An ultrasonic imaging system and ultrasonic imaging method, storage medium

Abstract

The application discloses an ultrasonic imaging system, an ultrasonic imaging method and a computer storage medium. The system comprises a probe, which emits ultrasonic waves to a thyroid gland or a breast to be detected and receives ultrasonic echoes to obtain ultrasonic echo signals; a processor, which processes the ultrasonic echo signals to obtain an ultrasonic image of the thyroid gland or the breast to be detected; detection information of the thyroid gland or the breast to be detected is obtained according to the ultrasonic image, the detection information of the thyroid gland to be detected comprises TI-RADS detection information, and the detection information of the breast to be detected comprises BI-RADS detection information; the confidence of the detection information is calculated; and a display, which displays the detection information and the confidence of the detection information. The application helps doctors to identify the credibility of the detection information obtained by a machine, and avoids misdiagnosis caused by blindly believing the detection information obtained by the machine.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of ultrasonic imaging, and in particular to an ultrasonic imaging method, an ultrasonic imaging device, and a storage medium. BACKGROUND

[0002] The development of intelligent medical diagnosis is driven by the change of technology, and the development of intelligent medical diagnosis greatly improves the efficiency and diagnosis rate of doctors. However, there are still some areas to be improved in intelligent diagnosis products. The result of intelligent diagnosis is not 100% correct, but the confidence level of the result is not reflected in existing products or schemes. Especially for breast and thyroid ultrasound, which has relatively more lesion signs in clinical diagnosis, inexperienced or junior doctors are prone to blindly believe the results of machine analysis, which affects the correctness of diagnosis. SUMMARY

[0003] The present application provides an ultrasonic imaging system, an ultrasonic imaging method, and a computer storage medium.

[0004] In a first aspect, the present application provides an ultrasonic imaging system, comprising:

[0005] a probe, configured to emit ultrasonic waves to a thyroid or breast to be measured and receive ultrasonic echoes to obtain ultrasonic echo signals;

[0006] a processor, configured to process the ultrasonic echo signals to obtain an ultrasonic image of the thyroid or breast to be measured, obtain detection information of the thyroid or breast to be measured according to the ultrasonic image, wherein the detection information of the thyroid to be measured comprises TI-RADS detection information, and the detection information of the breast to be measured comprises BI-RADS detection information, and calculate a confidence level of the detection information;

[0007] a display, configured to display the detection information and the confidence level of the detection information.

[0008] In a second aspect, the present application provides an ultrasonic imaging system, comprising:

[0009] a processor, configured to obtain an ultrasonic image of a thyroid or breast to be measured, obtain detection information of the thyroid or breast to be measured according to the ultrasonic image, wherein the detection information comprises TI-RADS detection information of the thyroid or BI-RADS detection information of the breast, and calculate a confidence level of the detection information;

[0010] a display, configured to display the detection information and the confidence level of the detection information.

[0011] In a third aspect, the present application provides an ultrasonic imaging method, comprising:

[0012] Ultrasound waves are emitted toward the thyroid or breast to be tested and the ultrasound echoes are received to obtain ultrasound echo signals.

[0013] The ultrasound echo signal is processed to obtain an ultrasound image of the thyroid or breast to be tested;

[0014] The detection information of the thyroid or breast to be tested is obtained based on the ultrasound image, and the detection information includes TI-RADS detection information of the thyroid or BI-RADS detection information of the breast.

[0015] Calculate the confidence level of the detection information;

[0016] Display the detection information and the confidence level of the detection information.

[0017] Fourthly, this application provides an ultrasound imaging method, comprising:

[0018] Acquire ultrasound images of the thyroid or breast tissue to be tested;

[0019] The detection information of the thyroid gland or breast to be tested is obtained based on the ultrasound image. The detection information of the thyroid gland to be tested includes TI-RADS detection information, and the detection information of the breast to be tested includes BI-RADS detection information.

[0020] Calculate the confidence level of the detection information;

[0021] Display the detection information and the confidence level of the detection information.

[0022] Fifthly, this application provides an ultrasound imaging system, comprising:

[0023] The processor, in real-time, processes and acquires ultrasound images of the tissue under test; obtains detection information based on the ultrasound images of the tissue under test; and calculates the confidence level of the detection information.

[0024] A display that shows the detection information and the confidence level of the detection information.

[0025] Sixthly, this application provides a computer storage medium storing a computer program applied to an ultrasound imaging device, wherein the computer program, when executed by a processor, implements the method described in the third or fourth aspect above.

[0026] This application acquires detection information based on ultrasound images of the tissue under test and calculates the confidence level of the detection information, helping doctors to identify the reliability of the detection information obtained by the machine and avoid misdiagnosis caused by blindly trusting the detection information obtained by the machine. Attached Figure Description

[0027] Figure 1 This is a schematic block diagram of one embodiment of an ultrasound imaging system;

[0028] Figure 2 This is a schematic flowchart illustrating one embodiment of the working process of an ultrasound imaging system;

[0029] Figure 3 This is a schematic flowchart illustrating one embodiment of the working process of an ultrasound imaging system;

[0030] Figure 4 This is a schematic flowchart illustrating one embodiment of the workflow of an ultrasound imaging system.

[0031] Figure 5 This is a schematic flowchart illustrating one embodiment of the workflow of an ultrasound imaging system.

[0032] Figure 6 This is a schematic flowchart illustrating one embodiment of the workflow of an ultrasound imaging system.

[0033] Figure 7 This is a schematic flowchart illustrating one embodiment of the workflow of an ultrasound imaging system.

[0034] Figure 8 This is a schematic flowchart illustrating one embodiment of the working process of an ultrasound imaging system;

[0035] Figure 9 This is a schematic flowchart illustrating one embodiment of the workflow of an ultrasound imaging system.

[0036] Figure 10 This is a schematic flowchart illustrating one embodiment of the workflow of an ultrasound imaging system.

[0037] Figure 11 This is a schematic flowchart illustrating one embodiment of the working process of an ultrasound imaging system;

[0038] Figure 12 This is a schematic flowchart illustrating one embodiment of the working process of an ultrasound imaging system;

[0039] Figure 13 This is a schematic block diagram of one embodiment of the display interface of an ultrasound imaging system's workflow;

[0040] Figure 14 This is a schematic block diagram of one embodiment of the display interface of an ultrasound imaging system's workflow;

[0041] Figure 15 This is a schematic flowchart illustrating one embodiment of the working process of an ultrasound imaging system. Detailed Implementation

[0042] Figure 1This is a schematic block diagram of the ultrasound imaging system according to an embodiment of this application. The ultrasound imaging system 10 may include a probe 100, a transmitting circuit 101, a transmit / receive selection switch 102, a receiving circuit 103, a beamforming circuit 104, a processor 105, and a display 106. The transmitting circuit 101 can excite the probe 100 to emit ultrasound waves towards the tissue under test; the receiving circuit 103 can receive the ultrasound echoes returned from the tissue under test through the probe 100, thereby obtaining ultrasound echo signals / data; the ultrasound echo signals / data are processed by the beamforming circuit 104 and then sent to the processor 105. The processor 105 processes the ultrasound echo signals / data to obtain ultrasound images of the tissue under test. The ultrasound images obtained by the processor 105 can be stored in a memory 107. These ultrasound images can be displayed on the display 106.

