Distributed virtual CBCT-based intelligent teaching method and system

Abstract

The invention discloses an intelligent teaching method and system based on distributed virtual CBCT, and the method comprises the steps: receiving a scanning request sent by a teaching user on a mobile terminal device based on a CBCT distributed middleware module, processing the scanning request, and obtaining analysis projection data; sending the CBCT distributed server cluster module to the CBCT distributed server cluster module; carrying out projection data calculation by utilizing the analyzed projection data based on a data storage module to obtain target projection data; obtaining reconstruction parameters set by a user in an offline reconstruction module in the mobile terminal equipment, and transmitting the reconstruction parameters to the CBCT intelligent image module; the CBCT intelligent image module carries out CBCT three-dimensional image reconstruction based on the reconstruction parameters and the target projection data; and transmitting the CBCT three-dimensional image to the mobile terminal device for display. According to the invention, the teaching cost can be reduced, and a teaching user can more truly enjoy the experience of real CBCT equipment operation.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a distributed virtual CBCT intelligent teaching method and system. Background Art

[0002] CBCT has become an important tool in the medical field with its advantages of high-resolution imaging, low radiation dose, fast scanning, three-dimensional imaging and efficient spatial resolution. Its wide range of application scenarios not only improves the accuracy of diagnosis, but also provides important support for precision treatment. Through the application of CBCT, medical professionals can better understand and handle complex clinical situations, thereby improving treatment outcomes and patient satisfaction. CBCT-related imaging technologies are increasingly in demand in the teaching and training of biomedical engineering and medical imaging. Compared with simple theoretical formula explanations, experimental teaching allows students to better understand and master CBCT's imaging process, imaging principles, related correction algorithms, imaging quality control and other knowledge. This is of great significance to improving the teaching effect of related majors and cultivating professional and technical personnel in biomedical engineering and medical imaging.

[0003] However, the CBCT equipment used in actual clinical or industrial settings is often expensive. Even if the equipment itself is shielded, there is still a risk of radiation. Moreover, these CBCT devices have high requirements for protection and use environment, and usually require venues and teaching staff with certain qualifications to conduct teaching demonstrations. It is difficult for general universities or research institutes to invest more funds to purchase and use these devices. Even if more funds are spent on purchasing equipment, they often face the dilemma of limited resources due to the small number of equipment and the large number of students, making it difficult to carry out efficient and high-quality teaching and research tasks.

[0004] Existing CBCT simulation technologies are often some open source programming toolkits, which can be used to simulate projection and CBCT image reconstruction of some specific digital phantoms. However, such open source toolkits are usually programs without intuitive display windows such as operation interfaces, and the internal CBCT scanning simulation is quite different from the real one, especially in real CBCT equipment, due to detector calibration, hardening artifacts such as rays passing through metal, scattering artifacts, and ring artifacts that cannot be simulated. Using such open source toolkits can only learn to simulate ideal CBCT imaging application scenarios, but this is far from the actual situation. Moreover, such open source packages usually lack systematic imaging image chain processing procedures, which is lacking for teaching staff or beginners. At present, there is still a lack of a method and system for CBCT intelligent teaching, which is separated from real hardware but can provide the same experience as real equipment. Including the operation process, imaging process, and reconstruction process are the same as real equipment. The development of CBCT intelligent teaching system is of great value for teaching staff and learners to understand and study CBCT technology. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a distributed virtual CBCT intelligent teaching method and system, which can reduce teaching costs and enable teaching users to enjoy the experience of operating real CBCT equipment more realistically.

[0006] In order to solve the above technical problems, the present invention provides a distributed virtual CBCT intelligent teaching method, the method comprising:

[0007] Based on the CBCT distributed middleware module, a scanning task request sent by a teaching user on a mobile terminal device is received, and the scanning task request is processed to obtain analytical projection data;

[0008] Sending the analyzed projection data to a CBCT distributed server cluster module;

[0009] Based on the data storage module in the CBCT distributed server cluster module, the projection data is calculated using the analytical projection data to obtain target projection data;

[0010] Acquire the reconstruction parameters set by the user in the offline reconstruction module in the mobile terminal device, and transmit the reconstruction parameters to the CBCT intelligent imaging module based on the CBCT distributed middleware module;

[0011] The CBCT intelligent imaging module performs CBCT three-dimensional image reconstruction based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image;

[0012] The CBCT three-dimensional image is transmitted to the mobile terminal device for display.

