Breast prone ultrasound imaging method, device, equipment and storage medium

Abstract

The present invention relates to the field of medical imaging technology, and discloses a method, apparatus, device, and storage medium for prone breast ultrasound imaging, which are applied to prone breast ultrasound equipment. The method comprises: acquiring multiple pre-scan images of target breast tissue, the multiple pre-scan images including images acquired from multiple different angles of the target breast tissue; respectively identifying skin boundaries in the multiple pre-scan images; based on the skin boundaries identified in each pre-scan image, respectively acquiring target ultrasound emission angles perpendicular to the skin boundaries; and during formal scanning and imaging, emitting ultrasound perpendicular to the target breast tissue based on the target ultrasound emission angles to acquire an ultrasound image. The present invention can ensure that the ultrasound emission direction is as perpendicular to the target breast tissue as possible during prone breast ultrasound imaging, thereby improving ultrasound image quality.

Description

Technical Field

[0001] The present invention relates to the technical field of medical imaging, and in particular to a method, device, equipment and storage medium for prone breast ultrasound imaging. Background Art

[0002] Prone breast ultrasound is an imaging procedure used to evaluate breast tissue. Compared to traditional supine ultrasound, prone ultrasound, performed with the patient lying prone with the breast hanging naturally, provides a different perspective for observing breast tissue structure. This provides clearer images, particularly of lesions deep within the chest wall or lymph nodes in the axillary area.

[0003] Advantages of this imaging modality include but are not limited to:

[0004] More natural breast position: In the prone position, the breasts are not pressed against the chest wall and can hang more naturally on the examination table, helping to better display the internal structure of the breast.

[0005] Reduced artifacts: Due to gravity, breast tissue is distributed more naturally, which may help reduce artifacts caused by compression and improve image quality.

[0006] Good visualization of deep tissues: Especially for areas close to the chest wall and axillary lymph nodes, the prone position can provide better views and resolution.

[0007] The angle of ultrasound incidence directly impacts image quality and diagnostic accuracy. The strongest reflected signal is obtained when ultrasound waves are incident perpendicularly (90 degrees) to the interface, as this minimizes energy loss in the reflected wave. Perpendicular incidence also simplifies analysis of reflected waves by reducing complexities caused by angle variations, such as refraction and scattering. Furthermore, in some cases, perpendicular incidence can improve image resolution.

[0008] During prone breast ultrasound imaging, the breast tissue naturally drapes when the patient is prone, and its shape and position differ significantly from those in the conventional supine position. This makes it difficult to standardize the ultrasound probe's angle of incidence. In other words, achieving vertical ultrasound incidence during prone breast ultrasound imaging is difficult. Summary of the Invention

[0009] In view of this, the present invention provides a method, apparatus, device and storage medium for prone breast ultrasound imaging to solve the problem that prone breast ultrasound imaging is difficult to achieve vertical incidence.

[0010] In a first aspect, the present invention provides a method for prone breast ultrasound imaging, which is applied to a prone breast ultrasound device, wherein the prone breast ultrasound device includes an ultrasound probe, and the method includes:

[0011] Acquiring a plurality of pre-scan images of target breast tissue, the plurality of pre-scan images comprising images acquired from a plurality of different angles of the target breast tissue;

[0012] Respectively identifying skin boundaries in the plurality of pre-scanned images;

[0013] Based on the skin boundary identified in each pre-scan image, respectively acquiring a target ultrasound emission angle perpendicular to the skin boundary;

[0014] During formal scanning and imaging, ultrasound waves perpendicular to the target breast tissue are emitted based on the target ultrasound emission angle to acquire ultrasound images.

[0015] In an optional embodiment, the respectively identifying and obtaining skin boundaries in the plurality of pre-scanned images includes:

[0016] performing contrast enhancement processing on the pre-scanned image to obtain a first image;

[0017] Performing edge processing on the first image to obtain a second image; the edge processing is edge enhancement filtering processing or edge extraction processing;

[0018] Binarizing the second image to obtain a binary image;

[0019] Extracting connected regions from the binary image, and filtering the extracted connected regions based on region size, position, and / or shape to obtain remaining connected regions;

[0020] Boundary curve fitting is performed on the boundary points of the remaining connected areas to obtain a continuous skin boundary line.

[0021] In an optional embodiment, the respectively identifying and obtaining skin boundaries in the plurality of pre-scanned images includes:

[0022] Using a deep learning model, performing breast region recognition on the pre-scan image;

[0023] Contour extraction is performed on the identified breast area to obtain a skin boundary curve.

[0024] In an optional embodiment, during the formal scanning imaging, emitting ultrasound perpendicular to the target breast tissue based on the target ultrasound emission angle includes:

[0025] determining an ultrasound probe angle based on the target ultrasound emission angle corresponding to each of the pre-scan images;

[0026] According to the determined angle of the ultrasound probe, the ultrasound probe is adjusted and an ultrasound beam is emitted.

[0027] In an optional embodiment, during the formal scanning imaging, emitting ultrasound perpendicular to the target breast tissue based on the target ultrasound emission angle includes:

[0028] determining a beam incident angle for a first target stage during a formal scanning process based on the target ultrasound emission angle corresponding to the pre-scan image;

[0029] The first target stage is determined according to the scanning angle, the starting scanning angle of the first target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next pre-scan image of the pre-scan image.

[0030] In an optional embodiment, determining the beam incident angle of the first target stage in the formal scanning process based on the target ultrasound emission angle corresponding to the pre-scan image includes:

[0031] Using the target ultrasound emission angle corresponding to the pre-scan image as the beam reference angle of the first target stage;

[0032] In the first target phase of the formal scanning process, a first ultrasound image acquired at a first moment is acquired;

[0033] identifying a skin boundary in the first ultrasound image;

[0034] Based on the skin boundary in the first ultrasound image, the beam reference angle is fine-tuned to obtain the beam incident angle, which is used as the beam incident angle at the second moment of the first target stage; the second moment is after the first moment and before the new beam incident angle is obtained.

[0035] In an optional embodiment, the breast prone ultrasound imaging method further includes:

[0036] Acquire a first target ultrasound image; the first target ultrasound image is a formal ultrasound image acquired at a third moment in the formal scanning process, or is the pre-scan image;

[0037] Acquire breast area, skin boundary, and various tissue recognition results in the first target ultrasound image;

[0038] Starting from the skin boundary, dividing the breast area into a plurality of depth zones according to depth;

[0039] Based on the tissue identification result, obtaining tissue distribution information within each of the depth partitions;

[0040] Determining corresponding gains according to the tissue distribution information of the depth partitions, and forming a target time gain compensation curve;

[0041] During the second target phase of the formal scanning process, adjusting the gain of the ultrasound signal reception according to the target time gain compensation curve until the next phase;

[0042] Among them, if the first target ultrasound image is the formal ultrasound image collected at the third moment, the starting moment of the second target stage is after the third moment, and the ending moment is when or after the new target time gain compensation curve is acquired; if the first target ultrasound image is the pre-scan image, the second target stage is determined according to the scanning angle, and the starting scanning angle of the second target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next frame of the pre-scan image.

