Ultrasonic instrument working mode switching method and device, equipment and medium

Abstract

The invention discloses an ultrasonic instrument working mode switching method and device, equipment and a medium, and relates to the technical field of ultrasonic equipment.The method comprises the steps that a to-be-detected picture is determined from ultrasonic images collected by a current ultrasonic instrument; performing image quality detection on the to-be-detected picture to obtain a current quality detection result; and determining whether the current ultrasonic instrument is suitable for being switched to a target working mode or not based on the current quality detection result. Before the ultrasonic instrument is switched to the target working mode, image quality detection can be carried out on the to-be-detected image data in the ultrasonic image, and whether the current ultrasonic instrument is suitable for being switched to the target working mode or not is determined according to the obtained current image quality detection result. Namely, the ultrasonic image acquired by the ultrasonic instrument can be subjected to quality control, and the situation that the working modes are still switched under the condition that the quality of the ultrasonic image is not high is avoided as much as possible.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic devices, and particularly relates to a method, device, equipment and medium for switching the working mode of an ultrasonic instrument. Background Art

[0002] Currently, after an ultrasonic instrument scans an ultrasonic image and an operator places a sampling frame in the region of interest in the ultrasonic image, the ultrasonic instrument automatically enters corresponding ultrasonic working modes such as Doppler.

[0003] However, in some cases, there are problems with the low image quality of the ultrasonic image collected by the ultrasonic instrument or the area of the ultrasonic image to be detected. On this basis, the ultrasonic inspection result obtained after the ultrasonic instrument switches to the corresponding working mode is inaccurate. Usually, in such cases, it is necessary to re-scan a new ultrasonic image and repeat the ultrasonic detection process once. That is to say, when the image quality is not high, the significance of continuing the ultrasonic inspection is not great, which will cause some unnecessary ultrasonic detection processes and result in a waste of time cost.

[0004] In summary, how to avoid the ultrasonic instrument from switching the working mode when the ultrasonic image quality is not high is a problem to be solved at present. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for switching the working mode of an ultrasonic instrument, which can avoid the ultrasonic instrument from switching the working mode when the ultrasonic image quality is not high. The specific solutions are as follows:

[0006] In a first aspect, the present application discloses a method for switching the working mode of an ultrasonic instrument, including:

[0007] Determine the picture to be detected from the ultrasonic image collected by the current ultrasonic instrument;

[0008] Perform image quality detection on the picture to be detected to obtain the current quality detection result;

[0009] Based on the current quality detection result, determine whether the current ultrasonic instrument is suitable for switching to the target working mode.

[0010] Optionally, the picture to be detected is the entire image of the ultrasonic image;

[0011] The performing image quality detection on the picture to be detected to obtain the current quality detection result includes:

[0012] Use a first deep learning model to perform image quality detection on the entire image of the ultrasonic image to obtain the current quality detection result;

[0013] Alternatively, calculate the image quality evaluation index of the entire image frame of the ultrasound image to obtain the current quality detection result.

[0014] Optionally, the using the first deep learning model to perform image quality detection on the entire image frame of the ultrasound image to obtain the current quality detection result includes:

[0015] Input the entire image frame of the ultrasound image into the first deep learning model; wherein, the first deep learning model includes a first classifier and a second classifier;

[0016] Use the first classifier to determine the tissue perspective type of the ultrasound image, and based on the tissue perspective type, use the second classifier to determine the current image quality detection result of the entire image frame of the ultrasound image; the tissue perspective type is used to characterize the target tissue displayed on the current ultrasound image and the corresponding perspective.

[0017] Optionally, the training set for training the first deep learning model includes several historical ultrasound images, first annotation information characterizing the tissue perspective type of the historical ultrasound images, and second annotation information characterizing the historical image quality detection results of the entire image frames of the historical ultrasound images;

[0018] wherein, the historical image quality detection result includes the image frame quality standard degree and the corresponding image frame quality score.

[0019] Optionally, the to-be-detected frame is the target region of interest frame in the ultrasound image;

[0020] The determining the to-be-detected frame from the ultrasound image collected by the current ultrasound instrument includes:

[0021] Detect the sampling position on the ultrasound image collected by the current ultrasound instrument;

[0022] Select the region frame corresponding to the sampling position from the ultrasound image as the target region of interest frame.

[0023] Optionally, the performing image quality detection on the to-be-detected frame to obtain the current quality detection result includes:

[0024] Use the second deep learning model to perform image quality detection on the target region of interest frame to obtain the current quality detection result;

[0025] Alternatively, calculate the image quality evaluation index of the target region of interest frame to obtain the current quality detection result.

[0026] Optionally, the training set for training the second deep learning model includes a number of historical region-of-interest images and third annotation information representing the historical image quality detection results of the historical region-of-interest images;

[0027] Wherein, the historical image quality detection results include the image frame quality standard and the corresponding image frame quality score.

[0028] Optionally, the performing image quality detection on the to-be-detected image to obtain the current quality detection result includes:

[0029] Performing image quality detection on the entire image frame of the ultrasonic image to obtain a first quality detection result;

[0030] Performing image quality detection on the target region-of-interest image in the ultrasonic image to obtain a second quality detection result.

[0031] Optionally, the determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result includes:

[0032] Performing weighted calculation on the image frame quality score in the first quality detection result and the image frame quality score in the second quality detection result to obtain a weighted calculation result;

[0033] Determining a first magnitude relationship between the weighted calculation result and a first preset threshold;

[0034] Determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the first magnitude relationship.

[0035] Optionally, the determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result includes:

[0036] Determining a second magnitude relationship between the image frame quality score in the first quality detection result and a second preset threshold;

[0037] Determining a third magnitude relationship between the image frame quality score in the second quality detection result and a third preset threshold;

[0038] Determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the second magnitude relationship and the third magnitude relationship.

[0039] Optionally, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, it further includes:

[0040] Determining corresponding prompt information based on the current quality detection result;

[0041] Use the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode.

[0042] Optionally, determining the corresponding prompt information based on the current quality detection result includes:

[0043] Determine the corresponding visual parameter value based on the current quality detection result;

[0044] Correspondingly, using the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode includes:

[0045] Assign the corresponding visual parameters of the sampling frame on the current ultrasonic image using the visual parameter value, so as to use the assigned sampling frame to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode.

