Breast Ultrasonic Imaging Method and Device

Abstract

An embodiment of the present invention provides a breast ultrasound imaging method and device. The method includes: acquiring an ultrasound image of the breast region of a subject; stratifying breast tissue based on the ultrasound image of the breast region to obtain a target layer, the target layer including a skin layer and / or a fat layer; quantifying the pressure intensity according to the deformation of the target layer to obtain a pressure quantification value; and displaying the ultrasound image of the breast region and the pressure quantification value on a display interface. The method of the embodiment of the present invention facilitates guiding the doctor to use an appropriate pressure intensity to obtain an ultrasound image by quantifying and displaying the doctor's pressure intensity during breast ultrasound imaging.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of medical ultrasound technology, and in particular to a breast ultrasound imaging method and device. Background Art

[0002] Breast cancer is a malignant tumor that develops in the mammary epithelium. Cancer statistics show that breast cancer ranks first in the incidence of malignant tumors in women, making early screening for breast cancer particularly important. Breast ultrasound can clearly demonstrate the location, morphology, internal structure, and adjacent tissue changes of all layers of breast soft tissue, including lesions. It is economical, convenient, non-invasive, painless, non-radioactive, and highly reproducible, making it a key method for early breast cancer screening.

[0003] Breast ultrasound imaging typically uses the direct method, in which the physician applies a coupling agent to the fully exposed surface of the patient's breast skin. The physician then places a handheld ultrasound probe against the patient's breast skin for imaging. To maintain good contact between the ultrasound probe and the breast skin, the physician applies a certain amount of pressure during breast ultrasound imaging. Studies have shown that the degree of pressure applied by the physician to soft tissue directly affects ultrasound imaging quality and the ultrasound appearance of breast lesions (for example, excessive pressure on soft lesions can alter the lesion's shape or cause localized blurring). Excessive pressure during breast ultrasound imaging can increase patient pain, particularly for postoperative patients or those experiencing tenderness. Currently, the amount of pressure applied during breast ultrasound imaging is entirely dependent on the physician's experience and habits, resulting in a high degree of operator dependency. Improper pressure can lead to poor ultrasound image quality or increased patient pain. Summary of the Invention

[0004] Embodiments of the present invention provide a breast ultrasound imaging method and apparatus for quantifying the pressure applied by a doctor during breast ultrasound imaging, so as to guide the doctor to adopt an appropriate pressure intensity.

[0005] In a first aspect, an embodiment of the present invention provides a breast ultrasound imaging method, comprising:

[0006] Acquiring an ultrasound image of the subject's breast area;

[0007] stratifying breast tissue based on an ultrasound image of the breast region to obtain a target layer, the target layer including a skin layer and / or a fat layer;

[0008] Quantifying the pressure intensity according to the deformation of the target layer to obtain a pressure quantization value;

[0009] The ultrasound image of the breast area and the pressure quantification value are displayed on the display interface.

[0010] In one embodiment, quantizing the pressing force according to the deformation of the target layer to obtain a pressure quantization value includes:

[0011] Obtaining the area and / or thickness of the target layer, where the thickness includes the average thickness, maximum thickness, or minimum thickness;

[0012] The pressing force is quantified according to the area and / or thickness of the target layer to obtain a pressure quantization value, and the pressure quantization value is negatively correlated with the area and / or thickness of the target layer.

[0013] In one embodiment, quantizing the pressing force according to the deformation of the target layer to obtain a pressure quantization value includes:

[0014] Determine the difference in area and / or thickness between the target layer and the reference layer, where the thickness includes an average thickness, a maximum thickness, or a minimum thickness;

[0015] The pressure intensity is quantified according to the difference value to obtain a pressure quantification value, and the pressure quantification value is positively correlated with the difference value.

[0016] In one embodiment, the reference level is obtained based on a pre-built breast ultrasound image database, or based on a real-time ultrasound scan of the subject's breast area.

[0017] In one embodiment, displaying the pressure quantification value on the display interface includes:

[0018] The pressure quantification value is displayed on the display interface through at least one of an energy bar, a radiation diagram, and a pointer diagram.

[0019] In one embodiment, performing breast tissue stratification based on an ultrasound image of a breast region to obtain a target level includes:

[0020] Based on the ultrasound image of the breast area, a target detection algorithm or a target segmentation algorithm is used to stratify the breast tissue to obtain the target level.

[0021] In one embodiment, the method further includes:

[0022] Determine image quality scores for ultrasound images of the breast region;

[0023] The image quality rating is displayed on the display interface.

[0024] In one embodiment, the method further includes:

[0025] When the image quality score is greater than a preset image quality score threshold, a corresponding prompt message is output, where the prompt message is used to prompt that the image quality corresponding to the current pressure quantization value meets the requirements.

[0026] In one embodiment, the image quality score includes an image quality score for the breast lesion region of the ultrasound image or an image quality score for the entire ultrasound image.

[0027] In one embodiment, the method further includes:

[0028] determining the displacement of a breast lesion region in an ultrasound image;

[0029] When the displacement remains unchanged or is within a preset threshold range, corresponding prompt information is output, and the prompt information is used to prompt that the image quality corresponding to the current pressure quantization value meets the requirements.

[0030] In one embodiment, the target layer further includes a glandular layer.

[0031] In one embodiment, obtaining an ultrasound image of a subject's breast region includes:

[0032] Transmitting ultrasonic waves to the breast area of the subject, receiving ultrasonic echoes returned from the breast area, obtaining ultrasonic echo data, and generating an ultrasonic image of the breast area of the subject based on the ultrasonic echo data;

[0033] or,

[0034] An ultrasound image of the breast region of the subject is obtained from a storage device.

[0035] In a second aspect, an embodiment of the present invention provides a breast ultrasound imaging method, comprising:

[0036] Acquiring an ultrasound image of the subject's breast area;

[0037] Acquire a breast lesion in the subject's breast area from an ultrasound image;

[0038] The pressure intensity is quantified according to the deformation of the breast lesion to obtain a pressure quantification value;

[0039] The ultrasound image of the breast area and the pressure quantification value are displayed on the display interface.

[0040] In one embodiment, displaying the pressure quantification value on the display interface includes:

[0041] The pressure quantification value is displayed on the display interface through at least one of an energy bar, a radiation diagram, and a pointer diagram.

