Ultrasonic image processing method and device and ultrasonic equipment

Abstract

The invention relates to an ultrasonic image processing method and device and ultrasonic equipment. The method comprises the following steps: acquiring multi-frame ultrasonic image data of a to-be-scanned object in a preoperative holding breathing state, and reconstructing based on the multi-frame ultrasonic image data to obtain a three-dimensional ultrasonic image; obtaining a target real-time ultrasonic image in the operation of the object to be scanned, and determining a corresponding reference ultrasonic section from the three-dimensional ultrasonic image based on the target real-time ultrasonic image; and registering the target real-time ultrasonic image with the reference ultrasonic section to obtain a first image. By means of the method, breathing compensation of the target real-time ultrasonic image can be achieved, the requirement for keeping the specific breathing state in the patient examination process is lowered, the detection efficiency is improved, and the image accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical image processing, in particular to an ultrasound image processing method and device. BACKGROUND

[0002] Ultrasound imaging has the advantages of real-time, no radiation, low cost, etc., so it is widely used as the preferred guidance method for many minimally invasive surgeries. However, the ultrasound image has defects such as insufficient resolution, which limits the accuracy and reliability of the ultrasound image in clinical application. In order to obtain more comprehensive anatomical information and functional information, different modal images can be registered, for example, two-dimensional ultrasound image data is registered with corresponding anatomical structures in another modal medical image. However, in ultrasound-guided interventional surgery, the respiratory motion of the patient will cause the position of the target organ to change, resulting in the ultrasound image being constantly changing. The displacement, rotation and deformation of the target organ caused by the respiratory motion will greatly interfere with the registration of the ultrasound image and other modal images, and the prior art does not provide a solution specifically for the organ displacement problem caused by respiratory motion. SUMMARY

[0003] Therefore, it is necessary to provide an ultrasound image processing method, device and ultrasound equipment aiming at the above technical problems.

[0004] The first aspect of the embodiments of the present application provides an ultrasound image processing method, comprising: acquiring a plurality of frames of ultrasound image data of a to-be-scan object in a preoperative breath-holding state, and reconstructing a three-dimensional ultrasound image based on the plurality of frames of ultrasound image data; acquiring a target real-time ultrasound image of the to-be-scan object in surgery, determining a corresponding reference ultrasound section from the three-dimensional ultrasound image based on the target real-time ultrasound image; and registering the target real-time ultrasound image and the reference ultrasound section to obtain a first image.

[0005] In some embodiments of the first aspect, the method further comprises: acquiring CT volume data or MR volume data of the to-be-scan object before surgery, and registering a corresponding reference CT section or a reference MR section from the CT volume data or MR volume data based on the target real-time ultrasound image or the first image.

[0006] In some embodiments of the first aspect, the method further comprises: superimposing the reference CT section or the reference MR section and the first image based on a user's operation instruction to obtain a second image.

[0007] In some embodiments of the first aspect, the method further comprises: acquiring a user's selection instruction, and displaying the first image and the reference CT section or the first image and the reference MR section side by side based on the selection instruction.

[0008] In some embodiments of the first aspect, reconstructing the three-dimensional ultrasound image based on the multi-frame ultrasound image data comprises: reconstructing the three-dimensional ultrasound image based on magnetic navigation information of the multi-frame ultrasound image data.

[0009] In some embodiments of the first aspect, determining the corresponding reference ultrasound section from the three-dimensional ultrasound image based on the target real-time ultrasound image comprises: determining the corresponding reference ultrasound section from the three-dimensional ultrasound image based on magnetic navigation information of the target real-time ultrasound image.

[0010] In some embodiments of the first aspect, the method further comprises: inputting the first image, the reference CT section and the reference MR section into an image analysis model, and outputting an analysis result, the analysis result comprising registration accuracy between images and / or image quality score.

[0011] In some embodiments of the first aspect, the method further comprises: automatically determining, based on the analysis result and preset display conditions, whether to display the first image and the reference CT section or to display the first image and the reference MR section.

