Ultrasonic imaging method, device and storage medium

Abstract

The present application provides an ultrasonic imaging method, device and storage medium, the method includes a first workflow and a second workflow, the first workflow includes: emitting a first ultrasonic wave to a target area of ​​a measured object, acquiring a first ultrasonic echo signal; generating a first ultrasonic image based on the first ultrasonic echo signal, selecting a standard section image from the first ultrasonic image; when there is no abnormality in the standard section image, storing the standard section image; when there is an abnormality in the standard section image, switching from the first workflow to a second workflow corresponding to the type of abnormality; the second workflow includes: emitting a second ultrasonic wave to an abnormal part of the measured object corresponding to the standard section image with the abnormality, acquiring a second ultrasonic echo signal; generating a second ultrasonic image based on the second ultrasonic echo signal, and storing the second ultrasonic image. The scheme of the present application can automatically switch the workflow to store the ultrasonic image of the abnormal section.

Description

Technical Field

[0001] The present application relates to the field of ultrasound technology, and more specifically to an ultrasound imaging method, device and storage medium. Background Art

[0002] With the promotion and development of ultrasound scanning and standardized diagnosis technology, the demand for abnormal section retention in clinical diagnosis has gradually increased and become more and more important. Ultrasound examinations are highly dependent on the level and experience of doctors. In order to improve the quality of examinations and diagnoses, ultrasound departments have carried out image quality control. One of the important links in the quality evaluation rules of ultrasound examinations is the requirement to store images of abnormal parts of the scanned object for abnormal conditions. Different types of abnormalities require different sections to be retained.

[0003] The abnormal sections retained in ultrasound scans vary, and there are certain difficulties for both beginners and experienced doctors. Specifically, there are many types of human abnormalities (masses, effusions, heart valve regurgitation, vascular stenosis, etc.), which are not easy for beginners to grasp. Even for senior doctors, sometimes there are problems with missing abnormalities and corresponding sections due to the following reasons, such as missing scans due to human factors, small lesions, or echo characteristics similar to surrounding tissues.

[0004] Ultrasound automatic workflow is a tool that can effectively improve doctors' scanning efficiency, but there is still room for improvement in the preservation of abnormal sections. For example, when using ultrasound automatic workflow, due to the different abnormalities of different patients, the usual examination workflow will not take it as part of the main protocol (a set of standard sections that must be checked), but is set to temporarily insert the corresponding section when an abnormality is found. In addition, the current ultrasound automatic workflow can only add one blank section at a time, and it is necessary to manually enter the section name, switch the image mode, manually annotate, select the measurement items, etc., which is very time-consuming and inefficient.

[0005] It can be seen that this field lacks an automated abnormal section intelligent analysis and preservation system to meet the needs of ultrasound scanning and diagnosis quality control, improve the efficiency and quality of ultrasound doctors' scanning and diagnosis, and is of great significance to ultrasound clinical diagnosis. Summary of the invention

[0006] In order to solve at least one of the above problems, the present application proposes an ultrasound imaging solution, which can intelligently detect abnormal sections and automatically switch workflows to store ultrasound images of abnormal sections. The ultrasound imaging solution proposed in the present application is briefly described below, and more details will be described in the specific implementation mode in conjunction with the accompanying drawings later.

[0007] According to one aspect of the present application, there is provided an ultrasound imaging method, the method comprising: a first workflow and a second workflow, wherein: the first workflow comprises: transmitting a first ultrasound wave to a target area of ​​an object under test, receiving an echo of the first ultrasound wave, and acquiring a first ultrasound echo signal based on the echo of the first ultrasound wave; generating a first ultrasound image based on the first ultrasound echo signal, and selecting a standard section image from the first ultrasound image; when there is no abnormality in the standard section image, storing the standard section image; when there is an abnormality in the standard section image, switching from the first workflow to a second workflow corresponding to the type of the abnormality; the second workflow comprises: transmitting a second ultrasound wave to an abnormal part of the object under test corresponding to the standard section image where the abnormality exists, receiving an echo of the second ultrasound wave, and acquiring a second ultrasound echo signal based on the echo of the second ultrasound wave; generating a second ultrasound image based on the second ultrasound echo signal, and storing the second ultrasound image.

[0008] According to another aspect of the present application, an ultrasound imaging method is provided, the method comprising a first workflow and a second workflow, wherein: the first workflow comprises: emitting a first ultrasound wave to a target area of ​​a measured object, receiving an echo of the first ultrasound wave, and acquiring a first ultrasound echo signal based on the echo of the first ultrasound wave; generating a first ultrasound image based on the first ultrasound echo signal, and selecting a standard section image from the first ultrasound image; in response to an operator's instruction to start an analysis process for the standard section image, starting an analysis process for the standard section image, the analysis process for the standard section image comprising an analysis process for the image quality of the standard section image and an analysis process for the image content of the standard section image; when the image quality of the standard section image does not meet predetermined requirements When the image quality of the standard section image reaches the predetermined requirement and there is no abnormality in the image content of the standard section image, the standard section image is stored; when the image quality of the standard section image reaches the predetermined requirement and there is an abnormality in the image content of the standard section image, the first workflow is switched to a second workflow corresponding to the type of the abnormality; the second workflow comprises: transmitting a second ultrasonic wave to the abnormal part corresponding to the standard section image of the measured object where the abnormality exists, receiving the echo of the second ultrasonic wave, and acquiring a second ultrasonic echo signal based on the echo of the second ultrasonic wave; generating a second ultrasonic image based on the second ultrasonic echo signal, and storing the second ultrasonic image.

[0009] According to another aspect of the present application, there is provided an ultrasound imaging method, the method comprising: acquiring a first scanning protocol for a target area, the first scanning protocol comprising a set of standard sections required to be scanned for the target area; in response to an instruction to execute the first scanning protocol for the target area of ​​the measured object, controlling the ultrasound probe to transmit a first ultrasound wave to the target area of ​​the measured object, receiving an echo of the first ultrasound wave, and acquiring a first ultrasound echo signal based on the echo of the first ultrasound wave; generating a first ultrasound image based on the first ultrasound echo signal, and selecting a standard section image from the first ultrasound image; storing the standard section image when no abnormality exists in the standard section image; and inserting a second scanning protocol into the first scanning protocol when an abnormality exists in the standard section image, the second scanning protocol comprising a set of scanning sections corresponding to the abnormal type of the standard section.

[0010] According to another aspect of the present application, an ultrasonic imaging device is provided, the device comprising an ultrasonic probe, a transmit / receive sequence controller and a processor, the ultrasonic probe, the transmit / receive sequence controller and the processor being used to execute a first workflow and a second workflow, wherein: the first workflow comprises: the transmit / receive sequence controller excites the ultrasonic probe to transmit a first ultrasonic wave to a target area of ​​a measured object, receives an echo of the first ultrasonic wave, and acquires a first ultrasonic echo signal based on the echo of the first ultrasonic wave; the processor generates a first ultrasonic image based on the first ultrasonic echo signal, and selects a standard section image from the first ultrasonic image; when there is no abnormality in the standard section image, the standard section image is stored; when it is determined that there is an abnormality in the standard section image, the first workflow is switched to a second workflow corresponding to the type of the abnormality; the second workflow comprises: the transmit / receive sequence controller excites the ultrasonic probe to transmit a second ultrasonic wave to an abnormal part of the measured object corresponding to the standard section image where the abnormality exists, receives an echo of the second ultrasonic wave, and acquires a second ultrasonic echo signal based on the echo of the second ultrasonic wave; the processor generates a second ultrasonic image based on the second ultrasonic echo signal, and stores the second ultrasonic image.

[0011] According to another aspect of the present application, an ultrasonic imaging device is provided, the device comprising an ultrasonic probe, a transmit / receive sequence controller and a processor, the ultrasonic probe, the transmit / receive sequence controller and the processor being used to execute a first workflow and a second workflow, wherein: the first workflow comprises: the transmit / receive sequence controller excites the ultrasonic probe to transmit a first ultrasonic wave to a target area of ​​a measured object, receives an echo of the first ultrasonic wave, and acquires a first ultrasonic echo signal based on the echo of the first ultrasonic wave; the processor generates a first ultrasonic image based on the first ultrasonic echo signal, and selects a standard section image from the first ultrasonic image; in response to an operator's instruction to start an analysis process for the standard section image, the analysis process for the standard section image is started, the analysis process for the standard section image comprising an analysis process for the image quality of the standard section image and an analysis process for the image content of the standard section image Process; when the image quality of the standard section image cannot meet the predetermined requirements, reselect the standard section image until the selected standard section image meets the predetermined requirements; when the image quality of the standard section image meets the predetermined requirements and there is no abnormality in the image content of the standard section image, store the standard section image; when the image quality of the standard section image meets the predetermined requirements and there is an abnormality in the image content of the standard section image, switch from the first workflow to the second workflow corresponding to the type of the abnormality; the second workflow includes: the transmit / receive sequence controller excites the ultrasound probe to transmit a second ultrasound wave to the abnormal part corresponding to the standard section image of the object under test where the abnormality exists, receives the echo of the second ultrasound wave, and obtains a second ultrasound echo signal based on the echo of the second ultrasound wave; the processor generates a second ultrasound image based on the second ultrasound echo signal, and stores the second ultrasound image.

[0012] According to another aspect of the present application, an ultrasonic imaging device is provided, the device comprising an ultrasonic probe, a transmit / receive sequence controller and a processor, wherein: the processor is used to obtain a first scanning protocol for a target area, the first scanning protocol comprising a set of standard sections required to be scanned for the target area; the processor is also used to control the transmit / receive sequence controller to excite the ultrasonic probe to transmit a first ultrasonic wave to the target area of ​​the measured object in response to an instruction to execute the first scanning protocol for the target area of ​​the measured object, receive an echo of the first ultrasonic wave, and obtain a first ultrasonic echo signal based on the echo of the first ultrasonic wave; the processor is also used to generate a first ultrasonic image based on the first ultrasonic echo signal, and select a standard section image from the first ultrasonic image; when there is no abnormality in the standard section image, the standard section image is stored; when there is an abnormality in the standard section image, a second scanning protocol is inserted into the first scanning protocol, the second scanning protocol comprising a set of scanning sections corresponding to the abnormal type of the standard section.

[0013] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored, and the computer program executes the above-mentioned ultrasound imaging method when running.

[0014] According to yet another aspect of the present application, a computer program is provided. When the computer program is executed by a computer or a processor, the computer program is used to execute the above-mentioned ultrasound imaging method.

[0015] According to the ultrasound imaging method and device of the embodiment of the present application, it is possible to intelligently detect abnormal sections, and automatically switch from a first workflow to a second workflow corresponding to the abnormal type when detecting abnormal sections, so as to store ultrasound images of the abnormal sections, thereby improving the efficiency and quality of doctors' scanning and diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 A schematic block diagram of an exemplary ultrasound imaging device for implementing an ultrasound imaging method according to an embodiment of the present application is shown.

[0018] Figure 2 A schematic flowchart of an ultrasound imaging method according to an embodiment of the present application is shown.

[0019] Figure 3A schematic flowchart showing switching to a second workflow in an ultrasound imaging method according to an embodiment of the present application is shown.