[0046] Optionally, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, it further includes:

[0047] If the current ultrasonic instrument is suitable for switching to the target working mode, adjust the volume size of the sampling frame according to the tissue structure type in the sampling frame on the current ultrasonic image.

[0048] Optionally, the method for switching the working mode of the ultrasonic instrument further includes:

[0049] Monitor whether a switching request for switching to the target working mode is obtained;

[0050] If the switching request is monitored, trigger the step of determining the picture to be detected from the ultrasonic images collected by the current ultrasonic instrument;

[0051] Correspondingly, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, it further includes:

[0052] If the current ultrasonic instrument is suitable for switching to the target working mode, directly switch the ultrasonic instrument to the target working mode.

[0053] In a second aspect, the present application discloses a device for switching the working mode of an ultrasonic instrument, including:

[0054] A detection picture determination module, configured to determine a picture to be detected from the ultrasonic images collected by the current ultrasonic instrument;

[0055] A quality detection module, configured to perform image quality detection on the picture to be detected to obtain a current quality detection result;

[0056] A result determination module, configured to determine whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current quality detection result.

[0057] In a third aspect, the present application discloses an electronic device, including:

[0058] A memory, configured to store a computer program;

[0059] A processor, configured to execute the computer program to implement the steps of the ultrasonic instrument working mode switching method disclosed above.

[0060] In a fourth aspect, the present application discloses a computer-readable storage medium, configured to store a computer program; wherein, when the computer program is executed by a processor, the steps of the ultrasonic instrument working mode switching method disclosed above are implemented.

[0061] It can be seen that the present application determines a picture to be detected from the ultrasonic images collected by the current ultrasonic instrument; performs image quality detection on the picture to be detected to obtain a current quality detection result; and determines whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current quality detection result. Thus, it can be seen that after the ultrasonic images are collected by the current ultrasonic instrument, it is necessary to perform image quality detection on the picture to be detected in the ultrasonic images, and determine whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current image quality detection result. That is to say, before switching the working mode of the ultrasonic instrument, the present application can perform quality control on the ultrasonic images collected by the ultrasonic instrument, and determine whether the current ultrasonic instrument is suitable for switching to a target working mode according to the quality control result, so as to avoid the situation of still switching the working mode when the quality of the ultrasonic images is not high as much as possible. Description of the Drawings

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0063] Figure 1 It is a flowchart of an ultrasonic instrument working mode switching method disclosed in the present application;

[0064] Figure 2 It is a flowchart of the first specific ultrasonic instrument working mode switching method disclosed in the present application;

[0065] Figure 3 It is a schematic diagram of the model structure of a ViT model disclosed in the present application;

[0066] Figure 4Flowchart of the second specific method for switching the working mode of the ultrasonic instrument disclosed in this application;

[0067] Figure 5 Schematic diagram of the model structure of a MobileNet model disclosed in this application;

[0068] Figure 6 Flowchart of the third specific method for switching the working mode of the ultrasonic instrument disclosed in this application;

[0069] Figure 7 Schematic diagram of the structure of a device for switching the working mode of an ultrasonic instrument disclosed in this application;

[0070] Figure 8 Schematic diagram of the structure of an electronic device disclosed in this application. Detailed implementation manners

[0071] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0072] Currently, there are problems with the low image quality of the ultrasonic images collected by the ultrasonic instrument or the area of the ultrasonic image to be detected. On this basis, the ultrasonic inspection results obtained after the ultrasonic instrument switches to the corresponding working mode are inaccurate. Usually in this case, it is necessary to rescan new ultrasonic images and repeat the ultrasonic detection process once. That is to say, when the image quality is not high, the significance of continuing the ultrasonic inspection is not great, which will cause some unnecessary ultrasonic detection processes and result in a waste of time costs. For this reason, the embodiments of this application disclose a method, device, equipment and medium for switching the working mode of an ultrasonic instrument, which can avoid the ultrasonic instrument from switching the working mode when the ultrasonic image quality is not high.

[0073] See Figure 1 As shown, the embodiments of this application disclose a method for switching the working mode of an ultrasonic instrument, and the method includes:

[0074] Step S11: Determine the area of the ultrasonic image to be detected from the ultrasonic images collected by the current ultrasonic instrument.

[0075] In this embodiment, after the ultrasonic images are collected by the current ultrasonic instrument, the area of the ultrasonic image to be detected is determined from the ultrasonic images. Among them, the area of the ultrasonic image to be detected refers to the area for which the image quality needs to be detected. The area of the ultrasonic image to be detected can be the entire image area of the ultrasonic image or a partial image area of the ultrasonic image. This embodiment does not limit this.

[0076] In addition, the ultrasonic image collected by the ultrasonic instrument in this embodiment can be a two-dimensional ultrasonic image, or a three-dimensional ultrasonic image, a four-dimensional ultrasonic image, etc. This embodiment does not limit the dimension of the ultrasonic image.

[0077] In this embodiment, the ultrasonic image can be an image collected in real time by the current ultrasonic instrument. That is, the current ultrasonic instrument collects ultrasonic images in real time and performs quality detection on them in real time to determine whether they are suitable for switching to ultrasonic working modes such as the Doppler mode.

[0078] Step S12: Perform image quality detection on the to-be-detected screen to obtain the current quality detection result.

[0079] In this embodiment, after the to-be-detected screen is determined, image quality detection is performed on it to obtain the current quality detection result corresponding to the to-be-detected screen. It should be noted that in this embodiment, the image quality detection can specifically be performed on the image clarity, image uniformity, and integrity of the tissue structure of the to-be-detected screen. In addition, the image quality detection of the to-be-detected screen can also be performed according to the user-defined image quality detection rules. This embodiment does not limit the method of image quality detection.

[0080] Step S13: Determine whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result.

[0081] In this embodiment, the current quality detection result can specifically be used to characterize the high or low image quality of the to-be-detected screen. If the current quality detection result characterizes that the image quality of the to-be-detected screen is high, it is determined that the current ultrasonic instrument is suitable for switching to the target working mode. If the current quality detection result characterizes that the image quality of the to-be-detected screen is low, it is determined that the current ultrasonic instrument is not suitable for switching to the target working mode. That is, in this application, by obtaining the current quality detection result of the to-be-detected screen, it is further determined whether the current ultrasonic instrument is suitable for switching to the target working mode. In this way, before switching the working mode of the ultrasonic instrument, this application can perform quality control on the ultrasonic image collected by the ultrasonic instrument to determine whether the current ultrasonic instrument is suitable for switching to the target working mode according to the quality control result, so as to avoid the situation of still switching the working mode when the ultrasonic image quality is not high as much as possible.