[0012] A second aspect of the embodiments of the present application provides an ultrasound image processing device, comprising: an acquisition unit configured to acquire a three-dimensional ultrasound image of a subject to be scanned in a preoperative breath-holding state and a target real-time ultrasound image of the subject to be scanned during surgery; a determination unit configured to determine a corresponding reference ultrasound section from the three-dimensional ultrasound image based on the target real-time ultrasound image; and a registration unit configured to register the target real-time ultrasound image and the corresponding reference ultrasound section to obtain a first image.

[0013] In some embodiments of the second aspect, the device further comprises: the acquisition unit is further configured to acquire CT volume data or MR volume data of the subject to be scanned before surgery; and the registration unit is further configured to register the target real-time ultrasound image or the first image from the CT volume data or the MR volume data to obtain a corresponding reference CT section or a reference MR section.

[0014] A third aspect of the embodiments of the present application provides an ultrasound device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned ultrasound image processing method when executing the computer program.

[0015] The ultrasonic image processing method, device and ultrasonic equipment have the following advantages: the core of the present application is that a plurality of ultrasonic image data in a preoperative breath-holding state are acquired, a three-dimensional ultrasonic image is generated by reconstruction, a corresponding reference ultrasonic section is determined from the three-dimensional ultrasonic image based on a real-time ultrasonic image of a target in an operation, and registration is performed, so that the real-time ultrasonic image of the target is compensated for respiration, the requirement that a patient maintains a specific respiration state during an examination process is reduced, a user does not need to artificially judge whether a respiration phase is appropriate, the detection efficiency is improved, and the accuracy of an image is improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 The flowchart of the ultrasonic image processing method provided by the embodiment of the present application is shown in the figure.

[0018] Figure 2 Another flowchart of the ultrasonic image processing method provided by the embodiment of the present application is shown in the figure.

[0019] Figure 3 The schematic diagram of image display of the ultrasonic image processing method provided by the embodiment of the present application is shown in the figure.

[0020] Figure 4 The structural block diagram of the ultrasonic image processing device provided by the embodiment of the present application is shown in the figure.

[0021] Figure 5 The structural block diagram of the ultrasonic equipment provided by the embodiment of the present application is shown in the figure.

[0022] Figure 6 The structural block diagram of the computer equipment provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the present application more clear, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0024] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or sets thereof.

[0025] In the description of the present application and the appended claims, the terms "first", "second", "third", etc. are used merely to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0026] In the present application, the reference "one embodiment" or "some embodiments" means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in further some embodiments" and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0027] In view of this, the present application provides an ultrasound image processing method, which can be applied to the field of medical image processing, especially in intraoperative ultrasound guided surgery, to realize registration of target real-time ultrasound images and preoperative images and provide users with more comprehensive lesion information.

[0028] In order to illustrate the technical solutions of the present application, specific embodiments are described below.

[0029] Please refer to Figure 1 , Figure 1 A flowchart of an ultrasound image processing method provided by an embodiment of the present application is shown, which can be applied to an ultrasound device.

[0030] Specifically, the method comprises the following steps:

[0031] S102, a plurality of frames of ultrasound image data of a to-be-scan object in a preoperative breath-holding state is acquired, and a three-dimensional ultrasound image is reconstructed based on the plurality of frames of ultrasound image data.

[0032] In actual operation, the patient can be required to hold his breath at the time of preoperative examination, and the object to be scanned is scanned by the ultrasound probe from multiple angles and multiple directions to obtain a series of two-dimensional ultrasound image data. These image data need to contain sufficient spatial information to ensure the accuracy of subsequent three-dimensional reconstruction. In a preferred embodiment, based on the magnetic navigation information of the multi-frame ultrasound image data, the multi-frame ultrasound image data is reconstructed to generate a three-dimensional ultrasound image. Specifically, a magnetic navigation sensor is installed on the ultrasound probe, and the spatial position and direction information of the probe is recorded synchronously at each frame of ultrasound image acquisition. The accurate position and direction of each two-dimensional image in three-dimensional space can be determined by using these magnetic navigation information, so that these two-dimensional images can be correctly placed in the three-dimensional space, and a more complete three-dimensional ultrasound image can be reconstructed by an interpolation algorithm. The interpolation algorithm includes cubic interpolation, trilinear interpolation, RBF interpolation, etc.