[0020] Figure 4A , Figure 4B and Figure 4C An exemplary schematic diagram showing switching to a second workflow in an ultrasound imaging method according to an embodiment of the present application is shown.

[0021] Figure 5 A schematic system flow of an ultrasound imaging method according to an embodiment of the present application is shown.

[0022] Figure 6 A schematic flowchart of an ultrasound imaging method according to another embodiment of the present application is shown.

[0023] Figure 7 A schematic flowchart of an ultrasound imaging method according to yet another embodiment of the present application is shown.

[0024] Figure 8 A schematic block diagram of an ultrasonic imaging device according to an embodiment of the present application is shown.

[0025] Fig. 9 A schematic block diagram of an ultrasonic imaging device according to another embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present application more obvious, the example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0027] First, refer to Figure 1 An exemplary ultrasonic imaging device for implementing the ultrasonic imaging method of an embodiment of the present application is described below.

[0028] Figure 1 FIG. 1 is a schematic diagram of a structural block diagram of an exemplary ultrasonic imaging device 10 for implementing the ultrasonic imaging method of an embodiment of the present application. Figure 1As shown, the ultrasonic imaging device 10 may include an ultrasonic probe 100, a transmit / receive selection switch 101, a transmit / receive sequence controller 102, a processor 103, a display 104, and a memory 105. The transmit / receive sequence controller 102 may excite the ultrasonic probe 100 to transmit ultrasonic waves to a target object (measured object), and may also control the ultrasonic probe 100 to receive ultrasonic echoes returned from the target object, thereby obtaining ultrasonic echo signals / data. The processor 103 processes the ultrasonic echo signals / data to obtain tissue-related parameters and ultrasonic images of the target object. The ultrasonic images obtained by the processor 103 may be stored in the memory 105, and these ultrasonic images may be displayed on the display 104.

[0029] In the embodiment of the present application, the display 104 of the aforementioned ultrasonic imaging device 10 may be a touch screen, a liquid crystal display, etc., or it may be an independent display device such as a liquid crystal display, a television, etc. that is independent of the ultrasonic imaging device 10, or it may be a display screen on an electronic device such as a mobile phone or a tablet computer.

[0030] In the embodiment of the present application, the memory 105 of the aforementioned ultrasonic imaging device 10 may be a flash memory card, a solid-state memory, a hard disk, etc.

[0031] An embodiment of the present application also provides a computer-readable storage medium, which stores multiple program instructions. After the multiple program instructions are called and executed by the processor 103, some or all of the steps in the ultrasound imaging method in each embodiment of the present application or any combination of the steps can be executed.

[0032] In one embodiment, the computer-readable storage medium may be the memory 105, which may be a non-volatile storage medium such as a flash memory card, a solid-state memory, or a hard disk.

[0033] In the embodiment of the present application, the processor 103 of the aforementioned ultrasonic imaging device 10 can be implemented by software, hardware, firmware or a combination thereof, and can use circuits, single or multiple application specific integrated circuits (ASICs), single or multiple general integrated circuits, single or multiple microprocessors, single or multiple programmable logic devices, or a combination of the aforementioned circuits or devices, or other suitable circuits or devices, so that the processor 103 can execute the corresponding steps of the ultrasonic imaging method in each embodiment.

[0034] Combine the following Figures 2 to 7 The ultrasonic imaging method in the present application is described in detail, and the method can be performed by the aforementioned ultrasonic imaging device 10.

[0035] Figure 2FIG. 2 shows a schematic flow chart of an ultrasound imaging method 200 according to an embodiment of the present application. Figure 2 As shown, the ultrasound imaging method 200 may include a first workflow (also referred to as a main protocol) and a second workflow (also referred to as a sub-protocol), wherein the first workflow may include the following steps:

[0036] In step S210, a first ultrasonic wave is transmitted to a target area of ​​the object to be measured, an echo of the first ultrasonic wave is received, and a first ultrasonic echo signal is acquired based on the echo of the first ultrasonic wave.

[0037] In step S220, a first ultrasound image is generated based on the first ultrasound echo signal, and a standard section image is selected from the first ultrasound image.

[0038] In step S230, it is determined (manually or automatically) whether the standard section image has an abnormality. If it is determined that the standard section image has no abnormality, step S240 is performed; if it is determined that the standard section image has an abnormality, step S250 is performed.

[0039] In step S240, the standard section image and the measurement result are stored.

[0040] In step S250, the first workflow is switched to a second workflow corresponding to the type of the exception, and the second workflow may include the following steps:

[0041] In step S251, a second ultrasonic wave is transmitted to the abnormal part of the object under test corresponding to the standard section image where the abnormality exists, an echo of the second ultrasonic wave is received, and a second ultrasonic echo signal is acquired based on the echo of the second ultrasonic wave.

[0042] In step S252 , a second ultrasonic image is generated based on the second ultrasonic echo signal, and the second ultrasonic image is stored.

[0043] In an embodiment of the present application, the object to be measured may be a person to be subjected to an ultrasonic examination, and the target area of ​​the object to be measured may be an area of ​​the body part of the object to be measured that needs to be subjected to an ultrasonic examination. In an embodiment of the present application, the first ultrasonic wave is emitted to the target area of ​​the object to be measured in order to obtain a first ultrasonic image of the target area of ​​the object to be measured so as to obtain a standard section image therefrom. Here, the first ultrasonic wave is so named in order to distinguish it from the second ultrasonic wave in the second workflow, and has no other limiting effect. After receiving the echo of the first ultrasonic wave, the first ultrasonic echo signal can be obtained, and the first ultrasonic echo signal can be processed to obtain the first ultrasonic image. Similarly, the first ultrasonic echo signal and the first ultrasonic image are so named in order to distinguish them from the second ultrasonic echo signal and the second ultrasonic image in the second workflow, respectively, and have no other limiting effect. Exemplarily, the first ultrasonic echo signal can be processed such as gain compensation, beamforming, orthogonal demodulation, image enhancement, etc. to obtain a first ultrasonic image of the target area of ​​the object to be measured.

[0044] Specifically, the ultrasonic device transmits an ultrasonic signal, and the transducer array element of the probe converts the electrical signal into an acoustic signal and transmits it to the target object; then the transducer array element of the probe converts the acoustic signal of the ultrasonic echo into an electrical signal; the signal is filtered and amplified by the analog circuit, and then converted into a digital signal by the analog-to-digital converter; the data of each array channel is further beamformed to obtain a radio frequency signal, and then the in-phase / orthogonal two-way orthogonal signal is obtained by orthogonal demodulation and sent to the subsequent imaging processing module. The use of gain compensation for the received ultrasonic echo signal can weaken the subsequent processing problems caused by the decrease in signal strength with depth. The signal after this processing is actually an analog signal. Therefore, in order to improve the signal processing efficiency and reduce the complexity of the hardware platform, an analog-to-digital converter is required to convert the analog echo signal into a digital echo signal. After the channel data after the analog-to-digital conversion is completed, the digital beam synthesis can be performed to form the scan line data according to the delay difference caused by the difference in the distance from the focal point to the channel. The data processing performed before this can be collectively referred to as front-end processing. The data obtained after this stage is completed can be called radio frequency signal data. The reason why it is called "RF" is that the signal carries the probe receiving clock frequency, and the carrier frequency happens to be in the RF band of the communication field. After acquiring the RF signal data, the signal carrier is removed through in-phase / quadrature demodulation, the tissue structure information contained in the signal is extracted, and filtering is performed to remove noise. At this time, the signal obtained is the baseband signal. All the processing required to process the RF signal to the baseband signal can be collectively referred to as mid-end processing. Finally, the intensity of the baseband signal is calculated and its grayscale level is logarithmically compressed and grayscale converted to obtain an ultrasound image. The processing completed at this time can be collectively referred to as back-end processing. So far, a frame of ultrasound image that can be displayed can be obtained.

[0045] In an embodiment of the present application, after acquiring the first ultrasound image, a standard section image can be selected from it. Here, according to the object to be measured and the target area to be measured, the selected standard section image can be a pre-set corresponding standard section image. For example, for scanning of different parts, the standard section image to be imaged is different. Of course, the standard section image to be selected can also be modifiable or settable by the operator. For example, the standard section image can be selected from the first ultrasound image in response to the operator's instruction to select the standard section image. Generally, the standard section image can be a standard section image that is valuable, meets the diagnostic needs, and has a consensus among experts. In addition, after selecting the standard section, the relevant parameters in the standard section image can be measured. The relevant parameters to be measured can be the corresponding parameters pre-set, or can be modifiable or settable by the operator. The measurement results of the relevant parameters in the standard section image can be used to determine whether the standard section image is abnormal (for example, if the measurement result of a parameter is not within the normal value range, it is determined that there is an abnormality); or, it can also be determined whether the standard section image is abnormal by other methods or in combination with other methods, as described later below. The following takes the heart scanning mode as an example to describe the relevant process of selecting the standard section image, as described below.

[0046] First, open the automatic scanning workflow, such as four-chamber heart and five-chamber heart section scanning in the heart scanning mode, and record the section type to be scanned; then, acquire an ultrasound image, compare the acquired image with the standard image of the section to be scanned, and determine whether it is a standard section image. If so, it can be selected as the standard section image for subsequent processing. When judging the standard section image, the structural information of the tissue or organ in the image, the positional relationship with the adjacent structures, and the image texture characteristics of the tissue structure can be considered; then, it can be determined whether there are items to be measured in the selected standard section image, and whether the corresponding measurement has been performed; finally, according to the judgment result, the doctor is given corresponding prompts.

[0047] In an embodiment of the present application, after selecting a standard section image, it is possible to automatically determine whether there is an abnormality in the standard section image. For example, it is possible to determine whether there is an abnormality in the standard section image by determining at least one of the following: whether the image content is consistent with the section name; whether there is an abnormal structure in the image.

[0048] In an embodiment of the present application, determining whether the image content is consistent with the section name may include: determining whether the human body structure features in the selected standard section image are consistent with the normal human body structure features stored in the standard section image database, if they are consistent, it can be determined that the image content is consistent with the section name, if they are inconsistent, it can be determined that the image content is inconsistent with the section name. Exemplarily, whether the image content is consistent with the section name can be determined by image matching or image classification, and these two methods are described below.

[0049] In the embodiment of the present application, determining whether the image content matches the section name by image matching may include the following steps: (1) Establishing a library: Establishing a detailed human section ultrasound library - each standard section in the protocol contains section images of normal human bodies and various disease populations to increase the matching range. This step can be an offline step. The library information needs to be established during the system design stage. During the scanning process, the library information already exists and can be used directly. (2) Tissue structure image matching: Each image in the library has its own characteristics (such as what shape of high echo is in what area of ​​the image, etc.). The image to be scanned (i.e., the selected standard section image) and the image of the corresponding section in the library are subjected to correlation calculation based on the extracted image features using a pattern matching algorithm. If the correlation is higher than a certain threshold, the match is considered successful. A successful match means that the human structure features in the selected standard section image are considered to be consistent with the normal human structure features stored in the standard section image database, that is, the image content is consistent with the section name.