[0082] Among them, the working modes of the ultrasonic image can be various ultrasonic scanning, diagnosis and treatment modes, Doppler modes, etc. In the following content of this embodiment, the technical solution of the present application will be described in detail mainly taking the target working mode as the Doppler mode specifically. That is, when the image quality of the area to be detected in the ultrasonic image is not high, it will lead to the problem that the obtained Doppler spectrum is also unclear. Therefore, in this case, it is not very meaningful to continue the ultrasonic examination. And through the solution of the present application, before switching the working mode of the ultrasonic instrument to the Doppler mode, the quality control of the ultrasonic image collected by the ultrasonic instrument can be carried out to determine whether the current ultrasonic instrument is suitable for switching to the Doppler mode according to the quality control result, so as to avoid the situation of obtaining an unclear Doppler spectrum.

[0083] It should be noted that which type of Doppler mode the ultrasonic instrument needs to switch to is determined by the operator. After the ultrasonic instrument scans the ultrasonic image, the operator selects and clicks the Doppler mode that the ultrasonic image needs to enter. The commonly used Doppler modes include pulsed spectral Doppler (PW), continuous spectral Doppler (CW), and tissue Doppler imaging (TDI). Among them, pulsed Doppler has high range resolution and can monitor blood flow at fixed points; continuous Doppler is mainly used for the detection of high-speed blood flow without aliasing; tissue Doppler is used to evaluate the systolic and diastolic functions of the whole heart and local parts.

[0084] Further, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, the following steps are also included: If the current ultrasonic instrument is suitable for switching to the Doppler mode, the volume size of the sampling frame is adjusted according to the tissue structure type in the sampling frame of the current ultrasonic image. Still taking the target working mode as the Doppler mode as an example, if it is determined based on the current quality detection result that the current ultrasonic instrument is suitable for switching to the Doppler mode, this embodiment will also automatically adjust the volume size of the sampling frame according to the tissue structure type in the sampling frame of the current ultrasonic image. It should be noted that for different tissue structure types, when sampling in the image area position corresponding to the tissue structure type, the corresponding sampling volume sizes are inconsistent. For example, taking a two-dimensional echocardiogram image as an example, the common tissue structure types in the heart structure and their corresponding sampling volume sizes are as follows: right ventricular outflow tract, sampling volume is 3-5 mm; pulmonary valve, sampling volume is 3-5 mm; mitral valve orifice, sampling volume is 1-3 mm; tricuspid valve orifice, sampling volume is 1-3 mm; lateral wall of mitral annulus, sampling volume needs to be less than 5 mm; interatrial septum of mitral annulus, sampling volume needs to be less than 5 mm; lateral wall of tricuspid annulus, sampling volume needs to be less than 5 mm; left ventricular outflow tract, sampling volume is 3-5 mm; aortic valve, sampling volume is 3-5 mm; aortic arch, sampling volume is 3-5 mm.

[0085] In the specific implementation manner, the above method further includes: monitoring whether a switching request for switching to the target working mode is obtained; if the switching request is monitored, triggering the step of determining the to-be-detected picture from the ultrasonic images collected by the current ultrasonic instrument; correspondingly, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, the following steps are also included: If the current ultrasonic instrument is suitable for switching to the target working mode, directly switching the ultrasonic instrument to the target working mode. It can be understood that through the foregoing content, after the ultrasonic instrument scans the ultrasonic image, the operator selects and clicks the Doppler mode required for the ultrasonic image. Then, after monitoring that the button control corresponding to the Doppler mode is clicked, it indicates that the switching request is monitored at this time. Therefore, the step of determining the to-be-detected picture from the ultrasonic images collected by the current ultrasonic instrument is triggered to perform image detection on the to-be-detected picture to obtain the current quality detection result. Correspondingly, if it is determined based on the current quality detection result that the current ultrasonic instrument is suitable for switching to the Doppler mode, the working mode of the ultrasonic instrument can be directly switched to the corresponding Doppler mode to complete the subsequent ultrasonic detection process.

[0086] It can be seen that in this application, a to-be-detected picture is determined from the ultrasonic image collected by the current ultrasonic instrument; the image quality of the to-be-detected picture is detected to obtain the current quality detection result; based on the current quality detection result, it is determined whether the current ultrasonic instrument is suitable for switching to the target working mode. Thus, it can be seen that after the ultrasonic image is collected by the current ultrasonic instrument in this application, it is necessary to detect the image quality of the to-be-detected picture in the ultrasonic image, and based on the current image quality detection result, it is determined whether the current ultrasonic instrument is suitable for switching to the target working mode. That is to say, before switching the working mode of the ultrasonic instrument, this application can perform quality control on the ultrasonic image collected by the ultrasonic instrument to determine whether the current ultrasonic instrument is suitable for switching to the target working mode according to the quality control result, so as to avoid the situation of still switching the working mode when the quality of the ultrasonic image is not high as much as possible.

[0087] See Figure 2 As shown, an embodiment of this application discloses a specific method for switching the working mode of an ultrasonic instrument. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution.

[0088] Specifically, it includes:

[0089] Step S21: Determine a to-be-detected picture from the ultrasonic image collected by the current ultrasonic instrument; the to-be-detected picture is the entire image picture of the ultrasonic image.

[0090] In this embodiment, it should be pointed out first that the specific process of obtaining the Doppler spectrum is as follows: 1. Adjust the ultrasonic image parameters to obtain a suitable ultrasonic image; 2. Enter the Doppler pre-activation mode; 3. Set a suitable sampling volume; 4. Place the sampling volume in the region of interest; 5. Enter the Doppler mode; 6. Adjust the measurement scale, baseline, scanning speed, and gain. From the above process, it can be seen that the image quality of the ultrasonic image itself and the image quality of the region of interest are the key factors affecting the Doppler spectrum morphology.

