Medical image generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a medical image generation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a PET dynamic image of a target part of a scanned object; performing quality analysis based on the PET dynamic image to obtain a quality analysis result; under the condition that the quality analysis result represents that the PET dynamic image does not meet the quality requirement, acquiring first scanning data corresponding to a preset acquisition duration; determining a counting rate of coincidence events based on the first scanning data; under the condition that the counting rate is smaller than the counting rate threshold value, prolonging the single-frame duration of the PET dynamic image to obtain first single-frame duration; acquiring second scanning data corresponding to the first single frame duration; according to the method, the target single-frame image of the target part is established based on the second scanning data, and the acquisition time of the single frame is prolonged, so that more scanning data can be acquired, and the quality of each reconstructed frame of image can be improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of medical images, and particularly relates to a medical image generation method and device, an electronic device, and a storage medium. BACKGROUND

[0002] According to literature statistics, 80% of Positron Emission Tomography (PET) / Computed Tomography (CT) images have quality problems. The quality of a PET image has a direct impact on the stability of a parameter map, but when the quality of a reconstructed image is found to have a problem, the image needs to be reconstructed again based on the collected data. For a dynamic image with a collection time of one hour, the actual image generation time will be longer. If the image has a problem, a large amount of time needs to be spent to reestablish the image, which affects the work efficiency of a doctor. SUMMARY

[0003] To solve the above problems, the present application provides a medical image generation method, device, electronic device, and storage medium, which can improve the quality of each frame of a reconstructed image, thereby improving the work efficiency of a doctor.

[0004] The present application provides a medical image generation method, which includes the following steps.

[0005] Obtaining a PET dynamic image of a target part of a scanning object;

[0006] Performing quality analysis based on the PET dynamic image to obtain a quality analysis result;

[0007] In a case where the quality analysis result indicates that the PET dynamic image does not meet a quality requirement, obtaining first scanning data with a preset collection time length;

[0008] Determining a count rate of coincidence events based on the first scanning data;

[0009] In a case where the count rate is less than a count rate threshold, extending a single-frame time length of the PET dynamic image to obtain a first single-frame time length;

[0010] Obtaining second scanning data corresponding to the first single-frame time length;

[0011] In a case where a count rate of coincidence events corresponding to the second scanning data is greater than the count rate threshold, establishing a target single-frame image of the target part based on the second scanning data.

[0012] In some embodiments, the establishing the target single-frame image of the target site based on the second scanning data comprises:

[0013] determining an intermediate single-frame image of the target site based on the second scanning data;

[0014] determining a signal-to-noise ratio of the intermediate single-frame image;

[0015] adjusting a first single-frame duration to obtain a second single-frame duration in a case where the signal-to-noise ratio is less than a signal-to-noise ratio threshold;

[0016] obtaining third scanning data corresponding to the second single-frame duration;

[0017] establishing the target single-frame image of the target site based on the third scanning data, wherein a signal-to-noise ratio corresponding to the target single-frame image is greater than the signal-to-noise ratio threshold.

[0018] In some embodiments, the method further comprises:

[0019] obtaining a pre-stored corresponding relationship and a body parameter of the scanning object, wherein the corresponding relationship comprises a corresponding relationship between a body parameter and a count rate threshold;

[0020] determining the count rate threshold based on the user body parameter and the corresponding relationship.

[0021] In some embodiments, the method further comprises:

[0022] determining an SUV value of the target single-frame image;

[0023] performing normalization processing on the SUV value to obtain a normalized SUV value;

[0024] determining a lesion condition of the target site based on the normalized SUV value.

[0025] In some embodiments, the determining the lesion condition of the target site based on the normalized SUV value comprises:

[0026] obtaining a normalized SUV value corresponding to a lesion condition;

[0027] comparing the normalized SUV value with the normalized SUV value corresponding to the lesion condition to obtain a comparison result;

[0028] determining the lesion condition of the target site based on the comparison result.

[0029] In some embodiments, the method further comprises:

[0030] obtaining a scanning instruction, the scanning instruction comprising a target site;

[0031] acquire a corresponding scan protocol based on the target site, and locate the target site of the scan object;

[0032] perform PET dynamic scanning on the target site of the scan object based on the scan protocol.

[0033] In some embodiments, the method further comprises:

[0034] outputting prompt information for prompting whether to adjust the scan duration;

[0035] In a case where the trigger information of adjusting the scan duration is acquired, adjusting the scan duration based on the third single-frame duration.