[0043] In an optional embodiment, in the second target phase during the formal scanning process, adjusting the gain of ultrasound signal reception according to the target time gain compensation curve includes:

[0044] If the first target ultrasound image is a pre-scan image, determining a starting point position of the gain according to a position of a skin boundary in a second ultrasound image, where the second ultrasound image is a formal ultrasound image acquired before the current moment;

[0045] The gain of ultrasonic signal reception is adjusted according to the starting position of the gain and the target time gain compensation curve.

[0046] In an optional embodiment, the breast prone ultrasound imaging method further includes:

[0047] Acquire a second target ultrasound image and a probe posture; wherein the second target ultrasound image is the third ultrasound image acquired at the fourth moment during the formal scanning process, and correspondingly, the probe posture is the probe posture during the formal scanning process; or the second target ultrasound image is the pre-scan image, and correspondingly, the probe posture is the probe posture during the pre-scan process or the probe posture during the formal scanning process;

[0048] determining a distance between the probe and the skin based on a skin boundary in the second target ultrasound image and a probe posture;

[0049] According to the preset subcutaneous target imaging depth and the distance, the transmitting focus point parameters and the receiving focus point parameters of the third target stage during the formal scanning process are determined; if the second target ultrasound image is the third ultrasound image, the third target stage includes one or more moments after the fourth moment; if the second target ultrasound image is the pre-scan image, the third target stage is determined according to the scanning angle, and the starting scanning angle of the third target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next frame of the pre-scan image.

[0050] In a second aspect, the present invention provides a prone breast ultrasound imaging device, which is applied to a prone breast ultrasound device. The prone breast ultrasound device includes an ultrasound probe, and the device includes:

[0051] a pre-scan image acquisition module, configured to acquire a plurality of pre-scan images of target breast tissue, wherein the plurality of pre-scan images include images acquired from a plurality of different angles of the target breast tissue;

[0052] a first skin boundary recognition module, configured to respectively recognize skin boundaries in the plurality of pre-scanned images;

[0053] a target ultrasound emission angle acquisition module, configured to respectively acquire a target ultrasound emission angle perpendicular to the skin boundary based on the skin boundary identified in each of the pre-scan images;

[0054] The ultrasound imaging module is used to transmit ultrasound perpendicular to the target breast tissue based on the target ultrasound transmission angle during formal scanning and imaging, and to acquire an ultrasound image.

[0055] In a third aspect, the present invention provides a breast prone ultrasound imaging device, comprising:

[0056] an imaging assembly, the imaging assembly comprising an ultrasound probe;

[0057] cups, which hold breast tissue;

[0058] Probe drive assembly, used to drive the probe to adjust the angle;

[0059] A support assembly, used to support the imaging assembly, the cup and the probe drive assembly;

[0060] The memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the breast prone ultrasound imaging method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0061] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the breast prone ultrasound imaging method of the first aspect or any corresponding embodiment thereof.

[0062] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the breast prone ultrasound imaging method of the first aspect or any corresponding embodiment thereof.

[0063] The prone breast ultrasound imaging method, apparatus, device, and storage medium provided by the embodiments of the present invention obtain the skin boundaries of the target breast tissue at multiple angles by pre-scanning the target breast tissue to be examined, that is, the external structure of the target breast tissue. This can determine the ultrasound emission angle in the formal scanning phase so that the ultrasound emission direction is as perpendicular as possible to the target breast tissue, thereby improving the quality of the ultrasound image and further enhancing the accuracy of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0065] Figure 1 is a schematic diagram of the imaging process of prone breast ultrasound imaging according to an embodiment of the present invention;

[0066] Figure 2 1 is a flow chart of a method for prone breast ultrasound imaging according to an embodiment of the present invention;

[0067] Figure 3 is a schematic diagram of a pre-scan imaging angle according to an embodiment of the present invention;

[0068] Figure 4 It is a schematic diagram of an ultrasound image;

[0069] Figure 5 According to an embodiment of the present invention Figure 4 One of the schematic diagrams of performing boundary recognition on an ultrasound image shown;

[0070] Figure 6 According to an embodiment of the present invention Figure 4 The second schematic diagram of performing boundary recognition on an ultrasound image shown;

[0071] Figure 7 is a schematic diagram of the probe angle according to an embodiment of the present invention;

[0072] Figure 8 is one of the schematic diagrams of fine-tuning the beam incident angle according to an embodiment of the present invention;

[0073] Figure 9 FIG2 is a second schematic diagram of fine-tuning the beam incident angle according to an embodiment of the present invention;

[0074] Figure 10 is a structural block diagram of a breast prone ultrasound imaging device according to an embodiment of the present invention;

[0075] Figure 11 1 is a schematic diagram of the hardware structure of a prone breast ultrasound imaging device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0076] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0077] like Figure 1 As shown, the imaging process of prone breast ultrasound imaging is that the ultrasound probe 102 rotates around the breast tissue 101 once, and multiple frames of ultrasound images are collected during the rotation process (103 indicates a single frame of ultrasound image).

[0078] According to an embodiment of the present invention, an embodiment of a method for prone breast ultrasound imaging is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of executable computer instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0079] In this embodiment, a breast prone ultrasound imaging method is provided, which can be used in a prone breast ultrasound device. The prone breast ultrasound device includes an ultrasound probe, Figure 2 FIG. 1 is a flow chart of a method for prone breast ultrasound imaging according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0080] Step S201 : Acquire multiple pre-scan images of target breast tissue, where the multiple pre-scan images include images acquired from multiple different angles of the target breast tissue.

[0081] Specifically, if Figure 1 and Figure 3As shown, during prone breast ultrasound imaging, the breast tissue to be examined is placed in cup 301, and the ultrasound probe 102 (referred to as the probe) rotates around cup 301, and thus around the breast tissue. The images captured by the ultrasound probe 102 at different rotation angles are the images captured at the different angles described above.

[0082] The breast prone ultrasound imaging method provided by the embodiment of the present invention has an imaging process divided into two stages: a pre-scan stage and a formal scanning stage. In the pre-scan stage, after the breast tissue is accurately positioned, the ultrasound probe is controlled to rotate around the breast tissue. During this process, a small number of pre-scan images are collected by sparse sampling. The number of pre-scan images can be 4, for example, from Figure 3 Images are captured from four angles 302 as shown. The number of pre-scan images can also be 8, 16, 32, etc., and is not limited here. The specific number of pre-scan images can be determined based on actual conditions such as imaging accuracy and equipment processing performance. The purpose of capturing pre-scan images is to obtain structural information (such as external contour information and internal tissue distribution information) of the target patient's breast tissue. This provides a basis for personalized setting of scanning parameters in the subsequent main scan phase, thereby improving the quality of ultrasound images captured during the main scan phase.

[0083] Step S202: respectively identifying and obtaining skin boundaries in the plurality of pre-scanned images.

[0084] Specifically, a deep learning algorithm or a traditional filtering algorithm can be used to identify the skin boundary in the pre-scan image.

