Section image acquisition method and device, computer equipment and readable storage medium

Abstract

The invention relates to a section image acquisition method and device, computer equipment and a readable storage medium, and the method comprises the steps: carrying out the detection of a medical image of a target object, and obtaining the type of the target object; according to the type of the target object, optimizing the medical image to obtain an optimized image, and according to the type of the target object, determining a scanning protocol matched with the medical image; and according to the section type in the scanning protocol, performing section capture on the optimized image to obtain a section image of the target object. By the adoption of the method, the workflow accuracy of ultrasonic inspection can be effectively improved, the definition and readability of the captured section image are improved, and subsequent section image recognition is facilitated.

Description

Technical Field

[0001] The present application relates to the field of image acquisition technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for obtaining a section image. Background Art

[0002] Ultrasound is a non-invasive, fast and visual examination device that is widely used in liver examinations. Ultrasound doctors need to scan different standard sections to diagnose diseases. Different clinical scenarios require different sections to be scanned.

[0003] Traditional medical imaging diagnosis methods usually involve doctors determining the corresponding scanning protocol based on patient files and oral information, and capturing the section based on the scanning protocol. However, this diagnostic scheme is highly dependent on the doctor's professional knowledge and clinical experience, which is difficult for beginners to master, and even senior doctors may make wrong judgments. Therefore, the existing method has the problem that the accuracy of the determined scanning protocol is low, which affects the accuracy of the captured section. Summary of the invention

[0004] Based on this, it is necessary to provide a section image acquisition method, apparatus, computer equipment, computer-readable storage medium and computer program product to address the technical problem that the accuracy of the determined scanning protocol in the above method is low, which affects the accuracy of the captured section.

[0005] In a first aspect, the present application provides a method for acquiring a section image. The method comprises:

[0006] Detecting a medical image of a target object to obtain a type of the target object;

[0007] According to the type of the target object, the medical image is optimized to obtain an optimized image, and according to the type of the target object, a scanning protocol matching the medical image is determined;

[0008] According to the section type in the scanning protocol, the section capture is performed on the optimized image to obtain the section image of the target object.

[0009] In one embodiment, detecting the medical image of the target object to obtain the type of the target object includes:

[0010] Acquiring physiological information of a patient corresponding to the target object;

[0011] The physiological information and the medical image are input into an image detection model for detection processing to obtain the type of the target object.

[0012] In one embodiment, optimizing the medical image according to the type of the target object to obtain an optimized image includes:

[0013] Determining corresponding image quality requirements according to the type of the target object;

[0014] When the image quality of the medical image meets the image quality requirement, using the medical image as an optimized image;

[0015] When the image quality of the medical image does not meet the image quality requirement, determining an ultrasound probe used to acquire the medical image;

[0016] If the performance of the ultrasound probe meets the preset conditions, the medical image is optimized according to the image quality requirements to obtain the optimized image.

[0017] In one embodiment, the method further comprises:

[0018] If the performance of the ultrasound probe does not meet the preset condition, a prompt message is generated; the prompt message is used to prompt the user to replace the ultrasound probe with a new one having better performance than the ultrasound probe;

[0019] After acquiring a new medical image collected by the new ultrasound probe, return to the step of detecting the medical image of the target object to obtain the type of the target object, until the image quality of the new medical image obtained meets the image quality requirements or the performance of the ultrasound probe used meets the preset conditions, and the optimized image is obtained through optimization.

[0020] In one embodiment, determining a scanning protocol that matches the medical image according to the type of the target object includes:

[0021] According to the type of the target object, multiple pre-constructed candidate scanning protocols corresponding to the target object are searched to obtain a scanning protocol that matches the medical image.

[0022] In one embodiment, after capturing the section of the optimized image according to the section type in the scanning protocol to obtain the section image of the target object, the method further includes:

[0023] According to the section type corresponding to the section image, measuring the section parameter value corresponding to the section image;

[0024] Displays the slice parameter value.

[0025] In one embodiment, measuring the slice parameter value corresponding to the slice image according to the slice type corresponding to the slice image includes:

[0026] Inputting the section image into a section measurement model, performing image segmentation processing on the section image in the section measurement model to obtain segmentation masks of each sub-object in the section image, and detecting key points for measuring the section parameter values;

[0027] Based on the segmentation mask of each of the sub-objects and the key points, a section parameter value corresponding to the section image is measured.