[0036] Embodiments of the present application provide a medical image generation device, comprising:

[0037] a first acquisition module configured to acquire a PET dynamic image of a target site of a scan object;

[0038] an analysis module configured to perform quality analysis based on the PET dynamic image to obtain a quality analysis result;

[0039] a second acquisition module configured to acquire first scan data of a preset acquisition duration in a case where the quality analysis result indicates that the PET dynamic image does not meet quality requirements;

[0040] a first determination module configured to determine a count rate of coincidence events based on the first scan data;

[0041] a first adjustment module configured to, in a case where the count rate is less than a count rate threshold, lengthen a single-frame duration of the PET dynamic image to obtain a first single-frame duration;

[0042] a third acquisition module configured to acquire second scan data corresponding to the first single-frame duration;

[0043] a building module configured to, in a case where a count rate of coincidence events corresponding to the second scan data is greater than a count rate threshold, build a target single-frame image of the target site based on the second scan data.

[0044] Embodiments of the present application provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the medical image generation method of any one of the above.

[0045] Embodiments of the present application provide a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the method of any one of the above.

[0046] The embodiment of the present application provides a computer program product, when the computer program product runs on a terminal device, makes an electronic device execute the medical image generation method.

[0047] The embodiment of the present application provides a medical image generation method, device, electronic device and storage medium, the PET dynamic image of the target part of the scanning object is acquired; quality analysis is performed based on the PET dynamic image, and a quality analysis result is obtained; in the case that the quality analysis result represents that the PET dynamic image does not meet the quality requirement, first scanning data corresponding to a preset acquisition time length is acquired; the count rate of coincidence events is determined based on the first scanning data; in the case that the count rate is less than the count rate threshold, a single frame time length of the PET dynamic image is extended to obtain a first single frame time length; second scanning data corresponding to the first single frame time length is acquired; and a target single frame image of the target part is established based on the second scanning data. Since the single frame acquisition time is extended, more scanning data can be acquired, and thus the quality of each frame image of the reconstruction can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0048] In the following, the present application will be described in more detail based on embodiments and with reference to the drawings.

[0049] Figure 1 The implementation flowchart of the medical image generation method provided by the embodiment of the present application is shown in the figure.

[0050] Figure 2 The structure diagram of the medical image generation device provided by the embodiment of the present application is shown in the figure.

[0051] Figure 3 The composition structure diagram of the electronic device provided by the embodiment of the present application is shown in the figure.

[0052] In the drawings, the same components are designated by the same reference numerals, and the drawings are not drawn according to the actual scale. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be described in more detail below with reference to the drawings, and the described embodiments should not be regarded as limiting the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0054] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0055] If there are similar descriptions of "first\second\third" in the application file, the following description is added. In the following description, the terms "first\second\third" are only used to distinguish similar objects and do not represent a specific order of the objects. Understandably, "first\second\third" can be interchanged in a specific order or sequence as allowed, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0057] Before introducing the embodiments of the present application, the problems in the related art are briefly introduced,

[0058] The frame time of the super-conventional dynamic image scanning is fixed. Generally, 2 seconds per frame is taken in the first 1 minute, then 10 seconds per frame is taken in 1-3 minutes, and 30 seconds per frame is taken in 3-6 minutes. These short frame times result in poor image quality. Since the image quality is poor, when it is found that the reconstructed image has quality problems, the image needs to be reconstructed again based on the collected data. For a dynamic image with a collection time of one hour, the actual image output time will be longer. If the image has problems, a lot of time will be spent to re-establish the image, which affects the work efficiency of the doctor.

[0059] Based on the problems in the related art, the embodiments of the present application provide a medical image generation method which can be applied to electronic devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, notebook computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), scanning devices, etc. The embodiments of the present application do not make any limitation on the specific type of electronic device.

[0060] In the embodiments of the present application, the scanning device can be a single modality device, such as a Positron Emission Tomography (PET) scanning device. In some embodiments, the scanning device can also be a multi-modality device, such as a PET / CT device, a PET / MR device, etc.

[0061] The function implemented by the medical image generation method provided in the embodiments of the present application can be implemented by calling program code by a processor of an electronic device, wherein the program code can be stored in a computer storage medium.

[0062] The embodiments of the present application provide a medical image generation method, Figure 1 The implementation process of the medical image generation method provided in the embodiments of the present application is shown in Figure 1 The implementation process of the medical image generation method provided in the embodiments of the present application is shown in

[0063] In step S101, a PET dynamic image of a target part of a scanning object is acquired.

[0064] In the embodiments of the present application, the scanning object can be a patient, and the target part can be any one of a head, a chest, an abdomen, etc.

[0065] In the embodiments of the present application, the PET dynamic image can be a three-dimensional image, and the PET dynamic image can be acquired in the following manner: the target part of the scanning object is determined by medical imaging technology, etc., a PET scanning device scans the target part of the scanning object, and a radioactive tracer is usually injected. Under the set scanning conditions, PET scanning is performed to acquire a PET image sequence of the target part, and the data obtained by PET scanning is converted into a PET dynamic image by an image reconstruction algorithm.