[0042] In one embodiment, the method further includes:

[0043] Determine image quality scores for ultrasound images of the breast region;

[0044] The image quality rating is displayed on the display interface.

[0045] In one embodiment, the method further includes:

[0046] When the image quality score is greater than a preset image quality score threshold, a corresponding prompt message is output, where the prompt message is used to prompt that the image quality corresponding to the current pressure quantization value meets the requirements.

[0047] In one embodiment, the image quality score includes an image quality score for the breast lesion region of the ultrasound image or an image quality score for the entire ultrasound image.

[0048] In one embodiment, the method further includes:

[0049] Determine the displacement of the area corresponding to the breast lesion;

[0050] When the displacement remains unchanged or is within a preset threshold range, corresponding prompt information is output, and the prompt information is used to prompt that the image quality corresponding to the current pressure quantization value meets the requirements.

[0051] In a third aspect, an embodiment of the present invention provides an ultrasonic imaging device, comprising:

[0052] Ultrasound probe;

[0053] The transmitting circuit is used to output the corresponding transmitting sequence to the ultrasonic probe according to the set mode, so as to control the ultrasonic probe to transmit the corresponding ultrasonic wave;

[0054] A receiving circuit, used for receiving the ultrasonic echo signal output by the ultrasonic probe and outputting ultrasonic echo data;

[0055] A display for outputting visual information;

[0056] A processor is configured to execute any of the above breast ultrasound imaging methods.

[0057] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the breast ultrasound imaging method as described in any one of the above items.

[0058] The breast ultrasound imaging method and device provided by the embodiments of the present invention obtain an ultrasound image of the breast area of the subject, and stratify the breast tissue based on the ultrasound image of the breast area to obtain a target layer, and then quantify the pressure intensity according to the deformation of the target layer to obtain a pressure quantification value, thereby realizing the quantification of the pressure intensity during the breast ultrasound imaging process. Furthermore, by displaying the ultrasound image of the breast area and the pressure quantification value on the display interface, the doctor can simultaneously view the ultrasound image and the corresponding pressure quantification value during the ultrasound scanning process, so that the doctor can timely adjust the pressure applied to the ultrasound probe according to the quality of the obtained ultrasound image, thereby improving the comfort of the subject while ensuring the quality of the ultrasound image. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A structural block diagram of an ultrasonic imaging device provided in one embodiment of the present invention;

[0060] Figure 2 A flowchart of a breast ultrasound imaging method provided by one embodiment of the present invention;

[0061] Figure 3 A schematic diagram of a breast ultrasound scanning method provided by one embodiment of the present invention;

[0062] Figure 4 A schematic diagram of breast tissue stratification according to an embodiment of the present invention;

[0063] Figures 5A-5C A schematic diagram of a display interface provided by an embodiment of the present invention;

[0064] Figures 6A-6C A schematic diagram of a display interface provided by yet another embodiment of the present invention;

[0065] Figure 7 This is a flowchart of a breast ultrasound imaging method provided by yet another embodiment of the present invention. DETAILED DESCRIPTION

[0066] The present invention will be further described in detail below by means of specific embodiments in conjunction with the accompanying drawings. Similar elements in different embodiments are numbered with associated similar elements. In the following embodiments, many detailed descriptions are provided to enable the present application to be better understood. However, those skilled in the art will readily appreciate that some of the features may be omitted in different circumstances, or may be replaced by other elements, materials, or methods. In some cases, some operations related to the present application are not shown or described in the specification. This is to avoid the core portion of the present application being overwhelmed by excessive descriptions, and for those skilled in the art, it is not necessary to describe these related operations in detail. They will fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0067] In addition, the features, operations, or characteristics described in the specification may be combined in any appropriate manner to form various embodiments. Furthermore, the steps or actions in the method description may be reordered or adjusted in a manner readily apparent to those skilled in the art. Therefore, the various sequences in the specification and drawings are provided solely for the purpose of clearly describing a particular embodiment and are not intended to be mandatory, unless otherwise specified.

[0068] The serial numbers assigned to components herein, such as "first," "second," etc., are used solely to distinguish the objects being described and do not convey any sequential or technical meaning. References to "connection" and "coupling" herein, unless otherwise specified, include both direct and indirect connections (couplings).

[0069] like Figure 1 As shown, the ultrasound imaging device provided by the present invention may include: an ultrasound probe 20, a transmitting / receiving circuit 30 (i.e., a transmitting circuit 310 and a receiving circuit 320), a beamforming module 40, an IQ demodulation module 50, a memory 60, a processor 70, and a human-computer interaction device. The processor 70 may include a control module 710 and an image processing module 720.

[0070] The ultrasound probe 20 includes a transducer (not shown) composed of multiple array elements arranged in an array. The array elements can be arranged in a row to form a linear array, or in a two-dimensional matrix to form a planar array. Multiple array elements can also form a convex array. The array elements are used to transmit ultrasonic beams based on excitation electrical signals, or to convert received ultrasonic beams into electrical signals. Therefore, each array element can be used to convert electrical pulse signals into and out of ultrasonic beams, thereby transmitting ultrasonic waves to a target area of human tissue (e.g., the breast area in this embodiment) and receiving echoes of ultrasonic waves reflected from the tissue. During ultrasonic testing, the transmitting circuit 310 and the receiving circuit 320 can control which array elements are used to transmit and which are used to receive ultrasonic beams, or control the time slots used to transmit and receive ultrasonic beams. Array elements participating in ultrasonic transmission can be simultaneously excited by electrical signals, thereby transmitting ultrasonic waves simultaneously; alternatively, array elements participating in ultrasonic transmission can be excited by multiple electrical signals separated by a certain time interval, thereby continuously transmitting ultrasonic waves separated by a certain time interval.

[0071] In this embodiment, the user moves the ultrasound probe 20 to select a suitable position and angle to transmit ultrasound to the breast area 10 and receive the echo of the ultrasound returned by the breast area 10, obtains and outputs the electrical signal of the echo, and the electrical signal of the echo is a channel analog electrical signal formed by the receiving array element as a channel, which carries amplitude information, frequency information and time information.