[0028] In a second aspect, the present application also provides a cross-sectional image acquisition device. The device comprises:

[0029] An image detection module, used to detect a medical image of a target object to obtain the type of the target object;

[0030] an optimization determination module, configured to optimize the medical image according to the type of the target object to obtain an optimized image, and to determine a scanning protocol matching the medical image according to the type of the target object; the scanning protocol includes a section to be acquired configured for the target object;

[0031] A section capture module is used to capture the section of the optimized image according to the section type in the scanning protocol to obtain a section image of the target object.

[0032] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0033] Detecting a medical image of a target object to obtain a type of the target object;

[0034] According to the type of the target object, the medical image is optimized to obtain an optimized image, and according to the type of the target object, a scanning protocol matching the medical image is determined;

[0035] According to the section type in the scanning protocol, the section capture is performed on the optimized image to obtain the section image of the target object.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0037] Detecting a medical image of a target object to obtain a type of the target object;

[0038] According to the type of the target object, the medical image is optimized to obtain an optimized image, and according to the type of the target object, a scanning protocol matching the medical image is determined;

[0039] According to the section type in the scanning protocol, the section capture is performed on the optimized image to obtain the section image of the target object.

[0040] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0041] Detecting a medical image of a target object to obtain a type of the target object;

[0042] According to the type of the target object, the medical image is optimized to obtain an optimized image, and according to the type of the target object, a scanning protocol matching the medical image is determined;

[0043] According to the section type in the scanning protocol, the section capture is performed on the optimized image to obtain the section image of the target object.

[0044] The above-mentioned section image acquisition method, device, computer equipment, storage medium and computer program product detect the medical image of the target object to obtain the type of the target object; optimize the medical image according to the type of the target object to obtain the optimized image, and determine the scanning protocol matching the medical image according to the type of the target object; according to the section type in the scanning protocol, the optimized image is section-captured to obtain the section image of the target object. The method determines the corresponding scanning protocol based on the type of the target object detected by the medical image of the target object, and can automatically identify the specific type of the target object. This decision-making method based on actual medical images is more objective, which can effectively improve the accuracy of the workflow of ultrasound examination and reduce the reliance on the subjective judgment of doctors, thereby reducing errors caused by lack of experience or misjudgment. In addition, the results obtained by this method are stable and reproducible, and the operation results of different doctors are consistent; further, the image captured by the standard section is an image optimized based on the type of the target object, which improves the quality of the image, thereby improving the clarity and readability of the captured section image, which is more conducive to the subsequent recognition of the section image. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] FIG1 is a schematic diagram of a flow chart of a method for acquiring a section image in one embodiment;

[0046] FIG2 is a schematic flow chart of a medical image optimization step in one embodiment;

[0047] FIG3 is a schematic diagram of a flow chart of an automatic measurement algorithm for a second liver portal image in one embodiment;

[0048] Figure 4 This is a diagram showing an example of the application of the second liver portal image automatic measurement algorithm in one embodiment;

[0049] FIG5 is a schematic flow chart of a method for acquiring a section image in another embodiment;

[0050] FIG6 is a structural block diagram of a section image acquisition device in one embodiment;

[0051] FIG. 7 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] In one embodiment, as shown in FIG1 , a cross-sectional image acquisition method is provided, which can be applied to an ultrasound system, and specifically to a processing device of an ultrasound system. It can be understood that an ultrasound system includes an ultrasound probe, a processor, and a display, etc. In actual applications, a doctor holds an ultrasound probe to perform an ultrasound scan on a certain part of a patient, obtains an ultrasound signal, transmits it to the processor for processing, and obtains an ultrasound image, which is displayed in real time on the display. This method is applied to the process of capturing cross-sectional images during ultrasound scanning. In this embodiment, the method includes the following steps:

[0054] Step S110, detecting the medical image of the target object to obtain the type of the target object.

[0055] The target object refers to the object of ultrasound scanning, which may be a biological tissue, such as the human liver.

[0056] The type of the target object is used to characterize the pathological condition of the target object. For example, for the liver, the type of the liver may include normal liver, fatty liver, cirrhosis, etc.