[0091] Therefore, in a specific embodiment, in order to obtain a clear and sharp Doppler spectrum, it is necessary to ensure that the image quality of the obtained ultrasonic image meets certain conditions, that is, the overall resolution, picture display of the ultrasonic image are standard, clear, and accurate. Therefore, in this embodiment, quality control is performed on the ultrasonic image itself, and the entire image picture of the ultrasonic image is used as the to-be-detected picture.

[0092] Step S22: Use the first deep learning model to detect the image quality of the entire image picture of the ultrasonic image to obtain the current quality detection result; or, calculate the image quality evaluation index of the entire image picture of the ultrasonic image to obtain the current quality detection result.

[0093] In a specific embodiment, the first deep learning model is used to perform image quality detection on the entire image of the ultrasound image to obtain the current quality detection result. That is, in this embodiment, the image quality detection is performed by combining the deep learning model to output the current quality detection result.

[0094] Specifically, the above-mentioned use of the first deep learning model to perform image quality detection on the entire image of the ultrasound image to obtain the current quality detection result includes: inputting the entire image of the ultrasound image into the first deep learning model; wherein, the first deep learning model includes a first classifier and a second classifier; using the first classifier to determine the tissue perspective type of the ultrasound image, and based on the tissue perspective type and using the second classifier to determine the current image quality detection result of the entire image of the ultrasound image; the tissue perspective type is used to characterize the target tissue and the corresponding perspective currently displayed on the ultrasound image.

[0095] That is, the entire image of the ultrasound image is input into the pre-trained first deep learning model. The first deep learning model includes two classifiers. Among them, the first classifier is used to determine the tissue perspective type of the ultrasound image, and the second classifier is used to determine the current image quality detection result of the entire image of the ultrasound image based on the tissue perspective type. In this embodiment, the first deep learning model can specifically adopt a ViT (Vision Transformer) model, and the original classification layer in the ViT model is used as the first classifier to determine the tissue perspective type of the ultrasound image, and an MLP Head (the layer structure finally used for classification) is added to the ViT model as the second classifier to determine the current image quality detection result of the entire image of the ultrasound image. The specific model structure of the ViT model can be referred to Figure 3 as shown in

[0096] Among them, the above-mentioned tissue perspective type refers to the target tissue and the corresponding perspective currently displayed on the ultrasound image. It can be understood that for the same target tissue, when the observation perspective changes, the scanned ultrasound image is also different. Taking the two-dimensional echocardiogram image as an example, the above-mentioned tissue perspective type specifically refers to the section structure type, and the perspective can correspond to the section cutting method, such as the transverse section, the longitudinal section, etc. Common section structure types are, for example, the parasternal long-axis view of the left ventricle, the right ventricular outflow tract view, the right ventricular inflow tract view, the parasternal short-axis view of the aortic root, the apical four-chamber view, and so on.

[0097] Further, the training set for training the first deep learning model includes a number of historical ultrasound images, first annotation information representing the tissue perspective type of the historical ultrasound images, and second annotation information representing the historical image quality detection results of the entire image frame of the historical ultrasound images; wherein, the historical image quality detection results include the image frame quality standard degree and the corresponding image frame quality score. That is, in this embodiment, by collecting historical ultrasound images and manually calibrating the tissue perspective type of the historical ultrasound images, the first annotation information is obtained, and by calibrating the historical image quality detection results of the entire image frame of the historical ultrasound images, the second annotation information is obtained; wherein, the historical image quality detection results may specifically include the image frame quality standard degree and the corresponding image frame quality score. It should be noted that the image frame quality standard degree can be divided into only two levels, namely standard and non-standard, or can be divided into three levels, namely standard, basically standard and non-standard. This embodiment does not limit the way of dividing the standard degree levels. In addition, in this embodiment, it is necessary to annotate both the tissue perspective type and the image quality detection results because, under different tissue perspective types, the evaluation methods of the image frame detection standard degree are different. Therefore, after determining the tissue perspective type of the ultrasound image, it is necessary to detect the image frame quality standard degree and the corresponding image frame quality score under this tissue perspective type.

[0098] In another specific implementation manner, this embodiment can also calculate the image quality evaluation index of the entire image frame of the ultrasound image to obtain the current quality detection result. The image quality evaluation index may specifically be the Peak Signal-to-Noise Ratio (PSNR), the Mean Structural Similarity Index Measure (SSIM), etc. It should be noted that when measuring the image quality using the image quality evaluation index, a reference image is required, that is, it is necessary to prepare a standard reference ultrasound image in advance, and then obtain the current quality detection result according to the similarity with the reference ultrasound image.

[0099] Step S23: Determine whether the current ultrasound instrument is suitable for switching to the target working mode based on the current quality detection result.

[0100] Among them, for the more specific processing process of the above step S23, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be elaborated here.

[0101] It can be seen that the embodiments of the present application perform quality control on the ultrasonic image itself, that is, the entire image screen of the ultrasonic image is used as the image to be detected. When performing image quality detection on the entire image screen of the ultrasonic image, the first deep learning model can be used to detect it to obtain the current quality detection result, or the image quality evaluation index of the entire image screen of the ultrasonic image can be calculated to obtain the current quality detection result. Finally, it is determined whether the current ultrasonic instrument is suitable for switching to the target working mode according to the current quality detection result of the entire image screen of the ultrasonic image. That is, before switching the working mode of the ultrasonic instrument, for example, before switching the working mode of the ultrasonic instrument to the Doppler mode, the entire image screen of the ultrasonic image is quality controlled to determine whether the current ultrasonic instrument is suitable for switching to the Doppler mode according to the quality control result, so as to avoid entering the Doppler mode when the quality of the entire image screen of the ultrasonic image is not high as much as possible.

[0102] See Figure 4 As shown, the embodiments of the present application disclose a specific method for switching the working mode of an ultrasonic instrument. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution.

[0103] Specifically, it includes:

[0104] Step S31: Detect the sampling position on the ultrasonic image collected by the current ultrasonic instrument, and select the area image corresponding to the sampling position from the ultrasonic image as the target region of interest image, and use the target region of interest image as the image to be detected.