[0033] S104, acquiring a target real-time ultrasound image of the object to be scanned in surgery, and determining a corresponding reference ultrasound section from the three-dimensional ultrasound image based on the target real-time ultrasound image.

[0034] During the operation, the user uses the ultrasound probe to scan the object to be scanned of the patient in real time to obtain a target real-time ultrasound image in the current state. The target real-time ultrasound image can be a current real-time ultrasound image frozen by the user, or a standard section meeting the requirements automatically recognized by the ultrasound device during the intraoperative real-time scanning process. The specific recognition process can be directly completed by using a model (CNN classification model, target detection model). The target real-time ultrasound image is used to reflect the real-time state of the patient's tissues and organs during the operation. The corresponding reference ultrasound section can be determined from the three-dimensional ultrasound image based on the magnetic navigation information of the target real-time ultrasound image. Specifically, by the spatial position relationship between the magnetic navigation information of the target real-time ultrasound image and each section in the three-dimensional ultrasound image, the section closest to the position and direction of the target real-time ultrasound image is determined as the reference ultrasound section.

[0035] S106, registering the target real-time ultrasound image and the reference ultrasound section to obtain a first image.

[0036] In the registration process, the respiratory displacement of the target real-time ultrasound image is corrected by the reference ultrasound section in the preoperative breath-holding state, the spatial transformation relationship (such as translation, rotation, nonlinear deformation) between the target real-time ultrasound image and the reference ultrasound section is solved, and then the displacement of the tissue in the target real-time ultrasound image caused by respiration is eliminated through the transformation. The registration algorithm such as rigid registration, affine registration, nonlinear registration can be used, and the preferred is the rigid registration based on the feature points, or the rigid registration of the feature points combined with the rigid registration of the magnetic navigation, to eliminate the deformation of the target real-time ultrasound image caused by respiration. Specifically, based on the reference ultrasound section, the non-rigid registration algorithm can be used to adjust each pixel point of the target real-time ultrasound image through the feature point matching and image deformation technology, to generate a first image. The registration process takes the preoperative breath-holding ultrasound image as the reference, and eliminates the influence of respiration on the target real-time ultrasound image.

[0037] In some embodiments of the present application, the method further comprises a step S108 of acquiring CT volume data or MR volume data of the object to be scanned before the operation, and registering the corresponding reference CT section or reference MR section from the CT volume data or MR volume data based on the target real-time ultrasound image or the first image.

[0038] The CT volume data or MR volume data of the to-be-scanned object collected in the preoperative planning stage can be a three-dimensional CT image or a three-dimensional MR image reconstructed from a plurality of CT image data or a plurality of MR image data collected, and can provide clearer anatomical structure information than an ultrasound image. Based on the target real-time ultrasound image or the first image, a dynamic spatial mapping relationship between the target real-time ultrasound image or the first image and the preoperative CT / MR volume data can be established by using a point-to-point registration, a surface-to-surface registration, a point-to-surface registration, or an AI automatic algorithm. When the target real-time ultrasound image or the first image changes with the movement of the probe, the corresponding section in the CT / MR volume data can be quickly called and automatically aligned through the mapping relationship. Specifically, in the point-to-point registration, a set of homologous anatomical landmark points (such as a blood vessel bifurcation point or a lesion edge corner point) are extracted from the target real-time ultrasound image at a certain moment or the first image at a certain moment and the preoperative CT / MR volume data. By using the spatial correspondence between the point sets, a transformation matrix of the target real-time ultrasound image at a certain moment or the first image at a certain moment and the preoperative CT / MR volume data is solved, a dynamic spatial mapping relationship between the target real-time ultrasound image and the preoperative CT / MR volume data is established, a reference CT section or a reference MR section corresponding to the target real-time ultrasound image is determined, and when the probe is moved or the transmission condition is changed, the target real-time ultrasound image or the corresponding first image will change. The landmark points in the ultrasound image are automatically tracked by using the ORB / FAST algorithm, the corresponding positions of the landmark points in the CT / MR volume data are synchronously calculated, the RANSAC algorithm is used to remove the drift of the mismatched points, and the transformation matrix is updated in real time. According to the updated transformation matrix, the corresponding section in the CT / MR volume data is extracted and aligned, and the ultrasound image and the reference CT section or the reference MR section are dynamically followed.

