aspects described above can be found in the relevant description in the first aspect above, and will not be repeated here. Attached Figure Description
[0019] Figure 1 A flowchart illustrating the implementation of a lesion observation and localization method based on scanned images, provided in an embodiment of this application;
[0020] Figure 2 A flowchart illustrating the implementation of a lesion observation and localization method based on scanned images, provided as another embodiment of this application;
[0021] Figure 3 A schematic diagram of a lesion observation and localization device based on scanned images provided in this application embodiment;
[0022] Figure 4 This is a structural block diagram of an ultrasonic scanning device provided in an embodiment of this application. Detailed Implementation
[0023] To make the technical problems, technical solutions, and beneficial effects to be solved by this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and are not intended to limit the scope of this application.
[0024] It should be noted that when a component is referred to as being "fixed to" or "set on" another component, it can be directly on or indirectly on that other component. When a component is referred to as being "connected to" another component, it can be directly connected to or indirectly connected to that other component.
[0025] It should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.
[0026] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.
[0027] Ultrasound scanning is a common method for scanning lesions in physiological tissues. Through ultrasound scanning, complete video images can be obtained, allowing for the examination and analysis of lesions in the target area of the patient.
[0028] However, ultrasound scans produce black-and-white images, requiring doctors to have extensive scanning and image interpretation experience to identify the location of lesions. Therefore, current methods for determining lesion feature observation areas suffer from a low degree of automation.
[0029] To address the aforementioned technical problems, this application provides a lesion observation and localization method based on scanned images. This method acquires the first key metric parameter of the current frame image during a pre-scan operation. When a new image is acquired during the pre-scan operation, the second key metric parameter of the new image is compared with the first key metric parameter to obtain a comparison result. Since key metric parameters can assist in lesion observation location, by comparing key metric parameters of different frame images during the pre-scan operation, a better comparison result can be selected, which is the optimal key metric parameter. Based on the comparison result, at least one set of key metric parameters is cached as target key metric parameters. Then, during the user's retracement operation, when the key metric parameter of the retracement image matches the target key metric parameter, the user is prompted that the current retracement position is the target observation position. This achieves automated determination of lesion feature observation areas, improving the accuracy of lesion feature observation area determination, reducing the number of scans, and increasing scanning efficiency.
[0030] This embodiment provides a method for lesion observation and localization based on scanned images, with the executing entity being an ultrasound scanning device. Specifically, it can be a control device or controller within the ultrasound scanning device. In practical use, users utilize an ultrasound scanning device to perform ultrasound scans on physiological tissues, obtaining ultrasound scan images. By executing the method provided in this embodiment, the lesion feature observation area can be quickly determined.
[0031] The following provides a detailed description of the lesion observation and localization method based on scanned images provided in this embodiment through specific implementation methods.
[0032] Figure 1 This document illustrates a flowchart of an implementation method for lesion observation and localization based on scanned images, provided in an embodiment of this application. Figure 1 As shown, the lesion observation and localization method based on scanned images includes the following steps:
[0033] S110: Obtain the first key metric parameter of the current frame image for the pre-scan operation.
[0034] The pre-scan operation can be an operation in pre-scan mode, an initial scan operation by the user, or a scan operation in a preset mode. During the pre-scanning process targeting the physiological tissue, multiple scan images can be generated.
[0035] The first key metric parameter refers to the medical information reflected in the current frame image, which can be used to assist in locating the optimal observation location of the lesion.
[0036] The first key metric parameter may specifically include: the length of the target physiological tissue, the volume of the target physiological tissue, the narrowing rate of the target physiological tissue boundary, the major / minor diameter of the target physiological tissue, the area of the target physiological tissue, and the image signal intensity of the target physiological tissue. It may also include the integrity of the sign, the clarity of the sign, the number of signs, the confidence level of the sign, and the severity of the sign. Furthermore, it may include the integrity of the lesion, the clarity of the lesion, the number of lesions, the confidence level of the lesion, the degree of the lesion, and the distribution of the lesion.
[0037] S120: When a new image is acquired during the pre-scanning operation, the second key metric parameter of the new image is compared with the first key metric parameter to obtain a comparison result.
[0038] In this context, a new image refers to an image scanned after the current frame. For example, when a pre-scan begins, the first frame obtained from the pre-scan of the target physiological tissue is the current frame, and the second frame is a new image obtained from the pre-scan operation.