[0105] In this embodiment, through the foregoing content, it can be seen that the image quality of the ultrasonic image itself and the image quality of the region of interest are both key factors affecting the Doppler spectrum morphology. Therefore, in order to obtain a clear and sharp Doppler spectrum, in a specific embodiment, it is necessary to ensure that the image quality of the region of interest meets certain conditions, that is, the position structure of the region of interest is complete, clear and accurate. For example, for the heart valve, since the heart is in a beating state, there may be cases where the image is blurred and the valve is not completely displayed at certain times. Therefore, in this embodiment, quality control is performed on the target region of interest image, and the target region of interest image is used as the image to be detected.

[0106] Specifically, by detecting the sampling position on the ultrasonic image collected by the current ultrasonic instrument, and selecting the area image corresponding to the sampling position from the ultrasonic image as the target region of interest image. It should be noted that the area image corresponding to the sampling position may specifically be the area image inside the sampling frame, or on the basis of including the area image inside the sampling frame, an additional image of the area near the sampling frame boundary may be added.

[0107] Step S32: Use the second deep learning model to perform image quality detection on the target region of interest image to obtain the current quality detection result; or, calculate the image quality evaluation index of the target region of interest image to obtain the current quality detection result.

[0108] In a specific embodiment, use the second deep learning model to perform image quality detection on the target region of interest image to obtain the current quality detection result. That is, in this embodiment, the current quality detection result is output by combining the deep learning model for image quality detection. In this embodiment, the second deep learning model can specifically adopt the MobileNet model, and the specific model structure of the MobileNet model can be referred to Figure 5 as shown in

[0109] It should be noted that the training set for training the second deep learning model includes several historical regions of interest images and third annotation information representing the historical image quality detection results of the historical regions of interest images; wherein, the historical image quality detection results include the image quality standard degree of the image and the corresponding image quality score. That is, in this embodiment, the historical regions of interest images are collected, and the third annotation information is obtained by artificially calibrating the historical image quality detection results of the historical regions of interest images; wherein, the historical image quality detection results can specifically include the image quality standard degree of the image and the corresponding image quality score. The image quality standard degree can be divided into only two levels, namely standard and non-standard, or can be divided into three levels, namely standard, basic standard and non-standard. This embodiment does not limit the way of dividing the standard degree level.

[0110] In another specific embodiment, this embodiment can also calculate the image quality evaluation index of the target region of interest image to obtain the current quality detection result. The image quality evaluation index can specifically be the peak signal-to-noise ratio, the average structural similarity, etc. It should be noted that when using the image quality evaluation index to measure the image quality, a reference image is required, that is, a standard reference region of interest image needs to be prepared in advance, and then the current quality detection result is obtained according to the similarity with the reference region of interest image.

[0111] Step S33: Determine whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result.

[0112] Among them, for a more specific processing process of the above step S33, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be elaborated here.

[0113] It can be seen that in the embodiment of the present application, quality control is performed on the target region of interest (ROI) image, that is, the target ROI image is used as the image to be detected. When performing image quality detection on the target ROI image of the ultrasound image, the first deep learning model can be used to detect it to obtain the current quality detection result, or the image quality evaluation index of the target ROI image can be calculated to obtain the current quality detection result. Finally, it is determined whether the current ultrasound instrument is suitable for switching to the target working mode according to the current quality detection result of the target ROI image. That is, before switching the working mode of the ultrasound instrument, for example, before switching the working mode of the ultrasound instrument to the Doppler mode, the present application can perform quality control on the target ROI image of the ultrasound image to determine whether the current ultrasound instrument is suitable for switching to the Doppler mode according to the quality control result, so as to avoid entering the Doppler mode when the quality of the target ROI image is not high as much as possible.

[0114] See Figure 6 As shown, the embodiment of the present application discloses a specific method for switching the working mode of an ultrasound instrument. Compared with the previous embodiment, this embodiment further describes and optimizes the technical solution.

[0115] Specifically, it includes:

[0116] Step S41: Determine the image to be detected from the ultrasound images collected by the current ultrasound instrument; the image to be detected is the entire image of the ultrasound image and the target ROI image in the ultrasound image.

[0117] In this embodiment, from the foregoing content, it can be seen that the image quality of the ultrasound image itself and the image quality of the ROI are the key factors affecting the Doppler spectrum morphology. Therefore, in order to obtain a clear and sharp Doppler spectrum, in a specific embodiment, it is necessary to ensure that the image quality of the obtained ultrasound image and the image quality of the ROI both meet certain conditions. Therefore, in this embodiment, the entire image of the ultrasound image and the target ROI image in the ultrasound image are both used as the images to be detected.

[0118] Step S42: Perform image quality detection on the entire image of the ultrasound image to obtain a first quality detection result; perform image quality detection on the target ROI image in the ultrasound image to obtain a second quality detection result.

[0119] In this embodiment, image quality detection is respectively performed on the entire image of the ultrasound image and the target ROI image in the ultrasound image to obtain a first quality detection result and a second quality detection result. Among them, the method for performing quality detection on the entire image of the ultrasound image and the target ROI image can refer to the content of the previous embodiment and will not be elaborated here.

[0120] Step S43: Determine whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result.

[0121] In a specific embodiment, the determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result includes: performing a weighted calculation on the image frame quality score in the first quality detection result and the image frame quality score in the second quality detection result to obtain a weighted calculation result; determining a first magnitude relationship between the weighted calculation result and a first preset threshold; and determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the first magnitude relationship.

[0122] That is, in this embodiment, after obtaining the first quality detection result of the entire image frame of the ultrasonic image and the second quality detection result of the target region of interest frame, a weighted calculation can be performed on the image frame quality scores therein to obtain a weighted calculation result, and then the weighted calculation result is compared with the first preset threshold to obtain a first magnitude relationship, so as to use the first magnitude relationship to determine whether the current ultrasonic instrument is suitable for switching to the Doppler mode. For example, assume that the image frame quality score is a value between 0 and 1, where 0 represents the lowest image frame quality and 1 represents the highest image frame quality, and the first preset threshold is 0.6. Suppose the image frame quality score in the first quality detection result is 0.4 and the image frame quality score in the second quality detection result is 0.8. Assume that after weighted calculation using a weighting coefficient, the obtained weighted calculation result is 0.72. Then at this time, the weighted calculation result is greater than the first preset threshold, so it is considered that the current ultrasonic instrument is suitable for switching to the Doppler mode. Otherwise, if the weighted calculation result is less than the first preset threshold, it is considered that the current ultrasonic instrument is not suitable for switching to the Doppler mode. It should be noted that the setting of the weighting coefficient in this embodiment needs to be specifically set according to the specific scenario, and there is no restriction on its value rule.