[0013] Optionally, after obtaining the target projection data, the method further comprises:

[0014] After obtaining the target projection data, the mobile terminal device displays the target projection data.

[0015] Optionally, the CBCT distributed middleware module is used to coordinate the collaborative work between the mobile terminal device and the CBCT distributed server cluster module.

[0016] Optionally, processing the scanning task request to obtain analytical projection data includes:

[0017] The scanning task request is translated and packaged to obtain parsed projection data.

[0018] Optionally, sending the parsed projection data to a CBCT distributed server cluster module includes:

[0019] The CBCT distributed middleware module determines allocation resources based on a load balancing algorithm;

[0020] The parsed projection data request is sent to a CBCT distributed server cluster module based on the allocated resources in combination with a preset distributed communication protocol and a message queue.

[0021] Optionally, the data storage module in the CBCT distributed server cluster module uses the analyzed projection data to perform projection data calculation to obtain target projection data, including:

[0022] The data storage module performs correction processing based on the stored real CBCT projection data combined with the analytical projection data to obtain the corrected analytical projection data, wherein the correction processing includes detector size conversion calculation processing, dark field correction processing, gain correction processing and bad pixel correction processing;

[0023] Target projection data is generated based on the corrected analytical projection data, wherein the target projection data includes sparse angle, limited angle and dual energy data.

[0024] Optionally, the detector size conversion calculation process is expressed as:

[0025]

[0026] Among them, P 2_2 (k, i, j) is the analytical projection data after the detector size conversion, k, i, j are the translation amounts in the three directions of the projection data, N is the number of projection data angles, U is the number of detectors in the horizontal direction, V is the number of detectors in the vertical direction, P 1_1 () is the analytical projection data before detector size conversion;

[0027] The dark field correction process is expressed as:

[0028]

[0029] Among them, P offset is the analytical projection data after dark field correction, N is the number of projection data angles, P unoffset is the analytical projection data without dark field correction, offset_template is the dark field correction template, : is the dimension;

[0030] The expression of the gain correction process is:

[0031]

[0032] Among them, P gainis the analytical projection data after gain correction, P ungain is the analytical projection data without gain correction processing, gain_template is the gain correction template, and : is the dimension;

[0033] The bad pixel correction process is expressed as:

[0034]

[0035] Among them, P defect is the analytical projection data after bad pixel correction, P undefect is the analyzed projection data without bad pixel correction processing, defect_template is the bad pixel correction template, and : is the dimension.

[0036] Optionally, the expression of the sparse angle is:

[0037]

[0038] Among them, P sparse is the sparse angle, : is the dimension, N is the number of projection data angles, M is the sparse multiple, P full For full-angle projection;

[0039] Optionally, the expression of the finite angle is:

[0040]

[0041] Among them, P limit is the finite angle, : is the dimension, q is the number of angles corresponding to the finite angle scan,, P full For full-angle projection;

[0042] The expression of the dual energy data is:

[0043]

[0044] Among them, P dual is dual-energy data, : is the dimension, N is the number of projection data angles, P high , P low These are two sets of projection data under different scanning voltages and with the same remaining parameters.

[0045] Optionally, the CBCT intelligent imaging module performs CBCT three-dimensional image reconstruction based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image, including:

[0046] The CBCT intelligent reconstruction module in the CBCT intelligent imaging module determines a reconstruction algorithm, a reconstruction filter kernel and a reconstruction artifact correction algorithm based on the reconstruction parameters;

[0047] Based on the reconstruction algorithm, the reconstruction filter kernel and the reconstruction artifact correction algorithm, the CBCT three-dimensional image reconstruction is performed in combination with the target projection data to obtain a CBCT three-dimensional image.

[0048] In addition, the present invention also provides a distributed virtual CBCT intelligent teaching system, which includes a CBCT distributed middleware module, a mobile terminal device, a CBCT distributed server cluster module and a CBCT intelligent imaging module. The CBCT distributed middleware module is connected to the mobile terminal device, the CBCT distributed server cluster module and the CBCT intelligent imaging module respectively. The system is configured to execute the above-mentioned distributed virtual CBCT intelligent teaching method.