[0050] In an embodiment of the present application, a traditional machine learning or deep learning method can be used to determine whether the image content matches the section name by image classification, for example, including the following steps: (1) Establishing a training database: For a specific detection position, such as the cross section of both kidneys, a certain amount of positive and negative samples are collected. Among them, the positive sample data is a standard cross section image of both kidneys, and the negative sample data is image data other than the standard cross section of both kidneys. (2) Training the section classification model: After the training database is annotated, that is, for each image, the doctor gives whether the image belongs to a standard section or a non-standard section, and by calculating the error between the predicted value and the annotated value of the neural network, it is continuously iterated and gradually approximated, and then the final standard section recognition model is obtained. Among them, the traditional machine learning method needs to first extract features from the image and input the feature matrix into the network model for training, while the deep learning model directly inputs the section image for training. (3) Recognition or classification of the section image: Use the trained model to process the image and determine whether the image content matches the section name.

[0051] In the embodiments of the present application, determining whether there is an abnormal structure in the image can be performed, for example, by means of target detection or image classification. By means of target detection technology, the detection of abnormal positions and the distinction of abnormal situations (i.e., abnormal types) can be achieved; by means of image classification technology, the determination of abnormal situations can be achieved without giving the abnormal position. In addition, determining whether there is an abnormal structure in the image can also be achieved by means of image matching methods in traditional image processing methods.

[0052] Generally, target detection and image classification can roughly include the following steps: (1) Establish a training database: For abnormal conditions at specific locations, such as nodular lesions in thyroid and breast scans, a certain amount of positive and negative samples are collected. Among them, the positive sample data is ultrasound image data with nodular lesions, region of interest (ROI) image blocks, etc., and the negative sample data is ultrasound image data without lesions and ROI image blocks, etc. (2) Train target detection and image classification models: After annotating the training database, the error between the predicted value and the annotated value of the neural network is calculated, and the error is continuously iterated and gradually approximated to obtain the final standard section recognition model. Among them, when training the image classification model, the annotated content is the label of whether the current image and ROI image block are normal or abnormal; in the target detection model, the annotated content is the abnormal and normal position and label of the current image and ROI image block. In addition, if the traditional machine learning method is used, it is necessary to first extract features from the image and input the feature matrix into the network model for training, while the deep learning model directly inputs the section image and ROI image block for training. (3) Identification of image content or detection of abnormal locations: Use the trained model to process the image and determine whether there are abnormalities or the location of abnormalities in the image.

[0053] The above exemplifies various ways of automatically determining whether a standard cross-section image has an abnormality. It should be understood that they are merely illustrative and not restrictive. Under the teachings of this application, any other suitable way may be used to automatically determine whether a standard cross-section image has an abnormality.

[0054] In another embodiment of the present application, the standard section image can be presented to the operator, and the operator can determine whether the standard section image has an abnormality; after making the determination, the operator can input the result of the determination through the human-computer interaction device so that the workflow continues to execute. In this embodiment, it is determined whether the standard section image has an abnormality based on the instruction input after the operator's judgment.

[0055] In an embodiment of the present application, when there is no abnormality in the standard section image, the standard section image can be stored, and the results of measuring the relevant parameters of the standard section image can also be stored; when there is an abnormality in the standard section image, the first workflow is switched to the second workflow corresponding to the type of abnormality determined. The specific content of the second workflow is described in detail later below.

[0056] In another embodiment of the present application, after selecting the standard section image from the first ultrasound image, it is also possible to determine whether the image quality meets the predetermined requirements, which can be performed simultaneously with the determination of whether the standard section image has an abnormality in the foregoing text, or can be performed one after the other. In an embodiment of the present application, when the image quality of the standard section image cannot meet the predetermined requirements, the standard section image can be reselected until the selected standard section image meets the predetermined requirements; when the image quality of the standard section image meets the predetermined requirements and the standard section image has no abnormalities, the standard section image is stored; when the image quality of the standard section image meets the predetermined requirements and the standard section image has an abnormality, the first workflow is switched to the second workflow corresponding to the type of the abnormality.

[0057] In an embodiment of the present application, the indicators for determining whether the image quality meets the predetermined requirements may include at least one of the following: image clarity; image uniformity; whether there are spots, snowflakes, or reticulations in the image; probe depth; and correlation between the operating frequency and the organ.

[0058] In an embodiment of the present application, whether the image clarity meets the predetermined requirements can be determined by an image blur detection method, for example, judging based on the gradient information in the image; in addition, it is also possible to judge whether the image is blurred by a machine learning method, and collect two types of data, clear images and blurred images of the part to be inspected, in advance as sample training models, and abstract the problem into a binary classification problem.

[0059] In an embodiment of the present application, determining whether the image uniformity meets the predetermined requirements can be done, for example, in the following manner: determining whether the histogram of the entire image is relatively average to ensure that the image grayscale is not concentrated in a certain area. In addition, for extreme cases, such as the problem that the image is too bright or too dark as a whole, it is also possible to consider calculating the grayscale mean of the image in the effective area and judging whether it is effective by a threshold. For example, the grayscale value range of a normal ultrasound image is 0 to 255. When calculating the mean value in the effective area of ​​the ultrasound image, if it is less than 40, it can be considered too dark; if it exceeds 200, it can be considered too bright.

[0060] In an embodiment of the present application, determining whether there are spots, snowflakes, or reticulations in an image can be performed by image classification, and distinguishing them through traditional neural networks or deep learning models.

[0061] In the embodiment of the present application, whether the probe depth meets the predetermined requirement can be determined by obtaining the effective area by threshold segmentation of image processing, and then calculating the proportion of the effective area to the entire image for judgment. If the proportion of the effective area meets the threshold requirement, it is determined whether the probe depth meets the predetermined requirement. Generally, the proportion of the effective area should be greater than one-half.

[0062] In the embodiments of the present application, the correlation between the working frequency and the organ can be determined by comparing the current section with the model of the probe actually used. To collect images of different organs, corresponding probes need to be used. For example, for superficial thyroid and breast, linear array probes with high frequency are used; for abdominal organs, convex array probes with low frequency are used.

[0063] As mentioned above, when the image quality of the standard section image meets the predetermined requirements and the standard section image has an abnormality, the first workflow is switched to the second workflow corresponding to the type of the abnormality. The second workflow may include: transmitting a second ultrasonic wave to the abnormal part of the object under test corresponding to the standard section image with the abnormality, receiving the echo of the second ultrasonic wave, and acquiring a second ultrasonic echo signal based on the echo of the second ultrasonic wave; generating a second ultrasonic image based on the second ultrasonic echo signal, and storing the second ultrasonic image.

[0064] Here, the second ultrasonic wave is emitted to the abnormal part of the object under test corresponding to the standard section image with abnormality in order to obtain the second ultrasonic image of the abnormal part of the object under test corresponding to the standard section image with abnormality. Here, the second ultrasonic wave is named so as to distinguish it from the first ultrasonic wave in the first workflow, and has no other restrictive effect. After receiving the echo of the second ultrasonic wave, the second ultrasonic echo signal can be obtained, and the second ultrasonic echo signal can be processed to obtain the second ultrasonic image. Similarly, the second ultrasonic echo signal and the second ultrasonic image are named so as to distinguish them from the first ultrasonic echo signal and the first ultrasonic image in the first workflow, respectively, and have no other restrictive effect. Exemplarily, the second ultrasonic echo signal can be processed such as gain compensation, beamforming, orthogonal demodulation, image enhancement, etc. to obtain a second ultrasonic image of the target area of ​​the object under test. After acquiring the second ultrasonic image, the second ultrasonic image can be stored, thereby realizing the storage of the ultrasonic image of the abnormal section.

[0065] In the embodiments of the present application, the second workflow can also be understood as a workflow (also referred to as a scanning protocol) for scanning a set of predefined scanning sections for types of human abnormalities visible to ultrasound, which has been appropriately or standardizedly configured, such as image mode, image parameters, annotations, body position maps, measurements, etc., and the execution order can be set to meet clinical use requirements and habits, which is equivalent to a sub-protocol or an inserted protocol or an additional protocol. In addition, since the second workflow switched to is a workflow for scanning a set of predefined scanning sections for types of human abnormalities visible to ultrasound, and the ultrasound image of the abnormal section will eventually be stored, switching to the second workflow can also be referred to as inserting a section.

[0066] In an embodiment of the present application, different abnormality types correspond to different second workflows. Among them, the types of abnormalities may include abnormalities that depend on anatomical locations and abnormalities in specific anatomical locations. Among them, abnormalities that depend on anatomical locations refer to abnormalities where the location of the abnormality cannot be known from the abnormality name, while abnormalities in specific anatomical locations refer to abnormalities where the location of the abnormality can be known from the abnormality name. Therefore, the second workflow switched to can be named according to the type of abnormality, wherein: when the type of abnormality is an abnormality that depends on anatomical locations, the naming of the second workflow switched to may include indicating the name of the abnormality and the location of the abnormality; when the type of abnormality is an abnormality in a specific anatomical location, the naming of the second workflow switched to may include indicating the name of the abnormality. For example, abnormalities that depend on anatomical locations, such as masses, effusions, etc., can occur in various parts of the body, and the naming of this type of second workflow needs to be coordinated with the name of the standard section to indicate the location where the abnormality is found. Abnormalities in specific anatomical locations, such as mitral regurgitation, fetal femoral length, etc., the name itself indicates the location where the abnormality occurs, and there is no need to add other location restrictions.

[0067] In an embodiment of the present application, there may be standardized requirements for which position in the first workflow to switch to the second workflow, so as to facilitate scanning and image browsing or be applicable to other scenarios. In one example, the switching operation may be performed on the section that has just completed image detection, because usually an abnormality is found during the scanning process of a standard section, and after saving the standard section, the abnormal detailed scanning and image retention will be performed directly. In view of the fact that most of the current automatic workflows are sequential scanning, that is, after completing the scanning workflow of a certain section, the scanning workflow of the next section will be automatically started, and the rules of the software system are generally operated on the currently selected object, so if the current section is in an unfinished state and the most recently completed section is the previous section of the selected section, it means that this is a natural jump of the process, and switching to the second workflow is for the most recently completed section operation (previous section) rather than the currently selected section. Of course, in other scenarios, it is also possible to switch to the second workflow from a manually specified position, that is, to achieve an artificial jump.

[0068] Combine the following Figure 3 A schematic flowchart of switching to a second workflow in an ultrasound imaging method according to an embodiment of the present application is described, and the flow can also be used as a part of the first workflow. Figure 3 As shown, process 300 may include the following steps:

[0069] In step S310, when the standard section image has an abnormality, it is determined whether the image detection of the standard section image is completed. If it is determined that the image detection of the standard section image is completed, step S320 is performed; if it is determined that the image detection of the standard section image is not completed, step S330 is performed.

[0070] In step S320, the second workflow is switched from the first node, where the first node is a node where the image detection of the standard section image is completed.

[0071] In step S330, it is determined whether the most recently completed section is the standard section image of the previous frame of the standard section image. If it is determined that the most recently completed section is the standard section image of the previous frame of the standard section image, step S340 is performed; if it is determined that the most recently completed section is not the standard section image of the previous frame of the standard section image, step S320 is performed.

