Method for acquiring scanning parameters, electronic equipment and CT (Computed Tomography) machine

Abstract

The invention provides a method for acquiring scanning parameters, electronic equipment and a CT (Computed Tomography) machine. The method for acquiring the scanning parameters is used for CT scanning and comprises the following steps: acquiring information data of a patient to be scanned; inputting the information data into a pre-trained convolutional neural network model to obtain scanning parameters; the step of pre-training the convolutional neural network model comprises obtaining information of a sample and a standard plain film scanning image; generating a label image after the radiation dose is reduced; generating scanning parameters of the sample; and constructing a pre-training convolutional neural network model based on the information of the sample, the standard plain film scanning image, the label image and the scanning parameters. The position capable of reducing radiation and the dose capable of reducing radiation can be obtained by using the convolutional neural network model, and the radiation dose is dynamically adjusted in one-time plain film scanning, so that the integrity and the positioning function of the plain film image are not influenced while the radiation dose accepted by the patient is reduced; therefore, the scanning process is optimized in an intelligent mode.

Description

Technical Field

[0001] The present disclosure relates to the technical field of medical devices, and more particularly, to a method for obtaining scanning parameters, an electronic device, and a CT scanner. Background Art

[0002] With the annual improvement of medical conditions in China, as well as the progress and popularization of medical technologies, more and more hospitals have a need for new high-end medical devices, such as CT (Computed Tomography) scanners. In recent years, the widespread use of CT has brought great benefits to the clinical diagnosis of diseases.

[0003] Plain film scanning is a medical imaging technique. During CT scanning, its main purpose is localization, that is, to determine the exact position of specific structures in the body (such as fracture sites, implant positions, organ positions, etc.) in three-dimensional space. This information is crucial for subsequent CT scans because it helps doctors accurately locate the scanning range to a specific area of interest.

[0004] Currently, CT devices in related technologies usually rely on the experience of technicians to adjust parameters to achieve an appropriate balance between image quality and radiation dose. In such methods, the scanning parameters remain unchanged throughout the scanning process, and patients are exposed to some unnecessary radiation dose. Summary of the Invention

[0005] The purpose of the present disclosure is to provide a method for obtaining scanning parameters, an electronic device, and a CT scanner, which can solve at least one of the above-mentioned technical problems. The specific solutions are as follows:

[0006] According to a specific embodiment of the present disclosure, on the one hand, the present disclosure provides a method for obtaining scanning parameters. The method for obtaining scanning parameters is used for plain film scanning of a CT, and the method for obtaining scanning parameters includes: obtaining information data of a patient to be scanned, where the information data includes: body type data and scanning position of the patient to be scanned; inputting the information data into a pre-trained convolutional neural network model to obtain scanning parameters; where the pre-trained convolutional neural network model includes: obtaining information of a sample and a standard plain film scanning image; the information of the sample includes: body type data of the sample, scanning position of the sample, and corresponding rated scanning parameters; generating a label image with reduced radiation dose based on the standard plain film scanning image; generating scanning parameters of the sample based on the label image; and constructing a pre-trained convolutional neural network model based on the information of the sample, the standard plain film scanning image, the label image, and the scanning parameters.

[0007] In an optional embodiment, the pre-trained convolutional neural network model further includes: performing plain film scanning on a plurality of different samples to obtain multiple sets of the label images and the scanning parameters.

[0008] In an alternative embodiment, the generating the labeled image with reduced radiation dose based on the standard plain film scan image includes: determining the boundary of the scanning position in each image of the standard plain film scan images; zeroing out the image data outside the first pixel range from the boundary to obtain the labeled image; wherein the image outside the first pixel range from the boundary is recognized as the area with reduced radiation dose during scanning.

[0009] In an alternative embodiment, the determining the boundary of the scanning position includes: determining the boundary of the scanning position based on the edge, shape, texture information, and scanning position of the standard plain film scan image.

[0010] In an alternative embodiment, the input of the pre-trained convolutional neural network model includes: the information of the sample, the standard plain film scan image; the output of the pre-trained convolutional neural network model includes: the labeled image and the scanning parameters.