[0049] In an embodiment of the present invention, a scanning request sent by a teaching user on a mobile terminal device is received based on a CBCT distributed middleware module to obtain parsed projection data, and a data storage module in a CBCT distributed server cluster module uses the parsed projection data to calculate projection data to obtain target projection data; the reconstruction parameters set by the user in an offline reconstruction module in the mobile terminal device are obtained, and the CBCT intelligent imaging module reconstructs a CBCT three-dimensional image based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image; the CBCT three-dimensional image is transmitted to the mobile terminal device for display, which is suitable for the teaching delay of the CBCT working principle and process, can reduce the teaching cost, and enable the teaching user to more realistically enjoy the experience of operating a real CBCT device. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a flow chart of a distributed virtual CBCT intelligent teaching method in an embodiment of the present invention;

[0052] Figure 2 Schematic diagram of the structure of the distributed virtual CBCT intelligent teaching system in the embodiment of the present invention

[0053] Figure 3 is a schematic diagram of the structure of a mobile terminal device in an embodiment of the present invention;

[0054] Figure 4It is a schematic diagram of the structure of the CBCT distributed server cluster module in an embodiment of the present invention;

[0055] Figure 5 It is a schematic diagram of the structural composition of the CBCT intelligent imaging module in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Embodiment 1

[0058] See also Figure 1 , Figure 1 : is a flow chart of a distributed virtual CBCT intelligent teaching method in an embodiment of the present invention, the method comprising:

[0059] S11: receiving a scanning task request sent by a teaching user on a mobile terminal device based on the CBCT distributed middleware module, and processing the scanning task request to obtain analytical projection data;

[0060] In the specific implementation process of the present invention, the CBCT distributed middleware module is used to coordinate the collaborative work between the mobile terminal device and the CBCT distributed server cluster module.

[0061] Furthermore, the processing of the scanning task request to obtain parsed projection data includes: translating and packaging the scanning task request to obtain parsed projection data.

[0062] Specifically, based on the CBCT distributed middleware module receiving the scanning task request sent by the teaching user on the mobile terminal device, the cone beam computed tomography (CBCT) distributed middleware module is used to manage and coordinate the data transmission and task allocation between the server cluster and the user terminal device to ensure the efficient operation and load balancing of the system. The CBCT distributed middleware module is a key component connecting the CBCT distributed server cluster and the user terminal device. Its main function is to ensure that each system module can work together efficiently and reliably in a distributed environment. It ensures the efficient operation and load balancing of the system by managing the communication, data flow and task allocation within the system. At the same time, the CBCT distributed middleware module can make the system still maintain high efficiency and stability when a large number of users access it concurrently. Its design enables the system to maintain high performance and low latency user experience when the complexity of the calculation and data transmission tasks increases. Therefore, the CBCT distributed middleware module is used to coordinate the collaborative work between the mobile terminal device and the CBCT distributed server cluster module. The scanning protocol in the scanning task request is translated and packaged by the CBCT distributed middleware module to obtain parsed projection data.

[0063] S12: sending the analyzed projection data to the CBCT distributed server cluster module;

[0064] In the specific implementation process of the present invention, the sending of the parsed projection data to the CBCT distributed server cluster module includes: the CBCT distributed middleware module determines the allocation resources based on the load balancing algorithm; based on the allocated resources combined with the preset distributed communication protocol and message queue, the parsed projection data request is sent to the CBCT distributed server cluster module.

[0065] Specifically, the CBCT distributed middleware module determines the allocation of resources based on the load balancing algorithm, such as polling, least connections, weighted polling, etc. to dynamically allocate system resources to ensure that the computing tasks are evenly distributed in the server cluster. Based on the allocated resources combined with the preset distributed communication protocol and message queue, the parsed projection data request is sent to the CBCT distributed server cluster module. Distributed communication protocols such as gRPC and HTTP are used to achieve low-latency and high-throughput data transmission between modules, and asynchronous task processing and load balancing are achieved through message queues to ensure reliable execution of tasks and high availability of the system. At the same time, the CBCT distributed middleware module also has monitoring and logging functions, which monitors the operating status of the system in real time and records the operation logs of each module to facilitate fault diagnosis and system optimization.

