Calculation method of radioactivity distribution in both lungs based on PET / CT dynamic imaging

Abstract

The present invention discloses a method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging. The method provided by the present invention includes: acquiring a first image set and a second image set, preprocessing the first image set and the second image set to obtain a target image set, wherein the first image set is a CT image set and the second image set is a PET image set; acquiring a target region of interest based on the first image set, wherein the target region of interest is a multi-level region of interest; and acquiring a target radioactivity distribution curve based on the target region of interest and the target image set. The present invention proposes a new method for automatically analyzing the radioactivity distribution in the lungs, which can realize accurate and automated evaluation of the radioactivity distribution in the lungs and provide data support for clinical practice.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging. Background Art

[0002] Chronic obstructive pulmonary disease (COPD) is one of the most common chronic respiratory diseases worldwide and one of the leading causes of morbidity and mortality worldwide. The core pathological mechanism of the disease is persistent respiratory inflammation, which leads to airway obstruction or airflow limitation, seriously damaging lung function. Early detection and scientific management and treatment strategies can effectively control the disease and significantly improve the quality of life of patients. However, there is currently a lack of early case detection strategies for COPD.

[0003] Therefore, the prior art still needs to be improved and enhanced. Summary of the invention

[0004] In view of the above-mentioned defects of the prior art, the present invention provides a method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, aiming to solve the problem of the lack of early case detection strategy for chronic obstructive pulmonary disease in the prior art.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect of the present invention, a method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging is provided, the method comprising:

[0007] Acquire a first image set and a second image set, and preprocess the first image set and the second image set to obtain a target image set, wherein the first image set is a CT image set and the second image set is a PET image set;

[0008] Acquire a target region of interest based on the first image set, wherein the target region of interest is a multi-level region of interest;

[0009] A target radioactivity distribution curve is acquired based on the target region of interest and the target image set.

[0010] The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, wherein the step of acquiring the first image set and the second image set comprises:

[0011] After acquiring a first image and a second image at a target time, acquiring the second image at a preset time interval until five second images are acquired;

[0012] The second first image is acquired when the third second image is acquired.

[0013] The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, wherein the preprocessing of the first image set and the second image set to obtain the target image set includes:

[0014] resampling the second images in the second image set to a spatial size consistent with the first image set;

[0015] Align the first three second images with the first first image to obtain three target images;

[0016] The latter two second images are aligned with the second first image to obtain the two target images.

[0017] The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, wherein the step of acquiring the target region of interest based on the first image set includes:

[0018] Inputting the first image set into a target segmentation model to obtain binary masks of both lungs and trachea;

[0019] Acquiring a target coordinate position based on the binary mask of the trachea, wherein the target position includes a coordinate position of a left main bronchus and a coordinate position of a right main bronchus;

[0020] The binary masks of the two lungs are scaled based on the target coordinate position and the target coefficient to obtain the target position of interest, where the target coefficient is multiple.

[0021] The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, wherein the binary mask of both lungs is scaled based on the target coordinate position and the target coefficient to obtain the target position of interest, comprises:

[0022] Scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients to obtain a hierarchical region of interest corresponding to the left lung;

[0023] The binary mask of the right lung is scaled based on the coordinate position of the right main bronchus and the multiple target coefficients to obtain a hierarchical region of interest corresponding to the right lung.

[0024] The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, wherein the step of scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients comprises:

[0025] Obtaining the Euclidean distance between each pixel point in the binary mask of the left lung and the coordinate position of the left main bronchus, taking the coordinate position of the left main bronchus as the center point, scaling each pixel point in the binary mask of the left lung based on the multiple target coefficients, and obtaining multiple left lung mask areas;

[0026] The multiple left lung masks are superimposed, and the original left lung mask is used to limit the superimposed mask range to obtain a layered region of interest corresponding to the left lung.

[0027] The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, wherein the step of obtaining a target radioactivity distribution curve based on the target region of interest and the target image set comprises:

[0028] Acquire a set of radioactivity counts in a region of interest at each level corresponding to the target image set;

[0029] The target radioactivity distribution curve is plotted based on the radioactivity count set.