[0039] The second key metric parameter refers to the medical information reflected in the new image. This medical information, combined with the medical information reflected in the current frame image, can accurately locate the position of the lesion.
[0040] The second key metric parameter may specifically include: the length of the target physiological tissue, the volume of the target physiological tissue, the narrowing rate of the target physiological tissue boundary, the major / minor diameter of the target physiological tissue, the area of the target physiological tissue, and the image signal intensity of the target physiological tissue. It may also include the integrity of the sign, the clarity of the sign, the number of signs, the confidence level of the sign, and the severity of the sign. Furthermore, it may include the integrity of the lesion, the clarity of the lesion, the number of lesions, the confidence level of the lesion, the degree of the lesion, and the distribution of the lesion.
[0041] It is understandable that key metric parameters in the same dimension may have different values in images from different frames. When comparing the second key metric parameter of a new image with the first key metric parameter of the current frame image, the second key metric parameter and the first key metric parameter should be compared as values under the same key metric parameter.
[0042] For example, the first key metric is the image signal intensity 50 of the target physiological tissue in the current frame image, and the second key metric is the image signal intensity 100 of the target physiological tissue in the new image. The image signal intensity 50 is compared with the image signal intensity 100, and the value 100 that is closer to the standard image signal intensity of the target physiological tissue is selected as the comparison result. This image signal intensity 100 is the obtained comparison result.
[0043] Furthermore, since multiple frames of images are scanned during the pre-scanning process, in some implementations, the second key metric parameter of each new image is compared with the previously determined comparison result, until the final comparison result is obtained.
[0044] For example, a complete processing procedure might be as follows: When the first frame image is scanned, this first frame image is the current frame image. The first key metric parameter of this first frame image is obtained. When the second frame image is scanned, this second frame image is the new image. The first key metric parameter of the first frame image is compared with the second key metric parameter of the second frame image to obtain a first comparison result. When the third frame image is scanned, this third frame image is the new image, and the second key metric parameter of this third frame image is compared with the first comparison result to obtain a second comparison result. This comparison is repeated until the key metric parameters of all scanned frames have been compared, resulting in the final comparison result.
[0045] In addition, in some implementations, after obtaining all key metric parameters in a pre-scan, the key metric parameters of all frame images can be compared, and the key metric parameter values that meet the conditions can be selected as the final comparison result.
[0046] S130: Based on the comparison results, cache at least one set of key metric parameters as target key metric parameters.
[0047] Since there can be multiple first and second key metrics, comparing the first and second key metrics can yield comparison results across multiple dimensions. For example, if the first and second key metrics include the boundary narrowing rate of the target physiological tissue, the image signal intensity of the target physiological tissue, the clarity of the sign, and the lesion confidence, then the comparison results should include the comparison results of the boundary narrowing rate of the target physiological tissue, the comparison results of the image signal intensity of the target physiological tissue, the comparison results of the clarity of the sign, and the comparison results of the lesion confidence.
[0048] When selecting target key measurement parameters, at least one set of key measurement parameters can be selected from multiple key measurement parameters based on the comparison results, and these target key measurement parameters can be cached. For example, in the example above, the parameter value of the comparison result corresponding to the image signal intensity of the target physiological tissue is selected as the parameter value of the image signal intensity in the target key measurement parameters, and the parameter value of the comparison result corresponding to the clarity of the sign is selected as the parameter value of the clarity of the sign in the target key measurement parameters.
[0049] S140: During the user's retrace operation, when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters, the user is prompted that the current retrace position is the target observation position.
[0050] The retrace operation refers to the scanning operation after the pre-scan operation has ended. Specifically, the retrace operation can be a scanning operation in retrace mode, a scanning operation in the opposite direction to the pre-scan operation, or a scanning operation in other preset modes.
[0051] In some implementations, the key metric parameters of the retrace image obtained by the retrace operation can be matched with the target key metric parameters. If the match is successful, the retrace position corresponding to the retrace image of the successfully matched key metric parameter is determined as the target observation position.
[0052] In some implementations, if the key metric parameter value of the retrace image is within the range of the target key metric parameter, it can be determined that the key metric parameter of the retrace image corresponding to the retrace operation is successfully matched with the target key metric parameter.