[0072] In step S340, the second workflow is switched from the second node, where the second node is the node where the image detection of the previous frame of standard section image is completed.

[0073] In this embodiment, determining whether the image detection of the standard section image is completed may include determining whether the measurement items of the standard section image are completed, including but not limited to the following situations: (1) whether the corresponding measurement has been performed, and if not, a prompt is given; (2) whether the position of the measurement ruler is appropriate, including but not limited to the following possibilities: a. whether the measurement ruler is near the boundary, such as the carotid intima-media thickness (IMT), the long diameter of the breast nodule, etc.; b. whether the measurement items meet the number and size requirements, such as when measuring the heart M-mode, two M-mode lines of diastole and systole are required, and usually there should be a certain difference in the distance between the two lines; c. whether the measurement ruler is at an accurate tissue structure position, such as the liver-kidney brightness ratio, whether the two ROIs are at the liver and kidney positions, or whether there are liver and kidney areas in the image, etc.

[0074] In this embodiment, if the currently selected section is a completed section, then the second workflow is switched after the currently selected section; if the currently selected section is an unfinished section and the most recently completed section (the most recently completed section refers to the section that last completed image detection before the image detection of the currently selected section) is the previous section of the currently selected section (sequential process, natural jump), then the second workflow is switched after the most recently completed section; if the currently selected section is an unfinished section and the most recently completed section is not the previous section of the currently selected section (artificial jump), then the second workflow is switched after the currently selected section.

[0075] Can be combined Figure 4A , Figure 4B and Figure 4C To understand the above process, FIG. 4A to FIG. 4C In the figure, the rectangle box represents the currently selected slice, and the broad arrow represents the location to switch to the second workflow. Figure 4A In , the currently selected slice is an unfinished slice and the most recently completed slice is the slice before the currently selected slice, so the second workflow is switched after the most recently completed slice. Figure 4B In the , the currently selected section is the completed section, so switch to the second workflow after the currently selected section; Figure 4C In the example, the currently selected slice is an unfinished slice and the most recently completed slice is not the previous slice of the currently selected slice (because the current slice is still the first slice and no image detection of any slice has been completed before this), so the second workflow is switched after the currently selected slice.

[0076] Generally, non-obstetric ultrasound examinations can be completed in a certain order, and when there is no abnormality, the next section is scanned directly. Therefore, most of the automatic ultrasound workflows will preset the protocol to automatically start the scanning workflow of the section in order (the scanning workflow of the section can be referred to as the section), which can reduce the steps of manually starting the section. However, when an abnormality is found in the section that has just been stored and an operation needs to be performed on it, since the next section is set to start automatically, the focus has actually jumped to the next section. At this time, the doctor needs to step back and switch the focus to the previous section before operating. However, since this is a low-frequency operation relative to the entire examination, the doctor will often forget to adjust the focus position due to inertial thinking, which will cause the problem of mistakenly adding the section to the next section (such as recording the wrong mass position). Therefore, according to the above method of the present application, automatically switching the section after determining the abnormality (i.e., switching to the second workflow) can not only improve the scanning efficiency, but also effectively reduce the situation where the doctor manually switches the section and makes mistakes, thereby improving the scanning quality.

[0077] In an embodiment of the present application, the first workflow may further include (not shown): when it is determined that there are multiple abnormalities in the standard cross-section image, switch from the first workflow to one of the multiple second workflows corresponding to the types of the multiple abnormalities, and after the one of the multiple second workflows to which the switch is made is executed, execute the remaining workflows in the multiple second workflows. This embodiment can be used in a scenario where there are multiple abnormalities in a standard cross-section image. Among them, if the multiple abnormalities of the standard cross-section image include multiple abnormalities of the same type, the multiple second workflows are distinguished from each other by different identifiers, for example, second workflows with the same type of abnormalities are distinguished from each other by adding suffixes (numbers).

[0078] In an embodiment of the present application, the first workflow may further include (not shown): when an abnormality exists in the standard section image and the type of the abnormality cannot be determined, switching from the first workflow to a second workflow corresponding to an unknown abnormality type. This embodiment may be used in a scenario where an abnormality of an unknown type exists, in which case a blank section may be switched.

[0079] In an embodiment of the present application, the first workflow may further include (not shown): when an abnormality exists in the standard section image, the type of the abnormality is identified so that the operator can confirm whether it is recognized, and the second workflow is switched in response to the operator's approval instruction. In this embodiment, when it is determined that the standard section image has an abnormality, it is not directly and automatically switched to the second workflow corresponding to the abnormality type, but the operator first confirms whether to recognize the automatically detected abnormality, and switches to the second workflow when the operator approves, which can further ensure the correctness of the workflow switching and further improve the scanning quality. In addition, if the operator does not approve, that is, the operator's disapproval instruction is received, it does not switch to the second workflow, but continues to perform the corresponding operation in the first workflow on the next frame of the standard section image. Alternatively, if the operator does not approve, it can also switch to the second workflow that the operator expects to switch to according to the operator's instruction. This embodiment can be used for scenarios where the abnormality is incorrectly identified. Further, it can also be directly switched from the first workflow to the second workflow based on the operator input. This embodiment can be used for scenarios where there is an abnormality but it is not automatically identified.

[0080] In a further embodiment of the present application, the second workflow may further include: measuring the relevant parameters of the abnormal part in the second ultrasound image, and storing the measurement results of the relevant parameters of the abnormal part. In this embodiment, not only the ultrasound image of the section with abnormality can be stored, but also the details of the abnormality can be further stored, providing a more accurate basis for the doctor's diagnosis, thereby further improving the quality of scanning and diagnosis.

[0081] Based on the above description, the ultrasound imaging method according to the embodiment of the present application can intelligently detect abnormal sections, and automatically switch from the first workflow to the second workflow corresponding to the abnormal type when detecting abnormal sections to store ultrasound images of the abnormal sections, thereby improving the efficiency and quality of doctors' scanning and diagnosis.

[0082] According to the ultrasound imaging method of the embodiment of the present application, an automatic workflow can be used to collect images. Each section is collected by the probe to obtain a real-time ultrasound image. The real-time image is frozen, a standard section image is selected, the display effect is adjusted, and the image detection is performed. After the system receives the storage instruction, the image quality control analysis of the stored ultrasound image can be performed to confirm whether the image quality meets the standard, determine whether there is an abnormality in the ultrasound section, and automatically process or prompt the operator to perform corresponding processing, just as Figure 5 shown.

[0083] Combine the following Figure 6 The ultrasonic imaging method 600 according to another embodiment of the present application is described. Figure 6 As shown, the ultrasound imaging method 600 may include (also referred to as a main protocol) and a second workflow (also referred to as a sub-protocol), wherein: the first workflow may include the following steps:

[0084] In step S610, a first ultrasonic wave is transmitted to a target area of ​​the object to be measured, an echo of the first ultrasonic wave is received, and a first ultrasonic echo signal is acquired based on the echo of the first ultrasonic wave.

[0085] In step S620, a first ultrasound image is generated based on the first ultrasound echo signal, and a standard section image is selected from the first ultrasound image;

[0086] In step S630, in response to the operator's instruction to start the analysis process of the image quality of the standard section image, the analysis process of the standard section image is started, including the analysis process of the image quality of the standard section image and the analysis process of the image content of the standard section image.

[0087] In step S640, determine whether the image quality of the standard section image meets the predetermined requirements and determine whether there is any abnormality in the standard section image. If the image quality of the standard section image does not meet the predetermined requirements, execute step S650; if the image quality of the standard section image meets the predetermined requirements, execute step S660 or step S670.

[0088] In step S650, a standard section image is reselected, and the process returns to step S640 for determination until the selected standard section image meets the predetermined requirement.

[0089] In step S660, when the image quality of the standard section image meets the predetermined requirement and there is no abnormality in the image content of the standard section image, the standard section image is stored.

[0090] In step S670, when the image quality of the standard section image meets the predetermined requirement and the image content of the standard section image is abnormal, the first workflow is switched to a second workflow corresponding to the type of the abnormality. The second workflow may include the following steps:

[0091] In step S671, a second ultrasonic wave is transmitted to the abnormal part of the object under test corresponding to the standard section image where the abnormality exists, an echo of the second ultrasonic wave is received, and a second ultrasonic echo signal is acquired based on the echo of the second ultrasonic wave.

[0092] In step S672, a second ultrasonic image is generated based on the second ultrasonic echo signal, and the second ultrasonic image is stored.

[0093] The ultrasonic imaging method 600 according to the embodiment of the present application is combined with the above Figures 2 to 5 The ultrasound imaging method 200 described is generally similar, only some specific processes are further refined. For the sake of brevity, the specific details of the ultrasound imaging method 600 are not repeated here, and the detailed process of the ultrasound imaging method 600 can be understood by referring to the above description.

[0094] Combine the following Figure 7 The ultrasonic imaging method 700 according to another embodiment of the present application is described. Figure 7 As shown, the ultrasound imaging method 700 may include the following steps:

[0095] In step S710, a first scanning protocol of the target area is acquired, where the first scanning protocol includes a set of standard sections required to scan the target area.

[0096] In step S720, in response to an instruction to execute a first scanning protocol on a target area of ​​the object under test, the ultrasonic probe is controlled to transmit a first ultrasonic wave to the target area of ​​the object under test, an echo of the first ultrasonic wave is received, and a first ultrasonic echo signal is acquired based on the echo of the first ultrasonic wave.

[0097] In step S730, a first ultrasound image is generated based on the first ultrasound echo signal, and a standard section image is selected from the first ultrasound image.

[0098] In step S740, it is determined (thoughtfully or automatically) whether there is any abnormality in the standard section image. If there is no abnormality, step S750 is executed, otherwise step S760 is executed.

[0099] In step S750, the standard section image is stored.

[0100] In step S760, a second scanning protocol is inserted into the first scanning protocol, wherein the second scanning protocol includes a set of scanning sections corresponding to the abnormal type of the standard section.

[0101] The ultrasonic imaging method 700 according to the embodiment of the present application is combined with the above Figures 2 to 5 The ultrasonic imaging method 200 described is generally similar, except that the ultrasonic imaging method 200 is described from the perspective of the workflow, while the ultrasonic imaging method 700 is described from the perspective of the scanning protocol. As described above, the workflow in the embodiment of the present application can also be regarded as a scanning protocol, and the switching between workflows can be understood as the switching between scanning protocols from another perspective. In addition, in the present application, the first workflow in the ultrasonic imaging methods 200 and 600 can be the main workflow, and the second workflow can be the sub-workflow. It can be understood that after switching from the main workflow to the sub-workflow because an abnormality is found in the standard section image, the main workflow can be returned to continue execution after the sub-workflow is executed, so it can also be understood as inserting a sub-workflow from the main workflow. Similarly, the first scanning protocol in the ultrasonic imaging method 700 can include a set of standard sections that need to be scanned for the target area, and the second scanning protocol can include a set of scanning sections corresponding to the abnormal type of the standard section. It can be understood that during the execution of the first scanning protocol, an abnormality may occur in the standard section, so a second scanning protocol corresponding to the abnormal type can be inserted.