[0039] In some embodiments of the present application, the reference CT section or the reference MR section can be superimposed on the first image to obtain a second image based on the operation instruction of the user.

[0040] During the operation process, the user can superimpose the reference CT section or the reference MR section on the first image, or superimpose the first image on the reference CT section or the reference MR section.

[0041] In some embodiments of the present application, please refer to Figure 2 The method further includes the step S110 of acquiring a selection instruction of the user, and displaying the first image and the reference CT section or the first image and the reference MR section based on the selection instruction.

[0042] During the surgery, the user can select to view different types of images as needed, and the system will display the corresponding images according to the user's selection instructions. Specifically, the display image type can be freely selected based on a switching button or a separate control button. For example, the user can select to view the first image and the reference CT image at the same time, or to view the first image and the reference MR image at the same time, and display the target real-time ultrasound image (first image) after respiratory compensation, while displaying the images of other modalities, to provide the user with more comprehensive anatomical information and functional information. The first image and the reference CT section / reference MR section can also be displayed side by side. Reference Figure 3 The left image is the first image, and the right image is the reference CT section. This side-by-side display can help the user intuitively compare the differences between the target real-time ultrasound image and the images of other modalities.

[0043] In some embodiments of the present application, the method further comprises inputting the first image, the reference CT section, and the reference MR section into an image analysis model, and outputting an analysis result, the analysis result including the registration accuracy between images and / or the image quality score.

[0044] The image analysis model can be a neural network model based on deep learning, which can be used to automatically evaluate the registration accuracy between the first image and the reference CT section, and the registration accuracy between the first image and the reference MR section. Specifically, the displacement change between the structures of different modal images, or the Dice Similarity Coefficient (DSC), the Structural Similarity Index (SSIM), etc. can be calculated. The image analysis model can also be used to automatically evaluate the image quality score of the reference CT section and the reference MR section, and to score the quality of images of different modalities.

[0045] In some embodiments of the present application, the method further comprises automatically determining to display the first image and the reference CT section, or to display the first image and the reference MR section, based on the analysis result and a preset display condition. The ultrasound device can automatically select the registration image with better display effect based on the registration accuracy between images and / or the image quality score, and in combination with the preset display condition. For example, when the registration accuracy of the reference CT section with respect to the first image is higher than the registration accuracy of the reference MR section with respect to the first image, the first image and the reference CT section are automatically displayed preferentially. The first image and the reference MR section can also be automatically displayed preferentially when the image quality score of the key anatomical structure (ROI region) in the reference MR section is higher. The preset display condition can also be determined based on the weighted sum of the registration accuracy between images and the image quality score, and can be set according to user needs.

[0046] The above method can realize real-time registration of the intraoperative target real-time ultrasound image and the corresponding ultrasound image in the preoperative breath-holding state, compensate for the influence of respiratory motion on the intraoperative target real-time ultrasound image, and simultaneously display the corresponding reference CT image or reference MR image and the target real-time ultrasound image (or the first image), thereby providing more comprehensive lesion information for the user and improving the accuracy and safety of the operation. In addition, the image analysis model is used to evaluate the registration accuracy and / or image quality score between images, and the optimal image combination is automatically selected for display according to the preset display condition, thereby reducing the requirement for the user's image judgment experience, automatically providing the best image for the user, and improving the work efficiency.

[0047] It should be understood that, although Figure 1 and 2 the steps in the flowcharts are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, Figure 1 and 2 at least some of the steps can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with other steps or steps or stages in other steps.

[0048] As Figure 4 The structure diagram of the ultrasound image processing device 200 provided by the embodiment of the application is shown, which is used to realize real-time registration of intraoperative ultrasound images and preoperative data, and improve the accuracy and efficiency of medical diagnosis.