[0072] The transmitting circuit 310 is configured to generate a transmit sequence under the control of the control module 710 of the processor 70. The transmit sequence is used to control some or all of the multiple array elements to transmit ultrasound waves toward biological tissue. Transmit sequence parameters include the array element positions, the number of array elements, and ultrasound beam transmission parameters (e.g., amplitude, frequency, number of transmissions, transmission interval, transmission angle, waveform, focal position, etc.). In some cases, the transmitting circuit 310 is further configured to phase-delay the transmitted beam so that different transmitting array elements transmit ultrasound waves at different times, allowing each transmitted ultrasound beam to be focused on a predetermined region of interest. Transmit sequence parameters may vary for different operating modes, such as B-image mode, C-image mode, and D-image mode (Doppler mode). After the echo signals are received by the receiving circuit 320 and processed by subsequent modules and corresponding algorithms, a B image reflecting tissue anatomical structure, a C image reflecting tissue anatomical structure and blood flow information, and a D image reflecting Doppler spectrum images can be generated.

[0073] The receiving circuit 320 is used to receive and process the electrical signals of ultrasonic echoes from the ultrasonic probe 20. The receiving circuit 320 may include one or more amplifiers, analog-to-digital converters (ADCs), and other components. The amplifiers are used to amplify the received electrical signals of ultrasonic echoes after appropriate gain compensation, and the ADCs are used to sample the analog echo signals at predetermined intervals, converting them into digitized signals. The digitized echo signals still retain amplitude, frequency, and phase information. The data output by the receiving circuit 320 can be sent to the beamforming module 40 for processing or to the memory 60 for storage.

[0074] The beamforming module 40 is signal-connected to the receiving circuit 320 and is used to perform beamforming processing, such as delay and weighted summation, on the signal output by the receiving circuit 320. Because the distances between the ultrasound receiving points in the measured tissue and the receiving array elements vary, the channel data of the same receiving point output by different receiving array elements have different delays. This requires delay processing, phase alignment, and weighted summation of the different channel data from the same receiving point to obtain beamformed ultrasound image data. The ultrasound image data output by the beamforming module 40 is also called radio frequency data (RF data). The beamforming module 40 outputs the RF data to the IQ demodulation module 50. In some embodiments, the beamforming module 40 may also output the RF data to the memory 60 for caching or storage, or directly output the RF data to the image processing module 720 of the processor 70 for image processing.

[0075] The beamforming module 40 may perform the aforementioned functions in hardware, firmware, or software. For example, the beamforming module 40 may include a central controller circuit (CPU), one or more microprocessor chips, or any other electronic components capable of processing input data according to specific logic instructions. When the beamforming module 40 is implemented in software, it may execute instructions stored on a tangible and non-transitory computer-readable medium (e.g., the memory 60) to perform beamforming calculations using any appropriate beamforming method.

[0076] The IQ demodulation module 50 removes the signal carrier through IQ demodulation, extracts the tissue structure information contained in the signal, and performs filtering to remove noise. The resulting signal is called a baseband signal (IQ data pair). The IQ demodulation module 50 outputs the IQ data pair to the image processing module 720 of the processor 70 for image processing. In some embodiments, the IQ demodulation module 50 also outputs the IQ data pair to the memory 60 for caching or storage, so that the image processing module 720 can read the data from the memory 60 for subsequent image processing.

[0077] The processor 70 is configured to be a central control circuit (CPU), one or more microprocessors, a graphics controller circuit (GPU) or any other electronic component that can process input data according to specific logical instructions. It can control peripheral electronic components according to input instructions or predetermined instructions, or read and / or save data from the memory 60. It can also process the input data by executing the program in the memory 60, for example, performing one or more processing operations on the collected ultrasound data according to one or more working modes. The processing operations include but are not limited to adjusting or limiting the form of ultrasound waves emitted by the ultrasound probe 20, generating various image frames for subsequent display on the display 80 of the human-computer interaction device, or adjusting or limiting the content and form displayed on the display 80, or adjusting one or more image display settings displayed on the display 80 (such as ultrasound images, interface components, and positioning areas of interest).

[0078] Image processing module 720 processes the data output by beamforming module 40 or IQ demodulation module 50 to generate a grayscale image showing signal strength variations within the scanning range. This grayscale image reflects the internal anatomical structure of the tissue, referred to as a B-image. Image processing module 720 can output the B-image to display on display 80 of the human-computer interaction device.

[0079] The human-computer interaction device is used for human-computer interaction, that is, receiving user input and outputting visual information; it can receive user input using a keyboard, operation buttons, mouse, trackball, etc., or a touch screen integrated with a display; it outputs visual information using a display 80.

[0080] The memory 60 can be a tangible and non-transitory computer-readable medium, such as a flash memory card, a solid-state memory, a hard disk, etc., for storing data or programs. For example, the memory 60 can be used to store the acquired ultrasound data or image frames generated by the processor 70 that are not immediately displayed, or the memory 60 can store a graphical user interface, one or more default image display settings, and programming instructions for the processor, the beamforming module, or the IQ decoding module.

[0081] It should be noted that Figure 1 The structure shown is for illustration only and may also include Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown. Figure 1 Each component shown in the figure may be implemented using hardware and / or software. Figure 1 The ultrasonic imaging device shown can be used to execute the breast ultrasonic imaging method provided by any embodiment of the present invention.

[0082] Please refer to Figure 2 , a breast ultrasound imaging method provided by an embodiment of the present invention may include:

[0083] S201. Acquire an ultrasonic image of the breast area of the subject.

[0084] When performing a breast examination based on ultrasound, it is first necessary to obtain an ultrasound image of the subject's breast area. In an optional embodiment, the ultrasound probe of the ultrasound imaging device can be used to transmit ultrasound waves to the subject's breast area, and receive ultrasound echoes returned from the breast area to obtain ultrasound echo data, and generate an ultrasound image of the subject's breast area based on the ultrasound echo data. Specifically, the doctor can apply a coupling agent to the skin surface of the subject's breast where it is fully exposed, and then hold the ultrasound probe close to the patient's breast skin for scanning. For example, a depth of 3 to 4 cm and a center frequency greater than or equal to 7.5 MHz can be used for scanning. When scanning, you can use the following methods: Figure 3 The vertical grid scan shown in the first figure can also be performed as shown in the following example. Figure 3 The horizontal grid scanning shown in the second figure can also be performed as follows Figure 3 The two middle and back images show a radial scan centered on the nipple. During the scan, the doctor applies pressure to the ultrasound probe to maintain good contact with the breast skin.