[0011] In an alternative embodiment, the pre-trained convolutional neural network model further includes: importing historical plain film scan data into the pre-trained convolutional neural network model to train the convolutional neural network model to output multiple sets of scanning parameter values; wherein the historical plain film scan data includes: the information of the sample, the standard plain film scan image, the labeled image generated based on the standard plain film scan image, and the scanning parameters.

[0012] According to a specific embodiment of the present disclosure, on the other hand, the present disclosure provides an acquisition unit for scanning parameters, which is used for CT scanning, and the acquisition unit for scanning parameters is configured to acquire scanning parameters by executing the method described in any one of the above technical solutions.

[0013] According to a specific embodiment of the present disclosure, on the other hand, the present disclosure provides a CT machine, which includes: the acquisition unit for scanning parameters described in the above technical solution.

[0014] According to a specific embodiment of the present disclosure, on the other hand, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any one of the above technical solutions is implemented.

[0015] According to a specific embodiment of the present disclosure, on the other hand, the present disclosure provides an electronic device, which includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any one of the above technical solutions.

[0016] The above solution of the embodiments of the present disclosure has at least the following beneficial effects compared with the prior art:

[0017] By using a convolutional neural network model, the present disclosure can obtain the positions where radiation can be reduced and the doses of radiation that can be reduced, dynamically adjust the radiation dose during a single plain film scan, and without affecting the integrity and positioning function of the plain film image while reducing the radiation dose received by the patient, thereby realizing the optimization of the scanning process in an intelligent manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The flowchart shows a method for obtaining scanning parameters according to an embodiment of the present disclosure.

[0019] Figure 2 The flowchart shows a method for pre-training a convolutional neural network model according to an embodiment of the present disclosure.

[0020] Figure 3 The schematic diagram shows a connection structure of an electronic device according to an embodiment of the present disclosure.

[0021] REFERENCE SIGNS

[0022] 301: Processing system; 302: ROM; 303: RAM; 304: Bus; 305: I / O interface; 306: Input system; 307: Output system; 308: Storage system; 309: Communication system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] In order to make the objectives, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below with reference to the accompanying drawings. Apparently, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the scope of protection of the present disclosure.

[0024] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "the" and "said" used in the embodiments of the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0025] It should be understood that the term " / and" used herein is only a description of the associated relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0026] It should be understood that although terms such as first, second, and third may be used to describe structures in the embodiments of the present disclosure, these structures should not be limited to these terms. These terms are only used to distinguish different structures. For example, without departing from the scope of the embodiments of the present disclosure, the first component may also be referred to as the second component, and similarly, the second component may also be referred to as the first component.

[0027] Depending on the context, the words "if" or "when" as used herein may be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0028] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the commodity or device comprising said element.

[0029] Currently, existing CT devices usually rely on the experience of technicians to adjust parameters to achieve an appropriate balance between image quality and radiation dose. In such methods, the scanning parameters remain unchanged throughout the scanning process, and the patient receives some unnecessary radiation dose. The manual adjustment in the related art is not only inefficient but also difficult to precisely control the radiation dose, which may thus affect the accuracy of image quality and pathological localization.

[0030] To solve at least one of the above-mentioned technical problems, the present disclosure provides a method for obtaining scanning parameters, an electronic device, and a CT scanner. The method for obtaining scanning parameters is used for CT scanning and may include: obtaining information data of a patient to be scanned, where the information data includes the body type data and the scanning position of the patient to be scanned; inputting the information data into a pre-trained convolutional neural network model to obtain scanning parameters; where the pre-trained convolutional neural network model includes: obtaining information of a sample and a standard plain film scan image; the information of the sample includes the body type data of the sample, the scanning position of the sample, and the corresponding rated scanning parameters; generating a labeled image with reduced radiation dose based on the standard plain film scan image; generating scanning parameters of the sample based on the labeled image; and constructing a pre-trained convolutional neural network model based on the information of the sample, the standard plain film scan image, the labeled image, and the scanning parameters. The present disclosure trains the pre-trained convolutional neural network model and realizes automatic and intelligent adjustment of scanning parameters through the pre-trained convolutional neural network model. The system mainly consists of three parts: data preparation, neural network model construction, and model application.