[0123] In another specific embodiment, the determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result includes: determining a second magnitude relationship between the image frame quality score in the first quality detection result and a second preset threshold; determining a third magnitude relationship between the image frame quality score in the second quality detection result and a third preset threshold; and determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the second magnitude relationship and the third magnitude relationship.

[0124] That is, after obtaining the first quality detection result of the entire image screen of the ultrasonic image and the second quality detection result of the target region of interest screen in this embodiment, the image screen quality score in the first quality detection result can be compared with a second preset threshold to obtain a second size relationship, and the image screen quality score in the second quality detection result can be compared with a third preset threshold to obtain a third size relationship. Then, it is determined whether the current ultrasonic instrument is suitable for switching to the Doppler mode according to the second size relationship and the third size relationship. For example, in one case, it is considered that the current ultrasonic instrument is not suitable for switching to the Doppler mode only when the image screen quality score in the first quality detection result is less than the second preset threshold and the image screen quality score in the second quality detection result is also less than the third preset threshold. In another case, in order to ensure higher image quality, it is considered that the current ultrasonic instrument is suitable for switching to the Doppler mode only when the image screen quality score in the first quality detection result is greater than the second preset threshold and the image screen quality score in the second quality detection result is also greater than the third preset threshold.

[0125] Step S44: Prompt whether the current ultrasonic instrument is suitable for switching to the target working mode.

[0126] In this embodiment, after determining whether the current ultrasonic instrument is suitable for switching to the Doppler mode based on the current quality detection result, it is also possible to further prompt whether the current ultrasonic instrument is suitable for switching to the Doppler mode.

[0127] Furthermore, the above-mentioned prompting of whether the current ultrasonic instrument is suitable for switching to the target working mode includes: determining corresponding prompt information based on the current quality detection result; using the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode. It should be noted that the form of the prompt information can be in the form of color, text, sound, etc. This embodiment does not limit the specific form of the prompt information. That is, first determine the corresponding prompt information according to the current quality detection result. For example, if the current quality detection result indicates that the image quality is high, it can be prompted through the prompt information that the current ultrasonic instrument is suitable for switching to the Doppler mode. If the current quality detection result indicates that the image quality is low, it can be prompted through the prompt information that the current ultrasonic instrument is not suitable for switching to the Doppler mode, so that after the operator receives the prompt information, it can be determined whether to switch the working mode of the current ultrasonic instrument to the Doppler mode.

[0128] Specifically, determining the corresponding prompt information based on the current quality detection result includes: determining the corresponding visual parameter value based on the current quality detection result; correspondingly, using the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode includes: assigning the corresponding visual parameter of the sampling frame on the current ultrasonic image by using the visual parameter value, so as to use the assigned sampling frame to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode. That is, in the specific implementation manner, the form of the prompt can be presented visually, then the corresponding prompt information is the corresponding visual parameter value, and then the corresponding visual parameter of the sampling frame on the current ultrasonic image is assigned by using the visual parameter value, so as to use the assigned sampling frame to prompt whether the current ultrasonic instrument is suitable for switching to the Doppler mode. For example, assuming that the quality detection results are divided into three levels: high, medium, and low, the visual parameter value is specifically the color parameter value, and assuming that high quality corresponds to green, medium quality corresponds to yellow, and low quality corresponds to red. Therefore, by assigning the color parameter value to the color parameter of the sampling frame, if the current quality detection result indicates high image quality, a green sampling frame is displayed; if the current quality detection result indicates medium image quality, a yellow sampling frame is displayed; if the current quality detection result indicates low image quality, a red sampling frame is displayed. Among them, when the sampling frame is red, it means that it is not recommended or not suitable to enter the Doppler mode at present. In this way, after seeing the corresponding color of the sampling frame, the operator can know the quality level of the current ultrasonic image and the picture of the region of interest, and the operator determines whether to enter the Doppler mode. That is, this embodiment only plays a prompting role here and does not limit the switching operation of the working mode of the ultrasonic instrument by the operator.

[0129] It can be seen that in the embodiment of the present application, the entire image screen of the ultrasonic image and the picture of the target region of interest in the ultrasonic image are both used as the pictures to be detected, and the image quality of the entire image screen of the ultrasonic image and the picture of the target region of interest in the ultrasonic image are respectively detected to obtain the first quality detection result and the second quality detection result, and then the first quality detection result and the second quality detection result are combined to jointly determine whether the current ultrasonic instrument is suitable for switching to the target working mode. Further, to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode, the form of the prompt information can be in the form of color, text, sound, etc. First, determine the corresponding prompt information according to the current quality detection result, and use the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode, so that after receiving the prompt information, the operator can determine whether to switch the current ultrasonic instrument to the target working mode.

[0130] See Figure 7As shown in the figure, an embodiment of the present application discloses an ultrasonic instrument working mode switching device, which includes:

[0131] A detection screen determination module 11, configured to determine a to-be-detected screen from the ultrasonic images collected by the current ultrasonic instrument;

[0132] A quality detection module 12, configured to perform image quality detection on the to-be-detected screen to obtain a current quality detection result;

[0133] A result determination module 13, configured to determine whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current quality detection result.

[0134] It can be seen that the present application determines a to-be-detected screen from the ultrasonic images collected by the current ultrasonic instrument; performs image quality detection on the to-be-detected screen to obtain a current quality detection result; and determines whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current quality detection result. Thus, after the ultrasonic images are collected by the current ultrasonic instrument, the present application needs to perform image quality detection on the to-be-detected screen in the ultrasonic images, and determine whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current image quality detection result. That is, before switching the working mode of the ultrasonic instrument, the present application can perform quality control on the ultrasonic images collected by the ultrasonic instrument to determine whether the current ultrasonic instrument is suitable for switching to a target working mode according to the quality control result, so as to avoid the situation of still switching the working mode when the quality of the ultrasonic images is not high as much as possible.