[0085] The following examples illustrate how to use deep learning algorithms and traditional filtering algorithms to identify skin boundaries in pre-scanned images.

[0086] In some optional specific implementations, step S202, namely, respectively identifying the skin boundaries in the plurality of pre-scanned images, includes:

[0087] Step S2021: Use a deep learning model to perform breast area recognition on the pre-scan image.

[0088] Specifically, the deep learning model can be, for example, U-Net or Attention U-Net. U-Net is a special convolutional neural network (CNN). Its name comes from the U-shaped structure of the network architecture. The main features of U-Net include: 1. Encoder-decoder structure: U-Net consists of a downsampling path (encoder) and an upsampling path (decoder). The encoder is used to capture the contextual information of the image, while the decoder is used for precise positioning. 2. Skip connection: In U-Net, there is a direct connection between the encoder and the decoder, which is called a "skip connection." These connections allow the decoder layer to access high-resolution feature maps, which is very important for accurate pixel-level predictions. Attention U-Net is an improvement to the original U-Net architecture that enhances the performance of the model by introducing an attention mechanism. The attention mechanism helps the network focus on important areas and ignore irrelevant background information, thereby improving segmentation accuracy.

[0089] During breast area recognition, the pre-scan image can be input into the deep learning model, and the deep learning model can output a pixel mask of the breast area.

[0090] Step S2022: extract the contour of the identified breast area to obtain a skin boundary curve.

[0091] like Figure 4 The pre-scanned image shown in FIG has a relatively obvious boundary feature. Therefore, Figure 5 and Figure 6 As shown, the deep learning segmentation network (i.e., deep learning model) can easily distinguish the skin boundary.

[0092] Specifically, you can use findContours() or cv2.Canny + cv2.approxPolyDP in OpenCV (Open Source Computer Vision Library) to extract contours and obtain the skin boundary curve. The skin boundary is the uppermost contour of the breast area or the boundary line closest to the probe.

[0093] Before using a deep learning model for skin boundary recognition, it must be trained. This training process involves collecting a large number of breast tissue ultrasound images (not necessarily of the target breast tissue or the target patient) as samples. Then, using human expert annotation or semi-automatic auxiliary tools, pixel-level segmentation and annotation of the breast regions in these breast tissue ultrasound images are performed to form breast region mask labels. Finally, the deep learning model is trained using breast tissue ultrasound image samples, using Dice Loss + BCE Loss (Dice Loss can also be called Dice Loss or Diss Loss, and BCE Loss is Binary Cross Entropy Loss) as the loss function to quantify the deviation between the model's recognition results and the breast region mask labels.

[0094] An embodiment of the present invention provides a skin boundary recognition method based on a deep learning semantic segmentation model (such as the U-Net series). The model is trained with the breast tissue region as the target class. The model outputs a breast region mask and extracts the skin boundary segment along the mask's upper edge or the edge closest to the probe. This robust method is suitable for automatic recognition scenarios involving diverse body shapes, varying image quality, and complex tissue structures.

[0095] Skin boundary recognition will serve as the basis for setting the imaging parameters of the ultrasound equipment in the subsequent formal scanning stage. The embodiment of the present invention can accurately identify the skin boundary in the pre-scan image through the above method, providing a reliable basis for the subsequent accurate setting of imaging parameters.

[0096] In some other optional specific implementations, step S202, namely, respectively identifying the skin boundaries in the plurality of pre-scanned images, includes:

[0097] Step S202a: performing contrast enhancement processing on the pre-scanned image to obtain a first image.

[0098] Specifically, histogram equalization (HE) or contrast limited adaptive histogram equalization (CLAHE) can be used to enhance the contrast of the pre-scan image to highlight the differences in tissue structure and boundaries.

[0099] Step S202b: performing edge processing on the first image to obtain a second image; the edge processing is edge enhancement filtering processing or edge extraction processing.

[0100] Specifically, high-pass filtering or the Laplacian operator can be applied to enhance high-frequency edges in the image and highlight areas with structural mutations. Alternatively, algorithms such as the Canny edge detection algorithm can be used to extract edges from the image.

[0101] Step S202c: binarize the second image to obtain a binary image.

[0102] Specifically, the Otsu (ie, Otsu's method) adaptive threshold algorithm or local adaptive threshold can be used to binarize the second image (ie, the edge map) to separate the highlight structure from the background.

[0103] In other embodiments, before binarization, contrast projection (such as taking the maximum brightness of each column or row, or performing a weighted operation) can be used to enhance the structural features of the image, highlight the highlighted areas or boundaries, and thus assist in determining candidate boundary areas.

[0104] Step S202d: extracting connected components from the binary image, and filtering the extracted connected components based on region size, position and / or shape to filter out pseudo boundaries and obtain remaining connected components, namely candidate boundary regions.

[0105] Step S202e: performing boundary curve fitting on the boundary points of the remaining connected regions to obtain a continuous skin boundary line. Specifically, the boundary curve fitting can be performed by applying a Hough line / curve detection algorithm or spline interpolation.

[0106] In an embodiment of the present invention, a traditional filtering algorithm is provided to identify skin boundaries in pre-scanned images. Specifically, by performing contrast enhancement, edge detection, and binarization on the ultrasound image, combined with traditional image processing processes such as region screening and curve fitting, the highlighted boundary line at the junction of the skin and the ultrasound coupling medium is extracted.

[0107] Step S203: Based on the skin boundary identified in each pre-scan image, a target ultrasound emission angle perpendicular to the skin boundary is obtained. The perpendicularity mentioned here does not need to be absolutely perpendicular, and close to perpendicularity is also acceptable.

[0108] Specifically, in embodiments of the present invention, the optimal angle of incidence can be estimated based on the tangent or normal direction of the skin boundary (for example, the tangent or normal direction corresponding to the point on the skin boundary closest to the probe). Specifically, the normal direction of the skin boundary in the pre-scan image can be used as the target ultrasound transmission angle. This is merely an example; angles determined by other geometric methods that ensure the ultrasound transmission direction is perpendicular to the target breast tissue can also be used as the target ultrasound transmission angle.

[0109] Step S204 , during formal scanning and imaging, ultrasound waves are emitted perpendicular to the target breast tissue based on the target ultrasound emission angle to acquire an ultrasound image.

[0110] Adjusting the ultrasound transmission angle can be achieved by adjusting the angle of the ultrasound probe or by adjusting the direction of the ultrasound beam. Of course, probe angle adjustment and beam angle adjustment can also be combined. The following examples illustrate adjusting the ultrasound probe angle and beam angle respectively.

[0111] In some optional specific implementations, step S204, i.e., transmitting ultrasound perpendicular to the target breast tissue based on the target ultrasound transmission angle during the formal scanning imaging, includes:

[0112] Step S2041: Determine the ultrasound probe angle based on the target ultrasound transmission angle corresponding to each pre-scan image. For example, the ultrasound probe angle can be determined by calculating the average or weighted average of multiple target ultrasound transmission angles (weighted by the number of occurrences of each target ultrasound transmission angle). Alternatively, the target ultrasound transmission angle with the highest number of occurrences can be selected as the ultrasound probe angle, or the median of the target ultrasound transmission angles can be used as the ultrasound probe angle.