[0066] S13: performing projection data calculation using the analytical projection data based on the data storage module in the CBCT distributed server cluster module to obtain target projection data;

[0067] In the specific implementation process of the present invention, the data storage module in the CBCT distributed server cluster module uses the analytical projection data to perform projection data calculation to obtain target projection data, including: the data storage module performs correction processing based on the stored real CBCT projection data combined with the analytical projection data to obtain the analytical projection data after correction processing, wherein the correction processing includes detector size conversion calculation processing, dark field correction processing, gain correction processing and bad pixel correction processing; based on the analytical projection data after correction processing, target projection data is generated, and the target projection data includes sparse angle, limited angle and dual-energy data.

[0068] Furthermore, the expression for the detector size conversion calculation process is:

[0069]

[0070] Among them, P 2_2 (k,i,j) is the analytical projection data after the detector size conversion, k, i, j are the translation amounts in the three directions of the projection data, N is the number of projection data angles, U is the number of detectors in the horizontal direction, V is the number of detectors in the vertical direction, P 1_1 () is the analytical projection data before detector size conversion;

[0071] The dark field correction process is expressed as:

[0072]

[0073] Among them, P offset is the analytical projection data after dark field correction, N is the number of projection data angles, P unoffset is the analytical projection data without dark field correction, offset_template is the dark field correction template, and : is the dimension;

[0074] The expression of the gain correction process is:

[0075]

[0076] Among them, P gain is the analytical projection data after gain correction, P ungain is the analytical projection data without gain correction processing, gain_template is the gain correction template, and : is the dimension;

[0077] The bad pixel correction process is expressed as:

[0078]

[0079] Among them, P defect is the analytical projection data after bad pixel correction, P undefect is the analyzed projection data without bad pixel correction processing, defect_template is the bad pixel correction template, and : is the dimension.

[0080] Furthermore, the expression of the sparse angle is:

[0081]

[0082] Among them, P sparse is the sparse angle, : is the dimension, N is the number of projection data angles, M is the sparse multiple, P full For full-angle projection;

[0083] Furthermore, the expression of the finite angle is:

[0084]

[0085] Among them, P limit is the finite angle, : is the dimension, q is the number of angles corresponding to the finite angle scan,, P full For full-angle projection;

[0086] The expression of the dual energy data is:

[0087]

[0088] Among them, P dual is dual-energy data, : is the dimension, N is the number of projection data angles, P high , P low These are two sets of projection data under different scanning voltages and with the same remaining parameters.

[0089] Further, after the target projection data is obtained, the method further includes: after the target projection data is obtained, the mobile terminal device displays the target projection data.

[0090] Specifically, the CBCT distributed server cluster module includes a computing module and a data storage module. The computing module is used to process computing requests of mobile terminal devices, such as reconstruction, reconstruction correction algorithm and other calculations. The data storage module stores some pre-prepared CBCT projection data in a real scanning environment and corresponding scanning device camera video data. The data storage module includes a projection generation module, which is used to generate projection data. The CBCT projection data in a real scanning environment stored in the data storage module is a full angle of the circle. The projection data corresponds to a detector working mode of 1x1. The voltage, current and height of the projection data are fixed. The projection data has not been corrected for dark field, gain and bad image. The data storage module performs correction processing based on the stored real CBCT projection data combined with the analytical projection data to obtain the corrected analytical projection data, wherein the correction processing includes detector size conversion calculation processing, dark field correction processing, gain correction processing and bad pixel correction processing; based on the corrected analytical projection data, target projection data is generated, and the target projection data includes sparse angle, limited angle and dual energy data.

[0091] Assuming that the full-angle uncorrected projection data with voltage akVp, current bmAs and height h stored in the data storage module is P, and its size is NUV, the expression for the detector size conversion calculation process is:

[0092]

[0093] Among them, P 2_2 (k,i,j) is the analytical projection data after the detector size conversion, k, i, j are the translation amounts in the three directions of the projection data, N is the number of projection data angles, U is the number of detectors in the horizontal direction, V is the number of detectors in the vertical direction, P 1_1 () is the analytical projection data before detector size conversion;

[0094] The dark field correction process is expressed as:

[0095]

[0096] Among them, P offset is the analytical projection data after dark field correction, N is the number of projection data angles, P unoffset is the analytical projection data without dark field correction, offset_template is the dark field correction template, and : is the dimension;

[0097] The expression of the gain correction process is:

[0098]

[0099] Among them, P gainis the analytical projection data after gain correction, P ungain is the analytical projection data without gain correction processing, gain_template is the gain correction template, and : is the dimension;

[0100] The bad pixel correction process is expressed as:

[0101]

[0102] Among them, P defect is the analytical projection data after bad pixel correction, P undefect is the analyzed projection data without bad pixel correction processing, defect_template is the bad pixel correction template, and : is the dimension.