[0135] In some specific embodiments, the to-be-detected screen is the entire image screen of the ultrasonic image;

[0136] Correspondingly, the quality detection module 12 specifically includes:

[0137] A first detection unit, configured to perform image quality detection on the entire image screen of the ultrasonic image by using a first deep learning model to obtain a current quality detection result.

[0138] In some specific embodiments, the to-be-detected screen is the entire image screen of the ultrasonic image;

[0139] Correspondingly, the quality detection module 12 specifically includes:

[0140] A second detection unit, configured to calculate an image quality evaluation index of the entire image screen of the ultrasonic image to obtain a current quality detection result.

[0141] In some specific embodiments, the first detection unit specifically includes:

[0142] An image input unit for inputting the entire image frame of the ultrasonic image into a first deep learning model; wherein, the first deep learning model includes a first classifier and a second classifier;

[0143] A model detection unit for using the first classifier to determine the tissue perspective type of the ultrasonic image, and based on the tissue perspective type and using the second classifier to determine the current image quality detection result of the entire image frame of the ultrasonic image; the tissue perspective type is used to characterize the target tissue displayed on the current ultrasonic image and the corresponding perspective.

[0144] In some specific embodiments, the training set for training the first deep learning model includes a number of historical ultrasonic images, first annotation information characterizing the tissue perspective type of the historical ultrasonic images, and second annotation information characterizing the historical image quality detection results of the entire image frames of the historical ultrasonic images;

[0145] Wherein, the historical image quality detection results include the image frame quality standard degree and the corresponding image frame quality score.

[0146] In some specific embodiments, the image to be detected is the target region of interest image in the ultrasonic image;

[0147] Correspondingly, the detection screen determination module 11 may specifically include:

[0148] A sampling position detection unit for detecting the sampling position on the ultrasonic image collected by the current ultrasonic instrument;

[0149] A screen selection unit for selecting the region image corresponding to the sampling position from the ultrasonic image as the target region of interest image.

[0150] In some specific embodiments, the quality detection module 12 may specifically include:

[0151] A third detection unit for using a second deep learning model to perform image quality detection on the target region of interest image to obtain the current quality detection result.

[0152] In some specific embodiments, the quality detection module 12 may specifically include:

[0153] A fourth detection unit for calculating the image quality evaluation index of the target region of interest image to obtain the current quality detection result.

[0154] In some specific embodiments, the training set for training the second deep learning model includes a number of historical region-of-interest images and third annotation information representing the historical image quality detection results of the historical region-of-interest images;

[0155] Among them, the historical image quality detection results include the standard degree of the image screen quality and the corresponding image screen quality score.

[0156] In some specific embodiments, the quality detection module 12 may specifically include:

[0157] A fifth detection unit for performing image quality detection on the entire image screen of the ultrasonic image to obtain a first quality detection result;

[0158] A sixth detection unit for performing image quality detection on the target region-of-interest screen in the ultrasonic image to obtain a second quality detection result.

[0159] In some specific embodiments, the result determination module 13 may specifically include:

[0160] A weighting unit for performing a weighted calculation on the image screen quality score in the first quality detection result and the image screen quality score in the second quality detection result to obtain a weighted calculation result;

[0161] A first size relationship determination unit for determining a first size relationship between the weighted calculation result and a first preset threshold;

[0162] A first mode switching unit for determining whether the current ultrasonic instrument is suitable for switching to a target working mode based on the first size relationship.

[0163] In some specific embodiments, the result determination module 13 may specifically include:

[0164] A second size relationship determination unit for determining a second size relationship between the image screen quality score in the first quality detection result and a second preset threshold;

[0165] A third size relationship determination unit for determining a third size relationship between the image screen quality score in the second quality detection result and a third preset threshold;

[0166] A second mode switching unit for determining whether the current ultrasonic instrument is suitable for switching to a target working mode based on the second size relationship and the third size relationship.

[0167] In some specific embodiments, after determining whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current quality detection result, the device further includes:

[0168] A prompt information determination unit, configured to determine corresponding prompt information based on the current quality detection result;

[0169] A prompt unit, configured to use the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to a target working mode.

[0170] In some specific embodiments, the prompt information determination unit is specifically configured to determine corresponding visual parameter values based on the current quality detection result;

[0171] Correspondingly, the prompt unit is specifically configured to assign corresponding visual parameters of the sampling frame on the current ultrasonic image by using the visual parameter values, so as to use the assigned sampling frame to prompt whether the current ultrasonic instrument is suitable for switching to a target working mode

[0172] In some specific embodiments, after determining whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current quality detection result, the device is further configured to, if the current ultrasonic instrument is suitable for switching to the target working mode, adjust the volume size of the sampling frame according to the tissue structure type in the sampling frame on the current ultrasonic image.

[0173] In some specific embodiments, the device is further configured to monitor whether a switching request for switching to a target working mode is obtained; if the switching request is monitored, trigger the step of determining a to-be-detected picture from the ultrasonic images collected by the current ultrasonic instrument;

[0174] Correspondingly, after determining whether the current ultrasonic instrument is suitable for switching to a target working mode based on the current quality detection result, the device is further configured to, if the current ultrasonic instrument is suitable for switching to the target working mode, directly switch the ultrasonic instrument to the target working mode.

[0175] Figure 8 The figure is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the ultrasonic instrument working mode switching method executed by the electronic device disclosed in any of the foregoing embodiments.

[0176] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and no specific limitation is imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is imposed here.

[0177] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0178] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, a random access memory, a disk, or an optical disc, etc. The resources stored thereon include an operating system 221, a computer program 222, data 223, etc., and the storage method can be short-term storage or permanent storage.

[0179] Among them, the operating system 221 is used to manage and control each hardware device on the electronic device 20 and the computer program 222, so as to implement the operation and processing of the massive data 223 in the memory 22 by the processor 21. It can be Windows, Unix, Linux, etc. In addition to the computer program that can be used to complete the ultrasonic instrument working mode switching method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks. The data 223 may include not only the data transmitted by the external device received by the electronic device, but also the data collected by its own input / output interface 25, etc.

[0180] Further, an embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the steps of the ultrasonic instrument working mode switching method disclosed in any of the foregoing embodiments are implemented.

[0181] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts between the various embodiments, reference can be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and reference can be made to the description of the method part for related parts.

[0182] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner 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 implementation should not be considered to exceed the scope of this application.