[0057] In a specific implementation, an ultrasonic probe is used to scan the target object using the current default parameters to obtain a medical image of the target object. After the processor obtains the medical image, it can detect and analyze the medical image to determine the type of the target object. In practical applications, an image detection model can be obtained through pre-training, and the medical image of the target object can be detected by the image detection model to obtain the type of the target object.

[0058] Step S120, optimizing the medical image according to the type of the target object to obtain an optimized image, and determining a scanning protocol that matches the medical image according to the type of the target object.

[0059] Among them, the scanning protocol, i.e. the scanning protocol of the ultrasonic automatic workflow, is a template protocol designed based on the basic operating process of ultrasonic examination and conforms to specific applications, which includes at least one section to be examined and its setting parameters. The scanning protocol is used to guide the user to scan each section of the biological tissue, and each section is configured with corresponding setting parameters; it provides operational convenience for ultrasonic scanning, ensures the standardization and integrity of the inspection process, prevents the omission of sections, and quickly obtains ultrasonic images of each section.

[0060] In the specific implementation, different target objects and different types have different corresponding scanning protocols. For example, taking the target object as the liver, the types of liver are normal liver, fatty liver, cirrhosis, etc. The scanning protocols for different types are different. Specifically, the scanning protocols corresponding to fatty liver and cirrhosis may contain more sections than the scanning protocols corresponding to normal liver. For example, cirrhosis can add scanning sections for the liver surface compared to normal liver. Therefore, when determining the scanning protocol, the corresponding scanning protocol needs to be determined according to the type of the target object.

[0061] Similarly, if the target object is of different types, the focus of subsequent scanning will be different. For example, if the target object is the liver, if the liver is detected to be normal, the goal of subsequent scanning is to generate a clear image with good details; if the liver is detected to be fatty liver, the goal of subsequent scanning is to focus more on the examination of liver fat deposition. Therefore, when optimizing the medical image of the target object, the type of the target object must also be considered, and the medical image must be optimized based on the type of the target object so that more effective cross-sectional images can be captured from the optimized image later.

[0062] Step S130 , performing section capture on the optimized image according to the section type in the scanning protocol to obtain a section image of the target object.

[0063] In a specific implementation, after determining the scanning protocol that matches the medical image, the optimized image can be captured one by one according to the slice type in the scanning protocol to obtain the slice image of the target object. The scanning protocol also includes the scanning order of each slice. When capturing the slice image, it is also necessary to capture each slice in turn according to the scanning order of each slice in the scanning protocol to obtain each slice image of the target object.

[0064] In practical applications, the optimized image can be sliced ​​and captured by the slice recognition model, and the captured slice is a standard slice. The slice recognition model can be a network model based on Convolutional Neural Networks (CNN), a network model based on transformer (a deep learning model architecture for natural language processing and other sequence-to-sequence tasks), and a network model based on Memba (a new selective structural state space model), etc. This application does not make specific restrictions on this.

[0065] In the above-mentioned section image acquisition method, the medical image of the target object is detected to obtain the type of the target object; according to the type of the target object, the medical image is optimized to obtain an optimized image, and according to the type of the target object, a scanning protocol matching the medical image is determined; the scanning protocol includes the image section to be collected configured for the target object; according to the section type in the scanning protocol, the optimized image is captured by the standard section to obtain the section image of the target object. The method determines the corresponding scanning protocol based on the type of the target object detected by the medical image of the target object, and can automatically identify the specific type of the target object. This decision-making method based on actual medical images is more objective, which can effectively improve the accuracy and efficiency of the workflow of ultrasound examination, reduce the reliance on the subjective judgment of doctors, and thus reduce the errors caused by lack of experience or misjudgment. In addition, the results obtained by this method are stable and reproducible, and the operation results of different doctors are consistent; further, the image captured by the standard section is an image optimized based on the type of the target object, which improves the quality of the image, thereby improving the clarity and readability of the captured section image, and is more conducive to the subsequent recognition of the section image.

[0066] In an exemplary embodiment, in the above step S110, the medical image of the target object is detected to obtain the type of the target object, including: obtaining physiological information of the patient corresponding to the target object; inputting the physiological information and the medical image into an image detection model for detection processing to obtain the type of the target object.

[0067] The physiological information may be understood as the value of the physiological index of the target object corresponding to the patient. For example, the physiological information may be the height, weight, etc. of the patient.