[0103] The expression of the sparse angle is:

[0104]

[0105] Among them, P sparse is the sparse angle, : is the dimension, N is the number of projection data angles, M is the sparse multiple, P full For full-angle projection;

[0106] The expression of the finite angle is:

[0107]

[0108] Among them, P limit is the finite angle, : is the dimension, q is the number of angles corresponding to the finite angle scan,, P full For full-angle projection;

[0109] The expression of the dual energy data is:

[0110]

[0111] Among them, P dual is dual-energy data, : is the dimension, N is the number of projection data angles, P high , P low These are two sets of projection data under different scanning voltages and with the same remaining parameters.

[0112] For the data storage module, what is stored in the database is the real CBCT projection data of different voltages, currents, and scanning fields of view and the corresponding scanning device camera video data prepared in advance. At the same time, after obtaining the target projection data, the mobile terminal device receives the target projection data and displays the target projection data.

[0113] S14: Acquire the reconstruction parameters set by the user in the offline reconstruction module in the mobile terminal device, and transmit the reconstruction parameters to the CBCT intelligent imaging module based on the CBCT distributed middleware module;

[0114] During the specific implementation of the present invention, the user sets reconstruction parameters in the offline reconstruction module of the mobile terminal device, and obtains the reconstruction parameters set by the user in the offline reconstruction module of the mobile terminal device. The set reconstruction parameters include reconstruction algorithm type, reconstruction filter kernel selection, reconstruction image size, correction algorithm options, voltage, current, detector correction options, scanning mode, etc.; it should be noted that the detector supports two working modes, the detector supports the selection of dark field, gain, and bad pixel correction; the scanning field of view supports three mode selections: large, medium, and small; the scanning mode supports five scanning modes: conventional, sparse angle, limited angle, dual energy, and positioning image; teaching users can arbitrarily combine the above combinations to generate scanning protocols to simulate real scanning situations. It is also based on the CBCT distributed middleware module to transmit the reconstruction parameters to the CBCT intelligent imaging module.

[0115] S15: The CBCT intelligent imaging module performs CBCT three-dimensional image reconstruction based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image;

[0116] In the specific implementation process of the present invention, the CBCT intelligent imaging module performs CBCT three-dimensional image reconstruction based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image, including: the CBCT intelligent reconstruction module in the CBCT intelligent imaging module determines a reconstruction algorithm, a reconstruction filter kernel and a reconstruction artifact correction algorithm based on the reconstruction parameters; performs CBCT three-dimensional image reconstruction based on the reconstruction algorithm, the reconstruction filter kernel and the reconstruction artifact correction algorithm in combination with the target projection data to obtain a CBCT three-dimensional image.

[0117] Specifically, the CBCT intelligent reconstruction module in the CBCT intelligent imaging module determines the reconstruction algorithm, reconstruction filter kernel and reconstruction artifact correction algorithm based on the reconstruction parameters. The reconstruction algorithm includes analytical reconstruction and iterative reconstruction. The reconstruction filter kernels include RAMLAK, SHEEP, CONSIN, HAMMING and HANNA. The reconstruction dimensions include 512x512 and 1024x1024 modes. It supports setting the reconstruction layer thickness, reconstruction iteration number and iteration hyperparameters. The reconstruction artifact correction algorithm supports six reconstruction correction algorithms including limited angle artifact correction, beam hardening water correction, beam hardening bone correction, metal artifact correction, ring artifact correction and truncation artifact correction. The CBCT intelligent imaging module determines the algorithm selected by the user, and performs CBCT three-dimensional image reconstruction based on the reconstruction algorithm, reconstruction filter kernel and reconstruction artifact correction algorithm in combination with the target projection data to obtain a CBCT three-dimensional image. It should be noted that the CBCT intelligent reconstruction module in the CBCT intelligent imaging module is located in the server cluster. It is responsible for converting the collected CBCT projection data into a three-dimensional image through various reconstruction algorithms. The computational tasks processed by this module are relatively complex and require high-performance computing resources. It is responsible for the actual reconstruction calculation and is the core module for processing data and generating images. It uses the computing resources of the server cluster to perform high-density reconstruction tasks and returns the reconstructed image to the user's terminal device after completion.