[0085] In another optional embodiment, a pre-stored ultrasound image of the subject's breast area may also be obtained from a storage device.

[0086] S202: Stratify breast tissue based on the ultrasound image of the breast area to obtain a target layer, where the target layer includes a skin layer and / or a fat layer.

[0087] Breast tissue includes the skin layer, fat layer, glandular layer, muscle layer and rib layer. The tissue structures of different layers are different, and the reflection intensity of ultrasound waves is also different. Therefore, the breast tissue can be stratified based on the ultrasound image of the breast area. In this embodiment, the ultrasound image of the breast area can be divided into five layers: skin layer, fat layer, glandular layer, muscle layer and rib layer, and then the target layer can be selected from them; or the specific tissue layers included in the target layer can be determined first, and then the target layer can be directly obtained from the ultrasound image of the breast area. It can be understood that during the ultrasound scanning process, when the doctor applies pressure to the ultrasound probe, the skin layer and the fat layer are easily deformed due to the external pressure. Therefore, the target layer in this embodiment can include only the skin layer, or only the fat layer, or both the skin layer and the fat layer.

[0088] The division of different tissue structures can be achieved based on the boundaries of each layer manually marked by the doctor on the ultrasound image, or the target layer can be obtained by stratifying the breast tissue using a target detection algorithm or a target segmentation algorithm based on the ultrasound image of the breast area.

[0089] In an optional implementation, breast tissue stratification can be detected based on deep learning. First, a deep learning breast tissue stratification detection network needs to be trained based on sample ultrasound images of the collected breast region. For the collected sample ultrasound images, experienced senior physicians annotate the breast tissue stratification. For example, the physician can annotate the minimum bounding box of each layer to obtain the annotation results. The deep learning breast tissue stratification detection network can adopt, but is not limited to, Faster RCNN, SSD, YOLO, CenterNet, CornerNet, etc. During the network training phase, the error between the detection results and the annotation results of each breast tissue layer is calculated during the iterative process. The weights in the network are continuously updated with the goal of minimizing the error. This process is repeated continuously so that the detection results gradually approach the true values of each breast tissue layer represented by the annotation results, thereby obtaining a trained breast tissue stratification detection model. The acquired ultrasound image of the subject's breast region is input into the trained breast tissue stratification detection model, and the various breast tissue layers can be automatically detected in the ultrasound image.

[0090] In another optional embodiment, the hierarchical structure of breast tissue can be detected by combining traditional image processing methods with machine learning methods. First, the region of interest can be determined in the acquired ultrasound image of the subject's breast area based on the image processing method, for example, the Select Search algorithm can be used; then the region of interest is transformed to a preset fixed size, and the image gradient, texture and other feature vectors are extracted from it using the image processing method, for example, the Sift operator, HoG operator, GLCM gray-level co-occurrence matrix, etc. can be extracted; then the feature vectors of the region of interest are trained using a machine learning algorithm to obtain a classification model of the region of interest; finally, the bounding boxes of each breast tissue layer are obtained using a regression method.

[0091] In another optional embodiment, a target segmentation algorithm can be used to automatically segment the various breast tissue layers from the acquired ultrasound image of the subject's breast region. Traditional image segmentation processing algorithms can be used, such as region-based segmentation algorithms such as region growing, watershed, and Otsu threshold methods; and gradient-based segmentation algorithms such as the Sobel operator and the Canny operator. Breast tissue layers can also be segmented based on deep learning. First, a deep learning breast tissue layer segmentation network is trained based on sample ultrasound images of the collected breast region. Experienced, senior physicians annotate the breast tissue layers on the collected sample ultrasound images. The annotated regions can be mask images of the breast tissue layers. For example, the skin layer can be annotated as a 0-pixel region, the fat layer as a 1-pixel region, and so on. Each breast tissue layer region is annotated with a fixed pixel value to generate an annotated mask image. Alternatively, the location information of each breast tissue layer can be written into an annotation file such as XML or JSON. The deep learning breast tissue hierarchical segmentation network can adopt, but is not limited to, typical network frameworks such as Unet, FCN, CAN, DeepLab, and HRNet, as well as networks improved upon these frameworks. During the network training phase, a sample ultrasound image and the corresponding annotated mask image or annotation file are input into the deep learning breast tissue hierarchical segmentation network. The error between the segmentation result output by the segmentation network and the annotation result is calculated. The error is minimized through continuous iteration until the segmentation result output by the segmentation network approaches the true annotated value, thereby obtaining a trained breast tissue hierarchical segmentation model. The acquired ultrasound image of the subject's breast region is input into the trained breast tissue hierarchical segmentation model, which can automatically segment the various breast tissue layers in the ultrasound image. A machine learning-based approach can also be used to achieve breast tissue structural hierarchical segmentation. First, a machine learning segmentation model is trained based on the collected sample ultrasound images and annotation results. For example, a machine learning model such as SVM, Kmeans, or Cmeans can be used to perform binary classification on the grayscale or texture values of image pixels, determining whether each pixel or the texture feature vector representing the current pixel belongs to the target layer. This allows the target layer to be obtained based on the ultrasound image of the breast region.

[0092] When the doctor applies pressure to the ultrasound probe, the glandular layer also deforms due to the external pressure. Although the deformation of the glandular layer is weaker than that of the skin and fat layers, it can still be used to assess the pressure intensity. Therefore, in an optional embodiment, the target layer can also include the glandular layer.

[0093] It should be noted that the specific implementation method of breast tissue stratification is not limited in this embodiment, and the result of breast tissue stratification may be displayed or not. Figure 4 A schematic diagram of breast tissue stratification provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the boundaries of the skin layer and the fat layer are drawn in the ultrasound image.

[0094] S203: quantify the pressing force according to the deformation of the target layer to obtain a pressure quantization value.

[0095] The mammary gland is a soft structure that deforms when pressure is applied. The greater the pressure, the greater the deformation. Therefore, the pressure intensity can be quantified based on the deformation of the target layer to obtain a pressure quantification value. It is understood that the pressure quantification value is positively correlated with the deformation of the target layer. In this embodiment, the deformation of the target layer can be measured by the thickness, area, etc. of the target layer.