[0113] Step S2042: Adjust the ultrasonic probe according to the determined ultrasonic probe angle and transmit an ultrasonic beam.

[0114] In the embodiment of the present invention, Figure 7 As shown, based on the extracted skin boundary, the angle between the probe and the skin surface in each direction is calculated by fitting the tangent direction 701 of the boundary curve ( Figure 7 The angle between the tangent direction 701 of the skin boundary curve and the probe surface 702 is calculated, and a comprehensive "standard skin angle vector" is derived based on this. This vector is used to calculate the globally optimal probe angle (corresponding to 703 in the figure) to achieve maximum vertical incidence, improving acoustic coupling and initial image quality.

[0115] Specifically, the ultrasound system automatically adjusts to the calculated optimal probe angle by controlling the probe drive structure (e.g., a robotic arm) and locks it to ensure stability and consistency in subsequent scans. This angle serves as the baseline angle of incidence for the entire inspection process and remains unchanged throughout all subsequent image acquisitions during the formal scanning phase, ensuring imaging consistency, comparability, and reconstruction accuracy.

[0116] In some optional specific implementations, step S204, i.e., transmitting ultrasound perpendicular to the target breast tissue based on the target ultrasound transmission angle during the formal scanning imaging, includes:

[0117] Step S204a, determining a beam incident angle for a first target stage during a formal scanning process based on the target ultrasound emission angle corresponding to the pre-scan image;

[0118] Among them, the first target stage is determined according to the scanning angle, the starting scanning angle of the first target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next frame of the pre-scan image of the pre-scan image (the scanning angle of the first target stage may not include the scanning angle of the next frame of the pre-scan image of the pre-scan image).

[0119] Specifically, step S204a, i.e., determining the beam incident angle of the first target stage in the formal scanning process based on the target ultrasound emission angle corresponding to the pre-scan image, includes:

[0120] Step S204a1: Using the target ultrasound emission angle corresponding to the pre-scan image as the beam reference angle of the first target stage.

[0121] That is, during the main scan, if the scan angle is between the scan angles corresponding to two adjacent pre-scan images, the target ultrasound transmission angle corresponding to the earlier of the two adjacent pre-scan images is used as the beam reference angle. In other embodiments, the beam reference angle corresponding to the current main scan angle can also be estimated based on the target ultrasound transmission angle corresponding to the adjacent pre-scan image, for example, by interpolation.

[0122] Step S204a2: Acquire a first ultrasound image acquired at a first moment in the first target phase of the formal scanning process.

[0123] Step S204a3: identifying the skin boundary in the first ultrasound image.

[0124] Step S204a4: Fine-tune the beam reference angle based on the skin boundary in the first ultrasound image to obtain the beam incident angle, which serves as the beam incident angle at a second moment in the first target phase. For example, the normal direction of the point in the first ultrasound image at which the skin boundary is closest to the probe can be used as the final beam incident angle. The second moment is after the first moment and before the new beam incident angle is obtained.

[0125] Specifically, the beam incident angle can be fine-tuned based on the formal scan image of each frame as the beam incident angle when the next frame of image is captured, or the beam incident angle can be fine-tuned every few frames, that is, the beam incident angle can be fine-tuned based on the formal scan image of the current frame as the beam incident angle when the next few frames of image are captured.

[0126] In an embodiment of the present invention, during the formal scanning process, in order to adapt to problems such as the complex breast shape, large changes in skin curvature, and strong directionality of the organ's internal structure, the ultrasound equipment integrates a fine-level beam angle dynamic fine-tuning algorithm to compensate for the limitations of the fixed angle of the physical probe and achieve more flexible directional scanning control.

[0127] Specifically, see Figure 8 and Figure 9 First, the target ultrasound emission angle 802 estimated based on the pre-scan image is used as the beam reference angle. This angle is nearly perpendicular to the probe's emission surface 801 after angle adjustment. Then, the beam incident angle 803 is obtained after fine-tuning based on the final scan image. For convenience of representation, the fine-tuning angle is larger in the figure; the actual fine-tuning angle is generally smaller. The embodiment of the present invention automatically adjusts the beam angle within a certain range to improve the imaging effect of different curvature areas. As the geometric shape of various parts of the breast fluctuates slightly, the ultrasound device can fine-tune the beam emission angle within a small angle range of ±θ (the value range of θ can be, for example, 2° to 5°) near each scan line to ensure that the sound beam is always perpendicular or nearly perpendicular to the skin and target structure, thereby improving reflectivity and signal-to-noise ratio.

[0128] The prone breast ultrasound imaging method provided in this embodiment obtains the skin boundaries of the target breast tissue at multiple angles by pre-scanning the target breast tissue to be examined, that is, the external structure of the target breast tissue. This can then determine the ultrasound transmission angle during the main scanning phase, so that the ultrasound transmission direction is as perpendicular to the target breast tissue as possible, thereby improving the quality of the ultrasound image and further enhancing the accuracy of diagnosis.

[0129] In this embodiment of the present invention, the ultrasound transmission angle during the subsequent main scan is determined based on the skin boundary recognition results from the pre-scan image. Furthermore, during the main scan, dynamic gain adjustment (ATGC) and focus correction are also performed based on the skin boundary recognition results. Therefore, after obtaining the skin boundary recognition results from the pre-scan image, the ultrasound device can cache and structure them for easy access during the subsequent main scan.

[0130] The following example illustrates the method of gain determination and focus correction during the formal scanning phase.

[0131] In some optional specific embodiments, the method for prone breast ultrasound imaging further includes:

[0132] Step 1: Acquire a first target ultrasound image; the first target ultrasound image is a formal ultrasound image acquired at the third moment in the formal scanning process, or is the pre-scan image.

[0133] The third moment is one moment or multiple moments in the formal scanning process.

[0134] Step 2: Acquire the breast area, skin boundary, and various tissue recognition results in the first target ultrasound image.

[0135] Specifically, if the first target ultrasound image is a pre-scan image, then after the pre-scan image is obtained, the breast region, skin boundary, and various tissue recognition results can be identified therein. Breast region recognition and skin boundary recognition are described in detail in the above embodiments and will not be further elaborated here.

[0136] If the first target ultrasound image is a final scan image during the final scan, recognition is performed on the final scan image after acquisition to obtain breast region, skin boundary, and various tissue recognition results. The breast region and skin boundary recognition method for the final scan image can be found in the pre-scan image recognition process described in the above embodiment and will not be further described here.

[0137] Tissue recognition can be performed based on grayscale features. Deep learning models can also be used to generate tissue distribution maps. Specific tissue recognition results include fat, glandular, and / or connective tissue.

[0138] The following example illustrates how to identify tissue in a first target ultrasound image using a deep learning model.

[0139] First, the original first target ultrasound image is preprocessed (noise suppression and enhancement), including: Gaussian filtering or median filtering to remove speckle noise; contrast stretching and histogram equalization to enhance tissue boundary contrast; and normalization to unify the grayscale range for subsequent deep learning model processing.

