Image preprocessing method, device, equipment and storage medium

Abstract

The embodiment of the present invention discloses an image preprocessing method, device, equipment and storage medium. By acquiring image acquisition data, the image acquisition data is input into a pre-trained preprocessing mode prediction model to obtain a preprocessing mode corresponding to the image acquisition data, and based on a preprocessing algorithm corresponding to the preprocessing mode, a preprocessing operation on the image acquisition data is performed. The problem of low preprocessing efficiency caused by starting multiple preprocessing processes for the same set of acquisition data in the prior art is solved. Through the preprocessing mode prediction model, the preprocessing mode corresponding to the image acquisition data can be determined, thereby improving the preprocessing efficiency and reducing resource waste.

Description

Technical Field

[0001] The embodiments of the present invention relate to data processing technology, and in particular to an image preprocessing method, device, equipment and storage medium. Background Art

[0002] For medical images acquired by imaging equipment, the post-processing workstation provides multiple post-processing applications to process them. The processing process usually includes data rearrangement, part segmentation, lesion extraction, etc. Behind these processing processes are complex image processing algorithms, which are time-consuming processes. Therefore, before pre-processing the medical image, a pre-processing mechanism is added. After the post-processing workstation receives the medical image, data rearrangement, part segmentation, lesion extraction and other processes are performed, and the processing results are saved. The operator can directly load the processing results, saving waiting time.

[0003] With the diversification of post-processing applications, it has become difficult to determine what kind of pre-processing to perform on specific data. For example, for common chest data, it is difficult for a computer to determine the doctor's preference whether the doctor wants to obtain the heart coronary artery results (corresponding to the heart post-processing application) or the lung nodule results (corresponding to the lung nodule post-processing application). In other words, when the collected data is pre-processed using the existing method, the pre-processing process of multiple post-processing applications is often started for the same set of collected data, so as to achieve the purpose of obtaining the processing results in advance.

[0004] However, for a set of collected data, users generally only need the processing result of one application. The redundant processing process wastes time, computing resources and storage resources. Summary of the invention

[0005] The embodiments of the present invention provide an image preprocessing method, device, equipment and storage medium to determine a preprocessing mode for a set of image acquisition data, thereby saving storage resources and improving preprocessing efficiency.

[0006] In a first aspect, an embodiment of the present invention provides an image preprocessing method, comprising:

[0007] Obtaining image acquisition data;

[0008] Inputting the image acquisition data into a pre-trained preprocessing mode prediction model to obtain a preprocessing mode corresponding to the image acquisition data;

[0009] Based on the preprocessing algorithm corresponding to the preprocessing mode, a preprocessing operation on the image acquisition data is performed.

[0010] Optionally, the training method of the preprocessing mode prediction model includes:

[0011] Acquire sample acquisition data and a sample preprocessing mode, wherein the sample acquisition data includes at least one of basic user information, acquisition device related information, and image related information;

[0012] Inputting the sample collection data into the original prediction model to obtain a prediction preprocessing model;

[0013] The network parameters of the original prediction model are adjusted according to the prediction preprocessing mode and the sample preprocessing mode to obtain the preprocessing mode prediction model.

[0014] Optionally, inputting the image acquisition data into a pre-trained pre-processing mode prediction model to obtain a pre-processing mode corresponding to the image acquisition data includes:

[0015] extracting a region of interest from the image acquisition data based on the preprocessing mode prediction model;

[0016] Determining, according to the image information of each pixel point of the region of interest, a label of a preprocessing mode corresponding to the image acquisition data and a probability of each of the labels;

[0017] A preprocessing mode corresponding to the image acquisition data is determined according to the probability of each of the labels.

[0018] Optionally, before inputting the sample collection data into the original prediction model, the method further includes:

[0019] The sample collection data is decentralized using a principal component analysis method, and a covariance matrix of the decentralized sample collection data is calculated;

[0020] Performing eigenvalue decomposition on the covariance matrix, extracting a set number of eigenvectors from the eigenvalue decomposition results, and projecting the sample collection data onto the eigenvectors to obtain a feature sequence of the sample collection data.

[0021] Optionally, performing a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode includes:

[0022] Determining at least one of an application name, an application mode, and a preference sequence corresponding to the preprocessing mode according to the label carried by the preprocessing mode;

[0023] A preprocessing operation on the image acquisition data is performed based on the processing logic of the preprocessing algorithm, wherein the preprocessing operation includes at least one of a denoising algorithm, a filtering algorithm, and a parameter setting processing algorithm.

[0024] Optionally, the image acquisition data is any one or a combination of ultrasound images, magnetic resonance images, computer tomography images, digital X-ray photography scan images, and molecular images.