[0096] S204: Display the ultrasound image of the breast area and the pressure quantification value on the display interface.

[0097] The display interface simultaneously displays an ultrasound image of the breast region and the corresponding pressure quantification value, allowing the physician to view both the ultrasound image and the corresponding pressure quantification value during the ultrasound scan. This allows the physician to adjust the pressure applied to the ultrasound probe in a timely manner based on the quality of the ultrasound image. For example, when the ultrasound image quality is good, the pressure can be appropriately reduced to improve the patient's comfort; when the ultrasound image quality is poor, the pressure can be appropriately increased to improve the image quality. To balance ultrasound image quality and patient comfort, the pressure is adjusted based on the displayed ultrasound image and pressure quantification value, so that an ultrasound image that meets quality requirements is obtained at the minimum pressure.

[0098] The pressure quantification value in this embodiment can be displayed in the form of text, graphics, tables, etc. For example, the numerical value of the pressure quantification value can be directly displayed on the display interface in the form of text, and the pressure quantification value can also be displayed on the display interface in at least one of an energy bar, a radiation diagram, and a pointer diagram. Figure 5A 、 Figure 5B and Figure 5C The schematic diagrams showing the pressure quantification value through energy bar, radiation diagram and pointer diagram are shown in turn. Figure 5A As shown in the figure, the arrows that gradually change from light to dark indicate the direction of the pressure from small to large. The size of the pressure is represented by filling the energy bar on the right. For example, the unit of each small grid can be set to 1mm deformation. During the doctor's scanning process, every time the average deformation difference of the target layer in the breast tissue structure increases by 1mm, it can be represented by adding 1 small grid in the energy bar. The quantified value of the doctor's pressure can also be presented in pie charts or polygonal forms, such as Figure 5BAs shown in the figure, as the doctor's pressing force increases, the color block spreads radially from the center point to the edge area. The color block can also be replaced by various forms such as gradient color, radial lines, and grids. When the doctor's pressing force reaches the peak or exceeds the predetermined pressure threshold, the color block will fill the entire base map area. Figure 5C As shown, the quantitative results of the doctor's pressing force can also be presented using a pointer diagram in the form of a dashboard. In this diagram, the quantitative value of the pressing force is indicated in real time by a pointer, dynamically prompting the doctor's pressing force during the current ultrasound scan. As the doctor's pressing force increases, the pointer rotates from one side of the dashboard to the other. When the pressing force reaches a peak value or exceeds a predetermined pressing force threshold, the pointer completely reaches the other side of the dashboard. It should be noted that the specific positions of the energy bar, radiation diagram, and pointer diagram used to indicate the quantitative pressure value in the display interface are not limited in this embodiment. For example, Figure 5A-5B The superimposed display is displayed on the acquired ultrasound image of the breast area of the subject, and can also be displayed in a preset area on the display interface separately from the ultrasound image.

[0099] In an optional embodiment, a curve showing changes in the pressure quantification value over time during the breast ultrasound scan can also be displayed on the display interface so that the doctor can intuitively grasp the changing trend of the pressure intensity during the breast ultrasound scan.

[0100] The breast ultrasound imaging method provided in this embodiment obtains an ultrasound image of the breast region of the subject, and performs breast tissue stratification based on the ultrasound image of the breast region to obtain a target layer. Then, the pressing force is quantified according to the deformation of the target layer to obtain a pressure quantification value, thereby realizing the quantification of the pressing force during the breast ultrasound imaging process. Furthermore, by displaying the ultrasound image of the breast region and the pressure quantification value on a display interface, the doctor can simultaneously view the ultrasound image and the corresponding pressure quantification value during the ultrasound scanning process, so that the doctor can timely adjust the pressure applied to the ultrasound probe according to the quality of the obtained ultrasound image, thereby improving the comfort of the subject while ensuring the quality of the ultrasound image.

[0101] On the basis of the above embodiments, how to quantify the pressing force according to the deformation of the target layer to obtain the pressure quantization value will be further elaborated below. In an optional embodiment, quantifying the pressing force according to the deformation of the target layer to obtain the pressure quantization value may include: obtaining the area and / or thickness of the target layer, the thickness includes the average thickness, the maximum thickness or the minimum thickness; quantifying the pressing force according to the area and / or thickness of the target layer to obtain the pressure quantization value, the pressure quantization value is negatively correlated with the area and / or thickness of the target layer. Taking the target layer including the skin layer and the fat layer as an example, assuming that the target layer obtained from the ultrasound image is as follows Figure 4 As shown, according to Figure 4The area or thickness of the target layer is determined by the boundary between the skin layer and the fat layer. The thickness can be the average thickness, maximum thickness, or minimum thickness. The area and thickness can be represented by image pixels, or the actual thickness and area can be determined based on the mapping relationship between ultrasound image pixels and the actual area and thickness. The greater the pressure, the smaller the thickness and area of the target layer. Therefore, the pressure quantization value is negatively correlated with the area and / or thickness of the target layer.

[0102] In another optional embodiment, quantifying the pressure intensity based on the deformation of the target layer to obtain a pressure quantification value may include: determining the difference in area and / or thickness between the target layer and a reference layer, where the thickness includes an average thickness, a maximum thickness, or a minimum thickness; and quantifying the pressure intensity based on the difference to obtain a pressure quantification value, where the pressure quantification value is positively correlated with the difference. The reference layer may be obtained based on a pre-constructed breast ultrasound image database, or may be obtained based on an ultrasound scan of the subject's breast area.

[0103] Specifically, the ultrasound image obtained by the doctor lightly touching the subject's skin can be used as the baseline image. When the target layer includes the skin layer, the skin layer in the baseline image is used as the baseline layer; when the target layer includes the fat layer, the fat layer in the baseline image is used as the baseline layer; when the target layer includes the skin layer and the fat layer, the skin layer and the fat layer in the baseline image are used as the baseline layer. After determining the baseline layer, the area and thickness of the baseline layer can be determined based on the baseline image. The area and / or thickness of the baseline layer can also be determined based on a pre-constructed breast ultrasound image database. For example, the average area and average thickness of the skin layer, as well as the average area and average thickness of the fat layer, can be determined based on data in the breast ultrasound image database.