[0031] The optional embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0032] Figure 1 The flowchart of the method for obtaining scanning parameters according to an embodiment of the present disclosure is shown. As Figure 1 shown, according to the specific implementation manners of the present disclosure, on the one hand, a method for obtaining scanning parameters is provided, and the method for obtaining scanning parameters may at least include the following steps:

[0033] S100. Obtain information data of a patient to be scanned, where the information data includes the body type data and the scanning position of the patient to be scanned.

[0034] S200. Input the information data into a pre-trained convolutional neural network model to obtain scanning parameters.

[0035] Figure 2 The flowchart of the method for the pre-trained convolutional neural network model according to an embodiment of the present disclosure is shown. As Figure 2 shown, where the pre-trained convolutional neural network model includes:

[0036] S300. Obtain information of a sample and a standard plain film scan image; the information of the sample includes the body type data of the sample, the scanning position of the sample, and the corresponding rated scanning parameters.

[0037] S400. Generate a labeled image with reduced radiation dose based on the standard plain film scan image.

[0038] S500. Generate the scanning parameters of the sample based on the labeled image.

[0039] S600. Construct a pre-trained convolutional neural network model based on the information of the sample, the standard plain film scanning image, the labeled image, and the scanning parameters.

[0040] The present disclosure utilizes a convolutional neural network model to obtain the positions where radiation can be reduced and the radiation doses that can be reduced, dynamically adjust the radiation dose during a single plain film scan, and without affecting the integrity and positioning function of the plain film image while reducing the radiation dose received by the patient, thereby realizing the optimization of the scanning process in an intelligent manner.

[0041] Among them, in steps S100 and S200, by inputting the patient information (i.e., the body type and scanning position of the patient) into the convolutional neural network model, the radiation dose that can be reduced at the position to be scanned is output, and the scanning voltage and scanning current are calculated based on the radiation dose. It should be noted that when scanning a position, such as the chest, abdomen, or leg, etc., different scanning parameter values are formed within each image or several pixels.

[0042] Among them, in step S300, specifically, it can be to obtain the scanning data of patients with different body types under different scanning parameters, and try to cover all common body types as much as possible to improve the diversity of the images. In an optional embodiment, the patient information may include at least one of weight and body type and the scanning position, and the position where the radiation dose can be reduced is confirmed by confirming the scanning position of the patient. It should be noted that the multiple scanning parameters are the scanning parameter settings of the CT machine during CT scanning, and the multiple scanning parameters may at least include: scanning voltage and scanning current.

[0043] Among them, in steps S400 and S500, a labeled image of the radiation dose that can be reduced for each image is generated, and the radiation dose that can be reduced when clear images can be produced at different positions of different body types is determined.

[0044] Specifically, step S400 includes:

[0045] S410. Determine the boundary of the scanning position within each image in the standard plain film scanning image.

[0046] S420. Zero out the image data outside the first pixel range from the boundary to obtain the labeled image; the image outside the first pixel range from the boundary is considered as the area where the radiation dose is reduced during scanning.

[0047] Among them, in steps S410 and S420, by marking the area outside the part (organ) to be scanned and then reducing the radiation dose of this area or even not scanning it, the power consumption during scanning can be reduced, and the radiation dose received by the scanned patient can also be reduced.

[0048] Among them, in step S600, based on the information of the samples with different body types and different positions, the standard radiograph scan images, the label images, and the scan parameters, and using data to train a convolutional neural network model to improve the accuracy of model prediction. The network structure of the convolutional neural network model may include multiple convolutional layers, pooling layers, and fully connected layers to fully learn features. By inputting the patient information (i.e., the body type and scan position of the patient) into the convolutional neural network model, the radiation dose that can be reduced at the position to be scanned is output, and the scan voltage and scan current are calculated based on the radiation dose. It should be noted that when scanning a position, for example: the chest, abdomen, or leg, etc., different scan parameter values are formed within each image or several pixels.