[0118] S16: Transmitting the CBCT three-dimensional image to the mobile terminal device for display.

[0119] In a specific implementation of the present invention, the CBCT three-dimensional image is transmitted to the mobile terminal device for display, and a user can view the reconstructed CBCT three-dimensional image in the mobile terminal device.

[0120] In an embodiment of the present invention, a scanning request sent by a teaching user on a mobile terminal device is received based on a CBCT distributed middleware module to obtain parsed projection data, and a data storage module in a CBCT distributed server cluster module uses the parsed projection data to calculate projection data to obtain target projection data; the reconstruction parameters set by the user in an offline reconstruction module in the mobile terminal device are obtained, and the CBCT intelligent imaging module reconstructs a CBCT three-dimensional image based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image; the CBCT three-dimensional image is transmitted to the mobile terminal device for display, which is suitable for the teaching delay of the CBCT working principle and process, can reduce the teaching cost, and enable the teaching user to more realistically enjoy the experience of operating a real CBCT device.

[0121] Embodiment 2

[0122] See also Figure 2 , Figure 2Schematic diagram of the structure of a distributed virtual CBCT intelligent teaching system in an embodiment of the present invention. The system includes: a CBCT distributed middleware module 21, a mobile terminal device 22, a CBCT distributed server cluster module 23 and a CBCT intelligent imaging module 24.

[0123] In the specific implementation of the present invention, the CBCT distributed middleware module 21 is used to coordinate and manage the software layers of various components and nodes in the system. It plays a key bridge role in the distributed virtual CBCT system, allowing different parts of the system to communicate and collaborate efficiently and reliably. It includes functions such as communication management, load balancing, data management, security management, and monitoring management.

[0124] The mobile terminal device 22 refers to a display device such as a computer, tablet or web page. It is equipped with interface buttons and has display interaction functions. It is connected to the computing cluster through the network, receives data from the cloud, and sends request tasks to the cloud for processing. Figure 3As shown in the figure, the mobile terminal device contains a mobile terminal interaction module, a database display interface, an offline reconstruction interface module, and an acquisition interface module. The acquisition interface module includes a scanning acquisition interface and a scanning projection preview. The mobile terminal interaction module refers to a program running on a local PC, tablet or other display device, which has a registration login interface, a database display interface, a scanning acquisition interface, and an offline reconstruction interface. In the registration login interface, users can register an account by email or mobile phone number. After successful registration, the user account and password are stored in the distributed user database for maintenance. The user enters the account and password in the login interface, and can log in to the database display interface of the mobile terminal after successful cloud verification. The database display interface displays the information of the CBCT experiment conducted by the previous user. The user can browse the experiments he has done before on this page, and browse the corresponding projection data and reconstruction result images. Select any experimental database entry to perform offline reconstruction. The offline reconstruction interface module pops up, and the user sets the reconstruction algorithm, such as analytical reconstruction or iterative reconstruction, reconstruction filter kernel, reconstruction image size, reconstruction layer thickness, iterative hyperparameters, correction processing options, etc. After the user sets the reconstruction parameters, click Start Reconstruction. The mobile device terminal transmits the current reconstruction parameters to the distributed service cluster through the network, and the distributed cluster processes the reconstruction request. The corresponding projection data is read from the data storage server and given to the CBCT reconstruction service on the computing cluster for reconstruction and correction. The reconstructed data is stored in the data storage server and transmitted to the mobile terminal device through the network for offline reconstruction interface display. The scanning acquisition interface is divided into two parts. The first part is the scanning projection preview and scanning camera data playback, and the second part is the scanning parameter option part. The scanning projection preview is used to play and display the projection data simulating the real scan, and the scanning camera data playback area is used to play and display the internal situation of the device corresponding to the projection data to achieve the purpose of real scanning simulation. Scan parameter options, support setting options: X-ray voltage, current, scanning height, detector Binning mode (1x1, 2x2), detector correction options, scanning field of view (large, medium, small), scanning mode (conventional scanning, dual energy, sparse angle, limited angle scanning). After the user sets the scanning parameters, clicks Confirm Scan, and the terminal sends this set of scanning parameters to the distributed cluster. The cluster processes the task and retrieves the corresponding projection data and camera data from the database and transmits them to the scanning acquisition interface for playback and display.