[0102] In an embodiment of the present application, the first scanning protocol may include at least the standard section type and the number of images to be taken, and may also include position information and scanning sequence information, etc., where the standard section can be understood as a schematic diagram of the standard section); the second scanning protocol may include the type and quantity of images to be scanned according to the type of abnormality, as well as different imaging modes (such as B mode, C mode, etc.), as well as annotations, measurements and other information.

[0103] In an embodiment of the present application, method 700 may further include (not shown): in response to an instruction to execute a second scanning protocol on the abnormal part corresponding to the standard cross-sectional image of the object under test where the abnormality exists, controlling the ultrasonic probe to transmit a second ultrasonic wave to the abnormal part corresponding to the standard cross-sectional image of the object under test where the abnormality exists, receiving an echo of the second ultrasonic wave, and acquiring a second ultrasonic wave echo signal based on the echo of the second ultrasonic wave; generating a second ultrasonic image based on the second ultrasonic wave echo signal, and storing the second ultrasonic image.

[0104] In an embodiment of the present application, when there are multiple abnormalities in the standard cross-sectional image, a second scanning protocol corresponding to each type of the multiple abnormalities may be inserted into the first scanning protocol.

[0105] In an embodiment of the present application, method 700 may further include (not shown): when an abnormality exists in the standard section image, determining whether the image detection of the standard section image is completed; when the image detection of the standard section image is completed, inserting the second scanning protocol at the first node, the first node being the node where the image detection of the standard section image is completed; when the image detection of the standard section image is not completed, determining whether the most recently completed section is the previous frame of standard section image of the standard section image: when the most recently completed section is the previous frame of standard section image, inserting the second scanning protocol at the second node, the second node being the node where the image detection of the previous frame of standard section image is completed; when the most recently completed section is not the previous frame of standard section image, inserting the second scanning protocol at the first node.

[0106] In an embodiment of the present application, the indicator based on whether the standard section image has an abnormality includes at least one of the following: whether the image content is consistent with the section name; whether there is an abnormal structure in the image.

[0107] In an embodiment of the present application, method 700 may further include (not shown): when the image quality of the standard section image cannot meet the predetermined requirements, reselecting the standard section image until the selected standard section image meets the predetermined requirements; when the image quality of the standard section image meets the predetermined requirements and there is no abnormality in the standard section image, storing the standard section image; when the image quality of the standard section image meets the predetermined requirements and there is an abnormality in the standard section image, inserting the second scanning protocol into the first scanning protocol.

[0108] The remaining details of the ultrasound imaging method 700 according to the embodiment of the present application are combined with the above Figures 2 to 5 The described ultrasound imaging method 200 is substantially similar and will not be described again here for the sake of brevity.

[0109] Based on the above description, the ultrasound imaging method according to the embodiment of the present application can intelligently detect abnormal sections and automatically insert a scanning protocol corresponding to the abnormal type when detecting abnormal sections to store ultrasound images of abnormal sections, thereby improving the efficiency and quality of doctors' scanning and diagnosis.

[0110] Combine the following Figure 8 An ultrasonic imaging device provided according to another aspect of the present application is described. Figure 8 FIG. 8 is a schematic block diagram of an ultrasonic imaging device 800 according to an embodiment of the present application. Figure 8As shown, the ultrasound imaging device 800 may include a transmit / receive sequence controller 810, an ultrasound probe 820, and a processor 830. The ultrasound imaging device 800 may be used to perform the following Figure 2 and Figure 6 Ultrasound imaging methods 200 , 600 , and 700 are shown.

[0111] When the ultrasonic imaging device 800 is used to perform the ultrasonic imaging method 200, the transmit / receive sequence controller 810, the ultrasonic probe 820 and the processor 830 are used to perform a first workflow and a second workflow, wherein: the first workflow includes: the transmit / receive sequence controller 810 stimulates the ultrasonic probe 820 to transmit a first ultrasonic wave to a target area of ​​the object to be measured, receives an echo of the first ultrasonic wave, and obtains a first ultrasonic echo signal based on the echo of the first ultrasonic wave; the processor 830 generates a first ultrasonic image based on the first ultrasonic echo signal, and selects a standard section image from the first ultrasonic image; when the standard section image is When there is no abnormality in the cross-sectional image, the standard cross-sectional image is stored; when it is determined that there is an abnormality in the standard cross-sectional image, the first workflow is switched to the second workflow corresponding to the type of the abnormality; the second workflow includes: the transmit / receive sequence controller 810 stimulates the ultrasound probe 820 to transmit a second ultrasound wave to the abnormal part of the object under test corresponding to the standard cross-sectional image where the abnormality exists, receives the echo of the second ultrasound wave, and acquires a second ultrasound echo signal based on the echo of the second ultrasound wave; the processor 830 generates a second ultrasound image based on the second ultrasound echo signal, and stores the second ultrasound image.

[0112] When the ultrasonic imaging device 800 is used to execute the ultrasonic imaging method 600, the transmit / receive sequence controller 810, the ultrasonic probe 820 and the processor 830 are used to execute a first workflow and a second workflow, wherein: the first workflow includes: the transmit / receive sequence controller 810 stimulates the ultrasonic probe 820 to transmit a first ultrasonic wave to a target area of ​​the object to be measured, receives an echo of the first ultrasonic wave, and acquires a first ultrasonic echo signal based on the echo of the first ultrasonic wave; the processor 830 generates a first ultrasonic image based on the first ultrasonic echo signal, and selects a standard section image from the first ultrasonic image; in response to an instruction of the operator to start an analysis process for the standard section image, the analysis process for the standard section image is started, the analysis process for the standard section image includes an analysis process for the image quality of the standard section image and an analysis process for the image content of the standard section image; when the standard section image is When the image quality of the image cannot meet the predetermined requirements, reselect the standard section image until the selected standard section image meets the predetermined requirements; when the image quality of the standard section image meets the predetermined requirements and there is no abnormality in the image content of the standard section image, store the standard section image; when the image quality of the standard section image meets the predetermined requirements and there is an abnormality in the image content of the standard section image, switch from the first workflow to the second workflow corresponding to the type of the abnormality; the second workflow includes: the transmit / receive sequence controller 810 excites the ultrasound probe 820 to transmit a second ultrasound wave to the abnormal part corresponding to the standard section image of the object under test where the abnormality exists, receives the echo of the second ultrasound wave, and obtains a second ultrasound echo signal based on the echo of the second ultrasound wave; the processor 830 generates a second ultrasound image based on the second ultrasound echo signal, and stores the second ultrasound image.

[0113] When the ultrasonic imaging device 800 is used to execute the ultrasonic imaging method 700, the processor 830 is used to obtain a first scanning protocol for the target area, wherein the first scanning protocol includes a set of standard sections required to be scanned for the target area; the processor 830 is also used to control the transmit / receive sequence controller 810 to excite the ultrasonic probe 820 to transmit a first ultrasonic wave to the target area of ​​the object to be measured, receive an echo of the first ultrasonic wave, and obtain a first ultrasonic echo signal based on the echo of the first ultrasonic wave in response to an instruction to execute the first scanning protocol for the target area of ​​the object to be measured; the processor 830 is also used to generate a first ultrasonic image based on the first ultrasonic echo signal, and select a standard section image from the first ultrasonic image; when there is no abnormality in the standard section image, the standard section image is stored; when there is an abnormality in the standard section image, a second scanning protocol is inserted into the first scanning protocol, wherein the second scanning protocol includes a set of scanning sections corresponding to the abnormal type of the standard section.

[0114] In an embodiment of the present application, the object to be measured may be a person to be subjected to an ultrasonic examination, and the target area of ​​the object to be measured may be an area of ​​the body part of the object to be measured that needs to be subjected to an ultrasonic examination. In an embodiment of the present application, the transmit / receive sequence controller 810 excites the ultrasonic probe 820 to transmit the first ultrasonic wave to the target area of ​​the object to be measured in order to obtain a first ultrasonic image of the target area of ​​the object to be measured so as to obtain a standard section image therefrom. Here, the first ultrasonic wave is so named to distinguish it from the second ultrasonic wave in the second workflow, and has no other limiting effect. After receiving the echo of the first ultrasonic wave, the ultrasonic probe 820 may obtain the first ultrasonic echo signal, and the processor 830 processes the first ultrasonic echo signal to obtain the first ultrasonic image. Similarly, the first ultrasonic echo signal and the first ultrasonic image are so named to distinguish them from the second ultrasonic echo signal and the second ultrasonic image in the second workflow, respectively, and have no other limiting effect. Exemplarily, the processor 830 may perform processing such as gain compensation, beamforming, orthogonal demodulation, image enhancement, etc. on the first ultrasonic echo signal to obtain a first ultrasonic image of the target area of ​​the object to be measured.

[0115] In an embodiment of the present application, after acquiring the first ultrasound image, the processor 830 may select a standard section image from it. Here, according to the object to be measured and the target area to be measured, the selected standard section image may be a corresponding standard section image set in advance. For example, for scanning of different parts, the standard section images to be image detected are different. Of course, the standard section image to be selected may also be modifiable or settable by the operator. In addition, after selecting the standard section, the processor 830 may measure the relevant parameters in the standard section image, and the relevant parameters to be measured may be corresponding parameters set in advance, or may be modifiable or settable by the operator. The measurement results of the relevant parameters in the standard section image may be used to determine whether there is an abnormality in the standard section image (for example, if the measurement result of a parameter is not within the normal value range, it is determined that there is an abnormality); or, it may be determined whether there is an abnormality in the standard section image by other means or in combination with other means, as described below.

[0116] In an embodiment of the present application, after selecting a standard section image, the processor 830 can automatically determine whether there is an abnormality in the standard section image. For example, the processor 830 can determine whether there is an abnormality in the standard section image by determining at least one of the following: whether the image content is consistent with the section name; whether there is an abnormal structure in the image.

[0117] In an embodiment of the present application, the processor 830 determines whether the image content is consistent with the section name, which may include: determining whether the human body structure features in the selected standard section image are consistent with the normal human body structure features stored in the standard section image database, if they are consistent, it can be determined that the image content is consistent with the section name, if they are inconsistent, it can be determined that the image content is inconsistent with the section name. Exemplarily, the processor 830 can determine whether the image content is consistent with the section name by image matching or image classification, and these two methods are described below.

[0118] In the embodiment of the present application, determining whether the image content matches the section name by image matching may include the following steps: (1) Establishing a library: Establishing a detailed human section ultrasound library - each standard section in the protocol contains section images of normal human bodies and various disease populations to increase the matching range. This step can be an offline step. The library information needs to be established during the system design stage. During the scanning process, the library information already exists and can be used directly. (2) Tissue structure image matching: Each image in the library has its own characteristics (such as what shape of high echo is in what area of ​​the image, etc.). The image to be scanned (i.e., the selected standard section image) and the image of the corresponding section in the library are subjected to correlation calculation based on the extracted image features using a pattern matching algorithm. If the correlation is higher than a certain threshold, the match is considered successful. A successful match means that the human structure features in the selected standard section image are considered to be consistent with the normal human structure features stored in the standard section image database, that is, the image content is consistent with the section name.