[0068] It is understandable that height and weight are basic physiological indicators of patients, which can provide important information about the patient's body shape and fat distribution. Different physiological information will affect the performance of medical images. For example, the imaging characteristics of tumors may be different in different patients; height and weight may affect the patient's body shape and fat distribution, thereby affecting the visualization of the liver; taller patients may have different liver positions and morphologies, and weight gain may cause changes in liver structure and function, thereby affecting imaging performance, etc. Therefore, in addition to the collected medical images of the target object, if the physiological information of the patient corresponding to the target object is also obtained, the type of the target object can be determined based on the physiological information and the medical image.

[0069] Specifically, an image detection model can be trained in advance with sample data, and the sample data may include physiological information of the patient corresponding to the sample object, sample medical images, and type labels of the sample objects. During training, the constructed initial image detection model is trained with the patient's physiological information and sample medical images as input variables, and the type labels of the sample objects as supervisory information to obtain a trained image detection model. When applying reasoning, the physiological information and medical images of the patient corresponding to the target object are input into the image detection model for detection processing, and the type of the target object is output.

[0070] In practical applications, image detection models can adopt machine learning-based solutions, such as network models based on Convolutional Neural Networks (CNN), network models based on transformer (a deep learning model architecture for natural language processing and other sequence-to-sequence tasks), network models based on Memba (a new selective structural state space model), and networks based on Support Vector Machine (SVM); solutions based on traditional algorithms can also be adopted, such as algorithms based on template matching, which are not specifically limited in this application.

[0071] In this embodiment, using the patient's physiological information as an additional feature to participate in the prediction of the target object type helps improve the prediction performance of the image detection model and improves the accurate assessment of the type of the target object. For example, specific image features may be common in patients of a certain body shape or weight, and physiological information can help the model learn the relationship between these features.

[0072] In an exemplary embodiment, as shown in FIG. 2 , in the above step S120, the medical image is optimized according to the type of the target object to obtain an optimized image, which can be specifically achieved by the following steps:

[0073] Step S121, determining the corresponding image quality requirement according to the type of the target object;

[0074] Step S122, when the image quality of the medical image meets the image quality requirement, the medical image is used as an optimized image;

[0075] Step S123, when the image quality of the medical image does not meet the image quality requirement, determining the ultrasound probe used to acquire the medical image;

[0076] Step S124: if the performance of the ultrasound probe meets the preset conditions, the medical image is optimized according to the image quality requirements to obtain an optimized image.

[0077] Step S125, if the performance of the ultrasound probe does not meet the preset condition, a prompt message is generated; the prompt message is used to prompt the user to replace the ultrasound probe with a new one having better performance than the ultrasound probe;

[0078] Step S126, after acquiring a new medical image collected by a new ultrasound probe, return to the step of detecting the medical image of the target object to obtain the type of the target object, until the image quality of the obtained new medical image meets the image quality requirements or the performance of the ultrasound probe used meets the preset conditions, and an optimized image is obtained through optimization.

[0079] Specifically, since the target objects are of different types, the focus of subsequent scanning will be different, and the corresponding image quality requirements will also be different. For example, different liver types require different image quality in terms of resolution, contrast, signal-to-noise ratio and dynamic range. Therefore, before optimizing medical images, the corresponding image quality requirements can be determined according to the type of target object. Compare whether the currently acquired medical image meets the image quality requirements. If yes, no optimization is required, and the current medical image can be used as an optimized image for subsequent section capture. If not, optimization is required.

[0080] When optimizing specifically, the optimization scheme of replacing the ultrasonic probe and the image optimization scheme of post-processing the image can be considered. Among them, the ultrasonic probe directly affects the quality of the image mainly through parameters such as frequency, and the optimization time and cost are lower. Post-processing may not effectively make up for the image defects caused by insufficient probe acquisition quality. Therefore, if the probe can be replaced, the optimization scheme of replacing the ultrasonic probe is given priority. Therefore, when the image quality of the medical image does not meet the image quality requirements, it can be first detected whether the image can be optimized by replacing the ultrasonic probe. The detection method is: determine the performance of the ultrasonic probe used when acquiring the current medical image, specifically parameters such as frequency, and compare it with the preset conditions. The preset conditions can be the performance parameters corresponding to the ultrasonic probe with the best image quality. If the performance reaches the preset conditions, it means that the image quality cannot be improved by replacing the ultrasonic probe with better performance. Then, the medical image can be post-processed to optimize the image, that is, the medical image is optimized according to the image quality requirements to obtain an optimized image. For example, taking the frequency as an example to represent the performance of the ultrasound probe, assuming that the frequency of the currently used ultrasound probe is 20 MHz, the frequency value corresponding to the ultrasound probe with the best image quality is also 20 MHz, indicating that the frequency of the currently used ultrasound probe has reached the threshold and the image quality cannot be improved by replacing an ultrasound probe with a higher frequency.