[0104] It can be understood that when the pressing force is greater, the deformation variable generated by the target layer is also greater, and the difference value of the area and / or thickness between the target layer and the reference layer is also greater, so the pressure quantification value is positively correlated with the difference value. Taking the difference value of the thickness between the target layer and the reference layer as an example of measuring the pressure quantification value of the deformation variable, the difference value can be the difference between the thickness of the target layer and the thickness of the reference layer, or it can be a proportional relationship, such as the ratio of the thickness of the target layer to the thickness of the reference layer, or the ratio of the thickness difference to the thickness of the reference layer. When the difference between the thickness of the target layer and the thickness of the reference layer is used to quantify the pressing force, every time the difference increases by 1 mm, the pressure quantification value can be increased. Figure 5A Add 1 small grid to the energy bar shown. When the difference decreases by 1mm, you can Figure 5A When the ratio of the thickness difference to the thickness of the base layer is used to quantify the pressing force, the following can be used: Figure 5BThe ratio of the color block in the base map to the thickness of the reference layer is used to represent the ratio of the thickness difference to the thickness of the reference layer. The greater the pressure, the greater the thickness difference, the greater the ratio of the thickness difference to the thickness of the reference layer, and the greater the ratio of the color block in the base map. When the ratio of the target layer thickness to the reference layer thickness is used to quantify the pressure, it can be used Figure 5C The percentage indicated by the pointer on the instrument panel, as shown in the pointer diagram, represents the ratio of the target layer thickness to the reference layer thickness. As the pressure increases, the target layer thickness decreases, and the ratio of the target layer thickness to the reference layer thickness also decreases. Therefore, as the pressure increases, the pointer moves from the right side of the instrument panel to the left side, displaying the pressure in real time.

[0105] The ultrasound image of the breast area and the pressure quantification value are displayed simultaneously on the display interface, making it easier for doctors to adjust the pressure applied to the ultrasound probe in a timely manner according to the quality of the obtained ultrasound image. However, at this time, the doctor still needs to make a judgment on the quality of the ultrasound image based on clinical experience, which is not only time-consuming but also not friendly to junior doctors. In order to further reduce the difficulty of the doctor's work and improve work efficiency, based on any of the above embodiments, the breast ultrasound imaging method provided in this embodiment may also include: determining the image quality score of the ultrasound image of the breast area; and displaying the image quality score on the display interface. By displaying the image quality score on the display interface, doctors can obtain the quality of the ultrasound image more intuitively and conveniently, which not only reduces the difficulty of work but also helps to improve work efficiency. In this embodiment, the image quality score can be determined based on the ultrasound image of the entire breast area, or based on the ultrasound image of the breast lesion area.

[0106] The image quality score of breast ultrasound images can be determined using a classification algorithm or a regression algorithm. When using a classification algorithm, during the training phase, a senior physician can annotate all ultrasound images in a breast ultrasound image database according to a binary classification criteria of high and low image quality. A classification model with binary classification capabilities is then trained based on the annotated data. Classification models include, but are not limited to, deep learning classification algorithm models and traditional image classification algorithm models. Deep learning classification algorithm models include, but are not limited to, network frameworks such as ResNet, VGG, HRNet, and Inception, as well as network frameworks derived from these frameworks; traditional image classification algorithm models include support vector machines, random forests, clustering algorithms, and the like. During the testing phase, the breast ultrasound image is input into the pre-trained classification algorithm model to obtain a classification probability value, typically between 0 and 1. After obtaining the probability value, it is mapped to a preset score range, typically expressed as a score range of 0 to 100. The score value mapped to the score range is determined as the image quality score of the breast ultrasound image. When using a regression algorithm, during the training phase, senior physicians can score ultrasound images in the breast ultrasound image database according to specific scoring criteria. Scoring methods include, but are not limited to, subjective observation by the physician, assigning integer scores within a range of values. Alternatively, fixed criteria can be used, such as clear lesion signs, no blurring, no artifacts, moderate image brightness, and partial rib coverage. A score of 5 is awarded if all five criteria are met, with a 1-point deduction for each missing criterion. A gold standard dataset for the regression algorithm is created based on the physicians' scores. The regression model can be constructed using a deep learning convolutional neural network (CNN) framework or an algorithmic model such as logistic regression. During the testing phase, ultrasound images of the breast region are input into the pre-trained regression model to obtain regression scores, which are then mapped to a preset range of values.

[0107] The image quality score is displayed on the display interface. The image quality score can be displayed directly on the interface in the form of text or in the form of graphics. In order to further facilitate the doctor to adjust the pressure intensity according to the image quality score, the image quality score can also be displayed in association with the pressure quantization value. Specifically, when the image quality score is greater than the preset image quality score threshold, a corresponding prompt message is output, which is used to indicate that the image quality corresponding to the current pressure quantization value meets the requirements. For example, the prompt can be provided in the form of interface highlighting, special symbols, color change, flashing, and sound prompts.

[0108] If the pressing force is displayed in the form of an energy bar, when a high-quality ultrasound image is scanned during real-time ultrasound scanning, that is, when the image quality score is greater than the preset image quality score threshold, a specific effect can be triggered in the small grid where the current pressing force is reached, including but not limited to highlighting, flashing, color change, special symbol marking, etc. Figure 6A When this higher image quality is achieved, a star mark is added to the current block or caliper position to record the position of the current compression force in the energy bar, and the ultrasound section image corresponding to the current compression force can also be recorded.

[0109] If the pressure is displayed in a radial pattern, when a high-quality ultrasound image is scanned during real-time ultrasound scanning, that is, when the image quality score is greater than the preset image quality score threshold, a specific effect can be triggered within the color block range reached by the current pressure, including but not limited to highlighting, flashing, color change, special symbol marking, etc. Figure 6B When this higher image quality is achieved, a circular coil is added at the current caliper or disc position to record the position of the current compression force in the radiation pattern, and the ultrasound section image corresponding to the current compression force can also be recorded.

[0110] If the pressure is displayed in the form of a pointer graph, when a high-quality ultrasound image is scanned during the real-time ultrasound scan, that is, the image quality score is greater than the preset image quality score threshold, a specific effect can be triggered at the instrument panel position where the current pressure is reached, including but not limited to highlighting, flashing, color change, special symbol marking, etc. Figure 6C When this higher image quality is achieved, a triangle mark is added to the instrument panel position indicated by the current pointer to record the position of the current pressure in the pointer diagram, and the ultrasound section image corresponding to the current pressure can also be recorded.