[0049] Specifically, during scanning, according to the standard operating procedures of the CT device, an initial scan voltage and scan current value are selected; then the patient information (body type information, which may include height, weight, etc.) and the scan part are input into the model (such as the chest, abdomen, leg, etc.), and this information helps the model understand the influence of the patient's body type on the radiation dose; the model predicts the change law of the radiograph image under different scan voltage and scan current values according to the input patient information and the characteristics of the scan part; the model generates scan parameter suggestions (scan voltage and scan current values) in time sequence, and these suggestions reflect the optimal settings for maintaining image quality while reducing the radiation dose. During the scanning process, the scan voltage and scan current values are adjusted in real time according to the change law predicted by the model. Through real-time adjustment, the scan parameters are dynamically optimized to adapt to the changes in the patient's body type and the characteristics of the scan part. During the scanning process, the system obtains the patient's body type information and the characteristics of the scan part in real time, and uses the trained neural network model to predict the changes in the image under different scan voltage and scan current values.

[0050] In some embodiments, the patient information may include at least one of weight and body type and the scan position, and the position where the radiation dose can be reduced is confirmed by confirming the scan position of the patient.

[0051] In some embodiments, the pre-trained convolutional neural network model further includes: performing radiograph scans on multiple different samples to obtain multiple sets of the label images and the scan parameters.

[0052] In some embodiments, generating the labeled image with reduced radiation dose based on the standard plain film scan image includes: determining the boundary of the scan position in each image of the standard plain film scan images; zeroing out the image data outside the first pixel range from the boundary to obtain the labeled image; wherein the image outside the first pixel range from the boundary is considered as the area with reduced radiation dose during scanning.

[0053] In some embodiments, determining the boundary of the scan position includes: determining the boundary of the scan position based on the edge, shape, texture information, and scan position of the standard plain film scan image. The adjustment process takes into account the radiation dose sensitivity of the model to each image region to ensure that key regions (such as bones or vital organs) receive sufficient radiation to guarantee image integrity.

[0054] In some embodiments, the input of the pre-trained convolutional neural network model includes: the information of the sample, the standard plain film scan image; the output of the pre-trained convolutional neural network model includes: the labeled image and the scan parameters.

[0055] In some embodiments, the pre-trained convolutional neural network model further includes: importing historical plain film scan data into the pre-trained convolutional neural network model to train the convolutional neural network model to output multiple sets of scan parameter values; wherein the historical plain film scan data includes: the information of the sample, the standard plain film scan image, the labeled image generated based on the standard plain film scan image, and the scan parameters.

[0056] During CT scanning, according to the standard operating procedures of the CT device, an initial kV and mA value are selected; then the patient information (body type information, which can include height, weight, etc.) and the scan location are input into the model (such as chest, abdomen, leg, etc.), and this information helps the model understand the impact of the patient's body type on the radiation dose; the model predicts the change law of the plain film image under different kV and mA values according to the input patient information and scan location characteristics; the model generates temporal scan parameter suggestions (kV and mA values), and these suggestions reflect the optimal settings for maintaining image quality while reducing radiation dose. During the scanning process, the kV and mA values are adjusted in real time according to the change law predicted by the model. Through real-time adjustment, the scan parameters are dynamically optimized to adapt to the changes in the patient's body type and scan location characteristics.

[0057] Specifically, constructing the pre-trained convolutional neural network model based on the information of the sample, the standard plain film scan image, the labeled image, and the scan parameters includes:

[0058] 1. Network architecture: including an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer;

[0059] 1) Input layer:

[0060] a) Convert the information of the sample, i.e., height Height and weight Weight, into normalized values, and the min-max normalization method can be used;

[0061] b) Scanning part feature S: Use one-hot encoding to represent different scanning parts. For example, the parts = ['chest', 'abdomen', 'leg'], and the matrix after one-hot encoding: chest: [1, 0, 0], abdomen: [0, 1, 0], etc.

[0062] c) Initial scanning parameters (i.e., rated scanning parameters): Convert the kV and mA values into normalized values;

[0063] d) Original plain film image (i.e., standard plain film scanning image);

[0064] 2) Convolutional layer: The specific structure is a layer composed of multiple convolutional kernels. Each convolutional kernel slides on the input image and performs element-wise multiplication and summation operations to generate a feature map. Specifically, for an input image X (i.e., the standard plain film scanning image), the convolutional operation of the i-th layer can be expressed as:

[0065]

[0066] where i and j here are the spatial coordinates on the output feature map Y, m is the index of the output feature map, and k, l, and p are the channel index and spatial coordinates of the convolutional kernel respectively. Usually, a batch normalization layer (BatchNormalization) and a ReLU activation function are followed after each convolutional layer to improve training stability and network performance.