[0081] If the performance of the currently used ultrasound probe does not meet the preset conditions, it means that an ultrasound probe with better performance can be replaced to improve the image quality, and a prompt message can be generated to prompt the doctor to replace the ultrasound probe. The prompt message can be in text form, for example, "The performance is poor, please replace the ultrasound probe", or it can be a sound prompt, or it can be an icon prompt, etc., which is not specifically limited in this application. After replacing the ultrasound probe, use the replaced new ultrasound probe to collect a new medical image of the target object again. Then return to step S110, perform image detection on the new medical image again, determine the type of the target object, and determine the corresponding image quality requirements according to the type of the target object. Until the image quality of the new medical image obtained meets the image quality requirements or the performance of the ultrasound probe used meets the preset conditions, the loop ends and an optimized image is obtained.

[0082] In this embodiment, the corresponding image quality requirements are determined by the type of target object, which can ensure that the optimized image meets the specific medical application requirements. This targeted optimization can reduce the number of unqualified images and improve the accuracy of diagnosis; by automatically detecting whether the performance of the probe meets the preset conditions and prompting to replace the probe when the conditions are not met, it can save the time and energy of medical staff and enhance the efficiency of the diagnosis process; by generating prompt information and re-performing quality inspection after acquiring new images, the whole process forms a closed loop. This circular feedback mechanism ensures that the image quality can be continuously improved after each acquisition until the diagnostic requirements are met, which can effectively prevent the risk of misdiagnosis caused by one-time acquisition that does not meet the standards. In addition, through an efficient image acquisition optimization process, the patient's examination time and waiting time can be shortened, and the efficiency of acquiring subsequent cross-sectional images can be improved.

[0083] In an exemplary embodiment, in the above step S120, a scanning protocol that matches the medical image is determined based on the type of the target object, including: based on the type of the target object, searching for a plurality of pre-constructed candidate scanning protocols corresponding to the target object to obtain a scanning protocol that matches the medical image.

[0084] In a specific implementation, scanning protocols corresponding to different types of target objects can be pre-constructed as multiple candidate scanning protocols, each type corresponds to a candidate scanning protocol one-to-one, and a mapping relationship between each type of target object and the scanning protocol is established. After determining the type of the target object, multiple pre-constructed candidate scanning protocols for the target object can be searched according to the mapping relationship to obtain the candidate scanning protocol corresponding to the type of the target object as the scanning protocol that matches the medical image of the target object, thereby obtaining the image section to be collected.

[0085] For example, for the target object liver, if its type is detected as fatty liver, the sections included in the determined scanning protocol are the first portal section and the second portal section, etc.

[0086] In this embodiment, taking into account the different emphases of scanning under different types, determining the scanning protocol based on the type of the target object can match a more accurate and appropriate scanning protocol, thereby improving the accuracy of the subsequent cross-sectional images acquired based on the scanning protocol.

[0087] In an exemplary embodiment, after the above step S130 captures the optimized image according to the section type in the scanning protocol to obtain the section image of the target object, it also includes: measuring the section parameter value corresponding to the section image according to the section type corresponding to the section image; and displaying the section parameter value.

[0088] The section type refers to the type of the section corresponding to the section image. For example, for the liver, the section type may be the first portal section, the second portal section, and the like.

[0089] The section parameter value is a parameter value that can be used to determine the type of the target object. For example, for the second portal section of the liver, the section parameter value can be the measured value of the maximum oblique diameter of the right lobe of the second portal, the inner diameter of the blood vessel, etc.