[0030] A second aspect of the present invention provides a device for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, comprising:

[0031] An image acquisition module, the image acquisition module is used to acquire a first image set and a second image set, preprocess the first image set and the second image set to obtain a target image set, the first image set is a CT image set, and the second image set is a PET image set;

[0032] A region acquisition module, the region acquisition module is used to acquire a target region of interest based on the first image set, the target region of interest is a multi-level region of interest;

[0033] A curve drawing module is used to obtain a target radioactivity distribution curve based on the target region of interest and the target image set.

[0034] According to a third aspect of the present invention, a terminal is provided, comprising a processor and a computer-readable storage medium communicatively connected to the processor, wherein the computer-readable storage medium is suitable for storing a plurality of instructions, and the processor is suitable for calling the instructions in the computer-readable storage medium to execute the steps of implementing any one of the above-mentioned methods for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging.

[0035] A fourth aspect of the present invention provides a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement the steps of any of the above-mentioned methods for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging.

[0036] Compared with the prior art, the present invention provides a method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging. The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging obtains a first image set and a second image set, preprocesses the first image set and the second image set to obtain a target image set, wherein the first image set is a CT image set, and the second image set is a PET image set, and then obtains a target region of interest based on the first image set, wherein the target region of interest is a multi-level region of interest, and finally obtains a target radioactivity distribution curve based on the target region of interest and the target image set. Based on PET / CT images, the present invention adopts a segmentation model based on deep learning, and proposes a new method for automatically analyzing the distribution of radioactivity in the lungs, combining PET images and CT images to achieve accurate and automated evaluation of the distribution of radioactivity in the lungs, and provide data support for clinical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of an embodiment of a method for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging provided by the present invention;

[0038] Figure 2 This is a flowchart of an implementation example of a method for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging provided by the present invention;

[0039] Figure 3 A schematic diagram of a PET / CT image of an embodiment of a method for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging provided by the present invention;

[0040] Figure 4 An example diagram of a visualization mask of an embodiment of a method for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging provided by the present invention;

[0041] Figure 5 A schematic diagram of a region of interest of an embodiment of a method for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging provided by the present invention;

[0042] Figure 6 A distribution change curve diagram of an embodiment of a method for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging provided by the present invention;

[0043] Figure 7 A structural principle diagram of an embodiment of a device for calculating radioactivity distribution in both lungs based on PET / CT dynamic imaging provided by the present invention;

[0044] Figure 8 A schematic diagram of the principles of an embodiment of a terminal provided by the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0047] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as herein.

[0048] The method for calculating the distribution of radioactivity in both lungs based on PET / CT dynamic imaging provided by the present invention can be applied to a terminal with computing capabilities, and the terminal can execute the method for calculating the distribution of radioactivity in both lungs based on PET / CT dynamic imaging provided by the present invention to segment the target in the image to be processed.

[0049] Embodiment 1

[0050] This embodiment is a new method for early detection of chronic obstructive pulmonary disease. In recent years, positron emission tomography / computed tomography (PET / CT) has provided a new perspective for the diagnosis and treatment of respiratory diseases. Studies have shown that inhalation of nebulized air can 18 F-NaF aerosol can be used for the diagnosis of lung tumors and inflammatory diseases. However, the reproducibility of quantitative measurements by PET / CT, the effect of drug uptake on age, and the confirmation of its prognostic value still need further study.

[0051] In current clinical practice, nebulized inhalation solvents mainly include normal saline or hypertonic saline. As an expectorant, hypertonic saline "absorbs water" from epithelial cells through its high osmotic pressure, rehydrates the aqueous layer around the cilia, promotes coughing, and directly affects the elasticity of mucus, which helps to discharge sputum. 18 F-NaF has similar physical and chemical properties to NaCl, and the aerosol particle sizes after atomization are comparable, which provides a basis for simulating the distribution of NaCl atomization inhalation in both lungs.