[0125] like Figure 4As shown, the CBCT distributed server cluster module 23 includes a computing module and a data storage module, which includes computing nodes, networks and storage devices. The computing nodes are equipped with computing resources such as CPU and GPU, which are used to provide computing resources for CBCT reconstruction and correction in the CBCT intelligent image processing module. The data stored in the storage device has two major parts. The first part is the projection data, which includes various combinations of different scanning voltages, currents, scanning heights, scanning fields of view, and scanning modes; the projection data is collected in advance on a real physical device, and the video data collected by the device will be recorded at the same time. The other part is the reconstructed image data obtained by processing the reconstruction after the mobile terminal device sends a reconstruction request. The computing nodes and storage devices are connected through a high-bandwidth, low-latency network to ensure fast data transmission and communication.

[0126] like Figure 5 As shown, the CBCT intelligent imaging module 24 includes a CBCT intelligent reconstruction module and a CBCT correction algorithm module. The CBCT reconstruction module refers to a program for reconstructing CBCT projection data, which receives projection data and reconstruction parameters as input and outputs a reconstructed image. Correspondingly, the CBCT correction algorithm module works together to complete the CBCT reconstruction and correction tasks. The CBCT correction algorithm module supports correction algorithms such as limited angle artifacts, beam hardening artifacts, beam hardening bones, metal artifacts, ring artifacts, and truncation artifacts.

[0127] The method of using the distributed virtual CBCT intelligent teaching system is described in detail as follows:

[0128] Step 1: Open the mobile terminal device, enter the account and password to log in, and enter the database interface after logging in;

[0129] Step 2: Browse and view previous experimental records, experimental projection data, and reconstruct result images in the database interface of the mobile terminal device;

[0130] Step 3: Click the Scan Interface button to enter the CBCT Scan Interface. In this interface, set the X-ray voltage, current, and scan height. Detector working mode, calibration options, scan field of view, and scan mode. Or select the corresponding experiment in the experiment drop-down list to generate scan information. Click Confirm Scan.

[0131] Step 4: After clicking Confirm Scan, the projection display area of ​​the acquisition interface will start playing the projection data and camera video signals acquired under the current parameters;

[0132] Step 5: Set the reconstruction parameters, such as analytical reconstruction, filter kernel selection, reconstruction size, etc. After the reconstruction parameters are set, click Start Reconstruction and the cloud server will execute the reconstruction task.

[0133] Step 6: After the reconstruction is completed, the user browses the reconstruction result image on the mobile terminal device.

[0134] In the specific implementation process of the present invention, the specific implementation methods of the system items can be referred to the above embodiments, which will not be repeated here.

[0135] In an embodiment of the present invention, a scanning request sent by a teaching user on a mobile terminal device is received based on a CBCT distributed middleware module to obtain parsed projection data, and a data storage module in a CBCT distributed server cluster module uses the parsed projection data to calculate projection data to obtain target projection data; the reconstruction parameters set by the user in an offline reconstruction module in the mobile terminal device are obtained, and the CBCT intelligent imaging module reconstructs a CBCT three-dimensional image based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image; the CBCT three-dimensional image is transmitted to the mobile terminal device for display, which is suitable for the teaching delay of the CBCT working principle and process, can reduce the teaching cost, and enable the teaching user to more realistically enjoy the experience of operating a real CBCT device.

[0136] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0137] In addition, the above is a detailed introduction to a distributed virtual CBCT intelligent teaching method and system provided by an embodiment of the present invention. In this article, specific examples are used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A distributed virtual CBCT intelligent teaching method, characterized in that: The method comprises: Based on the CBCT distributed middleware module, a scanning task request sent by a teaching user on a mobile terminal device is received, and the scanning task request is processed to obtain analytical projection data; Sending the analyzed projection data to a CBCT distributed server cluster module; Based on the data storage module in the CBCT distributed server cluster module, the projection data is calculated using the analytical projection data to obtain target projection data; Acquire the reconstruction parameters set by the user in the offline reconstruction module in the mobile terminal device, and transmit the reconstruction parameters to the CBCT intelligent imaging module based on the CBCT distributed middleware module; The CBCT intelligent imaging module performs CBCT three-dimensional image reconstruction based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image; The CBCT three-dimensional image is transmitted to the mobile terminal device for display.