[0049] The ultrasound image processing device can include:

[0050] An acquisition unit configured to acquire a three-dimensional ultrasound image of a subject to be scanned in a preoperative breath-holding state and a target real-time ultrasound image of the subject to be scanned during an operation;

[0051] A determination unit configured to determine a corresponding reference ultrasound section from the three-dimensional ultrasound image based on the target real-time ultrasound image;

[0052] A registration unit configured to register the target real-time ultrasound image and the corresponding reference ultrasound section to obtain a first image.

[0053] In some embodiments of the present application, the acquisition unit comprises an image data acquisition module and an image reconstruction module. The image data acquisition module is configured to acquire a plurality of frames of ultrasound image data of the subject in a preoperative breath-holding state. When the ultrasound probe is used to scan the subject, the subject is required to maintain the breath-holding state to reduce the influence of respiratory motion on image quality. The image data acquisition module can acquire ultrasound image data at multiple angles and multiple positions to ensure that the acquired data comprehensively covers the target region. The image reconstruction module is connected to the image data acquisition module and is configured to reconstruct a three-dimensional ultrasound image based on the plurality of frames of ultrasound image data. The module uses a voxel reconstruction algorithm to convert a sequence of two-dimensional ultrasound images into three-dimensional volume data. The image reconstruction module can also reconstruct a three-dimensional ultrasound image from the plurality of frames of ultrasound image data based on magnetic navigation information of the plurality of frames of ultrasound image data. The magnetic navigation information includes position and attitude information of the ultrasound probe during scanning. The spatial position relationship of each frame of image is recorded by a magnetic navigation system to improve the accuracy of three-dimensional reconstruction.

[0054] The image data acquisition module is also configured to acquire a target real-time ultrasound image of the subject during surgery. Specifically, the ultrasound image can be captured in real time during the surgery or diagnosis process to ensure the timeliness of the image. The image data acquisition module can be integrated with a magnetic navigation system to record the spatial position information of each frame of real-time image.

[0055] In some embodiments of the present application, the determination unit is connected to the acquisition module, specifically to the image data acquisition module and the image reconstruction module, and is configured to determine a corresponding reference ultrasound section from the three-dimensional ultrasound image based on the target real-time ultrasound image. Specifically, the corresponding reference ultrasound section can be determined from the three-dimensional ultrasound image based on the magnetic navigation information of the target real-time ultrasound image. The determination unit can determine the corresponding reference ultrasound section in the pre-reconstructed three-dimensional ultrasound image through the magnetic navigation information of the target real-time ultrasound image.

[0056] The registration unit is connected to the image data acquisition module and the determination unit and is configured to register the target real-time ultrasound image and the reference ultrasound section to obtain a first image. The module uses a non-rigid registration algorithm to accurately align the target real-time ultrasound image and the reference ultrasound section through feature point matching, image deformation and other techniques to generate a registered first image. The image registration process takes into account factors such as respiratory motion to ensure the accuracy of the registration result.

[0057] In some embodiments of the present application, the acquisition unit is also configured to acquire CT volume data or MR volume data of the subject before surgery.

[0058] In some embodiments of the present application, the registration unit is also configured to register a corresponding reference CT section or a reference MR section from the CT volume data or the MR volume data based on the target real-time ultrasound image or the first image.

[0059] Specifically, based on the target real-time ultrasound image or the first image, a dynamic spatial mapping relationship between the target real-time ultrasound image or the first image and the preoperative CT / MR volume data can be established by using a point-to-point registration, a surface-to-surface registration, a point-to-surface registration, or an AI automatic algorithm, and when the target real-time ultrasound image or the first image changes with the movement of the probe, the corresponding section in the CT / MR volume data can be quickly called and automatically aligned through the mapping relationship.

[0060] In some embodiments of the present application, the ultrasound image processing device can further include a user interaction module, a display module, an image analysis module, and an automatic display control module.