[0052] However, no study has proposed a new method based on PET / CT and 18 In similar studies, the calculation of parameters of the lung region of interest usually relies on manual or semi-automatic methods (such as seed point growth, level set, etc.), and a fully automated and more accurate calculation method has not been achieved.

[0053] Therefore, this embodiment provides a method for measuring the inhaled positron-emitting radiopharmaceutical aerosol (such as 18 Based on PET / CT images and a CT organ segmentation model based on deep learning, a new method for automatically analyzing the distribution of radioactivity in the lungs was proposed. This method can achieve accurate and automated evaluation of the distribution of radioactivity in the lungs, aiming to provide data support for clinical research on chronic obstructive pulmonary disease and provide a more accurate basis for personalized treatment and optimization of efficacy.

[0054] like Figure 1 As shown, in one embodiment of the method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, the steps include:

[0055] S100, acquiring a first image set and a second image set, and preprocessing the first image set and the second image set to obtain a target image set, wherein the first image set is a CT image set, and the second image set is a PET image set.

[0056] Wherein, acquiring the first image set and the second image set comprises:

[0057] After acquiring a first image and a second image at a target time, acquiring the second image at a preset time interval until five second images are acquired;

[0058] The second first image is acquired when the third second image is acquired.

[0059] This embodiment provides a method for automatically calculating the lung deposition rate based on PET / CT and positron-emission radiopharmaceutical aerosols, providing reliable data support for clinical research. First, PET / CT images are acquired and preprocessed, and then the trachea and lung masks are acquired from the CT images based on the deep learning organ segmentation model, and different regions of interest are divided in the lungs. Finally, the deposition rates of different regions of interest in the lungs are calculated based on the lung partition mask and the PET / CT images. The flowchart is as follows: Figure 2 shown.

[0060] Specifically, in this embodiment, the target patient's 18 Image data of F-NaF PET / CT dynamic scan. During the acquisition process, the target patient was scanned at 5 time points (30 minutes apart), where a PET scan was performed at each time point, but a CT scan was performed only at the first time point and the third time point. Therefore, the target patient had 2 CT scans to obtain the first image set, and 5 PET scans to obtain the second image set, where the three second images obtained by the first three PET scans correspond to the first image obtained by the first CT scan, and the two second images obtained by the last two PET scans correspond to the first image obtained by the second CT scan.

[0061] Specifically, for the extracted PET / CT image, the PET image, that is, the second image, is resampled to a spatial size consistent with the CT image, that is, the first image, and then normalized to a standard uptake value (SUV) image by injecting activity and body weight. Align the first three second images with the first first image to obtain three target images; align the last two second images with the second first image to obtain two target images. In this way, a total of five icon images are obtained to form the target image set. It is not difficult to see that the target image is a 3D image fused with PET / CT. Refer to Figure 3 ,exist Figure 3 In the figure, the first row is the maximum density projection image of PET, the second row is the fusion display of coronal CT image and PET image, and the third row is the fusion display of sagittal CT image and PET image.

[0062] S200: Acquire a target region of interest based on the first image set, where the target region of interest is a multi-level region of interest.

[0063] Specifically, after the CT image is obtained, a region of interest of the lung is extracted based on the CT image.

[0064] The acquiring a target region of interest based on the first image set comprises:

[0065] Inputting the first image set into a target segmentation model to obtain binary masks of both lungs and trachea;

[0066] Acquiring a target coordinate position based on the binary mask of the trachea, wherein the target position includes a coordinate position of a left main bronchus and a coordinate position of a right main bronchus;

[0067] The binary masks of the two lungs are scaled based on the target coordinate position and the target coefficient to obtain the target position of interest, where the target coefficient is multiple.

[0068] The step of scaling the binarized masks of the two lungs based on the target coordinate position and the target coefficient to obtain the target position of interest includes:

[0069] Scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients to obtain a hierarchical region of interest corresponding to the left lung;

[0070] The binary mask of the right lung is scaled based on the coordinate position of the right main bronchus and the multiple target coefficients to obtain a hierarchical region of interest corresponding to the right lung.