[0053] This application provides a method for lesion observation and localization based on scanned images. It acquires the first key metric parameter of the current frame image during a pre-scan operation. When a new image is acquired during the pre-scan operation, the second key metric parameter of the new image is compared with the first key metric parameter to obtain a comparison result. Since key metric parameters can assist in lesion observation location, by comparing key metric parameters of different frames in the pre-scan operation, a better comparison result can be selected, which is the optimal key metric parameter. Based on the comparison result, at least one set of key metric parameters is cached as target key metric parameters. Then, during the user's retracement operation, when the key metric parameter of the retracement image matches the target key metric parameter, the user is prompted that the current retracement position is the target observation position. Thus, it achieves automated determination of lesion feature observation areas, which not only improves the accuracy of lesion feature observation area determination but also reduces the number of scans and improves scanning efficiency.
[0054] In some implementations, the process of obtaining key metric parameters may include: extracting key metric parameters from the image to be identified using a key metric parameter extraction model to obtain key metric parameters; wherein the image to be identified includes the current frame image and / or the new image; and the key metric parameters include a first key metric parameter and / or a second key metric parameter.
[0055] Among them, the key metric parameter extraction model refers to an artificial intelligence model that can be used to extract key metric parameters. This key metric parameter extraction model can be a deep learning neural network model or a probabilistic graphical model used for image segmentation.
[0056] In some implementations, a model can be extracted using key metric parameters to segment the current frame image and / or a new image, and then the features of the segmented image can be measured to obtain a first key metric parameter and / or a second key metric parameter.
[0057] In other implementations, the key metric parameter extraction model can be used to directly process the current frame image and / or the new image to obtain the first key metric parameter and / or the second key metric parameter.
[0058] In some implementations, the key measurement parameters include at least a first type of parameter; the first type of parameter includes at least one of the following: length of the target physiological tissue, volume of the target physiological tissue, boundary narrowing rate of the target physiological tissue, major / minor axis of the target physiological tissue, area of the target physiological tissue, and image signal intensity of the target physiological tissue; the key measurement parameters include a first key measurement parameter and / or a second key measurement parameter.
[0059] The target physiological tissue refers to the physiological tissue scanned during the pre-scan and retrace operations. The first type of parameters indicates the parameters of the target physiological tissue, including its length, volume, boundary narrowing rate, major / minor axis, area, and image signal intensity.
[0060] Among them, the boundary stenosis rate refers to the degree of narrowing of the boundary of the target physiological tissue. For example, when the target physiological tissue is the carotid artery, if the carotid artery contains plaque, then the boundary stenosis rate of the target physiological tissue is the degree of narrowing of the carotid artery in non-plaque locations.
[0061] In some implementations, the key metrics also include a second type of parameters. The second type of parameters includes at least one of the following: completeness of signs, clarity of signs, number of signs, confidence level of signs, and severity of signs; and / or the second type of parameters includes at least one of the following: completeness of lesions, clarity of lesions, number of lesions, confidence level of lesions, severity of lesions, and distribution of lesions.
[0062] Among these, signs refer to the specific physical manifestations of a disease or pathological change in clinical practice. A lesion is an abnormal change in the body's tissues or cells under the influence of pathogenic factors, usually manifesting as structural or functional abnormalities. The observation location determined based on the second type of parameters is more helpful for users in the clinical observation of lesions.
[0063] The first key metric parameter may include a first type of parameter and / or a second type of parameter, and the second key metric parameter may include a first type of parameter and / or a second type of parameter.
[0064] Figure 2 A flowchart illustrating the implementation of a lesion observation and localization method based on scanned images, according to another embodiment of this application, is shown. Figure 2 As shown, with Figure 1 The difference in the illustrated embodiment is that, in this embodiment, after step S130, step S210 is also included. Specifically:
[0065] S210: If a target image frame is determined based on the target key metric parameters, then the target image frame is displayed.
[0066] In some implementations, the target image frame determined based on the target key metric parameter can be the image frame containing the same key metric parameter as the target key metric parameter, or it can be the image frame containing the key metric parameter within the floating range corresponding to the target key metric parameter.
[0067] The target image frame can be one of all the frames scanned in the pre-scan operation. In some implementations, some frames may have a key metric parameter that matches the target key metric parameter, while others may not. Therefore, when selecting the target image frame, the key metric parameters of multiple frames scanned in the pre-scan operation can be evaluated based on the target key metric parameter to obtain the target image frame.