[0066] In some embodiments, the PET dynamic image of the target part of the scanning object can also be acquired through a network.

[0067] In some embodiments, the PET dynamic image of the target part can also be acquired through a storage device.

[0068] In step S102, quality analysis is performed based on the PET dynamic image to obtain a quality analysis result.

[0069] In the embodiments of the present application, the quality analysis includes one or more of SUV value analysis, signal-to-noise ratio analysis, coefficient of variation analysis, noise equivalent count rate analysis, and artifact analysis.

[0070] In the embodiments of the present application, the PET dynamic image can be input into a neural network model to perform quality analysis and obtain a quality analysis result.

[0071] In the embodiments of the present application, a sample PET dynamic image can be acquired, and sample PET dynamic image data is preprocessed and feature extracted to meet the input requirements of a neural network model, and the sample PET dynamic image is labeled. A neural network model suitable for processing PET dynamic images is designed and constructed, which can include structures such as convolutional neural networks (CNN). Using the labeled PET dynamic image dataset, the constructed neural network model is trained to learn the quality characteristics of the PET image. The trained neural network model is evaluated by a validation set or test set to check its performance on the quality analysis task. The trained neural network model is applied to new PET dynamic image data for quality analysis, and a quality analysis result is obtained.

[0072] In the embodiments of the present application, the quality analysis result can include whether one or more of the SUV value, signal-to-noise ratio, coefficient of variation, noise equivalent count rate, etc. meets the set value, and whether there is an artifact.

[0073] In some embodiments, the quality analysis result can include that the quality requirement is not met.

[0074] Step S103, in the case that the quality analysis result represents that the PET dynamic image does not meet the quality requirement, first scanning data corresponding to a preset acquisition time length is acquired.

[0075] In the embodiments of the present application, if the quality analysis result does not meet the set value or there is an artifact, it can be considered that the PET dynamic image does not meet the quality requirement.

[0076] In the embodiments of the present application, the preset acquisition time length can be configured. When performing PET dynamic image scanning reconstruction, a doctor can set the preset acquisition time length. In the embodiments of the present application, the working principle of PET is to inject a drug containing a radionuclide into the subject, the radionuclide decays to produce a positron, the positron annihilates with the surrounding negative electron to produce a pair of back-to-back gamma photons, the gamma photons are received and recorded after passing through the subject by the PET detector, wherein the detector receives coincidence events, and an image is reconstructed according to the coincidence events to obtain a nuclide distribution map of the emitted positron.

[0077] In the embodiments of the present application, a user will receive an injection of a radioactive tracer, which will emit a positron in the body. After the radioactive tracer is fully distributed to the target site, scanning is performed. When scanning, the user will be placed in a scanning device, which will detect and record the coincidence events emitted by the tracer, and capture them through a highly sensitive camera, thereby acquiring first scanning data corresponding to a preset acquisition time length.

[0078] In some embodiments, the preset acquisition duration can be n times of a single frame duration, and the single frame duration can be preset. For example, the single frame duration can be set to 2s.

[0079] In step S104, a count rate of coincidence events is determined based on the first scanning data.

[0080] In the embodiments of the present application, the count rate is the number of coincidence events detected per unit time. Based on the first scanning data, the count rate of coincidence events can be calculated. The scanning device records the distribution of the radioactive tracer in the patient's body, and then calculates the number of coincidence events detected per unit time according to the half-life of the radioactive tracer and the sensitivity of the detector, thereby obtaining the count rate.

[0081] In step S105, in a case where the count rate is less than a count rate threshold, a single frame duration of the PET dynamic image is extended to obtain a first single frame duration.

[0082] In the embodiments of the present application, because different body information can have different physiological characteristics, the count rate threshold can also vary from person to person, and the count rate threshold can be determined based on the body information of the scanning object.

[0083] In the embodiments of the present application, the count rate threshold can be set by the medical staff according to the body information of the scanning object.

[0084] In some embodiments, before step S105, the method further comprises determining a count rate threshold based on the body information of the user, which can be achieved by the following steps:

[0085] Obtaining a pre-stored corresponding relationship and a body parameter of the scanning object, the corresponding relationship comprising a corresponding relationship between the body parameter and the count rate threshold; and determining the count rate threshold based on the body parameter and the corresponding relationship.

[0086] In the embodiments of the present application, the body parameter can include age, gender, and weight.

[0087] In the embodiments of the present application, the medical professionals can formulate the corresponding relationship between the age, gender, weight, and the count rate threshold according to the clinical experience and related research, and then store it in the electronic device. After obtaining the age, gender, and weight, the corresponding relationship can be called to determine the count rate threshold.