[0061] The user interaction module is used to obtain a selection instruction of a user. The module provides various interaction modes such as touch screen, mouse, keyboard, etc., allowing the user to select to display different image combination results according to clinical needs. The user interaction module has an intuitive operation interface, supports human-computer interaction modes such as gesture operation and voice control, and improves the operation convenience.

[0062] The display module is connected to the image data acquisition module, the determination unit, the registration unit, and the user interaction module, and is used to display the first image and the reference CT section or the first image and the reference MR section side by side based on the selection instruction of the user. The display module displays the above-mentioned image combination side by side, which is convenient for the user to intuitively compare and analyze. The display module uses a high-resolution medical display screen and supports multi-window display.

[0063] The image analysis module is connected to the registration unit and is used to input the first image, the reference CT section, and the reference MR section into an image analysis model and output an analysis result. The analysis result includes the registration accuracy between images and / or the image quality score. The image analysis module includes an image analysis model and uses a deep learning algorithm to automatically evaluate the registration accuracy between images and the image quality score, providing auxiliary diagnosis information for the user.

[0064] The automatic display control module is connected to the image analysis module and the display module and is used to automatically determine to display the first image and the reference CT section or to display the first image and the reference MR section based on the analysis result and a preset display condition. The module intelligently selects the optimal display content according to the image quality score, the registration accuracy, and other indicators, reducing the judgment burden of the user. The automatic display control module can automatically adjust the display strategy according to different clinical scenarios, for example, preferentially displaying the first image and the reference MR image in some tissue regions and preferentially displaying the first image and the reference CT image in other regions.

[0065] During the operation of the ultrasound image processing apparatus, first, the image data acquisition module acquires a plurality of ultrasound image data of a subject in a preoperative breath-holding state, and the image reconstruction module generates a three-dimensional ultrasound image. Meanwhile, the preoperative CT or MR volume data can also be acquired. During the operation, the image data acquisition module continuously acquires a target real-time ultrasound image, the determination unit finds a matching reference ultrasound section from the three-dimensional ultrasound image according to the target real-time ultrasound image, the registration unit registers the target real-time ultrasound image with the reference ultrasound section to obtain a first image, and compensates for the influence of intraoperative respiration on the target real-time ultrasound image. Similarly, a matching CT or MR reference section can also be found, and after registration with the target real-time ultrasound image, it is displayed to provide more imaging information for the user.

[0066] According to the analysis result obtained by the image analysis module, the automatic display control module determines the display image combination according to the analysis result. The user can also manually select the display content through the user interaction module, for example, manually selecting and displaying the first image and the reference CT section side by side, which facilitates the user to compare and analyze.

[0067] In some embodiments of the present application, the magnetic navigation system of the device has high-precision position tracking capability, and can record the six-degree-of-freedom position information of the ultrasound probe in real time. The magnetic navigation system includes a magnetic field generator and a receiver, the magnetic field generator generates a changing magnetic field, and the receiver is installed on the ultrasound probe to calculate the probe position and attitude by measuring the magnetic field change.

[0068] Through the real-time registration function of the device, the user can quickly register the target real-time ultrasound image with the reference ultrasound section in the preoperative breath-holding state during the operation, compensate for the influence of respiratory motion on intraoperative real-time ultrasound imaging, and simultaneously register and display other modal images with the target real-time ultrasound image, so as to facilitate the doctor to obtain more comprehensive structural information.

[0069] It should be noted that, for the convenience and brevity of description, the specific working process of the ultrasound image processing apparatus 200 described above can refer to Figures 1 to 2 the corresponding process of the method, which will not be repeated here.

[0070] As Figure 5 shown, it is a schematic diagram of an ultrasound device 300 provided by an embodiment of the present application. Specifically, the ultrasound device 300 can include a memory and a processor, the memory stores a computer program, and the processor implements the steps in the ultrasound image processing method embodiment when executing the computer program.

[0071] The computer program can be segmented into one or more modules / units, one or more modules / units are stored in the memory and executed by the processor to complete the present application. One or more units / modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the ultrasound device 300.