[0140] Next, a tissue segmentation model is used for inference. A medical image segmentation model based on a convolutional neural network (CNN) is used to perform pixel-level classification of different tissue types in the image. Typical network architectures include U-Net, ResUNet, DeepLabv3+, or nnU-Net. The model input is a preprocessed ultrasound image, and the output is a multi-channel tissue probability map, where each channel represents the distribution probability of adipose tissue, glandular tissue, connective tissue, etc. The argmax operation is performed on the output to obtain the final tissue category mask.

[0141] Finally, based on the tissue mask, we quantitatively analyze the distribution of different tissue types within the image. We calculate the depth range (pixel index / mm) occupied by each tissue type within the image. We also mark the center and boundaries of each tissue type, and construct zoning zones (e.g., superficial, intermediate, deep) based on the depth of each tissue type.

[0142] Step 3: Starting from the skin boundary, the breast area is divided into a plurality of depth partitions according to the depth, for example, 5 or 8 partitions.

[0143] Step 4: Based on the tissue identification result, obtain tissue distribution information within each of the depth partitions.

[0144] Specifically, the main tissue type in the depth partition can be determined according to the image proportion in the depth partition.

[0145] Step 5: Determine corresponding gains according to the tissue distribution information of the depth partitions, and form a target time gain compensation curve.

[0146] Specifically, the gain corresponding to the depth partition can be determined according to the main tissue type in the depth partition. For example, the gain of each tissue type can be determined by referring to Table 1 below, that is, the gain of each partition can be determined:

[0147] Table 1 Gain adjustment recommendations for each tissue type

[0148]

[0149] Specifically, different tissue types attenuate sound waves to varying degrees, typically like this:

[0150] Fatty tissue: low attenuation, small gain required;

[0151] Glandular tissue, medium attenuation, requires medium gain;

[0152] Connective tissue / dense glands have high attenuation and require high gain.

[0153] Of course, when determining the gain of each depth partition, it is still necessary to combine the depth information. For example, the gain of each depth partition can be preset according to the depth information, and then adjusted according to the organization situation within the depth partition to obtain the final gain of the depth partition.

[0154] Once the gains for each depth partition are determined, the target time-gain compensation curve can be generated. Specifically, the gain values ​​for each depth partition can be interpolated into a complete TGC (Time-Gain Compensation) curve to obtain the target time-gain compensation curve.

[0155] The goal of TGC is to compensate for the attenuation of ultrasound signals as they propagate through tissue, ensuring relatively consistent brightness across the entire image at different depths. Traditional TGC adjustment often involves manually setting the gain for different depth segments with a slider, or using fixed linear or exponential compensation functions. In an embodiment of the present invention, by identifying tissue types at different depths within the image and taking into account the attenuation characteristics of the tissue itself, a personalized TGC curve is set for each depth segment. In other words, rather than simply increasing linearly with depth, a nonlinear preset is implemented based on the tissue absorption coefficient / attenuation characteristics.

[0156] In other embodiments, the gain of a depth zone may be determined not according to the primary tissue type within the depth zone, but by first determining the area proportion of each tissue type within the depth zone and the attenuation coefficient of each tissue type, then determining a weight value for each tissue type based on the area proportion, performing a weighted average of the attenuation coefficients based on the weight values, and finally determining the gain of the depth zone based on the attenuation coefficient obtained from the weighted average.

[0157] Step 6: In the second target phase of the formal scanning process, the gain of the ultrasound signal reception is adjusted according to the target time gain compensation curve until the next phase.

[0158] If the first target ultrasound image is the official ultrasound image acquired at the third moment, then the start time of the second target stage is after the third moment, and the end time is when or after the new target time gain compensation curve is acquired. That is, in this embodiment of the present invention, during the official scanning process, the target time gain compensation curve is updated once per stage. Each stage can have a duration of only one frame or multiple frames. Specifically, during the official scanning process, a target time gain compensation curve can be generated in real time based on the ultrasound image of the current frame, serving as the time gain compensation curve for the acquisition of the next ultrasound image frame. If time is insufficient, the target time gain compensation curve can also be used as the time gain compensation curve for the acquisition of the next ultrasound image frame, or even as the time gain compensation curve for the acquisition of an ultrasound image two frames later. Furthermore, during the official scanning process, a target time gain compensation curve can also be generated in real time based on the ultrasound image of the current frame, serving as the time gain compensation curve for the acquisition of multiple consecutive ultrasound images. In other words, a strategy of predicting the next n frames based on the previous frame is adopted.

[0159] If the first target ultrasound image is the pre-scan image, the second target stage is determined according to the scanning angle, and the starting scanning angle of the second target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next pre-scan image after the pre-scan image. For example, Figure 3 As shown, if pre-scan images are only collected for the four scanning angles of up, down, left and right during the pre-scan process, then during the formal scanning process, if the probe is rotated to the upper angle, the ultrasound image will be collected using the time gain compensation curve corresponding to the pre-scan image of that angle, and in the subsequent scanning process, the ultrasound image will be collected using the time gain compensation curve until the probe is rotated to the scanning angle of the next pre-scan image, such as the angle on the right, and the ultrasound image will be collected using the time gain compensation curve corresponding to the pre-scan image of that angle.

[0160] In summary, the embodiments of the present invention provide two methods for determining ultrasound receiver gain: one method determines gain based on pre-scan images, and the other method adjusts gain based on images acquired during the final scan. This method, which adjusts gain based on images acquired during the final scan, implements a dynamic adaptive time gain compensation (ATGC) mechanism, dynamically adjusting the gain curve of the scan line and optimizing grayscale representation and tissue contrast across the entire image.

[0161] In other embodiments, if the gain is determined based on the pre-scan image, in addition to the above-mentioned technical solution (when the main scanning angle is between the scanning angles of two adjacent pre-scan images, the time gain compensation curve remains unchanged), an ultrasound image between two adjacent scan images can be calculated by interpolation or other methods, and then a new time gain compensation curve can be determined based on the calculated ultrasound image. This allows the time gain compensation curve to be updated when the main scanning angle is between the scanning angles of two adjacent pre-scan images, thereby improving the imaging quality of the main scan image.

[0162] In some specific implementations, the above step 6, i.e., the second target stage in the formal scanning process, adjusting the gain of the ultrasound signal reception according to the target time gain compensation curve, includes:

[0163] In step 61, if the first target ultrasound image is a pre-scan image, the gain starting point is determined based on the location of the skin boundary in the second ultrasound image. The second ultrasound image is a formal ultrasound image acquired before the current moment. Specifically, the second ultrasound image can be the previous formal ultrasound image or a formal ultrasound image acquired one or more frames later.

[0164] If the first target ultrasound image is a pre-scan image, then considering that the angle of the probe in the formal scanning stage has changed relative to the pre-scan stage, that is, the posture of the probe has changed relative to the pre-scan stage, therefore, the distance between the probe and the skin boundary has changed, it is necessary to determine the starting position of the gain based on the skin interface in the ultrasound image collected in the formal scanning stage, thereby improving the accuracy of the gain starting position and thus improving the quality of the ultrasound image.