[0088] In the embodiments of the present application, in the PET scan, if the count rate is less than the preset count rate threshold, it is usually considered to adjust the single frame duration to obtain more data. This is because a low count rate can mean that the distribution of the tracer is not ideal, or the signal-to-noise ratio of the scan is insufficient, which can affect the image quality and the identification of abnormal conditions. Therefore, the single frame duration needs to be extended to obtain the first single frame duration.

[0089] In the embodiments of the present application, the prolonging can be performed based on a time step, for example, the time step can be set, for example, can be set to 0.5S.

[0090] In the embodiments of the present application, the length of the prolonging can be different according to the model of the PET scanning device and the specific process of the medical institution.

[0091] Based on the above example, the first single-frame length can be 2.5s.

[0092] In step S106, the second scanning data corresponding to the first single-frame length is obtained.

[0093] In the embodiments of the present application, since the first single-frame length is longer than the single-frame length, the second scanning data can be more than the first scanning data, and more coincidence event counts can be obtained.

[0094] In step S107, if the coincidence event count rate corresponding to the second scanning data is greater than the count rate threshold, the target single-frame image of the target part is established based on the second scanning data.

[0095] In the embodiments of the present application, the count rate corresponding to the second scanning data can be determined, and if the count rate corresponding to the second scanning data is less than the count rate threshold, the single-frame length is continued to be prolonged.

[0096] In the embodiments of the present application, when the target single-frame image is established, the second scanning data can be processed and reconstructed to obtain the target single-frame image.

[0097] In some embodiments, the image generated by the second scanning data can be fused with other modalities of imaging (such as CT, MRI, etc.) to facilitate the doctor to analyze the target part of the scanning object more comprehensively and accurately.

[0098] The method provided by the embodiments of the present application can obtain the first scanning data corresponding to the first single-frame length in the case of scanning the target part of the user; determine the coincidence event count rate based on the first scanning data; prolong the first single-frame length to obtain the second single-frame length in the case that the count rate is less than the count rate threshold; obtain the second scanning data corresponding to the second single-frame length; and establish the target single-frame image of the target part based on the second scanning data, wherein the count rate of the second scanning data is greater than the count rate threshold, which can improve the quality of the reconstructed target single-frame image, thereby improving the work efficiency of the doctor.

[0099] In some embodiments, in step S107, establishing the target single-frame image of the target part based on the second scanning data can be realized by the following steps:

[0100] In step S1071, an intermediate single-frame image of the target site is determined based on the second scanning data.

[0101] In the embodiments of the present application, the intermediate single-frame image is obtained by image reconstruction using computed tomography (CT), PET or magnetic resonance imaging (MRI) technology, etc.

[0102] In step S1072, a signal-to-noise ratio of the intermediate single-frame image is determined.

[0103] In the embodiments of the present application, the signal-to-noise ratio is used to measure the ratio of signal to noise in the image, and is usually used to evaluate the quality of the image.

[0104] In the embodiments of the present application, the signal region in the intermediate single-frame image can be determined first. In medical imaging, this usually refers to the region of human tissue or organ. The signal can be the density, contrast or other characteristics of the tissue. Then the noise level in the image is determined. The noise can be random interference introduced by the imaging device, environmental factors or other sources. The noise level can usually be estimated by selecting a region in the image that does not contain signal. After the signal region and noise level are determined, the signal-to-noise ratio can be calculated, and the calculation formula of the signal-to-noise ratio can be represented as:

[0105] SNR = Signal / Noise;

[0106] Where Signal represents the intensity of the signal, and Noise represents the intensity of the noise. In medical imaging, the intensity of the signal and the noise is usually represented by a specific unit (such as Hounsfield unit or gray level).

[0107] In step S1073, the first single-frame duration is extended to obtain a second single-frame duration when the signal-to-noise ratio is less than a signal-to-noise ratio threshold.

[0108] In the embodiments of the present application, the signal-to-noise ratio threshold can be configured, and according to the specific application scenario and requirements, a signal-to-noise ratio threshold can be set to determine whether the quality of the image meets the quality requirements. If the signal-to-noise ratio is lower than the signal-to-noise ratio threshold, adjustment or optimization is needed to improve the quality of the image.

[0109] In the embodiments of the present application, the signal-to-noise ratio being less than the signal-to-noise ratio threshold can be considered as the image quality being not high, and the first single-frame duration needs to be extended.

[0110] In the above example, the second single-frame duration can be 3s.

[0111] In step S1074, third scanning data corresponding to the second single-frame duration is obtained.

[0112] In the embodiments of the present application, according to the adjusted third single-frame time length, more data can be obtained, which helps to improve the signal-to-noise ratio and improve the image quality.

[0113] In step S1075, a target single-frame image of the target site is established based on the third scanning data, wherein the signal-to-noise ratio corresponding to the target single-frame image is greater than a signal-to-noise ratio threshold.