[0068] In some implementations, since the target key metric parameters include multiple key metric parameters with different dimensions, when determining the target image frame based on the target key metric parameters, primary and secondary metric parameters can be selected from the target key metric parameters. The key metric parameters of each frame image are evaluated according to the weights corresponding to the primary and secondary metric parameters, and the frame image containing the key metric parameter with the highest score is determined as the target image frame.
[0069] In some implementations, a preset evaluation model can be used to evaluate the key metric parameters of each frame image to obtain the target image frame.
[0070] In some implementations, the target key metric parameters include at least a first value of the physiological tissue corresponding to the pre-scan operation; the key metric parameters of the retrace image include at least a second value of the physiological tissue corresponding to the retrace operation.
[0071] The process described above, in which the user performs a retrace operation, prompts the user that the current retrace position is the target observation position when the key metric parameter of the retrace image corresponding to the retrace operation matches the target key metric parameter, may include: during the user's retrace operation, when the first value matches the second value, prompting the user that the current retrace position is the target observation position.
[0072] The first value refers to the parameter value of the target key metric obtained from the pre-scan of the target physiological tissue. The second value refers to the parameter value of the key metric of the retrace image obtained from the retrace operation of the target physiological tissue.
[0073] There can be multiple first and second values. In some implementations, the first and second values are values in the same dimension, such as the first and second values being the image signal intensity values of the target physiological tissue.
[0074] In some implementations, during the user's retrace operation, a retrace image frame is obtained by scanning at each retrace position. Based on this retrace image frame, a second value of the key metric parameter corresponding to that retrace position can be obtained. If the second value is within the fluctuation range of the first value in the same dimension, it is determined that the second value matches the first value, and the user is prompted that the current retrace position is the target observation position.
[0075] In some implementations, the target key metric parameter is the key metric parameter corresponding to the best observation frame image in the pre-scan operation. The process described above, where, during the user's retrace operation, when the key metric parameter of the retrace image corresponding to the retrace operation matches the target key metric parameter, prompting the user that the current retrace position is the target observation position, may include: during the user's retrace operation, when the key metric parameter of the retrace image corresponding to the retrace operation matches the target key metric parameter, prompting the user that the current retrace position is the optimal observation position.
[0076] In this embodiment, if the target key metric parameter is the same as the key metric parameter corresponding to the best observation frame image in the pre-scan operation, then it indicates that the target key metric parameter is the key metric parameter for the most suitable observation position. Therefore, when the key metric parameter of the retrace image corresponding to the retrace operation matches the target key metric parameter, the user is prompted that the current retrace position is the optimal observation position. This optimal observation position can be the position where physiological tissue is observed most clearly, most three-dimensionally, and with the largest number of lesions.
[0077] Therefore, by matching the key metric parameters of the target with the key metric parameters of the retrace image corresponding to the retrace operation, the optimal observation location of physiological tissue can be quickly and accurately located.
[0078] In addition, the target key metric parameter can also be the key metric parameter corresponding to the best sharpness, or the key metric parameter corresponding to the maximum lesion integrity, etc. This target key metric parameter can be selected based on the dimension to be observed. By matching the determined target key metric parameter with the key metric parameters of the retrace image corresponding to the retrace operation, the optimal observation position in the corresponding dimension to be observed can be determined.
[0079] For example, the target key metric parameter can be the key metric parameter corresponding to the optimal sharpness. Based on matching the target key metric parameter with the key metric parameter of the retrace image corresponding to the retrace operation, the retrace position corresponding to the key metric parameter of the retrace image that matches the target key metric parameter can be determined as the observation position of the optimal sharpness of the target physiological tissue.