[0043] In one embodiment of this application, the display 106 of the aforementioned ultrasound imaging system 10 may be a touch screen, a liquid crystal display, or an independent display device such as a liquid crystal display or a television set, separate from the ultrasound imaging system 10, or a display screen on an electronic device such as a mobile phone or tablet computer, etc.

[0044] In practical applications, the processor 105 can be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor, so that the processor 105 can execute the corresponding steps of the ultrasound imaging method in the various embodiments of this application.

[0045] The memory 107 may be volatile memory, such as random access memory (RAM); or non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor.

[0046] In one embodiment, the tissue to be tested is a thyroid gland or breast tissue. A transmitting circuit 101 excites a probe 100 to emit ultrasound waves towards the thyroid gland or breast tissue. A receiving circuit 103 receives the ultrasound echoes returned from the thyroid gland or breast tissue via the probe 100 to obtain an ultrasound echo signal. A processor 105 processes the ultrasound echo signal to obtain an ultrasound image of the thyroid gland or breast tissue. The processor 105 is also used to obtain detection information of the thyroid gland or breast tissue based on the ultrasound image. The processor 105 calculates the confidence level of the detection information. Optionally, the processor 105 can also obtain ultrasound images for subsequent processing by retrieving ultrasound images stored in a memory 107 or receiving ultrasound images transmitted from other devices. A display 106 displays the detection information and the confidence level of the detection information. Optionally, the display 106 can also display the ultrasound image of the thyroid gland or breast tissue.

[0047] The following describes in detail the various embodiments of the ultrasound imaging system 10 in conjunction with its workflow.

[0048] like Figure 2 As shown, in one embodiment, the ultrasound imaging system 10 includes:

[0049] The probe emits ultrasound waves to the thyroid or breast tissue to be tested and receives the ultrasound echoes to obtain ultrasound echo signals.

[0050] The processor processes the ultrasound echo signal to acquire ultrasound images of the thyroid or breast to be tested.

[0051] The ultrasound images of the thyroid or breast to be tested can be at least one of various ultrasound images, such as B-mode ultrasound images, C-mode ultrasound images, M-mode ultrasound images, and elastography images.

[0052] The processor obtains detection information of the thyroid or breast tissue to be tested based on the ultrasound image.

[0053] The detection information for the thyroid gland to be tested includes TI-RADS detection information, and the detection information for the breast gland to be tested includes BI-RADS detection information. The processor obtains the detection information for the thyroid gland or breast gland to be tested based on the ultrasound image by: acquiring TI-RADS detection information from the ultrasound image of the thyroid gland to be tested, or acquiring BI-RADS detection information from the ultrasound image of the breast gland to be tested. TI-RADS (Thyroid Imaging Reporting and Data System) is a thyroid imaging reporting and data system that evaluates and comprehensively grades thyroid lesions based on different features in thyroid images. In this embodiment, the TI-RADS detection information may include evaluations of different image features in the imaging report, or it may include comprehensive grading. Similarly, BI-RADS (Breast Imaging Reporting and Data System) is a breast imaging reporting and data system that evaluates and comprehensively grades breast lesions based on different features in breast images. In this embodiment, the BI-RADS detection information may include evaluations of different image features in the imaging report, or it may include comprehensive grading. It should be emphasized that the TI-RADS or BI-RADS mentioned above can refer to any version of the TI-RADS or BI-RADS standard, and are not limited to a specific version.

[0054] In one embodiment, the detection information may include at least two features, such as... Figure 13 As shown, TI-RADS detection information can include features such as composition, echogenicity, morphology, margins, strong echoes, and TI-RADS grading. The processor 105 can acquire detection information based on the ultrasound image of the thyroid or breast to be tested. Furthermore, the processor 105 can also acquire at least two feature items of the detection information based on the ultrasound image of the thyroid or breast to be tested, respectively. For example, as... Figure 13 As shown, the detection information obtained by the processor 105 based on the ultrasound image of the thyroid gland to be tested includes the following features: the thyroid nodule in the ultrasound image is solid, the thyroid nodule has isoechoic echoes, the thyroid nodule has a transverse diameter > longitudinal diameter, the thyroid nodule has smooth edges, the thyroid nodule has no strong echoes, and the TI-RADS classification is TR1.

[0055] For ease of description, the detection information mentioned below may refer to the detection information as a whole or to at least one feature of the detection information.

[0056] 14. The processor calculates the confidence level of the detection information.

[0057] The results of obtaining detection information based on ultrasound images of the thyroid or breast tissue being tested may be biased due to various factors. Therefore, doctors need to refer to the confidence level of the detection information for a comprehensive judgment. After obtaining detection information of the thyroid or breast tissue being tested based on ultrasound images, the processor 105 can further calculate the confidence level of the detection information to indicate the reliability of the obtained detection information, facilitating accurate judgment by doctors.

[0058] In one embodiment, the confidence level of the detection information can be the total confidence level of at least two feature items. For example, the confidence level of the TI-RADS detection information can be the total confidence level of composition, echo, morphology, edge, strong echo, and TI-RADS level feature items; the confidence level of the detection information can be the total confidence level of composition, echo, morphology, edge, and strong echo feature items; or the total confidence level of a combination of at least two other feature items.

[0059] In another embodiment, the confidence level of the detection information can be the confidence level of at least one feature item of the detection information, including one confidence level corresponding to one feature item. For example, the confidence level of the detection information can be at least one of the following: confidence level of component feature item information, confidence level of echo feature item information, confidence level of morphological feature item information, confidence level of edge feature item information, confidence level of strong echo feature item information, and confidence level of TI-RADS level feature item information.

[0060] In one embodiment, the confidence level of the detection information can be a specific value, such as a score on a ten-point scale, a score on a percentage scale, or a percentage; or it can be a qualitative standard, including high confidence, relatively high confidence, medium confidence, low confidence, and low confidence.

[0061] The 15 monitors display the detection information and the confidence level of the detection information.

[0062] Optionally, the display 106 may also simultaneously display ultrasound images of the thyroid or breast to be tested. In one embodiment, the detection information and / or the confidence level of the detection information can be displayed after the user selects to enter a specific mode.

[0063] In one embodiment, the display 106 displays at least two feature items of the detection information and the total confidence level of the at least two feature items of the detection information. For example, the display 106 may display component feature items, echo feature items, morphological feature items, edge feature items, strong echo feature items, and the total confidence level of each of the above feature items, or the total confidence level of any at least two of the above feature items. For example, the confidence level may be displayed below or to the right of the corresponding at least two feature items, or in other easily viewable locations.

[0064] In one embodiment, the display 106 displays at least one feature item of the detection information, and displays the confidence level corresponding to the feature item in the vicinity of the at least one feature item. For example, the display 106 may display component feature item information and the confidence level of the component feature item information in its vicinity. The vicinity of the feature item information may be below or to the right of the feature item information, or other easily viewable locations.