[0072] The memory can be an internal storage unit of the ultrasound device 300, for example, a hard disk or an internal memory of the ultrasound device 300. The memory can also be an external storage device of the ultrasound device 300, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the ultrasound device 300. Further, the memory can include both the internal storage unit and the external storage device of the ultrasound device 300. The memory is used to store the computer program and other programs and data required by the ultrasound device 300. The memory can also be used to temporarily store data that has been output or will be output.

[0073] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), ready programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0074] The ultrasound device 300 can include, but is not limited to, the memory, the processor. Those skilled in the art can understand that the ultrasound device 300 can further include other components, for example, the ultrasound device 300 can further include an input / output device, a network access device, a bus, etc. Figure 5 The ultrasound device 300 is only an example and does not constitute a limitation on the ultrasound device 300, and can include more or fewer components than the illustration, or combine certain components, or different components, for example, the ultrasound device 300 can also include an input / output device, a network access device, a bus, etc.

[0075] As Figure 6As shown, the computer device provided by the embodiment of the present application can be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement the ultrasound image processing method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0076] Those skilled in the art can understand that, Figure 6 The structure shown in the above embodiment is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can comprise more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0077] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not contradict each other, they should be considered within the scope of the present application.

[0078] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that, for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. An ultrasound image processing method, characterized in that, The method includes: Acquire multiple frames of ultrasound image data of the subject under preoperative breath-holding state, and reconstruct a three-dimensional ultrasound image based on the multiple frames of ultrasound image data; Acquire the real-time ultrasound image of the target object during surgery, and determine the corresponding reference ultrasound section from the three-dimensional ultrasound image based on the real-time ultrasound image of the target. The first image is obtained by registering the real-time ultrasound image of the target with the reference ultrasound section.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the preoperative CT or MR body data of the object to be scanned, and based on the real-time ultrasound image of the target or the first image, register the corresponding reference CT or MR section from the CT or MR body data.

3. The method according to claim 2, characterized in that, The method further includes: based on the user's operation instructions, superimposing the reference CT section or the reference MR section on the first image to obtain a second image.

4. The method according to claim 2, characterized in that, The method further includes: obtaining a user's selection instruction, and displaying the first image and the reference CT section, or the first image and the reference MR section, side by side based on the selection instruction.

5. The method according to claim 1, characterized in that, The process of reconstructing a three-dimensional ultrasound image based on the multi-frame ultrasound image data includes: The three-dimensional ultrasound image is generated by reconstructing the multi-frame ultrasound image data based on the magnetic navigation information of the multi-frame ultrasound image data.

6. The method according to claim 5, characterized in that, The step of determining the corresponding reference ultrasound section from the three-dimensional ultrasound image based on the target real-time ultrasound image includes: Based on the magnetic navigation information of the real-time ultrasound image of the target, the corresponding reference ultrasound section is determined from the three-dimensional ultrasound image.

7. The method according to claim 2, characterized in that, The method further includes: inputting the first image, the reference CT section, and the reference MR section into an image analysis model, and outputting analysis results, wherein the analysis results include the registration accuracy between images and / or image quality scores.

8. The method according to claim 7, characterized in that, Based on the analysis results and preset display conditions, the system automatically determines whether to display the first image and the reference CT section, or to display the first image and the reference MR section.

9. An ultrasonic image processing device, characterized in that, The device includes: The acquisition unit is used to acquire a three-dimensional ultrasound image of the subject to be scanned in a preoperative breath-holding state and a real-time ultrasound image of the subject to be scanned during the operation. The determining unit is used to determine a corresponding reference ultrasound section from the three-dimensional ultrasound image based on the real-time ultrasound image of the target; A registration unit is used to register the real-time ultrasound image of the target with the corresponding reference ultrasound section to obtain a first image.

10. The apparatus according to claim 9, characterized in that, The acquisition unit is also used to acquire the preoperative CT or MR data of the object to be scanned. The registration unit is also used to register a corresponding reference CT section or reference MR section from the CT volume data or MR volume data based on the real-time ultrasound image of the target or the first image.

11. An ultrasonic device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes a computer program, it implements the steps of the method of any one of claims 1 to 8.

Images