[0080] Please see Figure 3 , Figure 3 This illustration shows a schematic diagram of a lesion observation and localization device based on scanned images, according to an embodiment of this application. In this embodiment, the lesion observation and localization device based on scanned images includes units used for performing... Figures 1 to 2 The steps in the corresponding embodiments. Please refer to the details. Figures 1 to 2 The relevant descriptions in the corresponding embodiments are shown below. For ease of explanation, only the parts relevant to this embodiment are shown. See also... Figure 3 The lesion observation and localization device based on scanned images includes: an acquisition module 301, a matching module 302, a storage module 303, and a prompting module 304. Specifically:
[0081] The acquisition module 301 is used to acquire the first key metric parameter of the current frame image in the pre-scan operation;
[0082] The matching module 302 is used to compare the second key metric parameter of the new image with the first key metric parameter when the pre-scanning operation acquires a new image, and obtain a comparison result;
[0083] Storage module 303 is used to cache at least one set of key metric parameters as target key metric parameters based on the comparison result;
[0084] The prompting module 304 is used to prompt the user that the current retrace position is the target observation position when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters during the user's retrace operation.
[0085] In one embodiment of this application, the acquisition module 301 described above can be used to perform:
[0086] The key metric parameters are extracted from the image to be identified using a key metric parameter extraction model. The image to be identified includes the current frame image and / or the new image. The key metric parameters include a first key metric parameter and / or a second key metric parameter.
[0087] In one embodiment of this application, the aforementioned key measurement parameters include at least a first type of parameter;
[0088] The first type of parameters includes at least one of the following: length of the target physiological tissue, volume of the target physiological tissue, boundary narrowing rate of the target physiological tissue, major / minor axis of the target physiological tissue, area of the target physiological tissue, and image signal intensity of the target physiological tissue;
[0089] The key metrics include a first key metric and / or a second key metric.
[0090] In one embodiment of this application, the aforementioned key measurement parameters further include a second type of parameter;
[0091] The second type of parameters includes at least one of the following: completeness of signs, clarity of signs, number of signs, confidence level of signs, and severity of signs; and / or
[0092] The second type of parameters includes at least one of the following: lesion integrity, lesion clarity, number of lesions, lesion confidence, lesion severity, and lesion distribution.
[0093] In one embodiment of this application, the lesion observation and localization device based on scanned images further includes:
[0094] The display module is used to display the target image frame if the target image frame is determined based on the target key metric parameters.
[0095] In one embodiment of this application, the aforementioned key metric parameters of the target include at least a first value of the physiological tissue corresponding to the pre-scan operation; the key metric parameters of the retrace image include at least a second value of the physiological tissue corresponding to the retrace operation.
[0096] The above-mentioned prompt module 304 can be used to execute:
[0097] During the user's retrace operation, when the first value matches the second value, the user is prompted that the current retrace position is the target observation position.
[0098] In one embodiment of this application, the aforementioned target key metric parameter is the key metric parameter corresponding to the best observation frame image in the pre-scanning operation;
[0099] The aforementioned prompt module 304 can also be used to execute:
[0100] During the user's retrace operation, when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters, the user is prompted that the current retrace position is the optimal observation position.
[0101] The lesion observation and localization device based on scanned images proposed in this embodiment realizes the automatic determination of the lesion feature observation area, which can not only improve the accuracy of determining the lesion feature observation area, but also reduce the number of scans and improve scanning efficiency.
[0102] It is understandable that the improvements and specific implementation methods related to this application have already been... Figures 1 to 2 The corresponding embodiments are described in detail. In specific implementation, it can be... Figures 1 to 2 Based on the corresponding embodiments, let Figure 3 The embodiments provide units and / or modules in the lesion observation and localization device based on scanned images to perform the steps in the above method embodiments, so they will not be repeated here.
[0103] Figure 4 This is a structural block diagram of an ultrasonic scanning device provided in an embodiment of this application. Figure 4 As shown, the ultrasound scanning device 4 in this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40, such as a program for a lesion observation and localization method based on scanned images. When the processor 40 executes the computer program 42, it implements the steps in the various embodiments of the lesion observation and localization method based on scanned images described above, for example... Figures 1 to 2 The steps shown are as follows. Alternatively, the processor 40 may implement the above steps when executing the computer program 42. Figure 3 The functions of each unit in the corresponding embodiments are described. Please refer to the following for details. Figure 3 The relevant descriptions in the corresponding embodiments are not repeated here.
[0104] For example, the computer program 42 can be divided into one or more units, which are stored in the memory 41 and executed by the processor 40 to complete this application. The one or more units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 42 in the ultrasound scanning device 4. For example, the computer program 42 can be divided into a determining unit, a display unit, a first execution unit, and a second execution unit, each with its specific functions as described above.