[0111] In an optional embodiment, the ultrasound image can also be evaluated by the BI-RADS grade of the breast lesion. On the basis of any of the above embodiments, the method provided in this embodiment may further include: determining the BI-RADS grade of the breast lesion in the breast area of the subject according to the ultrasound image; and displaying the BI-RADS grade on the display interface. By displaying the ultrasound image, pressure quantification value and BI-RADS grade on the display interface, the doctor can more intuitively adjust the pressure and scanning technique according to the BI-RADS grade to obtain an ultrasound image that meets the diagnostic needs. In this embodiment, there is no restriction on the method for determining the BI-RADS grade of the breast lesion in the breast area of the subject according to the ultrasound image. For example, a pre-trained BI-RADS grade model can be used to input the ultrasound image to obtain the corresponding BI-RADS grade of the breast lesion. The BI-RADS grade model is trained based on ultrasound images marked with BI-RADS grades.

[0112] In order to further facilitate doctors to adjust the pressure intensity according to the BIRADS grade, the BIRADS grade can also be displayed in association with the pressure quantification value. It can be understood that when multiple ultrasound section images scanned continuously have the same BIRADS grade, that is, the breast lesion analysis results are stable, it can prompt the doctor that the current pressure intensity is reasonable. Specifically, when the BI-RADS grade remains unchanged in a preset number of consecutive ultrasound images, a corresponding prompt message is output, which is used to prompt that the image quality corresponding to the current pressure quantification value meets the requirements. Among them, the prompt information can refer to the aforementioned related instructions and will not be repeated here.

[0113] In an optional embodiment, the ultrasound image can also be evaluated based on the displacement of the breast lesion. Based on any of the above embodiments, the method provided in this embodiment may further include: determining the displacement of the breast lesion region in the ultrasound image; and when the displacement remains unchanged or is within a preset threshold range, outputting a corresponding prompt message indicating that the image quality corresponding to the current pressure quantization value meets the requirements. By displaying the ultrasound image, the pressure quantization value, and the displacement of the breast lesion region on the display interface, the physician can more intuitively adjust the pressure and scanning technique based on the changes in the displacement to obtain an ultrasound image that meets diagnostic requirements. For example, when the displacement remains unchanged or is within an allowable threshold range, a corresponding prompt is given to indicate to the physician that the image quality is good at the pressure corresponding to the current pressure quantization value and meets the requirements for image printing / storage. The displacement can be the displacement of the center point of the lesion region, the displacement of the edge point, or the displacement of the entire lesion region. The specific method for characterizing the displacement of the lesion region is not limited here. The prompt message can refer to the relevant description above and will not be repeated here.

[0114] During ultrasound scanning, when the doctor applies pressure to the ultrasound probe, not only the skin and fat layers will be deformed due to the external pressure, but also the breast lesions will be deformed due to the external pressure. Therefore, the embodiment of the present invention also provides a breast ultrasound imaging method that quantifies the pressure intensity according to the deformation of the breast lesions. Figure 7 As shown, the breast ultrasound imaging method provided in this embodiment may include:

[0115] S701: Acquire an ultrasound image of the breast area of the subject.

[0116] The specific implementation method can be referred to S201 and will not be repeated here.

[0117] S702: Acquire breast lesions in the breast area of the subject from the ultrasound image.

[0118] In this embodiment, a target detection algorithm can be used to detect breast lesions from ultrasound images, or a target segmentation algorithm can be used to segment breast lesions from ultrasound images. In this embodiment, there is no limitation on the specific target detection algorithm and target segmentation algorithm used.

[0119] S703: quantify the pressing force according to the deformation of the breast lesion to obtain a pressure quantization value.

[0120] When a breast lesion is subjected to pressure applied to it by the outside world, it will deform. Moreover, the greater the pressure, the greater the deformation. Therefore, the pressing force can be quantified according to the deformation of the breast lesion to obtain a pressure quantization value. It is understandable that the pressure quantization value is positively correlated with the deformation of the breast lesion. In this embodiment, the deformation of the breast lesion can be measured by the thickness, area, etc. of the breast lesion. For example, the pressing force can be quantified by the difference in thickness of the breast lesion before and after pressing.

[0121] S704: Display the ultrasound image of the breast area and the pressure quantification value on the display interface.

[0122] The specific implementation method can be referred to S204 and will not be described in detail here.

[0123] The breast ultrasound imaging method provided in this embodiment obtains an ultrasound image of the breast region of the subject, obtains a breast lesion in the breast region of the subject from the ultrasound image, and then quantifies the pressure intensity according to the deformation of the breast lesion to obtain a pressure quantification value, thereby realizing the quantification of the pressure intensity during the breast ultrasound imaging process. Furthermore, by displaying the ultrasound image of the breast region and the pressure quantification value on a display interface, the doctor can simultaneously view the ultrasound image and the corresponding pressure quantification value during the ultrasound scanning process, so that the doctor can timely adjust the pressure applied to the ultrasound probe according to the quality of the obtained ultrasound image, thereby ensuring the quality of the ultrasound image while improving the comfort of the subject.

[0124] In an optional implementation, displaying the quantified pressure value on the display interface may include: displaying the quantified pressure value on the display interface through at least one of an energy bar, a radiation diagram, and a pointer diagram.

[0125] Based on the above embodiment, the method may further include: determining an image quality score for the ultrasound image of the breast region; and displaying the image quality score on a display interface. Optionally, when the image quality score is greater than a preset image quality score threshold, a corresponding prompt message is output, indicating that the image quality corresponding to the current pressure quantization value meets the requirements.

[0126] Based on the above embodiment, the method may further include: determining the BI-RADS grade of a breast lesion in a breast region of a subject based on an ultrasound image; and displaying the BI-RADS grade on a display interface. Optionally, when the BI-RADS grade remains unchanged in a predetermined number of consecutive ultrasound images, a corresponding prompt message is output, indicating that the image quality corresponding to the current pressure quantization value meets the requirements.