2. The distributed virtual CBCT intelligent teaching method according to claim 1 is characterized in that: After obtaining the target projection data, the method includes: After obtaining the target projection data, the mobile terminal device displays the target projection data.

3. The distributed virtual CBCT intelligent teaching method according to claim 1 is characterized in that: The CBCT distributed middleware module is used to coordinate the collaborative work between the mobile terminal device and the CBCT distributed server cluster module.

4. The distributed virtual CBCT intelligent teaching method according to claim 1 is characterized in that: The step of processing the scanning task request to obtain analytical projection data includes: The scanning task request is translated and packaged to obtain parsed projection data.

5. The distributed virtual CBCT intelligent teaching method according to claim 1 is characterized in that: The step of sending the analyzed projection data to the CBCT distributed server cluster module includes: The CBCT distributed middleware module determines allocation resources based on a load balancing algorithm; The parsed projection data request is sent to a CBCT distributed server cluster module based on the allocated resources in combination with a preset distributed communication protocol and a message queue.

6. The distributed virtual CBCT intelligent teaching method according to claim 1 is characterized in that: The data storage module in the CBCT distributed server cluster module uses the analyzed projection data to perform projection data calculation to obtain target projection data, including: The data storage module performs correction processing based on the stored real CBCT projection data combined with the analytical projection data to obtain the corrected analytical projection data, wherein the correction processing includes detector size conversion calculation processing, dark field correction processing, gain correction processing and bad pixel correction processing; Target projection data is generated based on the corrected analytical projection data, wherein the target projection data includes sparse angle, limited angle and dual energy data.

7. The distributed virtual CBCT intelligent teaching method according to claim 6 is characterized in that: The expression for the detector size conversion calculation process is: Among them, P 2_2 (k,i,j) is the analytical projection data after the detector size conversion, k, i, j are the translation amounts in the three directions of the projection data, N is the number of projection data angles, U is the number of detectors in the horizontal direction, V is the number of detectors in the vertical direction, P 1_1 () is the analytical projection data before detector size conversion; The dark field correction process is expressed as: Among them, P offset is the analytical projection data after dark field correction, N is the number of projection data angles, P unoffset is the analytical projection data without dark field correction, offset_template is the dark field correction template, and : is the dimension; The expression of the gain correction process is: Among them, P gain is the analytical projection data after gain correction, P ungain is the analytical projection data without gain correction processing, gain_template is the gain correction template, and : is the dimension; The bad pixel correction process is expressed as: Among them, P defect is the analytical projection data after bad pixel correction, P undefect is the analyzed projection data without bad pixel correction processing, defect_template is the bad pixel correction template, and : is the dimension.

8. The distributed virtual CBCT intelligent teaching method according to claim 6 is characterized in that: The expression of the sparse angle is: Among them, P sparse is the sparse angle, : is the dimension, N is the number of projection data angles, M is the sparse multiple, P full For full-angle projection; The expression of the finite angle is: Among them, P limit is the finite angle, : is the dimension, q is the number of angles corresponding to the finite angle scan,, P full For full-angle projection; The expression of the dual energy data is: Among them, P dual is dual-energy data, : is the dimension, N is the number of projection data angles, P high , P low These are two sets of projection data under different scanning voltages and with the same remaining parameters.

9. The distributed virtual CBCT intelligent teaching method according to claim 1 is characterized in that: The CBCT intelligent imaging module performs CBCT three-dimensional image reconstruction based on the reconstruction parameters and the target projection data to obtain a CBCT three-dimensional image, including: The CBCT intelligent reconstruction module in the CBCT intelligent imaging module determines a reconstruction algorithm, a reconstruction filter kernel and a reconstruction artifact correction algorithm based on the reconstruction parameters; Based on the reconstruction algorithm, the reconstruction filter kernel and the reconstruction artifact correction algorithm, the CBCT three-dimensional image reconstruction is performed in combination with the target projection data to obtain a CBCT three-dimensional image.

10. A distributed virtual CBCT intelligent teaching system, characterized in that: The system includes a CBCT distributed middleware module, a mobile terminal device, a CBCT distributed server cluster module and a CBCT intelligent imaging module. The CBCT distributed middleware module is connected to the mobile terminal device, the CBCT distributed server cluster module and the CBCT intelligent imaging module respectively. The system is configured to execute the distributed virtual CBCT intelligent teaching method described in any one of claims 1 to 9.

Images