[0119] In an embodiment of the present application, a traditional machine learning or deep learning method can be used to determine whether the image content matches the section name by image classification, for example, including the following steps: (1) Establishing a training database: For a specific detection position, such as the cross section of both kidneys, a certain amount of positive and negative samples are collected. Among them, the positive sample data is a standard cross section image of both kidneys, and the negative sample data is image data other than the standard cross section of both kidneys. (2) Training the section classification model: After the training database is annotated, that is, for each image, the doctor gives whether the image belongs to a standard section or a non-standard section, and by calculating the error between the predicted value and the annotated value of the neural network, it is continuously iterated and gradually approximated, and then the final standard section recognition model is obtained. Among them, the traditional machine learning method needs to first extract features from the image and input the feature matrix into the network model for training, while the deep learning model directly inputs the section image for training. (3) Recognition or classification of the section image: Use the trained model to process the image and determine whether the image content matches the section name.

[0120] In an embodiment of the present application, the processor 830 determines whether there is an abnormal structure in the image, for example, by means of target detection or image classification. By means of target detection technology, the detection of abnormal positions and the distinction of abnormal situations (i.e., abnormal types) can be achieved; by means of image classification technology, the determination of abnormal situations can be achieved without giving the abnormal position. In addition, determining whether there is an abnormal structure in the image can also be achieved by an image matching method in a traditional image processing method.

[0121] Generally, target detection and image classification can roughly include the following steps: (1) Establish a training database: For abnormal conditions at specific locations, such as nodular lesions in thyroid and breast scans, a certain amount of positive and negative samples are collected. Among them, the positive sample data is ultrasound image data with nodular lesions, region of interest (ROI) image blocks, etc., and the negative sample data is ultrasound image data without lesions and ROI image blocks, etc. (2) Train target detection and image classification models: After annotating the training database, the error between the predicted value and the annotated value of the neural network is calculated, and the error is continuously iterated and gradually approximated to obtain the final standard section recognition model. Among them, when training the image classification model, the annotated content is the label of whether the current image and ROI image block are normal or abnormal; in the target detection model, the annotated content is the abnormal and normal position and label of the current image and ROI image block. In addition, if the traditional machine learning method is used, it is necessary to first extract features from the image and input the feature matrix into the network model for training, while the deep learning model directly inputs the section image and ROI image block for training. (3) Identification of image content or detection of abnormal locations: Use the trained model to process the image and determine whether there are abnormalities or the location of abnormalities in the image.

[0122] The above exemplifies various ways in which the processor 830 automatically determines whether a standard cross-sectional image has an abnormality. It should be understood that these are merely illustrative and non-restrictive. Under the teachings of this application, any other suitable way may be used to automatically determine whether a standard cross-sectional image has an abnormality.

[0123] In another embodiment of the present application, the processor 830 can present the standard section image to the operator, and the operator can determine whether the standard section image has an abnormality; after making the determination, the operator can input the result of the determination through the human-computer interaction device so that the workflow continues to execute. In this embodiment, the processor 830 determines whether the standard section image has an abnormality based on the instruction input after the operator's judgment.

[0124] In an embodiment of the present application, when the processor 830 determines that there is no abnormality in the standard cross-section image, the standard cross-section image can be stored in a certain storage location, and the results of measuring relevant parameters of the standard cross-section image can also be stored; when the processor 830 determines that there is an abnormality in the standard cross-section image, it switches from the first workflow to the second workflow corresponding to the type of abnormality determined (inserting the second scanning protocol from the first scanning protocol).

[0125] In another embodiment of the present application, after selecting the standard section image from the first ultrasound image, the processor 830 may also determine whether the image quality meets the predetermined requirements, which may be performed simultaneously with the determination of whether the standard section image has an abnormality in the foregoing text, or may be performed sequentially. In an embodiment of the present application, when the image quality of the standard section image cannot meet the predetermined requirements, the standard section image may be reselected until the selected standard section image meets the predetermined requirements; when the image quality of the standard section image meets the predetermined requirements and the standard section image has no abnormalities, the standard section image is stored; when the image quality of the standard section image meets the predetermined requirements and the standard section image has an abnormality, the first workflow is switched to the second workflow corresponding to the type of the abnormality.

[0126] In an embodiment of the present application, the processor 830 may determine whether the image quality first meets the predetermined requirements based on specific indicators of the image quality. For example, the indicators based on which the processor 830 determines whether the image quality meets the predetermined requirements may include at least one of the following: image clarity; image uniformity; whether there are spots, snowflakes, or reticulation in the image; probe depth; and correlation between the operating frequency and the organ.

[0127] In an embodiment of the present application, whether the image clarity meets the predetermined requirements can be determined by an image blur detection method, for example, judging based on the gradient information in the image; in addition, it is also possible to judge whether the image is blurred by a machine learning method, and collect two types of data, clear images and blurred images of the part to be inspected, in advance as sample training models, and abstract the problem into a binary classification problem.

[0128] In an embodiment of the present application, determining whether the image uniformity meets the predetermined requirements can be done, for example, in the following manner: determining whether the histogram of the entire image is relatively average to ensure that the image grayscale is not concentrated in a certain area. In addition, for extreme cases, such as the problem that the image is too bright or too dark as a whole, it is also possible to consider calculating the grayscale mean of the image in the effective area and judging whether it is effective by a threshold. For example, the grayscale value range of a normal ultrasound image is 0 to 255. When calculating the mean value in the effective area of ​​the ultrasound image, if it is less than 40, it can be considered too dark; if it exceeds 200, it can be considered too bright.

[0129] In an embodiment of the present application, determining whether there are spots, snowflakes, or reticulations in an image can be performed by image classification, and distinguishing them through traditional neural networks or deep learning models.

[0130] In the embodiment of the present application, whether the probe depth meets the predetermined requirement can be determined by obtaining the effective area by threshold segmentation of image processing, and then calculating the proportion of the effective area to the entire image for judgment. If the proportion of the effective area meets the threshold requirement, it is determined whether the probe depth meets the predetermined requirement. Generally, the proportion of the effective area should be greater than one-half.

[0131] In the embodiments of the present application, the correlation between the working frequency and the organ can be determined by comparing the current section with the model of the probe actually used. To collect images of different organs, corresponding probes need to be used. For example, for superficial thyroid and breast, linear array probes with high frequency are used; for abdominal organs, convex array probes with low frequency are used.

[0132] As mentioned above, when the image quality of the standard section image meets the predetermined requirements and the standard section image has an abnormality, the first workflow is switched to the second workflow corresponding to the type of the abnormality. The second workflow may include: the transmission / reception sequence controller 810 excites the ultrasound probe 820 to transmit a second ultrasonic wave to the abnormal part of the object under test corresponding to the standard section image with the abnormality, receives the echo of the second ultrasonic wave, and acquires a second ultrasonic echo signal based on the echo of the second ultrasonic wave; the processor 830 generates a second ultrasonic image based on the second ultrasonic echo signal, and stores the second ultrasonic image.

[0133] Here, the transmit / receive sequence controller 810 excites the ultrasonic probe 820 to transmit the second ultrasonic wave to the abnormal part of the object under test corresponding to the standard section image with abnormality in order to obtain the second ultrasonic image of the abnormal part of the object under test corresponding to the standard section image with abnormality. Here, the second ultrasonic wave is named so as to distinguish it from the first ultrasonic wave in the first workflow, and has no other restrictive effect. After receiving the echo of the second ultrasonic wave, the ultrasonic probe 820 can obtain the second ultrasonic echo signal, and the processor 830 processes the second ultrasonic echo signal to obtain the second ultrasonic image. Similarly, the second ultrasonic echo signal and the second ultrasonic image are named so as to distinguish them from the first ultrasonic echo signal and the first ultrasonic image in the first workflow, respectively, and have no other restrictive effect. Exemplarily, the processor 830 can perform processing such as gain compensation, beamforming, orthogonal demodulation, image enhancement, etc. on the second ultrasonic echo signal to obtain a second ultrasonic image of the target area of ​​the object under test. After obtaining the second ultrasonic image, the processor 830 can store the second ultrasonic image in a certain storage location, thereby realizing the storage of the ultrasonic image of the abnormal section.

[0134] In an embodiment of the present application, the second workflow can also be understood as a workflow for scanning a predefined set of scanning sections for types of ultrasound-visible human abnormalities, which has been appropriately or standardizedly configured, such as image mode, image parameters, annotations, body position maps, measurements, etc., and the execution order can be set to meet clinical usage requirements and habits, which is equivalent to a sub-protocol or an inserted protocol or an additional protocol.

[0135] In an embodiment of the present application, different abnormality types correspond to different second workflows. Among them, the types of abnormalities may include abnormalities that depend on anatomical locations and abnormalities in specific anatomical locations. The processor 830 may name the inserted second workflow according to the type of abnormality, wherein: when the type of abnormality is an abnormality that depends on anatomical locations, the naming of the inserted second workflow may include indicating the name of the abnormality and the location of the abnormality; when the type of abnormality is an abnormality in a specific anatomical location, the naming of the inserted second workflow may include indicating the name of the abnormality. For example, abnormalities that depend on anatomical locations, such as masses, effusions, etc., may occur in various parts of the body. After insertion, the naming of this type of second workflow needs to be coordinated with the name of the standard section to indicate the location where the abnormality is found. Abnormalities in specific anatomical locations, such as mitral regurgitation, fetal femoral length, etc., the name itself indicates the location where the abnormality occurs, and there is no need to add other location restrictions.

[0136] In an embodiment of the present application, there may be standardized requirements for the position of inserting the second workflow in the first workflow, so as to facilitate scanning and image browsing or be applicable to other scenarios. In one example, the second workflow insertion operation may be performed on the section that has just completed image detection, because usually an abnormality is found during the scanning process of a certain standard section, and after saving the standard section, the abnormal detailed scanning and image retention will be performed directly. In view of the fact that most of the current automatic workflows are sequential scanning, that is, after completing the scanning workflow of a certain section, the scanning workflow of the next section will be automatically started, and the rules of the software system are generally operated on the currently selected object, so if the current section is in an unfinished state and the most recently completed section is the previous section of the selected section, it means that this is a natural jump of the process, and the insertion of the second workflow is for the most recently completed section operation (previous section) rather than the currently selected section. Of course, in other scenarios, the second workflow can also be inserted at a manually specified position, that is, an artificial jump is achieved.

[0137] In an embodiment of the present application, the processor 830 can determine the insertion position of the second workflow and insert the second workflow in the following manner: after determining that there is an abnormality in the standard section image, determine whether the image detection of the standard section image is completed: when it is determined that the image detection of the standard section image is completed, insert the second workflow at the first node, and the first node is the node where the image detection is completed; when it is determined that the image detection of the standard section image is not completed, determine whether the most recently completed section is the previous frame of standard section image of the standard section image: when it is determined that the most recently completed section is the previous frame of standard section image, insert the second workflow at the second node, and the second node is the node where the image detection of the previous frame of standard section image is completed; when it is determined that the most recently completed section is not the previous frame of standard section image, insert the second workflow at the first node. You can refer to the above text. Figure 3 and FIG. 4A to FIG. 4C For the sake of brevity, it will not be described here.