[0025] Optionally, the method further includes:

[0026] The preprocessed image acquisition data is subjected to at least one post-processing operation of data rearrangement, part segmentation, and feature information extraction to obtain a reconstructed image corresponding to the image acquisition data.

[0027] In a second aspect, an embodiment of the present invention further provides an image preprocessing device, comprising:

[0028] An image acquisition data acquisition module is used to acquire image acquisition data;

[0029] A preprocessing mode determination module, used for inputting the image acquisition data into a pre-trained preprocessing mode prediction model to obtain a preprocessing mode corresponding to the image acquisition data;

[0030] The preprocessing execution module is used to perform a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode.

[0031] In a third aspect, an embodiment of the present invention further provides an image preprocessing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the image preprocessing method as described in any one of the first aspects is implemented.

[0032] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, implements the image preprocessing method as described in any one of the first aspects.

[0033] The technical solution provided in this embodiment obtains image acquisition data, inputs the image acquisition data into a pre-trained preprocessing mode prediction model, obtains a preprocessing mode corresponding to the image acquisition data, and performs a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode. The problem of low preprocessing efficiency caused by starting multiple preprocessing processes for the same set of acquisition data in the prior art is solved. The preprocessing mode corresponding to the image acquisition data can be determined through the preprocessing mode prediction model, thereby improving the preprocessing efficiency and reducing resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of a flow chart of an image preprocessing method provided in Embodiment 1 of the present invention;

[0035] Figure 2A logical schematic diagram of an image preprocessing method provided in Embodiment 1 of the present invention;

[0036] Figure 3 A schematic diagram of the structure of an image preprocessing device provided in Embodiment 2 of the present invention;

[0037] Figure 4 A schematic diagram of the structure of an image preprocessing device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0039] Embodiment 1

[0040] Figure 1 This is a flowchart of an image preprocessing method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case where a preprocessing mode is determined by a preprocessing mode prediction model when image acquisition data is acquired. The method can be executed by an image preprocessing device, wherein the device can be implemented by software and / or hardware and is generally integrated in a terminal or image preprocessing device. For details, see Figure 1 As shown, the method may include the following steps:

[0041] S110, acquiring image acquisition data.

[0042] It can be understood that the image acquisition data is a medical image acquired by an image acquisition device. Depending on the type of image acquisition device, the image acquisition data can be any one or a combination of ultrasound images, magnetic resonance images, computed tomography images, digital X-ray photography scan images, and molecular images.

[0043] S120, inputting the image acquisition data into a pre-trained pre-processing mode prediction model to obtain a pre-processing mode corresponding to the image acquisition data.

[0044] It is understandable that the post-processing of image acquisition data is a time-consuming process. In order to save the time required for image post-processing, a pre-processing mechanism is added before the image acquisition data is post-processed. However, the post-processing application is diversified. The pre-processing mode corresponding to the image acquisition data cannot be determined only according to the set modality, the corresponding part of the image acquisition device, etc., and the pre-processing efficiency is low and resources are wasted. In this regard, the present embodiment inputs the image acquisition data into a pre-trained pre-processing mode prediction model, and determines the pre-processing mode corresponding to the image acquisition data through the pre-processing mode prediction model. Optionally, the method for determining the pre-processing mode corresponding to the image acquisition data is: extracting the region of interest of the image acquisition data based on the pre-processing mode prediction model, determining the label of the pre-processing mode corresponding to the image acquisition data and the probability of each label according to the image information of each pixel point in the region of interest, and determining the pre-processing mode corresponding to the image acquisition data according to the probability of each label. Optionally, the label of the pre-processing mode can be determined according to the image type of the image acquisition data, the image acquisition part, and the pre-processing algorithm included in the pre-processing mode.

[0045] Specifically, the preprocessing mode prediction model may include multiple subnetworks, extract at least one region of interest of the image acquisition data through the first subnetwork, calculate the image information of the pixels of each region of interest through the second subnetwork, such as calculating the gray value of each pixel, and determine the label of the corresponding preprocessing mode and the probability of the label according to the image information of the pixels of each region of interest through the third subnetwork, and output the preprocessing mode corresponding to the label with the highest probability as the result to obtain the preprocessing mode corresponding to the image acquisition data. Optionally, the preprocessing mode prediction model may be, but is not limited to, a convolutional neural network, a fully connected neural network, and other neural networks.