[0065] In one embodiment, confidence levels are displayed using level icons. These icons represent the degree of confidence through changes in their shape, color, or state. For example, level icons can include at least one of the following: icons with a variable number of icons, icons with a variable ratio, icons with a variable color, icons with a variable shape, icons with a pointer, number icons, and text icons. Exemplarily, icons with a variable number of icons can represent the degree of confidence through their quantity; icons with a variable ratio can represent the degree of confidence through the proportion of a specific part of the icon; icons with a variable color can represent the degree of confidence through their color; icons with a variable shape can represent the degree of confidence through their shape; icons with a pointer can represent the degree of confidence through the character the pointer points to; number icons can represent the degree of confidence through numbers; and text icons can represent the degree of confidence through text. It should be emphasized that text and numbers should also be understood as a type of text icon or number icon.

[0066] For example, such as Figure 13 As shown, the confidence level of a feature is indicated by the number of position icons following the feature information in the corresponding detection information. For example, three position icons follow a feature information with a solid component, indicating a high confidence level; only one position icon follows a feature information with isoechoic echoes, indicating a low confidence level. For instance, the position icons can also further indicate the current scanning location of the ultrasound image.

[0067] For example, such as Figure 14As shown, the confidence level is represented by the size of the illuminated portion on the circumference after the feature information of the corresponding detection information. For example, the confidence level of a feature information with a solid component is 70%, and the illuminated portion on the corresponding circumference occupies 70% of the circumference; the confidence level of a feature information with strong echo (no strong echo) is 10%, and the illuminated portion on the corresponding circumference occupies 10% of the circumference. Optionally, the specific confidence level number can be displayed in the middle of the circumference icon. Optionally, the illuminated portion on the circumference can be set to different colors according to different confidence level values. For example, for a feature information with a solid component, the illuminated portion on the corresponding confidence level circumference icon occupies 70% of the circumference, corresponding to a medium confidence level, and the illuminated portion is yellow; for a feature information with strong echo (no strong echo), the illuminated portion on the corresponding confidence level circumference icon occupies 10% of the circumference, corresponding to a low confidence level, and the illuminated portion is red.

[0068] In other embodiments, the variations of the icons can be combined in other ways to more intuitively display the level of confidence.

[0069] In one embodiment, the degree icon may include an icon displayed in conjunction with detection information. The degree icon can represent the confidence level of the detection information through visual changes such as shape, color, or state while displaying the detection information. For example, the degree icon may include a variable-state detection information icon. A variable-state detection information icon includes displaying the detection information through the icon, and representing the level of confidence through the state of the icon. The detection information icon includes an icon that displays the detection information. It should be emphasized that the text displaying the detection information itself is also a type of detection information icon. The state of the detection information icon includes: color state, shape state, size state, etc., and the state of the detection information icon varies according to the level of confidence of the detection information. Taking a variable-color detection information icon as an example, the degree icon can be a circular icon displaying the detection information. When the confidence level of the detection information is high, the circular icon is green; when the confidence level of the detection information is medium and within the required range, the circular icon is yellow; when the confidence level of the detection information is low, the circular icon is red. Optionally, the confidence level of the detection information icon with variable color can be represented by the background color of the detection information font or by the color of the detection information font itself.

[0070] In one embodiment, the detection information can be displayed either in a list or via indicator icons. The indicator icons include visual icons that indicate the detection information. For example, the indicator icon for component characteristic information can be a similar oil gauge icon, with indicators including: cystic, spongy, cystic-solid, and solid. By pointing to the solid indicator, the component characteristic information of the thyroid nodule in the ultrasound image is visually displayed as solid. Optionally, a confidence level icon can be combined with the indicator icon representing the detection information. For example, if a similar oil gauge icon indicates that the component characteristic information is solid, the confidence level of the solid result is high, and the oil gauge icon is displayed in green.

[0071] like Figure 3 As shown, in one embodiment, the processor 105 calculates the confidence level of the detection information, which may include:

[0072] 24 processors 105 calculate the effectiveness of ultrasound images.

[0073] The validity of an ultrasound image refers to whether the image is effective as the basis for detection information, or the degree of its effectiveness. Factors such as whether the ultrasound image is too bright or too dark, whether it is blurry, and whether its resolution is high enough all affect the validity of the ultrasound image. The validity of an ultrasound image can be a specific value, similar to the confidence level of detection information. Validity can be expressed as a score out of ten, a percentage out of ten, or a percentage; it can also be a qualitative standard, including valid or invalid.

[0074] The 25 processors 105 calculate the confidence level of the detection information based on the validity of the ultrasound images.

[0075] The higher the validity of an ultrasound image, the more reliable the detection information obtained from it, and the higher the confidence level of that information. Correspondingly, factors such as moderate brightness, clarity, and high resolution of the ultrasound image further determine its high validity. Therefore, the validity of an ultrasound image can be evaluated from at least one of these perspectives. Of course, the criteria for judging the validity of an ultrasound image are not limited to these; they can also be obtained by inputting the ultrasound image into an artificial intelligence model. For example, when the validity of an ultrasound image is a specific value, a functional relationship or other correspondence between image validity and the confidence level of the detection information can be established to calculate the confidence level of the detection information based on the validity of the ultrasound image. When the validity of an ultrasound image is a qualitative standard, a value can be assigned to the validity of the ultrasound image, thereby establishing a functional relationship or other correspondence between the validity of the ultrasound image and the confidence level of the detection information to calculate the confidence level of the detection information based on the validity of the ultrasound image; alternatively, a direct correspondence between the validity of the ultrasound image and the confidence level of the detection information can be established to calculate the confidence level of the detection information based on the validity of the ultrasound image.

[0076] like Figure 4 As shown, in one embodiment, the 24 processors 105 may calculate the validity of the ultrasound image, including:

[0077] Processor 105 calculates the clarity of ultrasound images based on ultrasound images. When acquiring detection information, ultrasound images are a crucial basis for obtaining that information. Higher clarity in ultrasound images corresponds to higher effectiveness, while lower clarity results in lower effectiveness. Similar to the effectiveness of ultrasound images, clarity can be a specific value, expressed as a score out of ten, a percentage, or a quantitative measure; it can also be a qualitative standard, including terms like "clear," "relatively clear," "relatively blurry," or "blurry."

[0078] The 32 processor 105 calculates the validity of ultrasound images based on their clarity.

[0079] For example, when the clarity of an ultrasound image is a specific value, a functional relationship or other correspondence can be established between image clarity and the effectiveness of the ultrasound image to calculate the effectiveness of the ultrasound image through image clarity. When the clarity of an ultrasound image is a qualitative standard, a value can be assigned to the clarity of the ultrasound image, thereby establishing a functional relationship or other correspondence between image clarity and the effectiveness of the ultrasound image to calculate the effectiveness of the ultrasound image through image clarity; alternatively, a direct correspondence can be established between image clarity and the effectiveness of the ultrasound image to calculate the effectiveness of the ultrasound image through image clarity.

[0080] Image sharpness can be calculated from dimensions such as whether the ultrasound image is too bright or too dark, or whether the resolution of the ultrasound image is high enough.

[0081] like Figure 5 As shown, in one embodiment, the processor 105 calculates the sharpness of the ultrasound image based on the ultrasound image, which may include:

[0082] 41. Processor 105 determines the effective region from the ultrasound image.

[0083] The effective region can be an ultrasound image region related to the acquisition of detection information. For example, for the thyroid gland, the effective region can be the ultrasound image region of the thyroid gland or the image region of a thyroid nodule, or other ultrasound image regions related to the acquisition of detection information.

[0084] The 42 processors detect gradient information in the effective region.