[0138] In general, non-obstetric ultrasound examinations can be completed in a certain order, and when there are no abnormalities, the next section is scanned directly. Therefore, most of the automatic ultrasound workflows will preset the protocol to automatically start the scanning workflow of the section in order (the scanning workflow of the section can be referred to as the section), which can reduce the steps of manually starting the section. However, when an abnormality is found in the section that has just been stored and an operation needs to be performed on it, since the next section is set to start automatically, the focus has actually jumped to the next section. At this time, the doctor needs to step back and switch the focus to the previous section before operating. However, since this is a low-frequency operation relative to the entire examination, the doctor will often forget to adjust the focus position due to inertial thinking, which will cause the problem of mistakenly adding the section to the next section (such as recording the wrong mass position). Therefore, the ultrasonic imaging device of the present application automatically inserts the section (i.e., inserts the second workflow) after determining the abnormality, which can not only improve the scanning efficiency, but also effectively reduce the situation where the doctor manually inserts the section and makes mistakes, thereby improving the scanning quality.

[0139] In an embodiment of the present application, the first workflow may further include (not shown): when the processor 830 determines that there are multiple abnormalities in the standard cross-section image, a second workflow corresponding to each type of the multiple abnormalities is inserted into the first workflow. This embodiment can be used in a scenario where there are multiple abnormalities in a standard cross-section image. When there are multiple abnormalities in the standard cross-section image, second workflows corresponding to each type of the multiple abnormalities can be inserted continuously. Among them, if the multiple abnormalities of the standard cross-section image include multiple abnormalities of the same type, the second workflows corresponding to each of the multiple abnormalities of the same type inserted by the processor 830 in the first workflow can be distinguished by different identifiers, for example, second workflows of the same type of abnormalities are distinguished from each other by adding suffixes (numbers).

[0140] In an embodiment of the present application, the first workflow may further include (not shown): when the processor 830 determines that the standard section image has an abnormality but cannot determine the type of the abnormality, inserting a second workflow corresponding to the unknown abnormality type into the workflow. This embodiment can be used in a scenario where an abnormality of an unknown type exists, in which a blank section can be inserted.

[0141] In an embodiment of the present application, the first workflow may also include (not shown): when the processor 830 determines that there is an abnormality in the standard section image, the type of the abnormality is identified so that the operator can confirm whether it is recognized, and the second workflow is inserted in response to the operator's approval instruction. In this embodiment, when the processor 830 determines that there is an abnormality in the standard section image, the second workflow corresponding to the abnormality type is not directly and automatically inserted, but the operator first confirms whether to recognize the automatically detected abnormality, and the second workflow is inserted only when the operator approves, which can further ensure the correctness of the insertion of the second workflow and further improve the scanning quality. In addition, if the operator does not approve, that is, the processor 830 receives the operator's disapproval instruction, the second workflow is not inserted, but the corresponding operation in the first workflow is continued to be performed on the next frame of the standard section image. Alternatively, if the operator does not approve, the processor 830 can also insert the second workflow that the operator expects to insert according to the operator's instruction. This embodiment can be used for scenarios where abnormality recognition errors are identified. Further, the processor 830 can also directly insert the second workflow in the first workflow based on the operator input. This embodiment can be used in scenarios where anomalies exist but are not automatically identified.

[0142] In a further embodiment of the present application, the inserted second workflow may further include: the processor 830 performs image detection on the relevant parameters of the abnormal part in the second ultrasound image, and stores the image detection results of the relevant parameters of the abnormal part. In this embodiment, not only the ultrasound image of the section with abnormality can be stored, but also the details of the abnormality can be further stored, providing a more accurate basis for the doctor's diagnosis, thereby further improving the quality of scanning and diagnosis.

[0143] Based on the above description, the ultrasound imaging device according to the embodiment of the present application can intelligently detect abnormal sections and automatically insert a second workflow corresponding to the abnormal type when detecting abnormal sections to store ultrasound images of the abnormal sections, thereby improving the efficiency and quality of doctors' scanning and diagnosis.

[0144] Combine the following Fig. 9 An ultrasonic imaging device provided according to another embodiment of the present application is described. Fig. 9FIG. 9 is a schematic block diagram of an ultrasonic imaging device 900 according to an embodiment of the present application. Fig. 9 As shown, the ultrasonic imaging device 900 includes a memory 910 and a processor 920. The memory 910 stores program codes for implementing the corresponding steps in the ultrasonic imaging methods 200, 600 and 700 according to the embodiments of the present application. The processor 920 is used to run the program codes stored in the memory 910 to perform the corresponding steps of the ultrasonic imaging methods 200, 600 and 700 according to the embodiments of the present application.

[0145] In addition, according to an embodiment of the present application, a storage medium is also provided, on which program instructions are stored, and when the program instructions are executed by a computer or a processor, the corresponding steps of the ultrasound imaging methods 200, 600 and 700 of the embodiments of the present application are executed. The storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media.

[0146] In addition, according to an embodiment of the present application, a computer program is also provided, which can be stored in a cloud or local storage medium. When the computer program is run by a computer or a processor, it is used to execute the corresponding steps of the ultrasound imaging method of the embodiment of the present application.

[0147] According to the ultrasound imaging method and device of the embodiment of the present application, abnormal sections can be intelligently detected, and a scanning protocol corresponding to the abnormal type can be automatically inserted when detecting abnormal sections to store ultrasound images of abnormal sections, thereby improving the efficiency and quality of doctors' scanning and diagnosis.

[0148] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0149] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0150] 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 only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0151] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0152] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various application aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with features less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0153] It will be understood by those skilled in the art that, except for mutually exclusive application points between features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0154] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0155] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules in the article analysis device according to the embodiment of the present application. The present application can also be implemented as a device program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0156] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0157] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An ultrasonic imaging method, characterized in that: The method comprises a first workflow and a second workflow, wherein: The first workflow includes: Transmitting a first ultrasonic wave to a target area of ​​the measured object, receiving an echo of the first ultrasonic wave, and acquiring a first ultrasonic echo signal based on the echo of the first ultrasonic wave; generating a first ultrasound image based on the first ultrasound echo signal, and selecting a standard section image from the first ultrasound image; When there is no abnormality in the standard section image, storing the standard section image; When there is an abnormality in the standard section image, switching from the first workflow to a second workflow corresponding to the type of the abnormality; The indicator for determining whether the standard section image has an abnormality includes at least one of the following: whether the image content is consistent with the section name, whether there is an abnormal structure in the image; and / or whether the standard section image has an abnormality is determined based on an instruction input by an operator; The second workflow includes: transmitting a second ultrasonic wave to the abnormal part of the object under test corresponding to the standard cross-sectional image where the abnormality exists, receiving the echo of the second ultrasonic wave, and acquiring a second ultrasonic echo signal based on the echo of the second ultrasonic wave; generating a second ultrasonic image based on the second ultrasonic echo signal, and storing the second ultrasonic image.

2. The method according to claim 1, characterized in that: The second workflow further includes: measuring relevant parameters of the abnormal part in the second ultrasound image, and storing the measurement results of the relevant parameters of the abnormal part.

3. The method according to claim 1, characterized in that The first workflow includes: when there are multiple abnormalities in the standard section image, switching from the first workflow to one of multiple second workflows corresponding to the types of the multiple abnormalities, and executing the remaining workflows of the multiple second workflows after the one switched to is executed.

4. The method according to claim 3, characterized in that When the multiple exceptions include multiple exceptions of the same type, the multiple second workflows are distinguished from each other by different identifiers.

5. The method according to claim 1, characterized in that The first workflow further includes: when there is an abnormality in the standard section image, determining whether the image detection of the standard section image is completed: When the image detection of the standard section image is completed, switching from the first node to the second workflow, the first node is the node where the image detection of the standard section image is completed; When the image detection of the standard section image is not completed, determining whether the most recently completed section is the previous frame of the standard section image of the standard section image: When the most recently completed section is the previous frame of standard section image, switching from the second node to the second workflow, the second node being the node where the image detection of the previous frame of standard section image is completed; When the most recently completed section is not the previous standard section image, switching from the first node to the second workflow.

6. The method according to claim 1, characterized in that The image content is obtained based on image matching or image classification.

7. The method according to claim 1, characterized in that Whether there is an abnormal structure in the image is determined based on target detection or image classification.

8. The method according to claim 1, characterized in that: The method further comprises: When the image quality of the standard section image cannot meet the predetermined requirement, reselecting the standard section image until the selected standard section image meets the predetermined requirement; When the image quality of the standard section image meets the predetermined requirement and there is no abnormality in the standard section image, storing the standard section image; When the image quality of the standard section image meets a predetermined requirement and an abnormality exists in the standard section image, the first workflow is switched to a second workflow corresponding to the type of the abnormality.

9. The method according to claim 8, characterized in that The indexes according to which whether the image quality meets the predetermined requirements include at least one of the following: image clarity; image uniformity; whether there are spots, snowflakes, or reticulations in the image; probe depth; and correlation between the operating frequency and the organ.

10. The method according to any one of claims 1 to 9, characterized in that: The first workflow further includes: when an abnormality exists in the standard section image, identifying the type of the abnormality so that the operator can confirm whether to approve it, and switching to the second workflow in response to the operator's approval instruction.

11. The method according to claim 10, characterized in that The first workflow also includes: if a disapproval instruction from the operator is received, not switching to the second workflow, and performing corresponding operations in the first workflow on the next frame of the standard section image.

12. The method according to claim 1, characterized in that The switching from the first workflow to the second workflow corresponding to the type of the abnormality is performed based on a switching instruction input by an operator.

13. The method according to any one of claims 1 to 9, characterized in that: The types of abnormalities include abnormalities that depend on anatomical locations and abnormalities in specific anatomical locations. The method further includes: naming the second workflow to be switched to according to the types of abnormalities, wherein: When the type of the abnormality is an abnormality dependent on an anatomical location, the naming of the second workflow to be switched to includes indicating the name of the abnormality and the location of the abnormality; When the type of the abnormality is an abnormality of a specific anatomical site, the naming of the second workflow to be switched to includes indicating the name of the abnormality.

14. The method according to any one of claims 1 to 9, characterized in that: The first workflow further includes: when an abnormality exists in the standard section image and the type of the abnormality cannot be determined, switching the first workflow to a second workflow corresponding to an unknown abnormality type.