[0165] Of course, in some other embodiments, the starting position of the gain may also be determined according to the position of the skin boundary in the pre-scan image.

[0166] Step 62: Adjust the gain of ultrasonic signal reception according to the starting position of the gain and the target time gain compensation curve.

[0167] In addition, if the first target ultrasound image is a formal ultrasound image acquired at the third moment in the formal scanning process, the starting point of the gain can be determined directly based on the position of the skin boundary in the formal ultrasound image.

[0168] The above-mentioned technical solution for determining the target time gain compensation curve not only effectively compensates for the attenuation caused by the increase in depth during the transmission of sound waves during the imaging process, but also takes into account the different reflection characteristics caused by differences in tissue structure. In addition, the embodiment of the present invention also identifies the skin boundary recognition result based on real-time image analysis, thereby identifying the skin starting point of the scanning path and setting this position as the starting point of the TGC curve, that is, realizing dynamic adjustment of the starting position of the gain, rather than using a uniform distance from the probe surface to the breast tissue to fix the starting position of the gain. The embodiment of the present invention can avoid excessive gain in conditions containing uneven water media or when the probe is not close to the skin.

[0169] In addition, the ultrasound device in the embodiment of the present invention can also refer to the tissue distribution data (such as fat area, gland area, lesion area) obtained in the pre-scan stage, as well as the real-time echo intensity distribution trend, to perform adaptive slope fine-tuning in the deep part of the image, thereby realizing the linkage adjustment of the gain curve slope and tissue type.

[0170] In some optional specific embodiments, the method for prone breast ultrasound imaging further includes:

[0171] Step I: Acquire a second target ultrasound image and a probe posture; wherein the second target ultrasound image is the third ultrasound image acquired at the fourth moment during the formal scanning process, and correspondingly, the probe posture is the probe posture during the formal scanning process; or the second target ultrasound image is the pre-scan image, and correspondingly, the probe posture is the probe posture during the pre-scan process or the probe posture during the formal scanning process.

[0172] Step II: Determine the distance between the probe and the skin based on the skin boundary in the second target ultrasound image and the probe posture. Specifically, the distance can be a vertical distance or a distance along the beam emission direction.

[0173] Step III: determining the emission focus point parameters and the reception focus point parameters of the third target stage during the formal scanning process according to the preset subcutaneous target imaging depth and the distance.

[0174] Specifically, if the second target ultrasound image is the third ultrasound image, the third target stage includes one or more moments after the fourth moment. If the second target ultrasound image is the pre-scan image, the third target stage is determined based on the scan angle. The starting scan angle of the third target stage is the scan angle corresponding to the pre-scan image, and the ending scan angle is the scan angle of the pre-scan image immediately following the pre-scan image (the third target stage may not include the ending scan angle).

[0175] In this embodiment of the present invention, the distance between the probe and the skin is dynamically measured based on the probe's position and the location of the skin boundary, yielding real-time aqueous medium thickness. This parameter directly determines the path required for propagation from the probe surface to the skin's surface, providing a key reference for subsequent focus depth calibration. This embodiment of the present invention provides two methods for determining focus parameters: one based on pre-scan images and the other based on the final scan image.

[0176] Specifically, regarding the preset subcutaneous target imaging depth, the ultrasound device can set the subcutaneous target imaging depth (e.g., 5mm below the skin) based on the location of the tissue layer where the physician desires the clearest image, and use this as a fixed focusing target. Subsequently, based on the water thickness data (i.e., the distance), the device automatically calculates the focusing path from the probe to the preset subcutaneous target imaging depth, dynamically setting the transmit and receive focus parameters to ensure that the beam energy is accurately focused on this area.

[0177] In an embodiment of the present invention, to balance image stability and computational efficiency, the focus position can be updated frame by frame, or updated every n frames using a sliding window strategy. In areas where tissue changes are slow, a low-frequency update strategy is used to reduce resource consumption.

[0178] In an embodiment of the present invention, during the actual scanning phase, the ultrasound device dynamically adjusts the focus position for each image frame to ensure that key structures are in the optimal imaging focus area. The goal is to consistently maintain the focus at a specific depth below the skin (e.g., 5mm or 8mm), thereby achieving stable focused imaging of key superficial structures. To achieve this, the ultrasound device carefully adjusts the beam focusing parameters, taking into account factors such as the skin boundary location, aqueous media thickness (i.e., the distance between the probe and the skin boundary), and tissue structure distribution.

[0179] The dynamic fine-tuning of the beam direction and the dynamic fine-tuning of the focus depth mentioned in the above embodiments of the present invention can be used separately or in combination. That is to say, in a prone breast ultrasound imaging embodiment, only the dynamic fine-tuning of the beam direction can be applied, or only the dynamic fine-tuning of the focus depth can be applied, or both the dynamic fine-tuning of the beam direction and the dynamic fine-tuning of the focus depth can be applied simultaneously. In areas with significant curvature or edge structures, it is recommended to fine-tune the beam emission angle and the focus parameters in conjunction so that the focus always falls on the target depth, while offsetting the offset effect caused by the angle change, thereby ensuring imaging continuity and clarity.

[0180] Through the above method, the ultrasound device does not need to calculate tissue depth or automatically determine the imaging layer. Instead, it always performs focus positioning and adaptive adjustment around the preset subcutaneous depth, ensuring high consistency of imaging quality in key areas in complex scanning paths and improving diagnostic reliability.

[0181] In summary, the prone breast ultrasound imaging method provided by the embodiment of the present invention, in the formal image acquisition stage, based on the parameter template established in the pre-scan stage, combined with the real-time feedback mechanism, dynamically controls the gain curve, beam direction, focal depth, etc. during the image acquisition process, thereby improving imaging quality and consistency.

[0182] This embodiment also provides a prone breast ultrasound imaging device for implementing the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0183] This embodiment provides a breast prone ultrasound imaging device, which is applied to a prone breast ultrasound device, such as Figure 10 As shown, the device includes:

[0184] A pre-scan image acquisition module 1001 is configured to acquire multiple pre-scan images of target breast tissue, wherein the multiple pre-scan images include images acquired from multiple different angles of the target breast tissue;

[0185] A first skin boundary recognition module 1002 is configured to respectively recognize skin boundaries in the plurality of pre-scanned images;

[0186] a target ultrasound emission angle acquisition module 1003, configured to acquire a target ultrasound emission angle perpendicular to the skin boundary based on the skin boundary identified in each pre-scan image;

[0187] The ultrasound imaging module 1004 is configured to transmit ultrasound perpendicular to the target breast tissue based on the target ultrasound transmission angle during formal scanning and imaging, and acquire an ultrasound image.