[0085] Processor 105 calculates the sharpness of the ultrasound image based on gradient information. Generally, the higher the gradient value, the richer the edge information of the image, and the sharper the image. For example, a functional relationship or other correspondence between the gradient information of the effective region and the image sharpness can be established. For instance, image sharpness can be calculated based on gradient information using functions such as the Brenner gradient function, the Tenengrad gradient function, and the Laplacian gradient function.

[0086] like Figure 6 As shown, in one embodiment, the processor 105 calculates the sharpness of the ultrasound image based on the ultrasound image, which may include:

[0087] 51. A first artificial intelligence model is trained by inputting two types of thyroid or breast ultrasound images: one with a clear effective region and the other with a blurred effective region. For example, the first artificial intelligence model can perform a binary classification problem of clear and blurred effective regions in ultrasound images. For the input ultrasound image to be tested, the first artificial intelligence model can input a clear or blurred classification result. It should be emphasized that the first artificial intelligence model can also classify the effective regions of ultrasound images into levels of clarity (clear, relatively clear, relatively blurred, blurred, etc.), thus enabling the first artificial intelligence model to output a clarity rating for the input ultrasound image to be tested.

[0088] The processor 105 inputs the ultrasound image of the thyroid or breast to be tested into the first artificial intelligence model to obtain a result indicating the clarity of the ultrasound image output by the first artificial intelligence model. Inputting the ultrasound image of the thyroid or breast to be tested into the first artificial intelligence model can obtain a classification result of clarity or blurriness, or a grade of clarity, output by the first artificial intelligence model. Optionally, a probability value of the classification result can also be obtained. For example, a classification result indicating a clear ultrasound image can be set to 1, and a classification result indicating a blurriness can be set to 0. Further, the image clarity can be set as a function of the image classification result, thereby calculating the image clarity. Optionally, by obtaining the probability value of the classification result output by the first artificial intelligence model, a functional relationship or other correspondence can be established between the classification result output by the first artificial intelligence model, the probability value of the classification result, and the clarity of the ultrasound image, thereby calculating the image clarity.

[0089] like Figure 7 As shown, in one embodiment, the processor 105 performs calculations on the effectiveness of the ultrasound images, which may include:

[0090] The 121 processor 105 determines the effective region from the ultrasound image.

[0091] The 122 processor calculates the average grayscale value of the effective region.

[0092] For example, the gray values ​​at various points within the effective area of ​​the ultrasound image can be averaged to obtain the total average gray value of the effective area; alternatively, the effective area of ​​the ultrasound image can be divided into multiple regions, and the average gray value of each region can be calculated separately.

[0093] 123. Calculate the validity of ultrasound images based on the grayscale mean.

[0094] For example, the threshold can be determined by whether the average grayscale value of the ultrasound image is within a certain range. The grayscale value of a normal ultrasound image ranges from 0 to 255. For the average grayscale value of the effective area, a threshold of 40 to 200 can be set. That is, when the average grayscale value of the effective area is below 40, the ultrasound image is considered too dark; when the average grayscale value of the effective area exceeds 200, the ultrasound image is considered too bright. It should be emphasized that this threshold range can be adjusted according to clinical requirements and is not limited to 40 to 200. For example, the validity of an ultrasound image can be assigned a value based on whether the mean grayscale value is within a threshold range, or to what extent it exceeds the threshold range. For instance, the mean grayscale value of the valid region can be set to a threshold between 40 and 200. When the mean grayscale value of the valid region is between 40 and 200, the validity of the ultrasound image is assigned a score of 10; when the mean grayscale value is between 35 and 40 or 200 and 205, the validity is assigned a score of 9; when the mean grayscale value is between 30 and 35 or 205 and 210, the validity is assigned a score of 8, and so on. It should be emphasized that the above is only one exemplary method for calculating the validity of an ultrasound image based on the mean grayscale value. Other correlations or functions between the mean grayscale value and the validity of ultrasound images can also be established to calculate the validity of ultrasound images using the mean grayscale value.

[0095] In one embodiment, the processor 105 performs a calculation of the validity of an ultrasound image, which may include: the processor 105 detecting the grayscale of the ultrasound image and determining the validity of the ultrasound image based on the grayscale of the ultrasound image.

[0096] Detecting the grayscale of an ultrasound image can be done by detecting the grayscale of the entire image, or by first identifying a valid region within the image and then detecting the grayscale within that region. Similarly, determining the validity of an ultrasound image based on its grayscale can be done by analyzing the overall grayscale of the image or by analyzing the grayscale within the valid region. This determination of validity includes, but is not limited to, whether the mean grayscale value is within a threshold range, whether the grayscale is uniform, and whether the extreme grayscale values ​​meet at least one of the following criteria. The threshold range for the mean grayscale value is as described above and will not be repeated here. For the uniformity of the grayscale, a grayscale histogram can be plotted. By judging whether the grayscale is uniformly distributed in the histogram, it can be ensured that the grayscale values ​​do not concentrate in a certain area, thus affecting the validity of the ultrasound image.

[0097] If the grayscale of an ultrasound image meets the grayscale standards—for example, if the average grayscale value is appropriate and the image is uniform—then the ultrasound image can accurately display the morphology of the thyroid or breast, and its effectiveness is high. Conversely, if the grayscale of an ultrasound image does not meet the grayscale standards, its effectiveness is low. Therefore, the effectiveness of an ultrasound image can be determined by its grayscale. For example, standards for the average grayscale value, grayscale uniformity, and grayscale extreme values ​​can be set for effective ultrasound images. Furthermore, the deviation between the grayscale value of the ultrasound image and the grayscale standards can be calculated, and a functional relationship or other correspondence between this deviation and image effectiveness can be established to determine the effectiveness of the ultrasound image through the relationship between the grayscale value and the grayscale standards. Of course, the deviation between the grayscale value of an ultrasound image and the grayscale standards can be evaluated from one perspective, such as the grayscale uniformity dimension; or it can be evaluated from multiple dimensions, such as the average grayscale value, grayscale extreme values, and grayscale uniformity, to comprehensively obtain the deviation between the grayscale value of the ultrasound image and the grayscale standards.

[0098] In one embodiment, the processor 105 performs a calculation of the validity of an ultrasound image, which may include: the processor 105 detecting whether there are spots, snowflake-like particles, or meshes in the ultrasound image, thereby determining the validity of the ultrasound image.

[0099] Detecting the presence of spots, snowflake-like patterns, or reticular patterns in ultrasound images can be done by inspecting the entire image or by first identifying a valid region within the image and then inspecting that region. Understandably, the presence of spots, snowflake-like patterns, or reticular patterns in an ultrasound image may obscure key structures of the thyroid or breast, affecting the image's validity. Therefore, a functional relationship or other correlation can be established between the presence of spots, snowflake-like patterns, or reticular patterns and image validity. For example, the larger the area of ​​spots, snowflake-like patterns, or reticular patterns in an ultrasound image, the lower the image validity; conversely, the smaller the area of ​​spots, snowflake-like patterns, or reticular patterns, the higher the image validity. When no spots, snowflake-like patterns, or reticular patterns are present in the ultrasound image, the image has the highest validity in terms of image defects. Furthermore, based on the different degrees of influence of the three factors on the identification of the thyroid or breast in the image, different weights can be assigned to the three image defects of spots, snowflakes, or reticular patterns, etc., so as to determine the validity of the ultrasound image based on whether spots, snowflakes, or reticular patterns exist in the detected ultrasound image.