[0114] In the embodiments of the present application, the third scanning data can be pre-processed, including denoising, filtering, artifact elimination and the like, to reduce noise and other interference. Then the processed third scanning data is reconstructed into an image, and the imaging parameters can be optimized according to the characteristics of the third scanning data. The adjustment of the imaging parameters can include the adjustment of parameters such as contrast, brightness, window width and window level, to ensure the best performance of image clarity and contrast.

[0115] In the embodiments of the present application, the reconstructed image can be analyzed to ensure that the image contains the required lesion information of the target site and to evaluate the quality and accuracy of the image. The target single-frame image of the target site can be generated according to the optimized imaging parameters and the analysis results.

[0116] The method provided in the embodiments of the present application acquires a PET dynamic image of a target site of a scanning object; performs quality analysis based on the PET dynamic image to obtain a quality analysis result; in a case where the quality analysis result indicates that the PET dynamic image does not meet the quality requirement, acquires first scanning data corresponding to a preset acquisition time length; determines a count rate of coincidence events based on the first scanning data; in a case where the count rate is less than a count rate threshold, extends a single-frame time length of the PET dynamic image to obtain a first single-frame time length; acquires second scanning data corresponding to the first single-frame time length; and establishes a target single-frame image of the target site based on the second scanning data. Since the single-frame acquisition time is extended, more scanning data can be acquired, thereby improving the quality of each reconstructed frame of the image.

[0117] In some embodiments, after step S107, the method further includes:

[0118] In step S108, a SUV value of the target single-frame image is determined.

[0119] In the embodiments of the present application, SUV (Standardized Uptake Value) is an index for evaluating tumor metabolic activity, which is commonly used for quantitative analysis of PET images. In medical imaging, SUV value can help doctors evaluate tumor activity and treatment response.

[0120] In the embodiments of the present application, a region of interest (ROI), usually a tumor or other lesion region, can be selected in the target single-frame image. Using the raw data of the PET scan, combined with the patient's weight, the injected dose of radioactive tracer, and other information, the SUV value in the ROI is calculated.

[0121] In the embodiments of the present application, the determination of the region of interest can be performed by tools in medical image processing software, such as manual delineation or automatic boundary detection algorithms.

[0122] In some embodiments, after the SUV value is determined, the SUV value can be determined and corrected. The SUV value can be calculated multiple times to ensure the stability and consistency of the results. This helps to exclude any deviation caused by errors or uncertainties. The parameters used to calculate the SUV value, including the injected dose of radioactive tracer, patient weight, scan time, etc., can be checked to ensure that the input of these parameters is accurate to avoid deviation of the calculation results.

[0123] Step S109, normalizing the SUV value to obtain a normalized SUV value.

[0124] In the embodiments of the present application, the SUV value is normalized, and the SUV value can be considered as a corrected base value based on the phantom test.

[0125] In the embodiments of the present application, the SUV value is influenced by various factors, including patient preparation, device performance, reconstruction algorithm, etc. Due to the influence of various factors, the SUV value does not have repeatability, therefore, by calculating the normalized SUV value, the differences between different patients, device performance, and reconstruction algorithm can be eliminated, so that the SUV value has better comparability and repeatability. The normalized SUV value can also be used to evaluate the treatment effect and prognosis, and is commonly used for follow-up and evaluation after PET / CT scanning.

[0126] The method provided in the embodiments of the present application can realize the comparability of SUV values across devices, patients, and time by determining the normalized SUV value, thereby eliminating the influence of differences in different hospital measuring instruments, different patients, and different detection times on the detection results.

[0127] Step S110, determining the lesion condition of the target site based on the normalized SUV value.

[0128] In the embodiments of the present application, when determining the lesion condition of the target site based on the normalized SUV value, clinical data and other imaging examination results are generally needed for comprehensive analysis. Generally, a site with a higher normalized SUV value may indicate that the tumor tissue takes up more glucose and has higher metabolic activity, which may be a malignant tumor. A site with a lower normalized SUV value may indicate normal tissue or a benign tumor.

[0129] In the embodiments of the present application, step S112 can be implemented by the following steps:

[0130] Step S1101: Obtain the normalized SUV value corresponding to the lesion condition.

[0131] In the embodiments of the present application, different normalized SUV values correspond to different lesion conditions. The lesion condition includes normal tissue or a reference lesion, and the normalized SUV value corresponding to the lesion condition can include the normalized SUV value of the normal tissue or the reference lesion.

[0132] Step S1102: Compare the normalized SUV value with the normalized SUV value corresponding to the lesion condition to obtain a comparison result.

[0133] In the embodiments of the present application, the comparison result can include whether there is a normalized SUV value corresponding to a lesion condition similar to the normalized SUV value.