[0067] 3) Pooling layer: Use max pooling, with a pooling window size of 2x2 and a stride Stride = 2;

[0068] 4) Fully connected layer: z = Wx + b, where W is the weight matrix, X is the input feature, and b is the bias; the number of neurons is set to 1024, use the ReLU activation function, and the Dropout ratio coefficient is set to 0.5 to prevent overfitting;

[0069] 5) Output layer: Output the dynamic scanning parameters P (i.e., the scanning parameter configuration) and the predicted plain film image The predicted scanning parameters include the kV and mA values at each scanning position to achieve reduced-dose plain film scanning; the predicted plain film image is the plain film image after reduced-dose processing predicted by the network (i.e., the labeled image).

[0070] PkV = f kV (X input , W)

[0071] P mA = f mA (X input , W)

[0072]

[0073] Finally, the output of the convolutional neural network will provide optimized scanning parameters for medical image analysis, thus helping clinicians to reduce radiation dose while retaining necessary information during plain film scanning.

[0074] 2. Hyperparameter selection: The initial learning rate can be set to 0.001, the batch size BatchSize, and the number of iterations (Epochs), which can be set to 300 epochs according to the model convergence. According to the specific embodiments of the present disclosure, on the other hand, a scanning parameter acquisition unit is provided for CT scanning, configured to obtain scanning parameters by executing the method described in any one of the above embodiments.

[0075] According to the specific embodiments of the present disclosure, on the other hand, an electronic device is provided, and this device is used for the method of obtaining scanning parameters. The electronic device may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0076] the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor can: obtain information data of the patient to be scanned, and the information data includes: body type data and scanning position of the patient to be scanned; input the information data into a pre-trained convolutional neural network model to obtain scanning parameters; wherein, the pre-trained convolutional neural network model includes: obtaining information of the sample and a standard plain film scan image; the information of the sample includes: body type data of the sample, scanning position of the sample, and corresponding rated scanning parameters; generating a labeled image with reduced radiation dose based on the standard plain film scan image; generating scanning parameters of the sample based on the labeled image; constructing a pre-trained convolutional neural network model based on the information of the sample, the standard plain film scan image, the labeled image, and the scanning parameters.

[0077] According to the specific embodiments of the present disclosure, on the other hand, a non-volatile computer storage medium is provided, and the computer storage medium stores computer-executable instructions, and these computer-executable instructions can execute the method of obtaining scanning parameters in any of the above method embodiments. It should be noted that the non-volatile computer storage medium is also referred to as a computer-readable storage medium.

[0078] Reference is made below to Figure 3 , which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0079] As Figure 3 shown, the electronic device may include a processing system (such as a central processing unit, a graphics processing unit, etc.) 301, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage system 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device are also stored. The processing system 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0080] Generally, the following systems may be connected to the I / O interface 305: an input system 306 that may include, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output system 307 that may include, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage system 308 that may include, for example, a magnetic tape, a hard disk, etc.; and a communication system 309. The communication system 309 may allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3 an electronic device with various systems is shown, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0081] In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present disclosure may include a computer program product, which may include a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication system 309, or installed from the storage system 308, or installed from the ROM 302. When the computer program is executed by the processing system 301, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

[0082] It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0083] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist separately and not be assembled into the electronic device.

[0084] The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device is enabled to: By using a convolutional neural network model in the present disclosure, the positions and doses where radiation can be reduced can be obtained, and the radiation dose can be dynamically adjusted during a single plain film scan, while reducing the radiation dose received by the patient without affecting the integrity and positioning function of the plain film image, thereby realizing the optimization of the scanning process in an intelligent manner.

[0085] Alternatively, the above computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: By using the convolutional neural network model in the present disclosure, the positions where radiation can be reduced and the radiation doses that can be reduced can be obtained, and the radiation dose can be dynamically adjusted during a single plain film scan. While reducing the radiation dose received by the patient, the integrity and positioning function of the plain film image are not affected, thus realizing the optimization of the scanning process in an intelligent manner.