[0100] For the detection of spots, snowflake-like textures, or mesh-like patterns in ultrasound images, it is possible to detect whether the texture of the ultrasound cross-section image conforms to a preset image texture standard. For example, an image texture detection model can be pre-trained, and the ultrasound cross-section image can be input into the detection model to obtain the detection result of whether the texture conforms to the preset image texture standard. Here, image texture includes: whether the image has spots, snowflake-like textures, or mesh-like patterns.

[0101] In one embodiment, the processor 105 performs calculations to determine the validity of an ultrasound image, which may include: the processor 105 detecting the percentage of the valid region of the ultrasound image and determining the validity of the ultrasound image based on the percentage of the valid region of the ultrasound image.

[0102] The effective region of an ultrasound image can be any ultrasound image region related to the acquisition of detection information. For example, for the thyroid gland, the effective region can be any area in the ultrasound image containing the thyroid gland image, or an image region containing thyroid nodules, or other ultrasound image regions related to the acquisition of detection information. Detecting the proportion of the effective region in an ultrasound image is primarily to ensure that the proportion of the effective region in the ultrasound cross-section image to the overall image is appropriate; for example, the proportion should not be too small, but should be greater than 1 / 2. For example, a specific detection method involves obtaining the effective region through image processing threshold segmentation, calculating the proportion of the effective region to the overall image region, and determining whether this proportion meets a preset requirement. The size or proportion of the effective region is related to parameters such as the ultrasound scanning depth or magnification / reduction factor. In one embodiment, it can be detected whether the ultrasound scanning depth meets a standard, for example, whether the ultrasound scanning depth is within a threshold range, thereby determining whether the proportion of the effective region of the ultrasound image is appropriate.

[0103] Understandably, if the effective area of ​​an ultrasound image is too small, it will be difficult to accurately reflect the morphology of the thyroid or breast on the ultrasound image, which is not conducive to obtaining detection information based on the ultrasound image. Therefore, the effectiveness of an ultrasound image can be determined by the effective area ratio. For example, the effective area ratio of an ultrasound image can be calculated, and a functional relationship or other correspondence between the effective area ratio of an ultrasound image and the image effectiveness can be established to determine the effectiveness of the ultrasound image.

[0104] In one embodiment, the processor 105 performs calculations to determine the validity of an ultrasound image, which may include: the processor 105 detecting the probe used, probe parameters, and / or imaging parameters, and determining the validity of the ultrasound image by the correspondence between the probe, probe parameters, and / or imaging parameters and the thyroid or breast tissue to be examined included in the ultrasound image.

[0105] When performing ultrasound examinations on patients, different probes, probe parameters, and imaging parameters need to be selected according to different examination sites to achieve the best imaging results for each site. For example, a high-frequency linear array probe is used for superficial thyroid and breast tissues, while a low-frequency convex array probe is used for abdominal organs. However, in practice, users may, due to lack of experience or negligence, incorrectly use ultrasound probes and corresponding probe parameters suitable for the abdomen, as well as the corresponding imaging parameters for the abdomen, during thyroid or breast ultrasound imaging. This will result in low-quality thyroid or breast ultrasound images, affecting the effectiveness of the ultrasound images. Similarly, users may incorrectly use imaging parameters suitable for the breast during thyroid ultrasound imaging, which will also result in low-quality thyroid ultrasound images, affecting the effectiveness of the ultrasound images.

[0106] The processor 105 can identify the tissue categories contained in an ultrasound image and compare them with the probe, probe parameters, and imaging parameters used to scan the ultrasound image. When the tissue categories in the ultrasound image correspond to the probe, probe parameters, and imaging parameters used, the validity of the ultrasound image is determined to be high; when the tissue categories in the ultrasound image do not correspond to the probe, probe parameters, and imaging parameters used, the validity of the ultrasound image is determined to be low. Specifically, the tissue categories in the ultrasound image can be compared with all of the probe, probe parameters, and imaging parameters used to scan the ultrasound image, or only one or both of the probe, probe parameters, and imaging parameters used to scan the ultrasound image can be compared to determine the correspondence, thereby determining the image's validity. Furthermore, a functional relationship or other correspondence can be established between the type of probe, probe parameters, and / or imaging parameters and the type of thyroid or breast tissue to be examined included in the ultrasound image, and the image's validity, to determine the validity of the ultrasound image through this correspondence.

[0107] like Figure 8 As shown, in one embodiment, the processor 105 calculates the confidence level of the detection information, which may include:

[0108] The processor 105 identifies target structures of the thyroid or breast in ultrasound images. Target structures of the thyroid or breast include tissue structures in the ultrasound image relevant to acquiring detection information. Identifying target structures of the thyroid or breast in ultrasound images can be achieved through image recognition, machine learning, or other methods. For example, target structures of the thyroid may include: thyroid tissue, carotid artery, trachea, etc.; target structures of the breast include layered structures, such as the skin layer, subcutaneous fat layer, glandular tissue layer, pectoral muscle layer, and rib layer.

[0109] The processor 105 calculates the confidence level of the detection information based on the recognition results of the target structure. It is understood that if the image includes the target structure of the thyroid or breast to be tested, the calculation of the detection information of the thyroid or breast based on that image is more reliable; if the image does not include the target structure of the thyroid or breast to be tested at all, or only includes a portion of the target structure, the calculation of the detection information of the thyroid or breast based on that image is less reliable. In one embodiment, similar to calculating the confidence level of the detection information based on the clarity of the ultrasound image, a functional relationship or other correspondence can be established between the confidence level of the detection information and whether the target structure is included and whether the target structure is fully included, so as to calculate the confidence level of the detection information based on the target structure of the thyroid or breast to be tested in the image.

[0110] like Figure 9 As shown, in one embodiment, taking a thyroid ultrasound image as an example, the processor 105 identifies target structures of the thyroid or breast in the ultrasound image, which may include:

[0111] The 71 processor 105 identifies thyroid tissue in ultrasound images of the thyroid gland being tested. Identification of thyroid tissue in ultrasound images can be achieved through image recognition, machine learning, and other methods.

[0112] The processor 105 identifies the positional relationship between thyroid tissue and other target structures. In one embodiment, when scanning the thyroid gland, it is often necessary to scan the left, right, and isthmus, resulting in some differences in the obtained ultrasound images. If a left-side image of the thyroid gland is obtained based on a left-side scan, but the detection information is analyzed based on a right-side image, the confidence level of the obtained detection information may be low. In one embodiment, the scanning orientation of the thyroid gland can be determined by identifying the positional relationship between thyroid tissue and other target structures in the thyroid ultrasound image, and whether it conforms to a preset scanning orientation. For example, if the carotid artery is on the left side of the thyroid gland, it is a right-side scan image; if the carotid artery is on the right side of the thyroid gland, it is a left-side scan image; if the thyroid gland is present on both sides of the image and the tracheal structure is present in the middle of the image, it is an isthmus scan image. If the scanning location of the thyroid gland determined by the position of other target structures and thyroid tissue in the image does not match or deviates from the preset location, the confidence level of the detection information is low; if the scanning location of the thyroid gland determined by the position of other target structures and thyroid tissue in the image matches the preset location, the confidence level of the detection information is high.