15. An ultrasonic imaging method, characterized in that: The method comprises a first workflow and a second workflow, wherein: The first workflow includes: Transmitting a first ultrasonic wave to a target area of ​​the measured object, receiving an echo of the first ultrasonic wave, and acquiring a first ultrasonic echo signal based on the echo of the first ultrasonic wave; generating a first ultrasound image based on the first ultrasound echo signal, and selecting a standard section image from the first ultrasound image; In response to an operator's instruction to start an analysis process for the standard section image, the analysis process for the standard section image is started, wherein the analysis process for the standard section image includes an analysis process for the image quality of the standard section image and an analysis process for the image content of the standard section image; When the image quality of the standard section image cannot meet the predetermined requirement, reselecting the standard section image until the selected standard section image meets the predetermined requirement; When the image quality of the standard section image meets the predetermined requirement and there is no abnormality in the image content of the standard section image, storing the standard section image; When the image quality of the standard section image meets the predetermined requirement and the image content of the standard section image is abnormal, switching from the first workflow to a second workflow corresponding to the type of the abnormality; The indicator according to which whether the image content of the standard section image is abnormal includes at least one of the following: whether the image content is consistent with the section name, whether there is an abnormal structure in the image; and / or whether the image content of the standard section image is abnormal is determined based on an instruction input by an operator; The second workflow includes: transmitting a second ultrasonic wave to the abnormal part corresponding to the standard cross-sectional image of the object under test where the abnormality exists, receiving the echo of the second ultrasonic wave, and acquiring a second ultrasonic echo signal based on the echo of the second ultrasonic wave; generating a second ultrasonic image based on the second ultrasonic echo signal, and storing the second ultrasonic image.

16. An ultrasonic imaging method, characterized in that: The method comprises: Acquire a first scanning protocol for the target area, wherein the first scanning protocol includes a set of standard sections required to scan the target area; In response to an instruction to execute a first scanning protocol on a target area of ​​the object to be measured, control the ultrasonic probe to transmit a first ultrasonic wave to the target area of ​​the object to be measured, receive an echo of the first ultrasonic wave, and acquire a first ultrasonic echo signal based on the echo of the first ultrasonic wave; generating a first ultrasound image based on the first ultrasound echo signal, and selecting a standard section image from the first ultrasound image; When there is no abnormality in the standard section image, storing the standard section image; When the standard section image has an abnormality, inserting a second scanning protocol into the first scanning protocol, wherein the second scanning protocol includes a set of scanning sections corresponding to the abnormal type of the standard section; The indicators for determining whether the standard section image has an abnormality include at least one of the following: whether the image content is consistent with the section name, whether there is an abnormal structure in the image; and / or whether the standard section image has an abnormality is determined based on instructions input by an operator.

17. The method according to claim 16, characterized in that The method further comprises: In response to an instruction to execute a second scanning protocol on the abnormal part corresponding to the standard cross-sectional image of the object under test in which the abnormality exists, the ultrasonic probe is controlled to transmit a second ultrasonic wave to the abnormal part corresponding to the standard cross-sectional image of the object under test in which the abnormality exists, receive the echo of the second ultrasonic wave, and acquire a second ultrasonic wave echo signal based on the echo of the second ultrasonic wave; generate a second ultrasonic image based on the second ultrasonic wave echo signal, and store the second ultrasonic image.

18. The method according to claim 16, characterized in that The method comprises: When there are multiple abnormalities in the standard section image, second scanning protocols corresponding to the types of the multiple abnormalities are inserted into the first scanning protocol.

19. The method according to claim 16, characterized in that The method further comprises: When the standard section image has an abnormality, determining whether the image detection of the standard section image is completed: When the image detection of the standard section image is completed, inserting the second scanning protocol at the first node, the first node is the node where the image detection of the standard section image is completed; When the image detection of the standard section image is not completed, determining whether the most recently completed section is the previous frame of the standard section image of the standard section image: When the most recently completed section is the previous frame of standard section image, inserting the second scanning protocol at the second node, the second node being the node where the image detection of the previous frame of standard section image is completed; When the most recently completed section is not the previous frame of standard section image, the second scanning protocol is inserted at the first node.

20. The method according to claim 19, characterized in that The method further comprises: When the image quality of the standard section image cannot meet the predetermined requirement, reselecting the standard section image until the selected standard section image meets the predetermined requirement; When the image quality of the standard section image meets the predetermined requirement and there is no abnormality in the standard section image, storing the standard section image; When the image quality of the standard section image meets the predetermined requirement and there is an abnormality in the standard section image, the second scanning protocol is inserted into the first scanning protocol.

21. An ultrasonic imaging device, characterized in that: The apparatus comprises an ultrasound probe, a transmit / receive sequence controller and a processor, wherein the ultrasound probe, the transmit / receive sequence controller and the processor are used to execute a first workflow and a second workflow, wherein: The first workflow includes: the transmit / receive sequence controller excites the ultrasound probe to transmit a first ultrasound wave to a target area of ​​the object to be measured, receives an echo of the first ultrasound wave, and acquires a first ultrasound echo signal based on the echo of the first ultrasound wave; the processor generates a first ultrasound image based on the first ultrasound echo signal, and selects a standard section image from the first ultrasound image; when the standard section image does not have an abnormality, the standard section image is stored; when it is determined that the standard section image has an abnormality, the first workflow is switched to a second workflow corresponding to the type of the abnormality; The indicator for determining whether the standard section image has an abnormality includes at least one of the following: whether the image content is consistent with the section name, whether there is an abnormal structure in the image; and / or whether the standard section image has an abnormality is determined based on an instruction input by an operator; The second workflow includes: the transmit / receive sequence controller stimulates the ultrasound probe to transmit a second ultrasound wave to the abnormal part of the object under test corresponding to the standard cross-sectional image where the abnormality exists, receives the echo of the second ultrasound wave, and acquires a second ultrasound echo signal based on the echo of the second ultrasound wave; the processor generates a second ultrasound image based on the second ultrasound echo signal, and stores the second ultrasound image.

22. The device according to claim 21, characterized in that The second workflow further includes: measuring relevant parameters of the abnormal part in the second ultrasound image, and storing the measurement results of the relevant parameters of the abnormal part.

23. The device according to claim 21, characterized in that The processor is also used for: when there are multiple abnormalities in the standard section image, switching from the first workflow to one of multiple second workflows corresponding to the types of the multiple abnormalities, and executing the remaining workflows of the multiple second workflows after the one switched to is executed.

24. The device according to claim 21, characterized in that The processor is further configured to: when an abnormality exists in the standard section image, determine whether the image detection of the standard section image is completed: When the image detection of the standard section image is completed, switching from the first node to the second workflow, the first node is the node where the image detection of the standard section image is completed; When the image detection of the standard section image is not completed, determining whether the most recently completed section is the previous frame of the standard section image of the standard section image: When the most recently completed section is the previous frame of standard section image, switching from the second node to the second workflow, the second node being the node where the image detection of the previous frame of standard section image is completed; When the most recently completed section is not the previous standard section image, switching from the first node to the second workflow.

25. The device according to any one of claims 21 to 24, characterized in that The processor is further configured to: when an abnormality exists in the standard section image and the type of the abnormality cannot be determined, switch the first workflow to a second workflow corresponding to an unknown abnormality type.

26. An ultrasound imaging device, comprising an ultrasound probe, a transmit / receive sequence controller, and a processor, wherein the ultrasound probe, the transmit / receive sequence controller, and the processor are used to execute a first workflow and a second workflow, wherein: The first workflow includes: The transmit / receive sequence controller excites the ultrasonic probe to transmit a first ultrasonic wave to a target area of ​​the measured object, receives an echo of the first ultrasonic wave, and acquires a first ultrasonic echo signal based on the echo of the first ultrasonic wave; The processor generates a first ultrasound image based on the first ultrasound echo signal, and selects a standard section image from the first ultrasound image; in response to an instruction from an operator to start an analysis process for the standard section image, starts an analysis process for the standard section image, wherein the analysis process for the standard section image includes an analysis process for image quality of the standard section image and an analysis process for image content of the standard section image; When the image quality of the standard section image cannot meet the predetermined requirement, reselecting the standard section image until the selected standard section image meets the predetermined requirement; When the image quality of the standard section image meets the predetermined requirement and there is no abnormality in the image content of the standard section image, storing the standard section image; When the image quality of the standard section image meets the predetermined requirement and the image content of the standard section image is abnormal, switching from the first workflow to a second workflow corresponding to the type of the abnormality; The indicator according to which whether the image content of the standard section image is abnormal includes at least one of the following: whether the image content is consistent with the section name; whether there is an abnormal structure in the image; and / or whether the image content of the standard section image is abnormal is determined based on an instruction input by an operator; The second workflow includes: the transmit / receive sequence controller stimulates the ultrasound probe to transmit a second ultrasound wave to the abnormal part corresponding to the standard cross-sectional image of the object under test where the abnormality exists, receives the echo of the second ultrasound wave, and acquires a second ultrasound echo signal based on the echo of the second ultrasound wave; the processor generates a second ultrasound image based on the second ultrasound echo signal, and stores the second ultrasound image.

27. An ultrasonic imaging device, characterized in that: The device comprises an ultrasound probe, a transmit / receive sequence controller and a processor, wherein: The processor is used to obtain a first scanning protocol for the target area, wherein the first scanning protocol includes a set of standard sections required to scan the target area; The processor is further configured to, in response to an instruction to execute a first scanning protocol on a target area of ​​the measured object, control the transmit / receive sequence controller to excite the ultrasonic probe to transmit a first ultrasonic wave to the target area of ​​the measured object, receive an echo of the first ultrasonic wave, and acquire a first ultrasonic echo signal based on the echo of the first ultrasonic wave; The processor is further configured to generate a first ultrasound image based on the first ultrasound echo signal, select a standard section image from the first ultrasound image; when the standard section image does not have an abnormality, store the standard section image; when the standard section image has an abnormality, insert a second scanning protocol into the first scanning protocol, wherein the second scanning protocol includes a scanning section set corresponding to the abnormal type of the standard section; The indicator for determining whether the standard section image has an abnormality includes at least one of the following: whether the image content matches the section name; whether there is an abnormal structure in the image; and / or whether the standard section image has an abnormality is determined based on instructions input by an operator.

28. The device according to claim 27, characterized in that The processor is further configured to: In response to an instruction to execute a second scanning protocol on the abnormal part corresponding to the standard cross-sectional image of the object under test in which the abnormality exists, the transmit / receive sequence controller is controlled to excite the ultrasound probe to transmit a second ultrasonic wave to the abnormal part corresponding to the standard cross-sectional image of the object under test in which the abnormality exists, receive the echo of the second ultrasonic wave, and acquire a second ultrasonic wave echo signal based on the echo of the second ultrasonic wave; generate a second ultrasonic image based on the second ultrasonic wave echo signal, and store the second ultrasonic image.

29. The device according to claim 27, characterized in that The processor is further configured to: When there are multiple abnormalities in the standard section image, second scanning protocols corresponding to the types of the multiple abnormalities are inserted into the first scanning protocol.

30. The device according to claim 27, characterized in that The processor is further configured to: When the standard section image has an abnormality, determining whether the image detection of the standard section image is completed: When the image detection of the standard section image is completed, inserting the second scanning protocol at the first node, the first node is the node where the image detection of the standard section image is completed; When the image detection of the standard section image is not completed, determining whether the most recently completed section is the previous frame of the standard section image of the standard section image: When the most recently completed section is the previous frame of standard section image, inserting the second scanning protocol at the second node, the second node being the node where the image detection of the previous frame of standard section image is completed; When the most recently completed section is not the previous frame of standard section image, the second scanning protocol is inserted at the first node.

31. A storage medium, characterized in that: The storage medium stores a computer program, which executes the ultrasonic imaging method according to any one of claims 1 to 20 when running.

Images