[0105] The ultrasound scanning device may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of the ultrasound scanning device 4 and does not constitute a limitation on the ultrasound scanning device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, the ultrasound scanning device may also include input / output devices, network access devices, buses, etc.
[0106] The processor 40 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.
[0107] The memory 41 can be an internal storage unit of the ultrasound scanning device 4, such as a hard disk or memory of the ultrasound scanning device 4. The memory 41 can also be an external storage device of the ultrasound scanning device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the ultrasound scanning device 4. Furthermore, the memory 41 can include both internal and external storage units of the ultrasound scanning device 4. The memory 41 is used to store the computer program and other programs and data required by the ultrasound scanning device. The memory 41 can also be used to temporarily store data that has been output or will be output.
[0108] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for lesion observation and localization based on scanned images, characterized in that, include: Obtain the first key metric parameter of the current frame image in the pre-scan operation; When a new image is acquired during the pre-scanning operation, the second key metric parameter of the new image is compared with the first key metric parameter to obtain a comparison result; Based on the comparison results, at least one set of key metrics parameters should be cached as target key metrics parameters. During the user's retrace operation, when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters, the user is prompted that the current retrace position is the target observation position.
2. The lesion observation and localization method based on scanned images according to claim 1, characterized in that, The steps for obtaining key metric parameters include: The key metric parameters are extracted from the image to be identified using a key metric parameter extraction model. The image to be identified includes the current frame image and / or the new image. The key metric parameters include a first key metric parameter and / or a second key metric parameter.
3. The lesion observation and localization method based on scanned images according to claim 1, characterized in that, The key metric parameters include at least the first type of parameters; The first type of parameters includes at least one of the following: length of the target physiological tissue, volume of the target physiological tissue, boundary narrowing rate of the target physiological tissue, major / minor axis of the target physiological tissue, area of the target physiological tissue, and image signal intensity of the target physiological tissue; The key metrics include a first key metric and / or a second key metric.
4. The lesion observation and localization method based on scanned images according to claim 3, characterized in that, The key metric parameters also include a second type of parameters; The second type of parameters includes at least one of the following: completeness of signs, clarity of signs, number of signs, confidence level of signs, and severity of signs; and / or The second type of parameters includes at least one of the following: lesion integrity, lesion clarity, number of lesions, lesion confidence, lesion severity, and lesion distribution.
5. The lesion observation and localization method based on scanned images according to any one of claims 1 to 4, characterized in that, After the step of caching at least one set of key metric parameters as target key metric parameters based on the comparison result, the method further includes: If a target image frame is determined based on the target key metric parameters, then the target image frame is displayed.
6. The lesion observation and localization method based on scanned images according to claim 1, characterized in that, The target key metric parameters include at least a first value of the physiological tissue corresponding to the pre-scan operation; the key metric parameters of the retrace image include at least a second value of the physiological tissue corresponding to the retrace operation. During the user's retrace operation, when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters, the user is prompted that the current retrace position is the target observation position, including: During the user's retrace operation, when the first value matches the second value, the user is prompted that the current retrace position is the target observation position.
7. The lesion observation and localization method based on scanned images according to claim 1, characterized in that, The target key metric parameter is the key metric parameter corresponding to the best observation frame image in the pre-scanning operation; During the user's retrace operation, when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters, the user is prompted that the current retrace position is the target observation position, including: During the user's retrace operation, when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters, the user is prompted that the current retrace position is the optimal observation position.
8. A lesion observation and localization device based on scanned images, characterized in that, include: The acquisition module is used to acquire the first key metric parameters of the current frame image in the pre-scan operation; The matching module is used to compare the second key metric parameter of the new image with the first key metric parameter when the pre-scan operation acquires a new image, and obtain a comparison result; The storage module is used to cache at least one set of key metric parameters as target key metric parameters based on the comparison results; The prompting module is used to prompt the user that the current retrace position is the target observation position when the key metric parameters of the retrace image corresponding to the retrace operation match the target key metric parameters during the user's retrace operation.
9. An ultrasonic scanning device, characterized in that, include: The device includes a memory, a processor, and a computer program stored in the memory and executable on the ultrasound scanning device, wherein the processor executes the computer program to implement the steps of the lesion observation and localization method based on scanned images as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the lesion observation and localization method based on scanned images as described in any one of claims 1 to 7.