[0113] Continuing with the thyroid gland as an example, the location of thyroid tissue and other target structures is not limited to the orientation of other target structures within the thyroid tissue. It can also include the location of the thyroid tissue and other target structures on the ultrasound image, and the size of the image space occupied by the thyroid tissue and other target structures. In another embodiment, taking a thyroid ultrasound image as an example, when scanning the thyroid gland, in order to obtain detection information, a standard cross-sectional image of the thyroid gland needs to be acquired. According to the standard cross-sectional image, specific other target structures must appear on the image, and the thyroid tissue must occupy a certain proportion of the image. If, based on the location of other target structures in the image and the image size of the thyroid tissue, it is determined that the ultrasound image of the thyroid gland under test meets the preset conditions of the standard cross-section, then the confidence level of the detection information is high; if, based on the positional relationship of other target structures in the image and the image size of the thyroid tissue, it is determined that the ultrasound image of the thyroid gland under test does not meet the preset conditions of the standard cross-section, then the confidence level of the detection information is low.

[0114] Specifically, similar to calculating the confidence level of detection information through the validity of ultrasound images, a functional relationship or other correspondence between the confidence level of detection information and the aforementioned degree of conformity can be established to calculate the confidence level of detection information through the degree of conformity.

[0115] like Figure 10 As shown, in one embodiment, the processor 105 identifies target structures of the thyroid or breast in an ultrasound image, which may include:

[0116] The 81 processor 105 trains at least one second artificial intelligence model by inputting an ultrasound image of a thyroid or breast containing the target structure.

[0117] Taking the thyroid gland as an example, several thyroid ultrasound images are acquired in advance, and the thyroid tissue within these images is marked. These images are then input into at least one second artificial intelligence (AI) model to train the model. Furthermore, other target structures within the thyroid ultrasound images, such as the carotid artery and trachea, can also be marked. Similarly, at least one second AI model can be trained by inputting ultrasound images of the breast containing target structures; for example, ultrasound images of the breast with its layered structures marked can be input into at least one second AI model. This can be achieved by training a single second AI model to identify all target structures in the thyroid or breast; or by training multiple second AI models, with each model corresponding to one target structure for identification.

[0118] The processor 105 inputs the ultrasound image of the thyroid or breast to be tested into at least one second artificial intelligence model to obtain the identification result of the target structure of the thyroid or breast in the ultrasound image output by at least one second artificial intelligence model.

[0119] For example, continuing with the thyroid gland, the ultrasound image of the thyroid gland to be tested is input into at least one second artificial intelligence model. The at least one second artificial intelligence model will output the identification result of whether thyroid tissue is present. Further, it may also include the identification result of the location of thyroid tissue and the location of other target structures. Optionally, it may also output the probability value of the judgment result of whether the target structure of thyroid gland is present.

[0120] In one embodiment, similar to calculating the confidence level of detection information through the validity of ultrasound images, a functional relationship or other correspondence can be established between the confidence level of the detection information and the recognition result of at least one second artificial intelligence output, so as to calculate the confidence level of the detection information through the output recognition result. For example, in the case of thyroid ultrasound images, the confidence level of the detection information can also be comprehensively calculated by combining the recognition result of the positional relationship between thyroid tissue and other target structures; furthermore, the confidence level of the detection information can also be comprehensively calculated by combining the output result of whether the target structure of the thyroid is included and the probability value of that result. Similar to the thyroid, the confidence level of the detection information can also be calculated by using a second artificial intelligence model to identify target structures, positional relationships between target structures, or probability values ​​of output results in breast ultrasound images.

[0121] like Figure 11 As shown, in one embodiment, the processor 105 obtains detection information of the thyroid or breast tissue to be tested based on the ultrasound image, which may include:

[0122] The 93 processor 105 trains at least one third artificial intelligence model by inputting ultrasound images of the thyroid or breast corresponding to the detection information.

[0123] When the detection information includes multiple feature items, a third artificial intelligence model can be trained by inputting an ultrasound image with multiple feature items into the third artificial intelligence model. The third artificial intelligence model is responsible for the detection of multiple feature items. Alternatively, multiple third artificial intelligence models can be trained by inputting an ultrasound image with one feature item into each third artificial intelligence model. The multiple third artificial intelligence models are responsible for the detection of multiple feature items respectively.

[0124] The processor 105 inputs the ultrasound image of the thyroid or breast to be tested into at least one third artificial intelligence model and obtains the detection information output by at least one third artificial intelligence model.

[0125] When the detection information includes multiple feature items, a third artificial intelligence model can be trained to detect multiple feature items. The ultrasound image of the thyroid or breast to be tested is input into the third artificial intelligence model to obtain multiple feature items of the detection information of the thyroid or breast to be tested. Alternatively, multiple third artificial intelligence models can be trained to detect multiple feature items respectively. The ultrasound image of the thyroid or breast to be tested is input into the multiple third artificial intelligence models to obtain multiple feature items of the detection information of the thyroid to be tested.

[0126] In one embodiment, the processor 105's calculation of the confidence level of the detection information may include:

[0127] 95. Calculate the confidence level of the detection information based on the performance of at least one third AI model. The performance of the third AI can be the probability value of obtaining the detection information result output by the third AI model at the same time as outputting the detection information. A functional relationship or other correspondence can be established between the probability value of the detection result and the confidence level of the detection information, so as to calculate the confidence level of the detection information through the probability of the third AI detection result. The performance of the third AI may also be other factors that affect the confidence level of the detection information output by the third AI. The confidence level of the detection information can be calculated by assigning values ​​or establishing a correspondence between them and the confidence level of the detection information. Wherein, when at least one third AI model is a single third AI model, the performance of the single third AI model is the performance of the single third AI model; when at least one third AI model is multiple third AI models, the performance of the single third AI model can be a statistical value of the performance of multiple third AI models, including: average, median, maximum or minimum, etc.

[0128] In one embodiment, the processor 105's calculation of the confidence level of the detection information may include: calculating the indicator confidence level of the detection information using at least two indicators; and calculating the confidence level of the detection information by weighting the confidence levels of at least two indicators. Indicators may include, but are not limited to, the image validity mentioned above, the target structure of the thyroid or breast in the ultrasound image, and the performance of the artificial intelligence model; any indicator from which the confidence level of the detection information can be calculated can be used as the indicator confidence level. In one embodiment, the indicator confidence level of the detection information can be directly used as the confidence level of the detection information; in another embodiment, the confidence level of the detection information can also be calculated by weighting the indicator confidence levels of at least two detection information. The weights in the weighted calculation can be adjusted according to clinical needs or the performance of the device. Calculating the confidence level of the detection information by weighting the indicator confidence levels of at least two detection information takes into account multiple influencing factors, resulting in a more accurate confidence level for the detection information.

[0129] like Figure 15As shown, in one embodiment, an ultrasound imaging system includes:

[0130] Processor 105 acquires ultrasound images of the thyroid or breast tissue to be tested. The ultrasound images of the thyroid or breast tissue to be tested acquired by processor 105 can be obtained through real-time ultrasound scanning, by reading ultrasound images pre-stored in memory 107, or by being remotely sent to processor 105 by other devices.