[0134] Step S1103: Determine the lesion condition of the target site based on the comparison result.

[0135] In the embodiments of the present application, if the normalized SUV value is similar to the normalized SUV value of the normal tissue or the reference lesion, the lesion condition can be determined.

[0136] The method provided in the embodiments of the present application can facilitate comparison and verification experiments of multiple modalities and multiple scans by normalizing the SUV value.

[0137] In some embodiments, before step S101, the method further includes:

[0138] Step S1011: Obtain a scanning instruction, wherein the scanning instruction includes a target site.

[0139] In the embodiments of the present application, a doctor or a clinician can directly issue a scanning instruction, so that the electronic device obtains the scanning instruction. In the embodiments of the present application, the target site can include the brain, the heart, the lung, etc.

[0140] Step S1012: Obtain a corresponding scanning protocol based on the target site, and locate the target site of the scanning object.

[0141] In the embodiments of the present application, the scanning protocol includes specific steps and parameter settings for scanning. Generally, medical personnel will set the scanning protocol before scanning. The parameters can include: scanning duration, injection dose, etc.

[0142] In the embodiments of the present application, the target site can be determined by using previous image data or other image guidance. For example, previous CT or MRI images can be used to guide the scanning position, ensuring that the new scan corresponds to the previous image.

[0143] In some embodiments, guide lines or markers can be placed on the target site to facilitate accurate positioning during scanning. These guide lines or markers can be placed by X-ray, ultrasound or other image guidance techniques.

[0144] In some embodiments, an image of the user can be obtained and then input into a neural network model to determine the position of the target site, thereby completing positioning.

[0145] For example, if the head is scanned, the intelligent positioning target organ is the brain. If the scanning area is the lung, the intelligent positioning target organ is the aorta.

[0146] Step S1013, performing PET dynamic scanning on the target site of the scanning object based on the scanning protocol.

[0147] In the embodiments of the present application, the target site can be automatically scanned by PET dynamic scanning based on the scanning protocol.

[0148] In some embodiments, after step S107, the method further includes:

[0149] Step S112, outputting prompt information for prompting whether to adjust the scanning duration.

[0150] In the embodiments of the present application, due to the change of single frame duration, if the number of frames of the obtained image remains unchanged, the scanning duration will also change. Therefore, prompt information can be outputted to prompt the user whether to adjust the scanning duration.

[0151] In the embodiments of the present application, the prompt information can be outputted by a display device. The prompt information can include a selection option for selecting whether to adjust the scanning duration.

[0152] Step S110, in the case where the trigger information for adjusting the scanning duration is obtained, adjusting the scanning duration based on the second single frame duration.

[0153] In the embodiments of the present application, the user can make actual selection according to the actual situation and the operation manual of the device.

[0154] If the user selects to adjust the scan duration, the trigger information of adjusting the scan duration can be obtained based on the foregoing example.

[0155] It should be noted that, in the embodiments of the present application, the adjustment of the single-frame duration and the scan duration can be determined based on artificial intelligence technology.

[0156] In the embodiments of the present application, the artificial intelligence technology can automatically predict a reasonable scan duration based on the second single-frame duration by learning and analyzing a large amount of data.

[0157] Based on the foregoing embodiments, the embodiments of the present application provide a specific example application. In liver segmentation based on CT, the counting rate of coincidence events is determined based on scan data while scanning. If the counting rate is less than a counting rate threshold, the acquisition duration corresponding to a single frame is adjusted, so that more scan data is obtained, and the PET image of the liver region is reconstructed by more scan data, which can improve the image quality of each frame. At the same time, since the single-frame acquisition time is changed, the overall scan duration also needs to be corrected. A counting rate threshold corresponding to different time periods, different ages, genders, and weights can be defined to optimize the single-frame acquisition time.

[0158] The method provided by the embodiments of the present application controls the image quality by the single-frame duration, realizes quality control of the image, can guarantee the quality of the image, and can unify the standard by comparing the normalized SUV value corresponding to the lesion condition, so that multi-center image comparison becomes possible.

[0159] Based on the foregoing embodiments, the embodiments of the present application provide a medical image generation device. The modules included in the device and the units included in the modules can be implemented by a processor in a computer device. Of course, the device can also be implemented by a specific logic circuit. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor unit (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA).

[0160] The embodiments of the present application provide a medical image generation device, Figure 2 A structural diagram of the medical image generation device provided by the embodiments of the present application is shown in FIG. 2. Figure 2 As shown in FIG. 2, the medical image generation device 200 includes:

[0161] The first acquisition module 201 is configured to acquire a PET dynamic image of a target part of a scan object.

[0162] The analysis module 202 is configured to perform quality analysis on the PET dynamic image to obtain a quality analysis result.