[0127] This document is described with reference to various exemplary embodiments. However, those skilled in the art will recognize that changes and modifications may be made to the exemplary embodiments without departing from the scope of this document. For example, the various operational steps and components used to perform the operational steps may be implemented in different ways (e.g., one or more steps may be deleted, modified, or incorporated into other steps) depending on the specific application or considering any number of cost functions associated with the operation of the system.

[0128] Additionally, as will be appreciated by those skilled in the art, the principles of this disclosure may be embodied in a computer program product on a computer-readable storage medium pre-loaded with computer-readable program code. Any tangible, non-transitory computer-readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu-ray discs, etc.), flash memory, and / or the like. These computer program instructions may be loaded onto a general-purpose computer, a special-purpose computer, or other programmable data processing device to form a machine, such that the instructions executed on the computer or other programmable data processing device can generate a device that implements a specified function. These computer program instructions may also be stored in a computer-readable memory, which can instruct the computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the computer-readable memory can form an article of manufacture that includes an implementation device that implements the specified function. The computer program instructions may also be loaded onto a computer or other programmable data processing device, causing the computer or other programmable device to execute a series of operational steps to produce a computer-implemented process, such that the instructions executed on the computer or other programmable device provide the steps for implementing the specified function.

[0129] Although the principles of this invention have been shown in various embodiments, many modifications of structure, arrangement, proportion, elements, materials and components that are particularly suitable for specific environments and operational requirements can be used without departing from the principles and scope of this invention. The above modifications and other changes or amendments are intended to be included within the scope of this invention.

[0130] The foregoing detailed description has been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes can be made without departing from the scope of this disclosure. Therefore, the present disclosure will be considered in an illustrative rather than a restrictive sense, and all such modifications will be included within its scope. Similarly, the advantages, other advantages and solutions to the problems of the various embodiments have been described above. However, the benefits, advantages, solutions to the problems and any elements that can produce these, or make them more specific, should not be interpreted as critical, required or necessary. The term "comprising" and any other variants used in this article are all non-exclusive inclusions, so that a process, method, article or device that includes a list of elements includes not only these elements, but also other elements that are not explicitly listed or do not belong to the process, method, system, article or device. In addition, the term "coupled" and any other variants used in this article refer to physical connections, electrical connections, magnetic connections, optical connections, communication connections, functional connections and / or any other connections.

[0131] The above examples are used to illustrate the present invention, which are only used to help understand the present invention and are not intended to limit the present invention. Those skilled in the art can make several simple deductions, modifications or substitutions based on the concept of the present invention.

Claims

1. A breast ultrasound imaging method, characterized in that: include: Acquiring an ultrasound image of the subject's breast area; Performing breast tissue stratification based on the ultrasound image of the breast region to obtain a target layer, wherein the target layer includes a skin layer and / or a fat layer; quantifying the pressing force according to the deformation of the target layer to obtain a pressure quantization value; The deformation of the target level includes: the area and / or thickness of the target level; determining an image quality score for the ultrasound image of the breast region; determining a displacement of a breast lesion region of the ultrasound image; determining the BI-RADS grade of a breast lesion in the breast area of the subject according to the ultrasound image; Displaying the ultrasound image of the breast area, the pressure quantification value, the BI-RADS grade, the image quality score, and the displacement on a display interface; wherein the image quality score, the BI-RADS grade, and the pressure quantification value are displayed in association with each other; When the image quality score is greater than a preset image quality score threshold, a specific effect is triggered and a corresponding prompt message is output, wherein the prompt message is used to indicate that the image quality corresponding to the current pressure quantization value meets the requirements; the image quality score includes an image quality score for the breast lesion area of the ultrasound image or an image quality score for the entire ultrasound image; When the displacement is within a preset threshold range, a corresponding prompt message is output, wherein the prompt message is used to indicate that the image quality corresponding to the current pressure quantization value meets the requirements; When the BI-RADS grade remains unchanged in a preset number of consecutive ultrasound images, outputting corresponding prompt information, the prompt information being used to indicate that the image quality corresponding to the current pressure quantization value meets the requirements; An ultrasound image obtained by lightly touching the skin of the subject's breast area is used as a reference image; When the target layer includes the skin layer, the skin layer in the reference image is used as the reference layer; when the target layer includes the fat layer, the fat layer in the reference image is used as the reference layer; when the target layer includes the skin layer and the fat layer, the skin layer and the fat layer in the reference image are used as the reference layer; determining the area and / or thickness of the reference level according to the reference image; The step of quantizing the pressing force according to the deformation of the target layer to obtain a pressure quantization value includes: Determining a difference in area and / or thickness between the target layer and the reference layer, wherein the thickness includes an average thickness, a maximum thickness, or a minimum thickness; The pressing intensity is quantified according to the difference value to obtain a pressure quantization value, and the pressure quantization value is positively correlated with the difference value.

2. The method according to claim 1, wherein The reference level is obtained based on a pre-constructed breast ultrasound image database, or is obtained based on a real-time ultrasound scan of the breast area of the subject.

3. The method according to claim 1, wherein Displaying the pressure quantification value on the display interface includes: The pressure quantification value is displayed on the display interface through at least one of an energy bar, a radiation diagram, and a pointer diagram.

4. The method according to claim 1, wherein The step of performing breast tissue stratification based on the ultrasound image of the breast region to obtain a target level includes: The target level is obtained by performing breast tissue stratification based on the ultrasound image of the breast area using a target detection algorithm or a target segmentation algorithm.

5. The method according to any one of claims 1 to 4, wherein The target layer also includes a glandular layer.

6. The method according to claim 1, wherein The step of obtaining an ultrasonic image of the breast area of the subject includes: transmitting ultrasonic waves to the breast region of the subject, receiving ultrasonic echoes returned by the breast region, obtaining ultrasonic echo data, and generating an ultrasonic image of the breast region of the subject based on the ultrasonic echo data; or, An ultrasound image of the breast region of the subject is obtained from a storage device.

7. An ultrasonic imaging device, characterized in that: include: Ultrasound probe; a transmitting circuit, configured to output a corresponding transmitting sequence to the ultrasonic probe according to a set mode, so as to control the ultrasonic probe to transmit corresponding ultrasonic waves; a receiving circuit, configured to receive the ultrasonic echo signal output by the ultrasonic probe and output ultrasonic echo data; A display for outputting visual information; A processor, configured to execute the breast ultrasound imaging method according to any one of claims 1 to 6.

Images