[0188] In some optional implementations, the first skin boundary identification module 1002 includes:

[0189] an enhancement processing unit, configured to perform contrast enhancement processing on the pre-scanned image to obtain a first image;

[0190] an edge processing unit, configured to perform edge processing on the first image to obtain a second image; the edge processing may be edge enhancement filtering processing or edge extraction processing;

[0191] A binarization unit, configured to binarize the second image to obtain a binary image;

[0192] a connected region extraction and filtering unit, configured to extract connected regions from the binary image and filter the extracted connected regions based on region size, position and / or shape to obtain remaining connected regions;

[0193] The curve fitting unit is used to perform boundary curve fitting on the boundary points of the remaining connected areas to obtain a continuous skin boundary line.

[0194] In some optional implementations, the first skin boundary identification module 1002 includes:

[0195] an intelligent recognition unit, configured to perform breast region recognition on the pre-scan image using a deep learning model;

[0196] The contour extraction unit is used to extract the contour of the identified breast area to obtain a skin boundary curve.

[0197] In some optional embodiments, the ultrasound imaging module 1004 includes:

[0198] an ultrasound probe angle determination unit, configured to determine an ultrasound probe angle based on the target ultrasound emission angle corresponding to each of the pre-scan images;

[0199] The ultrasonic probe angle adjustment unit is used to adjust the ultrasonic probe according to the determined ultrasonic probe angle and transmit an ultrasonic beam.

[0200] In some optional embodiments, the ultrasound imaging module 1004 is specifically configured to determine a beam incidence angle in a first target phase during a formal scanning process based on the target ultrasound emission angle corresponding to the pre-scan image;

[0201] The first target stage is determined according to the scanning angle, the starting scanning angle of the first target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next pre-scan image of the pre-scan image.

[0202] In some optional embodiments, the ultrasound imaging module 1004 includes:

[0203] a beam reference angle determining unit, configured to use the target ultrasound emission angle corresponding to the pre-scan image as the beam reference angle of the first target stage;

[0204] a first ultrasound image acquisition unit, configured to acquire a first ultrasound image acquired at a first moment in the first target phase of a formal scanning process;

[0205] an identification unit, configured to identify a skin boundary in the first ultrasound image;

[0206] A fine-tuning unit is used to fine-tune the beam reference angle based on the skin boundary in the first ultrasound image to obtain the beam incident angle as the beam incident angle at the second moment of the first target stage; the second moment is after the first moment and before the new beam incident angle is obtained.

[0207] In some optional embodiments, the prone breast ultrasound imaging device further comprises:

[0208] a first target ultrasound image acquisition module, configured to acquire a first target ultrasound image; the first target ultrasound image is a formal ultrasound image acquired at a third moment in the formal scanning process, or is the pre-scan image;

[0209] an image recognition result acquisition module, configured to acquire recognition results of the breast area, skin boundary, and various tissues in the first target ultrasound image;

[0210] a partitioning module, configured to divide the breast area into a plurality of depth partitions according to depth, starting from the skin boundary;

[0211] a tissue distribution information acquisition module, configured to acquire tissue distribution information within each of the depth partitions based on the tissue identification result;

[0212] a gain curve generating module, configured to determine corresponding gains according to the tissue distribution information of the depth partitions, and form a target time gain compensation curve;

[0213] a gain adjustment module, configured to adjust the gain of ultrasound signal reception according to the target time gain compensation curve during the second target phase of the formal scanning process until the next phase;

[0214] Among them, if the first target ultrasound image is the formal ultrasound image collected at the third moment, the starting moment of the second target stage is after the third moment, and the ending moment is when or after the new target time gain compensation curve is acquired; if the first target ultrasound image is the pre-scan image, the second target stage is determined according to the scanning angle, and the starting scanning angle of the second target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next frame of the pre-scan image.

[0215] In some optional implementations, the gain adjustment module includes:

[0216] a gain starting point determining unit, configured to determine a gain starting point position according to a position of a skin boundary in a second ultrasound image if the first target ultrasound image is a pre-scan image, where the second ultrasound image is a formal ultrasound image acquired before a current moment;

[0217] The gain adjustment unit is used to adjust the gain of the ultrasonic signal reception according to the starting position of the gain and the target time gain compensation curve.

[0218] In some optional embodiments, the prone breast ultrasound imaging device further comprises:

[0219] an acquisition module, configured to acquire a second target ultrasound image and a probe posture; wherein the second target ultrasound image is the third ultrasound image acquired at the fourth moment during the formal scanning process, and correspondingly, the probe posture is the probe posture during the formal scanning process; or the second target ultrasound image is the pre-scan image, and correspondingly, the probe posture is the probe posture during the pre-scan process or the probe posture during the formal scanning process;

[0220] a distance determination module, configured to determine the distance between the probe and the skin based on a skin boundary in the second target ultrasound image and a probe posture;

[0221] A focus depth determination module is used to determine the transmitting focus point parameters and the receiving focus point parameters of the third target stage during the formal scanning process based on the preset subcutaneous target imaging depth and the distance; if the second target ultrasound image is the third ultrasound image, the third target stage includes one or more moments after the fourth moment; if the second target ultrasound image is the pre-scan image, the third target stage is determined according to the scanning angle, and the starting scanning angle of the third target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next pre-scan image frame of the pre-scan image.

[0222] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0223] The breast prone ultrasound imaging device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0224] The embodiment of the present invention also provides a breast prone ultrasound imaging device having the above Figure 10 The prone breast ultrasound imaging device is shown.

[0225] See also Figure 11 , Figure 11 FIG. 1 is a schematic structural diagram of a breast prone ultrasound imaging device provided by an optional embodiment of the present invention. Figure 11As shown, the breast prone ultrasound imaging device includes:

[0226] an imaging assembly, the imaging assembly comprising an ultrasound probe;

[0227] cups, which hold breast tissue;

[0228] Probe drive assembly, used to drive the probe to adjust the angle;

[0229] A support assembly, used to support the imaging assembly, the cup and the probe drive assembly;

[0230] One or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the breast prone ultrasound imaging device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Figure 11 A processor 10 is taken as an example.

[0231] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0232] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0233] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the prone breast ultrasound imaging device, etc. In addition, the memory 20 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the prone breast ultrasound imaging device via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0234] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0235] The breast prone ultrasound imaging device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 can be connected via a bus or other means. Figure 11 The bus connection is taken as an example.

[0236] The input device 30 can receive input numeric or character information and generate key input signals related to user settings and function control of the prone breast ultrasound imaging device. For example, it can be a touch screen, keypad, mouse, trackpad, touchpad, pointer, one or more mouse buttons, trackball, joystick, etc. The output device 40 can include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibration motors). Such display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, monitors, and plasma displays. In some optional embodiments, the display device can be a touch screen.

[0237] The breast prone ultrasound imaging device also includes a communication interface for the breast prone ultrasound imaging device to communicate with other devices or a communication network.

[0238] In addition, the breast prone ultrasound imaging device may also include some other structures, which can be configured according to actual needs and will not be listed in detail here.