[0071] The step of scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients comprises:

[0072] Obtaining the Euclidean distance between each pixel point in the binary mask of the left lung and the coordinate position of the left main bronchus, taking the coordinate position of the left main bronchus as the center point, scaling each pixel point in the binary mask of the left lung based on the multiple target coefficients, and obtaining multiple left lung mask areas;

[0073] The multiple left lung masks are superimposed, and the original left lung mask is used to limit the superimposed mask range to obtain a layered region of interest corresponding to the left lung.

[0074] The step of scaling the binary mask of the right lung based on the coordinate position of the right main bronchus and the plurality of target coefficients comprises:

[0075] Obtaining the Euclidean distance between each pixel point in the binary mask of the right lung and the coordinate position of the right main bronchus, taking the coordinate position of the right main bronchus as the center point, scaling each pixel point in the binary mask of the right lung based on the multiple target coefficients, and obtaining multiple right lung mask areas;

[0076] The multiple right lung masks are superimposed, and the original right lung mask is used to limit the superimposed mask range to obtain a layered region of interest corresponding to the right lung.

[0077] Specifically, refer to Figure 4 , the method of obtaining the target region of interest based on the first image set is to input the first image into the target segmentation network, which is a segmentation network trained in advance, and extract the lung and trachea masks based on the target segmentation network. In other words, the CT image of the target patient is input into the trained organ segmentation neural network model, and the binary masks of both lungs and trachea are obtained through the model prediction output. The binary masks of both lungs and the trachea show the positions of different lobes of the lungs on both sides and the trachea in the first image. Figure 4 As shown, Figure 4 This is an example of a binary mask of both lungs and trachea in a CT image, where Figures a, b, and d are transverse, sagittal, and coronal sections of the CT image, and Figure c is a 3D display of the lung and trachea masks.

[0078] After obtaining the binary masks of the two lungs and the trachea, the target coordinate position is acquired based on the binary masks of the trachea.

[0079] Specifically, the area in the three-dimensional space where the binary mask of the trachea is located is identified, and each cross section is traversed layer by layer from top to bottom in the Z-axis direction to detect the number of connected domains in the layer. When it is detected that the number of connected domains increases from one to two, the level at which the tracheal bifurcation is identified is determined. According to the average anatomical length of the left and right main bronchi and the deflection angle between them and the extension line of the tracheal midline, it is set to search 3 layers from the right side downward and 6 layers from the left side downward from the tracheal bifurcation level, so that the areas of the left main bronchus and the right main bronchus are located. The average value of the regional coordinates of the left main bronchus is taken as the coordinate position of the left main bronchus, and the average value of the regional coordinates of the right main bronchus is taken as the coordinate position of the right main bronchus.

[0080] After determining the target coordinate position in the CT image, for the lobed lung mask, the left and right sides are fused with the respective lobes to obtain the masks of the left and right lungs. For each pixel point in the left and right lung masks, the Euclidean distance between it and the corresponding left and right main bronchial coordinates is calculated respectively, and the pre-defined target coefficient is used to reduce the lung regions on both sides with the main bronchial coordinate point as the center. Specifically, the binary mask of the left lung is scaled based on the coordinate position of the left main bronchus and multiple target coefficients; the binary mask of the right lung is scaled based on the coordinate position of the right main bronchus and multiple target coefficients. Specifically, it includes: calculating each pixel coordinate in the left and right lung regions, and obtaining the scaled position according to the proportionally reduced coordinate position to form the scaled lung mask. Superimpose the lung masks after each reduction, and use the original lung mask to limit the superimposed mask area, and finally obtain the region of interest layered from the periphery of the lung to the main bronchus for subsequent analysis of the radioactivity distribution in the lungs, such as Figure 5 As shown, in Figure 5 In the figure, Figures a, b and d are transverse, sagittal and coronal sections of the CT image, and Figure c is a 3D display of the layered lung. In this embodiment, the target coefficients are 3 groups of scaling coefficients, which are 0.5, 0.8 and 1 respectively. In more embodiments, the setting of the target coefficients can be adjusted according to the layering requirements of the region of interest in the lung.

[0081] S300, acquiring a target radioactivity distribution curve based on the target region of interest and the target image set.