[0046] Optionally, the preprocessing mode prediction model can be obtained by training with sample acquisition data and sample preprocessing mode. The training method of the preprocessing mode prediction model is: obtaining sample acquisition data and sample preprocessing mode, wherein the sample acquisition data includes at least one of user basic information, acquisition device related information and image related information; inputting the sample acquisition data into the original prediction model to obtain the prediction preprocessing mode; adjusting the network parameters of the original prediction model according to the prediction preprocessing mode and the sample preprocessing mode to obtain the preprocessing mode prediction model. The user basic information includes information such as user gender, height and weight; the acquisition device related information includes information such as body inspection part, protocol name, image acquisition device modality, image acquisition device sequence description and user positioning status; the image related information includes information such as image slice thickness, pixel spacing, number of image rows, number of image columns, phase information, heart rate and viewing angle. The sample acquisition data and the sample preprocessing mode can both carry labels for end-to-end training of the original prediction model.

[0047] In this embodiment, in order to reduce the correlation between the features of the sample collection data during the training process, the sample collection data can be preprocessed before the sample collection data is input into the original prediction model. The specific method is: the sample collection data is decentralized by principal component analysis, and the covariance matrix of the decentralized sample collection data is calculated, the covariance matrix is ​​decomposed by eigenvalue, a set number of eigenvectors are extracted from the eigenvalue decomposition result, the sample collection data is projected onto the eigenvector, and the feature sequence of the sample collection data is obtained, and then the feature sequence of the sample collection data is input into the original prediction model, and the original prediction model is trained by the sample collection data and the sample preprocessing mode to obtain the preprocessing mode prediction model. Optionally, the covariance matrix can be written as a series of linear operations (including scaling and rotation), the eigenvalue decomposition result represents the rotation matrix, and the eigenvalue represents the scale factor, and the eigenvector points to the direction of the maximum variance of the data of the covariance matrix. By projecting the sample collection data onto the eigenvector, the dimension of the sample collection data can be reduced.

[0048] S130, performing a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode.

[0049] Optionally, at least one of the application name, application mode and preference sequence corresponding to the preprocessing mode can be determined according to the label carried by the preprocessing mode, and the preprocessing operation of the image acquisition data can be performed based on the processing logic of the preprocessing algorithm, wherein the preprocessing operation includes at least one of a denoising algorithm, a filtering algorithm and a parameter setting processing algorithm. As described in the above steps, the label of the preprocessing mode can be determined according to the image type of the image acquisition data, the image acquisition part and the preprocessing algorithm included in the preprocessing mode. Accordingly, if the label carried by the preprocessing mode is determined, the application name, application mode and preference sequence of the preprocessing mode are determined according to the label, a specific preprocessing algorithm is selected, and a denoising operation, a filtering operation or a parameter setting operation is performed according to the processing logic of the preprocessing algorithm to complete the preprocessing operation of the image acquisition data.

[0050] like Figure 2 The figure shows a logical diagram of an image preprocessing method. Figure 2 The method includes the training process of the preprocessing mode prediction model and the process of determining a preprocessing mode using the preprocessing mode prediction model. Figure 2To explain the above content, when training the preprocessing mode prediction model, the sample acquisition data and the sample preprocessing mode are archived to the post-processing workstation, and a sample preprocessing mode manually triggered by a technician is received. The post-processing workstation records the sample acquisition data corresponding to the sample preprocessing mode triggered by the technician, and determines whether the data volume of the sample acquisition data reaches the training sample volume. If reached, the original prediction model is trained according to the sample preprocessing mode triggered by the technician and the corresponding sample acquisition data, and the obtained prediction preprocessing mode is displayed. If it is determined whether the prediction preprocessing mode is consistent with the sample preprocessing mode, other sample preprocessing modes are triggered to train the original prediction model according to all sample preprocessing modes and sample acquisition data until the original prediction model is trained, and the trained preprocessing mode prediction model is used to determine the preprocessing mode of the image acquisition data and perform preprocessing operations.

[0051] Furthermore, after performing the preprocessing operation on the image acquisition data, the preprocessed image acquisition data may be subjected to at least one post-processing operation of data rearrangement, part segmentation, and feature information extraction to obtain a reconstructed image corresponding to the image acquisition data.

[0052] The technical solution provided in this embodiment obtains image acquisition data, inputs the image acquisition data into a pre-trained preprocessing mode prediction model, obtains a preprocessing mode corresponding to the image acquisition data, and performs a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode. The problem of low preprocessing efficiency caused by starting multiple preprocessing processes for the same set of acquisition data in the prior art is solved. The preprocessing mode corresponding to the image acquisition data can be determined through the preprocessing mode prediction model, thereby improving the preprocessing efficiency and reducing resource waste.

[0053] Embodiment 2

[0054] Figure 3 This is a schematic diagram of the structure of an image preprocessing device provided by Embodiment 2 of the present invention. Figure 3 As shown, the device includes: an image acquisition data acquisition module 210, a preprocessing mode determination module 220 and a preprocessing mode determination module 230.