[0131] The processor 105 obtains detection information of the thyroid or breast to be tested based on the ultrasound image. The detection information includes TI-RADS detection information of the thyroid or BI-RADS detection information of the breast.

[0132] The 143 processor calculates the confidence level of the detection information.

[0133] The 144 monitor displays the detection information and the confidence level of the detection information.

[0134] For the workflow of ultrasound imaging systems similar to those in other embodiments, please refer to the description above, which will not be repeated here.

[0135] One embodiment includes an ultrasound imaging method, comprising:

[0136] Ultrasound waves are emitted toward the thyroid or breast to be tested and the ultrasound echoes are received to obtain ultrasound echo signals.

[0137] Processing ultrasound echo signals to obtain ultrasound images of the thyroid or breast tissue to be tested;

[0138] The detection information of the thyroid or breast to be tested is obtained from the ultrasound images. The detection information includes TI-RADS detection information of the thyroid or BI-RADS detection information of the breast.

[0139] Calculate the confidence level of the detection information;

[0140] Displays the detection information and the confidence level of the detection information.

[0141] The ultrasound imaging system disclosed above can perform this ultrasound imaging method, and will not be repeated here to avoid repetition.

[0142] One embodiment includes an ultrasound imaging method, comprising:

[0143] Obtain ultrasound images of the thyroid or breast tissue to be tested;

[0144] The detection information of the thyroid or breast to be tested is obtained from the ultrasound images. The detection information of the thyroid to be tested includes TI-RADS detection information, and the detection information of the breast to be tested includes BI-RADS detection information.

[0145] Calculate the confidence level of the detection information;

[0146] Display the detection information and the confidence level of the detection information.

[0147] The ultrasound imaging system disclosed above can perform this ultrasound imaging method, and will not be repeated here to avoid repetition.

[0148] like Figure 12 As shown, in one embodiment, ultrasound images are not limited to those of the thyroid or breast. For other tissues requiring diagnostic information in clinical practice, the confidence level of the diagnostic information can also be calculated to guide the doctor's diagnosis. In one embodiment, an ultrasound imaging device may include:

[0149] 111 processor 105 acquires ultrasound images of the tissue under test;

[0150] The processor 112 105 acquires detection information based on the ultrasound image of the tissue to be tested; the detection information includes various information related to the tissue to be tested that can assist medical staff in analyzing the pathological condition of the tissue to be tested.

[0151] The 113 processor calculates the confidence level of the detection information;

[0152] The 114 monitor displays the detection information and the confidence level of the detection information.

[0153] In addition, embodiments of the present invention also provide a computer storage medium on which a computer program is stored. When the computer program is executed by a computer or processor, the aforementioned functions can be implemented. Figures 2 to 12 The steps described herein include calculating and displaying detection information and the confidence level of the detection information from one or more ultrasound images of the tissue under test. For example, the computer storage medium is a computer-readable storage medium.

[0154] In one embodiment, computer program instructions, when executed by a computer or processor, cause the computer or processor to perform the following steps: acquiring an ultrasound image of the thyroid or breast to be tested; acquiring detection information based on the ultrasound image of the thyroid or breast to be tested, including: acquiring TI-RADS detection information based on the ultrasound image of the thyroid to be tested, or acquiring BI-RADS detection information based on the ultrasound image of the breast to be tested; calculating the confidence level of the detection information; and displaying the detection information and the confidence level of the detection information.

[0155] Computer storage media may include, for example, a memory card for a smartphone, a storage component for a tablet computer, a hard disk for a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB storage device, or any combination of the above storage media. A computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0156] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0157] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0159] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0160] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0161] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0162] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0163] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules in the article analysis device according to embodiments of the present invention. The present invention can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0164] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0165] The above description is merely a specific embodiment of the present invention or an explanation of that embodiment. The scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An ultrasound imaging system, characterized in that, include: The probe emits ultrasound waves toward the thyroid or breast gland to be tested and receives ultrasound echoes to obtain ultrasound echo signals. The processor processes the ultrasound echo signal to obtain an ultrasound image of the thyroid or breast to be tested; and obtains detection information of the thyroid or breast to be tested based on the ultrasound image, wherein the detection information of the thyroid to be tested includes TI-RADS detection information and the detection information of the breast to be tested includes BI-RADS detection information. Calculate the confidence level of the detection information; wherein, calculating the confidence level of the detection information includes: calculating the indicator confidence level of the detection information using at least two indicators, the indicators including: the effectiveness of the ultrasound image, the target structure of the thyroid or breast in the ultrasound image, or the performance of the artificial intelligence model; and weighting the confidence levels of the at least two indicators to obtain the confidence level of the detection information, wherein the influencing factors of the effectiveness of the ultrasound image include at least one of the following: whether the ultrasound image is too bright or too dark, whether the ultrasound image is blurry, and whether the resolution of the ultrasound image is high enough. A display that shows the detection information and the confidence level of the detection information.

2. The system as described in claim 1, characterized in that, The detection information includes at least two feature items, wherein calculating the confidence level of the detection information includes calculating the total confidence level of the at least two feature items.

3. The system as described in claim 1, characterized in that, The detection information includes at least one feature item; Calculating the confidence level of the detection information includes: calculating the confidence level of at least one feature item information of the detection information.

4. The system as described in claim 3, characterized in that, The display of the detection information and the confidence level of the detection information includes... Display at least one feature of the detection information, and display the confidence level corresponding to the feature in the vicinity of the at least one feature.

5. The system as described in claim 1, characterized in that, The display of the detection information and the confidence level of the detection information includes: displaying the confidence level through a degree icon, wherein the degree icon represents the magnitude of the confidence level through changes in the icon.

6. The system as described in claim 5, characterized in that, The degree icon includes at least one of the following icon types: A variable number of icons, wherein the number of icons represents the level of confidence; A variable-scale icon, wherein the confidence level is represented by the proportion of a specific part of the icon; A color-changing icon, wherein the color of the icon represents the degree of confidence; A variable-shape icon, wherein the confidence level is represented by the shape of the icon; An icon with a pointer, wherein the confidence level is indicated by the character pointed to by the pointer; Numerical icons, wherein the numerical icons represent the level of confidence; and Text icons, where the text represents the level of confidence.

7. The system as described in claim 5, characterized in that, The degree icon includes an icon displayed in conjunction with the detection information, wherein the icon displayed in conjunction with the detection information includes: The detection information icon has a variable state. The detection information is displayed through the detection information icon, and the state of the detection information icon indicates the level of confidence.

8. The system according to any one of claims 1 to 7, characterized in that, The display of the detection information and the confidence level of the detection information includes: displaying the detection information through a list or displaying the detection information through an indicator icon.

9. The system according to any one of claims 1 to 7, characterized in that, The processor performs calculations to determine the confidence level of the detection information, including: Calculate the validity of the ultrasound image; The confidence level of the detection information is calculated based on the validity of the ultrasound images.

10. The system as described in claim 9, characterized in that, The calculation of the validity of the ultrasound image performed by the processor includes: The resolution of the ultrasound image is calculated based on the ultrasound image. The validity of the ultrasound image is calculated based on the clarity of the ultrasound image.

11. The system as claimed in claim 10, characterized in that, The processor's calculation of the clarity of the ultrasound image based on the ultrasound image includes: Determine the effective region from the ultrasound images; Detect the gradient information of the effective region; The clarity of the ultrasound image is calculated based on the gradient information.