[0082] The step of acquiring a target radioactivity distribution curve based on the target region of interest and the target image set includes:

[0083] Acquire a set of radioactivity counts in a region of interest at each level corresponding to the target image set;

[0084] The target radioactivity distribution curve is plotted based on the radioactivity count set.

[0085] After acquiring the stratified region of interest, based on the CT lung mask behind the stratified region of interest, in the target image set, the radioactivity counts in different regions are calculated based on the mask area of ​​each layer, and the calculation method is the volume of the region (unit: cm3) multiplied by the average value of the regional SUV (unit: g / ml).

[0086] Specifically, in this embodiment, the target image set includes 5 target images, each of which corresponds to the distribution of radioactive substances in the lungs of the target user at a time point. 18The composite image of F-NaF PET / CT dynamic scan. The following four target images were acquired 30 minutes apart. 18 F-NaF PET / CT dynamic scanning synthetic image. In more embodiments, it may not be 18 F-NaF PET / CT images, but other types of positron-emitting radiopharmaceutical aerosol imaging PET / CT, can also be used to calculate the lung radioactivity distribution using the method described in this embodiment. Based on the stratified regions of interest, the radioactivity count value of each region is obtained in each of the target images.

[0087] It is not difficult to see that, since there are three target coefficients in this embodiment, which are 0.5, 0.8 and 1 respectively, that is to say, the target region of interest includes three layers, which are regions of interest layered from the periphery of the lung to the main bronchus. In this embodiment, they are the peripheral lung region of interest, the middle lung region of interest and the inner lung region of interest. In more embodiments, the target region of interest can also be divided into different levels (more circles, different scaling factors), or different regions (such as by lung lobe, lung segment), and the distribution of radioactivity in the lungs under different levels of detail and different regions can be calculated.

[0088] Then, after calculating the radioactivity count value of each region in the peripheral lung region of interest, the middle lung region of interest and the inner lung region of interest, the percentage of the radioactivity count value of each region to the overall radioactivity count value is further calculated to obtain the radioactivity ratio of each part of the lung. By counting the radioactivity ratio of the lung at different time points, the radioactivity distribution change curve of the target patient in the entire cycle can be drawn, that is, the target radioactivity distribution curve, such as Figure 6 Through the above method, the radioactivity distribution curves corresponding to different patients can be obtained. In this way, the dynamic radioactivity changes of aerosolized 18F-NaF in the lungs of each patient can be observed based on the radioactivity distribution curves, providing data support for clinical practice.

[0089] In summary, the method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging provided in this embodiment obtains a first image set and a second image set, preprocesses the first image set and the second image set to obtain a target image set, wherein the first image set is a CT image set and the second image set is a PET image set, and then obtains a target region of interest based on the first image set, wherein the target region of interest is a multi-level region of interest, and finally obtains a target radioactivity distribution curve based on the target region of interest and the target image set. This embodiment is based on PET / CT images and adopts a segmentation model based on deep learning to propose a new method for automatically analyzing the distribution of radioactivity in the lungs, combining PET images and CT images to achieve accurate and automated evaluation of the distribution of radioactivity in the lungs, and provide data support for clinical practice.

[0090] It should be understood that, although the various steps in the flowcharts given in the accompanying drawings of the present specification are displayed in sequence according to the indications of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-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 sub-steps or stages of other steps.

[0091] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable 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 memory, storage, database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0092] Embodiment 2

[0093] Based on the above embodiments, the present invention also provides a device for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging. Figure 7 As shown, the device for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging includes:

[0094] An image acquisition module, the image acquisition module is used to acquire a first image set and a second image set, and preprocess the first image set and the second image set to obtain a target image set, the first image set is a CT image set, and the second image set is a PET image set, as described in the first embodiment;

[0095] A region acquisition module, the region acquisition module is used to acquire a target region of interest based on the first image set, the target region of interest is a multi-level region of interest, as specifically described in the first embodiment;

[0096] A curve drawing module, the curve drawing module is used to obtain a target radioactivity distribution curve based on the target region of interest and the target image set, as specifically described in the first embodiment.