[0239] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0240] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0241] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for prone breast ultrasound imaging, characterized in that: Applied to a prone breast ultrasound device, the method comprises: Acquiring a plurality of pre-scan images of target breast tissue, the plurality of pre-scan images comprising images acquired from a plurality of different angles of the target breast tissue; Respectively identifying skin boundaries in the plurality of pre-scanned images; Based on the skin boundary identified in each pre-scan image, respectively acquiring a target ultrasound emission angle perpendicular to the skin boundary; During formal scanning and imaging, ultrasound waves are emitted perpendicular to the target breast tissue based on the target ultrasound emission angle to acquire an ultrasound image; During the formal scanning imaging, emitting ultrasound perpendicular to the target breast tissue based on the target ultrasound emission angle includes: determining a beam incident angle for a first target stage during a formal scanning process based on the target ultrasound emission angle corresponding to the pre-scan image; The first target stage is determined according to the scanning angle, the starting scanning angle of the first target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next pre-scan image after the pre-scan image; The determining, based on the target ultrasound emission angle corresponding to the pre-scan image, a beam incidence angle of a first target stage in a formal scanning process, includes: Using the target ultrasound emission angle corresponding to the pre-scan image as the beam reference angle of the first target stage; In the first target phase of the formal scanning process, a first ultrasound image acquired at a first moment is acquired; identifying a skin boundary in the first ultrasound image; Based on the skin boundary in the first ultrasound image, the beam reference angle is fine-tuned to obtain the beam incident angle, which is used as the beam incident angle at the second moment of the first target stage; the second moment is after the first moment and before the new beam incident angle is obtained.

2. The method according to claim 1, characterized in that The step of respectively identifying skin boundaries in the plurality of pre-scanned images includes: performing contrast enhancement processing on the pre-scanned image to obtain a first image; Performing edge processing on the first image to obtain a second image; the edge processing is edge enhancement filtering processing or edge extraction processing; Binarizing the second image to obtain a binary image; Extracting connected regions from the binary image, and filtering the extracted connected regions based on region size, position, and / or shape to obtain remaining connected regions; Boundary curve fitting is performed on the boundary points of the remaining connected areas to obtain a continuous skin boundary line.

3. The method according to claim 1, characterized in that The step of respectively identifying skin boundaries in the plurality of pre-scanned images includes: Using a deep learning model, performing breast region recognition on the pre-scan image; Contour extraction is performed on the identified breast area to obtain a skin boundary curve.

4. The method according to claim 1, wherein During the formal scanning imaging, emitting ultrasound perpendicular to the target breast tissue based on the target ultrasound emission angle includes: determining an ultrasound probe angle based on the target ultrasound emission angle corresponding to each of the pre-scan images; According to the determined angle of the ultrasound probe, the ultrasound probe is adjusted and an ultrasound beam is emitted.

5. The method according to claim 1, wherein Also includes: Acquire a first target ultrasound image; the first target ultrasound image is a formal ultrasound image acquired at a third moment in the formal scanning process, or is the pre-scan image; Acquire breast area, skin boundary, and various tissue recognition results in the first target ultrasound image; Starting from the skin boundary, dividing the breast area into a plurality of depth zones according to depth; Based on the tissue identification result, obtaining tissue distribution information within each of the depth partitions; Determining corresponding gains according to the tissue distribution information of the depth partitions, and forming a target time gain compensation curve; During the second target phase of the formal scanning process, adjusting the gain of the ultrasound signal reception according to the target time gain compensation curve until the next phase; Among them, if the first target ultrasound image is the formal ultrasound image collected at the third moment, the starting moment of the second target stage is after the third moment, and the ending moment is when or after the new target time gain compensation curve is acquired; if the first target ultrasound image is the pre-scan image, the second target stage is determined according to the scanning angle, and the starting scanning angle of the second target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next frame of the pre-scan image.

6. The method according to claim 5, characterized in that In the second target phase of the formal scanning process, adjusting the gain of ultrasound signal reception according to the target time gain compensation curve includes: If the first target ultrasound image is a pre-scan image, determining a starting point position of the gain according to a position of a skin boundary in a second ultrasound image, where the second ultrasound image is a formal ultrasound image acquired before the current moment; The gain of ultrasonic signal reception is adjusted according to the starting position of the gain and the target time gain compensation curve.

7. The method according to claim 1, characterized in that Also includes: Acquire a second target ultrasound image and a probe posture; wherein the second target ultrasound image is the third ultrasound image acquired at the fourth moment during the formal scanning process, and correspondingly, the probe posture is the probe posture during the formal scanning process; or the second target ultrasound image is the pre-scan image, and correspondingly, the probe posture is the probe posture during the pre-scan process or the probe posture during the formal scanning process; determining a distance between the probe and the skin based on a skin boundary in the second target ultrasound image and a probe posture; According to the preset subcutaneous target imaging depth and the distance, the transmitting focus point parameters and the receiving focus point parameters of the third target stage during the formal scanning process are determined; if the second target ultrasound image is the third ultrasound image, the third target stage includes one or more moments after the fourth moment; if the second target ultrasound image is the pre-scan image, the third target stage is determined according to the scanning angle, and the starting scanning angle of the third target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next frame of the pre-scan image.

8. A breast prone ultrasound imaging device, characterized in that: Applicable to a prone breast ultrasound device, the device comprises: a pre-scan image acquisition module, configured to acquire a plurality of pre-scan images of target breast tissue, wherein the plurality of pre-scan images include images acquired from a plurality of different angles of the target breast tissue; a first skin boundary recognition module, configured to respectively recognize skin boundaries in the plurality of pre-scanned images; a target ultrasound emission angle acquisition module, configured to respectively acquire a target ultrasound emission angle perpendicular to the skin boundary based on the skin boundary identified in each of the pre-scan images; An ultrasound imaging module, configured to transmit ultrasound perpendicular to the target breast tissue based on the target ultrasound emission angle during formal scanning and imaging, and acquire an ultrasound image; The ultrasound imaging module is specifically configured to determine a beam incident angle in a first target phase during a formal scanning process based on the target ultrasound emission angle corresponding to the pre-scan image; The first target stage is determined according to the scanning angle, the starting scanning angle of the first target stage is the scanning angle corresponding to the pre-scan image, and the ending scanning angle is the scanning angle of the next pre-scan image after the pre-scan image; The ultrasonic imaging module includes: a beam reference angle determining unit, configured to use the target ultrasound emission angle corresponding to the pre-scan image as the beam reference angle of the first target stage; a first ultrasound image acquisition unit, configured to acquire a first ultrasound image acquired at a first moment in the first target phase of a formal scanning process; an identification unit, configured to identify a skin boundary in the first ultrasound image; A fine-tuning unit is used to fine-tune the beam reference angle based on the skin boundary in the first ultrasound image to obtain the beam incident angle as the beam incident angle at the second moment of the first target stage; the second moment is after the first moment and before the new beam incident angle is obtained.

9. A breast prone ultrasound imaging device, characterized in that: include: an imaging assembly, the imaging assembly comprising an ultrasound probe; cups, which hold breast tissue; Probe drive assembly, used to drive the probe to adjust the angle; A support assembly, used to support the imaging assembly, the cup and the probe drive assembly; A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the breast prone ultrasound imaging method according to any one of claims 1 to 7 by executing the computer instructions.

Images