[0183] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0184] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0185] The above has introduced in detail a method, apparatus, device and storage medium for switching the working mode of an ultrasonic instrument. Specific examples are used in this text to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for switching the working mode of an ultrasonic instrument, characterized in that, it includes: Determine a picture to be detected from the ultrasonic images collected by the current ultrasonic instrument; Perform image quality detection on the picture to be detected to obtain the current quality detection result; Based on the current quality detection result, determine whether the current ultrasonic instrument is suitable for switching to the target working mode.

2. The method for switching the working mode of an ultrasonic instrument according to claim 1, characterized in that, The picture to be detected is the entire image picture of the ultrasonic image; The performing image quality detection on the picture to be detected to obtain the current quality detection result includes: Using a first deep learning model to perform image quality detection on the entire image picture of the ultrasonic image to obtain the current quality detection result; Or, calculate the image quality evaluation index of the entire image picture of the ultrasonic image to obtain the current quality detection result.

3. The method for switching the working mode of an ultrasonic instrument according to claim 2, characterized in that, The using a first deep learning model to perform image quality detection on the entire image picture of the ultrasonic image to obtain the current quality detection result includes: Input the entire image picture of the ultrasonic image into the first deep learning model; wherein, the first deep learning model includes a first classifier and a second classifier; Using the first classifier to determine the tissue perspective type of the ultrasonic image, and based on the tissue perspective type and using the second classifier to determine the current image quality detection result of the entire image picture of the ultrasonic image; the tissue perspective type is used to characterize the target tissue and the corresponding perspective displayed on the current ultrasonic image.

4. The method for switching the working mode of an ultrasonic instrument according to claim 3, characterized in that, The training set for training the first deep learning model includes a number of historical ultrasonic images, first annotation information characterizing the tissue perspective type of the historical ultrasonic images, and second annotation information characterizing the historical image quality detection results of the entire image pictures of the historical ultrasonic images; wherein, the historical image quality detection results include the image picture quality standard degree and the corresponding image picture quality score.

5. The method for switching the working mode of an ultrasonic instrument according to claim 1, characterized in that, The picture to be detected is the target region of interest picture in the ultrasonic image; The determining a picture to be detected from the ultrasonic images collected by the current ultrasonic instrument includes: Detect the sampling position on the ultrasonic image collected by the current ultrasonic instrument; Select the region picture corresponding to the sampling position from the ultrasonic image as the target region of interest picture.

6. The method for switching the working mode of an ultrasonic instrument according to claim 5, characterized in that, The performing image quality detection on the picture to be detected to obtain the current quality detection result includes: Using a second deep learning model to perform image quality detection on the target region of interest picture to obtain the current quality detection result; Or, calculate the image quality evaluation index of the target region of interest picture to obtain the current quality detection result.

7. The method for switching the working mode of an ultrasonic instrument according to claim 6, characterized in that, the training set for training the second deep learning model includes a number of historical pictures of regions of interest and third annotation information representing the historical image quality detection results of the historical pictures of regions of interest; wherein, the historical image quality detection results include the standard degree of the image picture quality and the corresponding image picture quality score.

8. The method for switching the working mode of an ultrasonic instrument according to claim 1, characterized in that, the performing image quality detection on the picture to be detected to obtain the current quality detection result includes: performing image quality detection on the entire image picture of the ultrasonic image to obtain a first quality detection result; performing image quality detection on the picture of the target region of interest in the ultrasonic image to obtain a second quality detection result.

9. The method for switching the working mode of an ultrasonic instrument according to claim 8, characterized in that, the determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result includes: performing weighted calculation on the image picture quality score in the first quality detection result and the image picture quality score in the second quality detection result to obtain a weighted calculation result; determining a first magnitude relationship between the weighted calculation result and a first preset threshold; determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the first magnitude relationship.

10. The method for switching the working mode of an ultrasonic instrument according to claim 8, characterized in that, the determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result includes: determining a second magnitude relationship between the image picture quality score in the first quality detection result and a second preset threshold; determining a third magnitude relationship between the image picture quality score in the second quality detection result and a third preset threshold; determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the second magnitude relationship and the third magnitude relationship.

11. The method for switching the working mode of an ultrasonic instrument according to any one of claims 1 to 10, characterized in that, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, it further includes: determining corresponding prompt information based on the current quality detection result; using the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode.

12. The method for switching the working mode of an ultrasonic instrument according to claim 11, characterized in that, the determining corresponding prompt information based on the current quality detection result includes: determining corresponding visual parameter values based on the current quality detection result; correspondingly, the using the prompt information to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode includes: using the visual parameter values to assign corresponding visual parameters to the sampling frame on the current ultrasonic image, so as to use the assigned sampling frame to prompt whether the current ultrasonic instrument is suitable for switching to the target working mode.

13. The method for switching the working mode of an ultrasonic instrument according to any one of claims 1 to 10, characterized in that, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, it further includes: if the current ultrasonic instrument is suitable for switching to the target working mode, adjusting the volume size of the sampling frame according to the tissue structure type in the sampling frame on the current ultrasonic image.

14. The method for switching the working mode of an ultrasonic instrument according to any one of claims 1 to 10, characterized in that, it further includes: monitoring whether a switching request for switching to the target working mode is obtained; if the switching request is monitored, triggering the step of determining the picture to be detected from the ultrasonic images collected by the current ultrasonic instrument; correspondingly, after determining whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result, it further includes: if the current ultrasonic instrument is suitable for switching to the target working mode, directly switching the ultrasonic instrument to the target working mode.

15. An apparatus for switching the working mode of an ultrasonic instrument, characterized in that, it includes: a detection picture determination module, configured to determine a picture to be detected from the ultrasonic images collected by the current ultrasonic instrument; a quality detection module, configured to perform image quality detection on the picture to be detected to obtain a current quality detection result; a result determination module, configured to determine whether the current ultrasonic instrument is suitable for switching to the target working mode based on the current quality detection result.

16. An electronic device, characterized in that, it includes: a memory, configured to store a computer program; a processor, configured to execute the computer program to implement the steps of the method for switching the working mode of an ultrasonic instrument according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that, it is used to store a computer program; wherein, when the computer program is executed by a processor, the steps of the method for switching the working mode of an ultrasonic instrument according to any one of claims 1 to 14 are implemented.

Images