[0090] In the specific implementation, after the optimized image obtained by the doctor during the scanning process is captured based on the scanning protocol, the captured section can be further automatically measured to measure the corresponding section parameter value. After the measurement is completed, the measured section parameter value can be displayed to confirm the correctness of the measurement result by the doctor. Different sections correspond to different section parameter values. Therefore, the corresponding section parameter value needs to be measured according to the section type of the section image.

[0091] More specifically, when measuring the section parameter value corresponding to the section image, each sub-object in the section image may be segmented first, and then the corresponding section parameter value may be obtained based on the segmentation result. For example, for the second hepatic portal section image, the segmentation result of the liver, hepatic vein, portal vein and other sub-objects may be obtained, and the measurement value of the maximum oblique diameter of the right lobe of the second hepatic portal and the value of the inner diameter of the blood vessel may be determined based on the segmentation result.

[0092] In this embodiment, according to the slice type of the slice image, the slice parameter value corresponding to the slice image is measured, and the situation of the target object can be evaluated more accurately according to the slice parameter value.

[0093] Furthermore, in an exemplary embodiment, according to the type of slice corresponding to the slice image, measuring the slice parameter value corresponding to the slice image includes: inputting the slice image into a slice measurement model, performing image segmentation processing on the slice image in the slice measurement model to obtain segmentation masks of each sub-object in the slice image, and detecting key points for measuring the slice parameter value; based on the segmentation masks and key points of each sub-object, measuring the slice parameter value corresponding to the slice image.

[0094] In a specific implementation, a section measurement model can be pre-trained using sample data, and the sample data can include sample section images and section parameter value labels of the sample section images. During training, the sample section images are used as input variables, and the section parameter value labels of the sample section images are used as supervisory information for training to obtain a trained section measurement model. The section measurement model can be a neural network model, such as a network model based on a convolutional neural network.

[0095] After obtaining the cross-sectional image of the target object, the cross-sectional image can be input into the cross-sectional measurement model, and the cross-sectional measurement model processes the cross-sectional image to obtain the corresponding cross-sectional parameter value. In the cross-sectional measurement model, the cross-sectional image is first segmented to obtain the segmentation mask of each sub-object in the cross-sectional image, and the cross-sectional image is key-point detected to obtain the key points used to measure the cross-sectional parameter value. Based on the segmentation mask and key points of each sub-object, the cross-sectional parameter value corresponding to the cross-sectional image is measured.

[0096] For example, taking the automatic measurement of the second liver portal image as an example, as shown in FIG3 , it is a flow chart of the automatic measurement algorithm of the second liver portal image. Figure 4 This is an application example of automatic measurement of the second hepatic portal image. For the second hepatic portal image, the section measurement model based on the convolutional neural network first segments the mask of the liver and hepatic vein, as well as the key points for measuring the position mark. Then, based on the liver segmentation result, the salient point detection of the liver contour is performed, and then the upper edge point of the liver is extracted based on the position information. The points on the upper edge of the liver are traversed, and a vertical line perpendicular to the tangent direction of the upper edge point of the liver is sent downward at the corresponding position. The distance from the intersection of this vertical line and the liver to the upper edge point is used as the distance of the measurement line, and the maximum value of all distances is found, which is the measurement value of the maximum oblique diameter of the right lobe of the second hepatic portal.

[0097] And, the inner diameter of the blood vessel is determined based on the segmentation result of the hepatic vein and the landmark key points of the hepatic vein measurement position. Specifically, firstly, based on the extension of the hepatic vein segmentation result and the aspect ratio of the circumscribed rectangle, the number of branches of the hepatic vein is judged, which may be one, two or three. Then, the hepatic vein is refined to obtain the skeleton line of the blood vessel, and the skeleton line is divided into the corresponding number of branches based on the number of branches. The refined results of each blood vessel are traversed, and the skeleton line located on the left side of the key point position is intercepted. At the same time, a vertical line perpendicular to the skeleton line is emitted to both sides of the blood vessel, and the distance between the intersection with the blood vessel is used as the inner diameter of the blood vessel.

[0098] Furthermore, after all required sections have been captured and correspondingly measured, the results can be displayed on the display. If the doctor is not satisfied with the measurement results, the automatic measurement results can be manually edited. After all sections have been reviewed and confirmed by the doctor, the processor can automatically generate a corresponding report based on the sections and measurement results.