[0163] The second acquisition module 203 is configured to acquire first scanning data of a preset acquisition time length when the quality analysis result indicates that the PET dynamic image does not meet the quality requirement.

[0164] The first determination module 204 is configured to determine a count rate of coincidence events based on the first scanning data.

[0165] The first adjustment module 205 is configured to prolong a single-frame time length of the PET dynamic image to obtain a first single-frame time length when the count rate is less than a count rate threshold.

[0166] The third acquisition module 206 is configured to acquire second scanning data corresponding to the first single-frame time length.

[0167] The establishment module 207 is configured to establish a target single-frame image of the target part based on the second scanning data when a count rate of coincidence events corresponding to the second scanning data is greater than the count rate threshold.

[0168] In some embodiments, the establishment module includes:

[0169] The first determination unit is configured to determine an intermediate single-frame image of the target part based on the second scanning data.

[0170] The second determination unit is configured to determine a signal-to-noise ratio of the intermediate single-frame image.

[0171] The adjustment unit is configured to adjust the first single-frame time length to obtain a second single-frame time length when the signal-to-noise ratio is less than a signal-to-noise ratio threshold.

[0172] The first acquisition unit is configured to acquire third scanning data corresponding to the second single-frame time length.

[0173] The establishment unit is configured to establish a target single-frame image of the target part based on the third scanning data, where a signal-to-noise ratio corresponding to the target single-frame image is greater than a signal-to-noise ratio threshold.

[0174] In some embodiments, the medical image generation apparatus further includes:

[0175] The fourth acquisition module is configured to acquire a pre-stored corresponding relationship and a body parameter of the scanning object, where the corresponding relationship includes a corresponding relationship between a body parameter and a count rate threshold.

[0176] The second determination module is configured to determine a count rate threshold based on the user body parameter and the corresponding relationship.

[0177] In some embodiments, the medical image generation apparatus further comprises:

[0178] a third determination module configured to determine an SUV value based on the target single-frame image;

[0179] a normalization processing module configured to perform normalization processing on the SUV value to obtain a normalized SUV value;

[0180] a fourth determination module configured to determine a lesion condition of the target part based on the normalized SUV value.

[0181] In some embodiments, the fourth determination module comprises:

[0182] a third acquisition unit configured to acquire a normalized SUV value corresponding to the lesion condition;

[0183] a comparison unit configured to compare the normalized SUV value with the normalized SUV value corresponding to the lesion condition to obtain a comparison result;

[0184] a fourth determination unit configured to determine the lesion condition of the target part based on the comparison result.

[0185] In some embodiments, the medical image generation apparatus further comprises:

[0186] a fifth acquisition module configured to acquire a scanning instruction, the scanning instruction comprising a target part;

[0187] a sixth determination module configured to acquire a corresponding scanning protocol based on the target part, and locate the target part of the scanning object;

[0188] a scanning module configured to perform PET dynamic scanning on the target part of the scanning object based on the scanning protocol.

[0189] In some embodiments, the medical image generation apparatus further comprises:

[0190] an output module configured to output prompt information for prompting a user whether to adjust a scanning duration;

[0191] a second adjustment module configured to, in a case where trigger information for adjusting the scanning duration is acquired, adjust the scanning duration based on the second single-frame duration.

[0192] Embodiments of the present application provide an electronic device; Figure 3 The composition structure schematic diagram of the electronic device provided by the embodiments of the present application is as follows: Figure 3As shown, the electronic device 300 includes: a processor 301, at least one communication bus 302, a user interface 303, at least one external communication interface 304, a memory 305. Wherein, the communication bus 302 is configured to realize the connection communication between the components. Wherein, the user interface 303 can include a display screen, and the external communication interface 304 can include a standard wired interface and a wireless interface. The processor 301 is configured to execute the program of the image establishing method stored in the memory to realize the steps in the medical image generation method provided in the above embodiments.

[0193] In the embodiments of the present application, if the image establishing method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read Only Memory), a magnetic disk or an optical disk, and various media that can store program codes. Thus, the embodiments of the present application are not limited to any specific hardware and software combination.

[0194] Correspondingly, the embodiments of the present application provide a storage medium having a computer program stored thereon, and the computer program is executed by a processor to realize the steps in the medical image generation method provided in the above embodiments.

[0195] The embodiments of the present application further provide a computer program product, when the computer program product is run on a terminal device, the electronic device executes the medical image generation method described in any one of the above embodiments.