[0086] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages may include object-oriented programming languages such as Java, Smalltalk, C++, and may also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, which may include a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0087] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0088] According to a specific embodiment of the present disclosure, on the other hand, a CT machine is provided, which may include, for example: the computer-readable storage medium as described in any one of the above embodiments and / or the electronic device as described in any one of the above embodiments.

[0089] The present disclosure aims to protect a method for obtaining scanning parameters, an electronic device, and a CT machine. The method for obtaining scanning parameters is used for CT scanning and may include: obtaining information data of a patient to be scanned, where the information data includes the body type data and the scanning position of the patient to be scanned; inputting the information data into a pre-trained convolutional neural network model to obtain scanning parameters; where the pre-trained convolutional neural network model includes: obtaining information of a sample and a standard plain film scan image; the information of the sample includes the body type data of the sample, the scanning position of the sample, and the corresponding rated scanning parameters; generating a labeled image with reduced radiation dose based on the standard plain film scan image; generating scanning parameters of the sample based on the labeled image; and constructing a pre-trained convolutional neural network model based on the information of the sample, the standard plain film scan image, the labeled image, and the scanning parameters. The present disclosure realizes automated and intelligent adjustment of scanning parameters by analyzing the relationship between radiation dose and image quality. The system mainly consists of three parts: data preparation, neural network model construction, and model application. The present disclosure uses a convolutional neural network model. By defining data with qualified image quality, the positions where radiation can be reduced and the radiation dose that can be reduced can be obtained, and the radiation dose is dynamically adjusted during a single plain film scan. While reducing the radiation dose received by the patient, the integrity and positioning function of the plain film image are not affected, thereby realizing the optimization of the scanning process in an intelligent manner.

[0090] Finally, it should be noted that the embodiments in this specification are described in a progressive manner, and the key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the system or device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0091] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for obtaining scanning parameters for CT plain film scanning, characterized in that: include: Acquiring information data of a patient to be scanned, the information data including: body shape data and scanning position of the patient to be scanned; Inputting the information data into a pre-trained convolutional neural network model to obtain scanning parameters; Wherein, the pre-trained convolutional neural network model includes: Acquire sample information and a standard flat film scanning image; the sample information includes: the sample's body shape data, the sample's scanning position, and corresponding rated scanning parameters; generating a label image with reduced radiation dose based on the standard flat film scan image; generating scanning parameters of the sample based on the label image; A pre-trained convolutional neural network model is constructed based on the sample information, the standard flat film scan image, the label image and the scanning parameters.

2. The method for obtaining scanning parameters according to claim 1, characterized in that: The pre-trained convolutional neural network model also includes: A plurality of different samples are subjected to flat sheet scanning to obtain a plurality of sets of label images and scanning parameters.

3. The method for obtaining scanning parameters according to claim 1, characterized in that: The step of generating a label image with reduced radiation dose based on the standard flat film scan image comprises: Determining the boundaries of the scanning position in each of the standard flat film scan images; Returning image data outside a first pixel range from the boundary to zero to obtain the label image; The image outside the first pixel range from the boundary is identified as an area with reduced radiation dose during scanning.

4. The method for obtaining scanning parameters according to claim 3, characterized in that: Determining the boundaries of the scanning position includes: The boundary of the scanning position is determined based on the edge, shape, texture information, and scanning position of the standard flat film scanning image.

5. The method for obtaining scanning parameters according to claim 1, characterized in that: The input of the pre-trained convolutional neural network model includes: information of the sample and the standard flat film scan image; The output of the pre-trained convolutional neural network model includes: the label image and the scanning parameters.

6. The method for obtaining scanning parameters according to claim 3, characterized in that: The pre-trained convolutional neural network model also includes: Importing historical plain film scanning data into the pre-trained convolutional neural network model, and training the convolutional neural network model to output multiple sets of scanning parameter values; The historical flat film scanning data includes: sample information, the standard flat film scanning image, the label image generated based on the standard flat film scanning image, and the scanning parameters.

7. A scanning parameter acquisition unit for CT scanning, characterized in that: The method is configured to obtain scanning parameters by executing the method according to any one of claims 1 to 6.

8. A CT machine, characterized in that: include: The scanning parameter acquisition unit as claimed in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method according to any one of claims 1 to 6.

Images