[0099] In this embodiment, by using the section measurement model to perform image segmentation processing, each sub-object in the section image can be accurately extracted, thereby improving the accuracy of section parameter value measurement. This refined processing reduces erroneous measurements caused by noise and interference, and the method can achieve automatic measurement of section parameter values, reducing the need for manual intervention, thereby improving measurement efficiency and measurement accuracy. Furthermore, key points are usually representatives of lesions or tissue features. By assisting the measurement of section parameter values ​​through key point detection, state parameters related to pathology and physiology can be obtained more effectively.

[0100] In one embodiment, in order to facilitate those skilled in the art to understand the embodiment of the present application, the following takes the medical image as an ultrasound image and the target object as a liver as an example, and describes the specific example in conjunction with the accompanying drawings. Referring to FIG5 , a specific flow diagram of a section image acquisition method is shown, including the following steps:

[0101] Step S510: Detect the ultrasonic image of the liver to obtain the liver type.

[0102] Specifically, an ultrasound probe is used to scan the patient's liver to obtain an ultrasound image. If the patient's height, weight and other information are also obtained, the patient's height, weight and other information are input into the image detection model together with the ultrasound image of the liver for detection to obtain the patient's liver type.

[0103] Step S520: Optimize the ultrasound image of the liver according to the liver type to obtain an optimized image.

[0104] Specifically, the corresponding image quality requirement is determined according to the liver type, and if the quality of the liver ultrasound image meets the image quality requirement, the liver ultrasound image is used as the optimized image.

[0105] If the quality of the ultrasound image of the liver does not meet the image quality requirement and the performance of the ultrasound probe meets the preset conditions, the ultrasound image is optimized according to the image quality requirement to obtain an optimized image.

[0106] If the quality of the ultrasound image of the liver does not meet the image quality requirements and the performance of the ultrasound probe does not meet the preset conditions, a prompt message is generated to prompt the user to replace the ultrasound probe with a higher performance to obtain a new optimized image, and then perform detection again with the new optimized image until the image quality meets the image quality requirements or the performance of the ultrasound probe used meets the preset conditions.

[0107] Step S530, matching the corresponding scanning protocol according to the liver type.

[0108] Step S540, according to the scanning order of each liver section in the scanning protocol, the optimized image is captured to obtain at least one section image of the liver.

[0109] Step S550: for each section image, automatically measuring the section parameter value corresponding to the section image.

[0110] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0111] Based on the same inventive concept, the embodiment of the present application also provides a section image acquisition device for implementing the section image acquisition method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more section image acquisition device embodiments provided below can refer to the limitations of the section image acquisition method above, and will not be repeated here.

[0112] In one embodiment, as shown in FIG6 , a section image acquisition device is provided, comprising: an image detection module 610, an optimization determination module 620 and a section capture module 630, wherein:

[0113] An image detection module 610 is used to detect a medical image of a target object to obtain a type of the target object;

[0114] The optimization determination module 620 is used to optimize the medical image according to the type of the target object to obtain an optimized image, and to determine a scanning protocol that matches the medical image according to the type of the target object; the scanning protocol includes a slice to be collected configured for the target object;

[0115] The section capture module 630 is used to capture the section of the optimized image according to the section type in the scanning protocol to obtain the section image of the target object.

[0116] In one embodiment, the above-mentioned image detection module 610 is also used to obtain physiological information of the patient corresponding to the target object; input the physiological information and the medical image into the image detection model for detection processing to obtain the type of the target object.

[0117] In one embodiment, the above-mentioned optimization determination module 620 is also used to determine the corresponding image quality requirements according to the type of the target object; when the image quality of the medical image meets the image quality requirements, the medical image is used as the optimized image; when the image quality of the medical image does not meet the image quality requirements, the ultrasound probe used to collect the medical image is determined; if the performance of the ultrasound probe meets the preset conditions, the medical image is optimized according to the image quality requirements to obtain an optimized image.

[0118] In one embodiment, the above-mentioned optimization determination module 620 is also used to generate a prompt message if the performance of the ultrasound probe does not meet the preset conditions; the prompt message is used to prompt the replacement of a new ultrasound probe with better performance than the ultrasound probe; after obtaining a new medical image collected by the new ultrasound probe, return to the step of detecting the medical image of the target object to obtain the type of the target object, until the image quality of the obtained new medical image meets the image quality requirements or the performance of the ultrasound probe used meets the preset conditions, and an optimized image is obtained through optimization.