[0196] The above description of the electronic device and the storage medium embodiments is similar to the description of the above method embodiments, and has similar beneficial effects to the method embodiments. For technical details not disclosed in the computer device and storage medium embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0197] It should be understood that every feature, structure, or characteristic described herein is within a preferred embodiment of the present application. It should be noted that the foregoing embodiments are merely exemplary and are not to be construed as limiting the present application. It should also be noted that features from one embodiment can be combined with features from another embodiment. It should also be noted that the words "comprise," "comprising," "comprises," "include," "including," and "includes" when used in this specification and in the following claims are not to be interpreted so as to exclude other additives, components, elements or steps. It should be understood that the terms "a" or "an," as used herein, mean "one or more" when applied to any feature in the specification and claims.

[0198] It should be noted that, as used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component" includes a plurality of such components. In this specification and in the claims, the term "on" or "onto" means "directly on or onto," unless otherwise indicated. The term "coupled" means either directly connected to or indirectly connected with the aid of one or more intervening components.

[0199] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0200] The units described above as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0201] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a unit alone, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0202] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a computer readable storage medium, and the program performs the steps of the above-mentioned method embodiments when executed; and the foregoing storage medium includes a mobile storage device, a read only memory (ROM), a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0203] Alternatively, the integrated units of the present application can be stored in a computer readable storage medium if they are realized in the form of software function modules and sold or used as independent products. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products, and the computer software products are stored in a storage medium, including a plurality of instructions for causing a controller to execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes a mobile storage device, a ROM, a magnetic disc or an optical disc, and various storage medium capable of storing program codes.

[0204] The above is only an embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A medical image generation method, characterized in that: include: Acquiring a PET dynamic image of a target area of ​​a scanned object; Performing quality analysis based on the PET dynamic image to obtain a quality analysis result; When the quality analysis result indicates that the PET dynamic image does not meet the quality requirement, obtaining first scan data with a preset acquisition time; determining a count rate of coincidence events based on the first scan data; When the count rate is less than the count rate threshold, extending the single-frame duration of the PET dynamic image to obtain a first single-frame duration; Acquire second scanning data corresponding to the first single frame duration; When the count rate of the coincident event corresponding to the second scanning data is greater than a count rate threshold, a target single-frame image of the target part is established based on the second scanning data.

2. The method according to claim 1, characterized in that The establishing of a target single-frame image of the target part based on the second scanning data includes: determining an intermediate single-frame image of the target part based on the second scanning data; determining a signal-to-noise ratio of the intermediate single-frame image; When the signal-to-noise ratio is less than a signal-to-noise ratio threshold, extending the first single-frame duration to obtain a second single-frame duration; Acquire third scanning data corresponding to the second single frame duration; A target single-frame image of the target part is established based on the third scanning data, wherein a signal-to-noise ratio corresponding to the target single-frame image is greater than a signal-to-noise ratio threshold.

3. The method according to claim 1, characterized in that The method further comprises: Acquiring a pre-stored correspondence relationship and a body parameter of the scanned object, wherein the correspondence relationship includes: a correspondence relationship between the body parameter and a count rate threshold; The count rate threshold is determined based on the body parameter and the corresponding relationship.

4. The method according to claim 2, characterized in that The method further comprises: Determining the SUV value of the target single-frame image; Normalizing the SUV value to obtain a normalized SUV value; The lesion condition of the target site is determined based on the normalized SUV value.

5. The method according to claim 4, characterized in that Determining the lesion condition of the target site based on the normalized SUV value includes: Obtain the normalized SUV value corresponding to the lesion condition; Comparing the normalized SUV value with the normalized SUV value corresponding to the lesion condition to obtain a comparison result; The pathological condition of the target site is determined based on the comparison result.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining a scanning instruction, wherein the scanning instruction includes a target part; Acquiring a corresponding scanning protocol based on the target part, and locating the target part of the scan object; A PET dynamic scan is performed on the target part of the scan object based on a scan protocol.

7. The method according to claim 2, characterized in that The method further comprises: Output a prompt message to prompt the user whether to adjust the scanning time; When trigger information for adjusting the scan duration is obtained, the scan duration is adjusted based on the second single frame duration.

8. A medical image generating device, characterized in that: include: A first acquisition module is used to acquire a PET dynamic image of a target part of the scanned object; An analysis module, configured to perform quality analysis based on the PET dynamic image to obtain a quality analysis result; a second acquisition module, configured to acquire first scan data of a preset acquisition time length when the quality analysis result indicates that the PET dynamic image does not meet the quality requirement; a first determining module, configured to determine a count rate corresponding to an event based on the first scanning data; a first adjustment module, configured to extend the single-frame duration of the PET dynamic image to obtain a first single-frame duration when the count rate is less than the count rate threshold; A third acquisition module is used to acquire second scanning data corresponding to the first single frame duration; An establishing module is configured to establish a target single-frame image of the target part based on the second scanning data when a count rate of a coincident event corresponding to the second scanning data is greater than a count rate threshold.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the medical image generating method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the medical image generating method according to any one of claims 1 to 7 is implemented.

Images