12. The system as described in claim 10, characterized in that, The processor's calculation of the clarity of the ultrasound image based on the ultrasound image includes: The first artificial intelligence model was trained by inputting two types of thyroid or breast ultrasound images, one with a clear effective region and the other with a blurred effective region. The ultrasound image of the thyroid or breast to be tested is input into the first artificial intelligence model to obtain the result of the clarity of the ultrasound image output by the first artificial intelligence model.

13. The system as described in claim 9, characterized in that, The processor performs calculations to determine the validity of the ultrasound image, including: Determine the effective region from the ultrasound images; Calculate the average gray value of the effective region; The validity of the ultrasound image is calculated based on the mean gray value.

14. The system as described in claim 9, characterized in that, The calculation of the validity of the ultrasound image performed by the processor includes: The grayscale of the ultrasound image is detected, and the validity of the ultrasound image is determined by the grayscale of the ultrasound image; or, The validity of the ultrasound image is determined by detecting the presence of spots, snowflake-like particles, or a network pattern; or, The validity of the ultrasound image is determined by detecting the effective region percentage of the ultrasound image; or, The validity of the ultrasound image is determined by the correspondence between the type of the probe, probe parameters, and / or imaging parameters and the thyroid or breast tissue to be examined included in the ultrasound image.

15. The system according to any one of claims 1 to 7, characterized in that, The processor performs calculations to determine the confidence level of the detection information, including: Identify the target structures of the thyroid or breast in the ultrasound image; The confidence level of the detection information is calculated based on the recognition results of the target structure.

16. The system as described in claim 15, characterized in that, The target structures of the thyroid gland include at least one of the following: thyroid tissue, carotid artery, and trachea.

17. The system as claimed in claim 16, characterized in that, The processor performs the following actions to identify target structures of the thyroid gland in the ultrasound image: Identify thyroid tissue in an ultrasound image of the thyroid gland to be tested; Identify the positional relationship between the thyroid tissue and other target structures.

18. The system as described in claim 15, characterized in that, The target structure of the breast includes a layered structure, which includes at least one of the following: skin layer, subcutaneous fat layer, glandular tissue layer, pectoral muscle layer, and rib layer.

19. The system as described in claim 15, characterized in that, The processor performs the task of identifying target structures of the thyroid or breast in the ultrasound image, including: At least one second artificial intelligence model is trained by inputting ultrasound images of the thyroid or breast containing the target structure; The ultrasound image of the thyroid or breast to be tested is input into the at least one second artificial intelligence model to obtain the identification result of the target structure of the thyroid or breast in the ultrasound image output by the at least one second artificial intelligence model.

20. The system according to any one of claims 1 to 7, characterized in that, The processor executes the following steps to obtain detection information for the thyroid or breast tissue to be tested based on the ultrasound image: At least one third artificial intelligence model is trained by inputting ultrasound images of the thyroid or breast containing detection information. The ultrasound image of the thyroid or breast to be tested is input into the at least one third artificial intelligence model to obtain the detection information output by the at least one third artificial intelligence model.

21. The system as claimed in claim 20, characterized in that, The processor performs calculations to determine the confidence level of the detection information, including: The confidence level of the detection information is calculated based on the performance of the at least one third artificial intelligence model.

22. An ultrasound imaging system, characterized in that, include: A processor that acquires ultrasound images of the thyroid or breast to be tested; The detection information of the thyroid or breast to be tested is obtained based on the ultrasound image, and the detection information includes TI-RADS detection information of the thyroid or BI-RADS detection information of the breast. Calculate the confidence level of the detection information; wherein, calculating the confidence level of the detection information includes: calculating the indicator confidence level of the detection information using at least two indicators, the indicators including: the effectiveness of the ultrasound image, the target structure of the thyroid or breast in the ultrasound image, or the performance of the artificial intelligence model; and weighting the confidence levels of the at least two indicators to obtain the confidence level of the detection information, wherein the influencing factors of the effectiveness of the ultrasound image include at least one of the following: whether the ultrasound image is too bright or too dark, whether the ultrasound image is blurry, and whether the resolution of the ultrasound image is high enough. A display that shows the detection information and the confidence level of the detection information.

23. An ultrasound imaging method, characterized in that, include: Ultrasound waves are emitted toward the thyroid or breast to be tested and the ultrasound echoes are received to obtain ultrasound echo signals. The ultrasound echo signal is processed to obtain an ultrasound image of the thyroid or breast to be tested; The detection information of the thyroid or breast to be tested is obtained based on the ultrasound image, and the detection information includes TI-RADS detection information of the thyroid or BI-RADS detection information of the breast. Calculate the confidence level of the detection information; wherein, calculating the confidence level of the detection information includes: calculating the indicator confidence level of the detection information using at least two indicators, the indicators including: the effectiveness of the ultrasound image, the target structure of the thyroid or breast in the ultrasound image, or the performance of the artificial intelligence model; and weighting the confidence levels of the at least two indicators to obtain the confidence level of the detection information, wherein the influencing factors of the effectiveness of the ultrasound image include at least one of the following: whether the ultrasound image is too bright or too dark, whether the ultrasound image is blurry, and whether the resolution of the ultrasound image is high enough. Display the detection information and the confidence level of the detection information.

24. An ultrasound imaging method, characterized in that, include: Obtain ultrasound images of the thyroid or breast tissue to be tested; The detection information of the thyroid gland or breast to be tested is obtained based on the ultrasound image. The detection information of the thyroid gland to be tested includes TI-RADS detection information, and the detection information of the breast to be tested includes BI-RADS detection information. Calculate the confidence level of the detection information; wherein, calculating the confidence level of the detection information includes: calculating the indicator confidence level of the detection information using at least two indicators, the indicators including: the effectiveness of the ultrasound image, the target structure of the thyroid or breast in the ultrasound image, or the performance of the artificial intelligence model; and weighting the confidence levels of the at least two indicators to obtain the confidence level of the detection information, wherein the influencing factors of the effectiveness of the ultrasound image include at least one of the following: whether the ultrasound image is too bright or too dark, whether the ultrasound image is blurry, and whether the resolution of the ultrasound image is high enough. Display the detection information and the confidence level of the detection information.

25. An ultrasound imaging system, characterized in that, include, A processor that processes and acquires ultrasound images of the tissue to be tested; Detection information is obtained based on the ultrasound image of the tissue to be tested; Calculate the confidence level of the detection information; wherein, calculating the confidence level of the detection information includes: calculating the indicator confidence level of the detection information using at least two indicators, the indicators including: the effectiveness of the ultrasound image, the target structure of the thyroid or breast in the ultrasound image, or the performance of the artificial intelligence model; and weighting the confidence levels of the at least two indicators to obtain the confidence level of the detection information, wherein the influencing factors of the effectiveness of the ultrasound image include at least one of the following: whether the ultrasound image is too bright or too dark, whether the ultrasound image is blurry, and whether the resolution of the ultrasound image is high enough. A display that shows the detection information and the confidence level of the detection information.

26. A computer storage medium having a computer program stored thereon, applied to an ultrasound imaging apparatus, wherein the computer program, when executed by a processor, implements the method as described in claim 23 or 24.

Images