[0097] Embodiment 3

[0098] Based on the above embodiments, the present invention also provides a terminal, such as Figure 8 As shown, the terminal includes a processor 10 and a memory 20. Figure 8 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0099] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a radioactivity distribution calculation program 30 for bilateral lungs based on PET / CT dynamic imaging is stored on the memory 20, and the radioactivity distribution calculation program 30 for bilateral lungs based on PET / CT dynamic imaging can be executed by the processor 10, thereby realizing the radioactivity distribution calculation method for bilateral lungs based on PET / CT dynamic imaging in the present application.

[0100] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other chip, used to run the program code or process data stored in the memory 20, such as executing the method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging.

[0101] In one embodiment, when the processor 10 executes the calculation program 30 for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging in the memory 20, the following steps are implemented:

[0102] Acquire a first image set and a second image set, and preprocess the first image set and the second image set to obtain a target image set, wherein the first image set is a CT image set, and the second image set is a PET image set;

[0103] Acquire a target region of interest based on the first image set, wherein the target region of interest is a multi-level region of interest;

[0104] A target radioactivity distribution curve is acquired based on the target region of interest and the target image set.

[0105] Wherein, acquiring the first image set and the second image set comprises:

[0106] After acquiring a first image and a second image at a target time, acquiring the second image at a preset time interval until five second images are acquired;

[0107] The second first image is acquired when the third second image is acquired.

[0108] The preprocessing of the first image set and the second image set to obtain a target image set includes:

[0109] resampling the second images in the second image set to a spatial size consistent with the first image set;

[0110] Align the first three second images with the first first image to obtain three target images;

[0111] The latter two second images are aligned with the second first image to obtain the two target images.

[0112] Wherein, acquiring a target region of interest based on the first image set includes:

[0113] Inputting the first image set into a target segmentation model to obtain binary masks of both lungs and trachea;

[0114] Acquiring a target coordinate position based on the binary mask of the trachea, wherein the target position includes a coordinate position of a left main bronchus and a coordinate position of a right main bronchus;

[0115] The binary masks of the two lungs are scaled based on the target coordinate position and the target coefficient to obtain the target position of interest, where the target coefficient is multiple.

[0116] The step of scaling the binarized masks of the two lungs based on the target coordinate position and the target coefficient to obtain the target position of interest includes:

[0117] Scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients to obtain a hierarchical region of interest corresponding to the left lung;

[0118] The binary mask of the right lung is scaled based on the coordinate position of the right main bronchus and the multiple target coefficients to obtain a hierarchical region of interest corresponding to the right lung.

[0119] The step of scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients includes:

[0120] Obtaining the Euclidean distance between each pixel point in the binary mask of the left lung and the coordinate position of the left main bronchus, taking the coordinate position of the left main bronchus as the center point, scaling each pixel point in the binary mask of the left lung based on the multiple target coefficients, and obtaining multiple left lung mask areas;

[0121] The multiple left lung masks are superimposed, and the original left lung mask is used to limit the superimposed mask range to obtain a layered region of interest corresponding to the left lung.

[0122] Wherein, acquiring a target radioactivity distribution curve based on the target region of interest and the target image set includes:

[0123] Acquire a set of radioactivity counts in a region of interest at each level corresponding to the target image set;

[0124] The target radioactivity distribution curve is plotted based on the radioactivity count set.