[0119] In one embodiment, the above-mentioned optimization determination module 620 is also used to search for a plurality of pre-built candidate scanning protocols corresponding to the target object according to the type of the target object, and obtain a scanning protocol that matches the medical image.

[0120] In one embodiment, the above-mentioned device further includes a parameter measurement module, which is used to measure the slice parameter value corresponding to the slice image according to the slice type corresponding to the slice image; and display the slice parameter value.

[0121] In one embodiment, the parameter measurement module is also used to input the section image into the section measurement model, in which the section image is segmented to obtain the segmentation mask of each sub-object in the section image, and detect the key points used to measure the section parameter value; based on the segmentation mask and key points of each sub-object, the section parameter value corresponding to the section image is measured.

[0122] Each module in the above-mentioned section image acquisition device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0123] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a cross-sectional image acquisition method is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, a trackball or a touch pad set on the housing of the computer device, or an external keyboard, touch pad or mouse, etc.

[0124] Those skilled in the art will understand that the structure shown in FIG. 7 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0127] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0129] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0130] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for acquiring a section image, characterized in that: The method comprises: Detecting a medical image of a target object to obtain a type of the target object; According to the type of the target object, the medical image is optimized to obtain an optimized image, and according to the type of the target object, a scanning protocol matching the medical image is determined; According to the section type in the scanning protocol, the section capture is performed on the optimized image to obtain the section image of the target object.

2. The method according to claim 1, characterized in that The detecting the medical image of the target object to obtain the type of the target object includes: Acquiring physiological information of a patient corresponding to the target object; The physiological information and the medical image are input into an image detection model for detection processing to obtain the type of the target object.

3. The method according to claim 1, characterized in that The step of optimizing the medical image according to the type of the target object to obtain an optimized image includes: Determining corresponding image quality requirements according to the type of the target object; When the image quality of the medical image meets the image quality requirement, using the medical image as an optimized image; When the image quality of the medical image does not meet the image quality requirement, determining an ultrasound probe used to acquire the medical image; If the performance of the ultrasound probe meets the preset conditions, the medical image is optimized according to the image quality requirements to obtain the optimized image.

4. The method according to claim 3, characterized in that: The method further comprises: If the performance of the ultrasound probe does not meet the preset condition, a prompt message is generated; the prompt message is used to prompt the user to replace the ultrasound probe with a new one having better performance than the ultrasound probe; After acquiring a new medical image collected by the new ultrasound probe, return to the step of detecting the medical image of the target object to obtain the type of the target object, until the image quality of the new medical image obtained meets the image quality requirements or the performance of the ultrasound probe used meets the preset conditions, and the optimized image is obtained through optimization.

5. The method according to claim 1, characterized in that Determining a scanning protocol that matches the medical image according to the type of the target object includes: According to the type of the target object, multiple pre-constructed candidate scanning protocols corresponding to the target object are searched to obtain a scanning protocol that matches the medical image.

6. The method according to any one of claims 1 to 5, characterized in that After capturing the section of the optimized image according to the section type in the scanning protocol to obtain the section image of the target object, the method further includes: According to the section type corresponding to the section image, measuring the section parameter value corresponding to the section image; Displays the slice parameter value.

7. The method according to claim 6, characterized in that The measuring, according to the section type corresponding to the section image, a section parameter value corresponding to the section image, comprises: Inputting the section image into a section measurement model, performing image segmentation processing on the section image in the section measurement model to obtain segmentation masks of each sub-object in the section image, and detecting key points for measuring the section parameter values; Based on the segmentation mask of each of the sub-objects and the key points, a section parameter value corresponding to the section image is measured.

8. A section image acquisition device, characterized in that: The device comprises: An image detection module, used to detect a medical image of a target object to obtain the type of the target object; an optimization determination module, configured to optimize the medical image according to the type of the target object to obtain an optimized image, and to determine a scanning protocol matching the medical image according to the type of the target object; the scanning protocol includes a section to be acquired configured for the target object; A section capture module is used to capture the section of the optimized image according to the section type in the scanning protocol to obtain a section image of the target object.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the cross-sectional image acquisition method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the section image acquisition method according to any one of claims 1 to 7 are implemented.

Images