[0125] Embodiment 4

[0126] The present invention also provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging as described above.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, characterized in that: The method comprises: Acquire a first image set and a second image set, and preprocess the first image set and the second image set to obtain a target image set, wherein the first image set is a CT image set, and the first image set includes two lung CT images of a target patient, and the second image set is a PET image set, and the second image set includes five lung PET images of the target patient; Acquire a target region of interest based on the first image set, wherein the target region of interest is a multi-level region of interest; Acquire a target radioactivity distribution curve based on the target region of interest and the target image set; The acquiring a target region of interest based on the first image set comprises: Inputting the first image set into a target segmentation model to obtain binary masks of both lungs and trachea; Acquiring a target coordinate position based on the binary mask of the trachea, wherein the target coordinate position includes a coordinate position of a left main bronchus and a coordinate position of a right main bronchus; Scaling the binary mask of the two lungs based on the target coordinate position and the target coefficient to obtain the target region of interest, wherein the target coefficient is multiple; The step of scaling the binary masks of the two lungs based on the target coordinate position and the target coefficient to obtain the target region of interest includes: Scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients to obtain a hierarchical region of interest corresponding to the left lung; Scaling the binary mask of the right lung based on the coordinate position of the right main bronchus and the plurality of target coefficients to obtain a hierarchical region of interest corresponding to the right lung; The step of acquiring a target radioactivity distribution curve based on the target region of interest and the target image set includes: Acquire a set of radioactivity counts in a region of interest at each level corresponding to the target image set; The target radioactivity distribution curve is plotted based on the radioactivity count set.

2. The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging according to claim 1, characterized in that: The acquiring of the first image set and the second image set comprises: After acquiring a first image and a second image at a target time, acquiring the second image at a preset time interval until five second images are acquired; The second first image is acquired when the third second image is acquired.

3. The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging according to claim 2, characterized in that: The preprocessing of the first image set and the second image set to obtain a target image set includes: resampling the second image in the second image set to a spatial size consistent with that of the first image set; Align the first three second images with the first first image to obtain three target images; The latter two second images are aligned with the second first image to obtain the two target images.

4. The method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging according to claim 1, characterized in that: The step of scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients comprises: Obtaining the Euclidean distance between each pixel point in the binary mask of the left lung and the coordinate position of the left main bronchus, taking the coordinate position of the left main bronchus as the center point, scaling each pixel point in the binary mask of the left lung based on the multiple target coefficients, and obtaining multiple left lung mask areas; The multiple left lung mask regions are superimposed, and the original left lung mask region is used to limit the superimposed mask range to obtain a layered region of interest corresponding to the left lung.

5. A device for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging, characterized in that: include: An image acquisition module, the image acquisition module is used to acquire a first image set and a second image set, preprocess the first image set and the second image set to obtain a target image set, the first image set is a CT image set, the first image set includes two lung CT images of a target patient, the second image set is a PET image set, the second image set includes five lung PET images of the target patient; A region acquisition module, the region acquisition module is used to acquire a target region of interest based on the first image set, the target region of interest is a multi-level region of interest; A curve drawing module, the curve drawing module is used to obtain a target radioactivity distribution curve based on the target region of interest and the target image set; The acquiring a target region of interest based on the first image set comprises: Inputting the first image set into a target segmentation model to obtain binary masks of both lungs and trachea; Acquiring a target coordinate position based on the binary mask of the trachea, wherein the target coordinate position includes a coordinate position of a left main bronchus and a coordinate position of a right main bronchus; Scaling the binary mask of the two lungs based on the target coordinate position and the target coefficient to obtain the target region of interest, wherein the target coefficient is multiple; The step of scaling the binary masks of the two lungs based on the target coordinate position and the target coefficient to obtain the target region of interest includes: Scaling the binary mask of the left lung based on the coordinate position of the left main bronchus and the plurality of target coefficients to obtain a hierarchical region of interest corresponding to the left lung; Scaling the binary mask of the right lung based on the coordinate position of the right main bronchus and the plurality of target coefficients to obtain a hierarchical region of interest corresponding to the right lung; The step of acquiring a target radioactivity distribution curve based on the target region of interest and the target image set includes: Acquire a set of radioactivity counts in a region of interest at each level corresponding to the target image set; The target radioactivity distribution curve is plotted based on the radioactivity count set.

6. A terminal, characterized in that: The terminal includes: a processor, a computer-readable storage medium communicatively connected to the processor, the computer-readable storage medium being suitable for storing a plurality of instructions, and the processor being suitable for calling the instructions in the computer-readable storage medium to execute the steps of the method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging as described in any one of claims 1 to 4 above.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for calculating the radioactivity distribution in both lungs based on PET / CT dynamic imaging as described in any one of claims 1-4.

Images