[0055] Among them, the image acquisition data acquisition module 210 is used to acquire image acquisition data; the preprocessing mode determination module 220 is used to input the image acquisition data into a pre-trained preprocessing mode prediction model to obtain the preprocessing mode corresponding to the image acquisition data; the preprocessing execution module 230 is used to perform preprocessing operations on the image acquisition data based on the preprocessing algorithm corresponding to the preprocessing mode.

[0056] On the basis of the above technical solutions, the device further includes: a preprocessing mode prediction model training module; wherein the preprocessing mode prediction model training module is used to obtain sample acquisition data and sample preprocessing mode, wherein the sample acquisition data includes at least one of user basic information, acquisition device related information and image related information;

[0057] Inputting the sample collection data into the original prediction model to obtain a prediction preprocessing model;

[0058] The network parameters of the original prediction model are adjusted according to the prediction preprocessing mode and the sample preprocessing mode to obtain the preprocessing mode prediction model.

[0059] On the basis of the above technical solutions, the preprocessing mode determination module 220 is further used to extract the region of interest of the image acquisition data based on the preprocessing mode prediction model;

[0060] Determining, according to the image information of each pixel point of the region of interest, a label of a preprocessing mode corresponding to the image acquisition data and a probability of each of the labels;

[0061] A preprocessing mode corresponding to the image acquisition data is determined according to the probability of each of the labels.

[0062] On the basis of the above technical solutions, the device further includes: a sample collection data preprocessing module; wherein the sample collection data preprocessing module is used to perform decentralized processing on the sample collection data using a principal component analysis method, and calculate the covariance matrix of the decentralized sample collection data;

[0063] Performing eigenvalue decomposition on the covariance matrix, extracting a set number of eigenvectors from the eigenvalue decomposition results, and projecting the sample collection data onto the eigenvectors to obtain a feature sequence of the sample collection data.

[0064] On the basis of the above technical solutions, the preprocessing mode determination module 230 is used to determine at least one of the application name, application mode and preference sequence corresponding to the preprocessing mode according to the label carried by the preprocessing mode;

[0065] A preprocessing operation on the image acquisition data is performed based on the processing logic of the preprocessing algorithm, wherein the preprocessing operation includes at least one of a denoising algorithm, a filtering algorithm, and a parameter setting processing algorithm.

[0066] On the basis of the above technical solutions, the image acquisition data is any one or a combination of ultrasound images, magnetic resonance images, computer tomography images, digital X-ray photography scan images, and molecular images.

[0067] On the basis of the above-mentioned technical solutions, the device also includes: a post-processing module; wherein the post-processing module is used to perform at least one post-processing operation of data rearrangement, part segmentation and feature information extraction on the pre-processed image acquisition data to obtain a reconstructed image corresponding to the image acquisition data.

[0068] The technical solution provided in this embodiment obtains image acquisition data, inputs the image acquisition data into a pre-trained preprocessing mode prediction model, obtains a preprocessing mode corresponding to the image acquisition data, and performs a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode. The problem of low preprocessing efficiency caused by starting multiple preprocessing processes for the same set of acquisition data in the prior art is solved. The preprocessing mode corresponding to the image acquisition data can be determined through the preprocessing mode prediction model, thereby improving the preprocessing efficiency and reducing resource waste.

[0069] Embodiment 3

[0070] Figure 4 A schematic diagram of the structure of an image preprocessing device provided in Embodiment 3 of the present invention. Figure 4 A block diagram of an exemplary image pre-processing device 12 suitable for implementing embodiments of the present invention is shown. Figure 4 The image preprocessing device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0071] like Figure 4 As shown, the image preprocessing device 12 is in the form of a general-purpose computing device. The components of the image preprocessing device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0072] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0073] The image pre-processing device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the image pre-processing device 12, including volatile and non-volatile media, removable and non-removable media.

[0074] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The image pre-processing device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive can be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a group of program modules (such as an image acquisition data acquisition module 210, a preprocessing mode determination module 220, and a preprocessing mode determination module 230 of an image preprocessing device), which are configured to perform the functions of various embodiments of the present invention.

[0075] A program / utility 44 having a set of program modules 46 (e.g., image acquisition data acquisition module 210, preprocessing mode determination module 220, and preprocessing mode determination module 230 of an image preprocessing device) may be stored in, for example, memory 28. Such program modules 46 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include the implementation of a network environment. The program modules 46 generally perform the functions and / or methods in the embodiments described herein.

[0076] The image preprocessing device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may also communicate with one or more devices that enable a user to interact with the image preprocessing device 12, and / or may communicate with any device that enables the image preprocessing device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the image preprocessing device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the image preprocessing device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the image preprocessing device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0077] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing an image preprocessing method provided by an embodiment of the present invention, the method comprising:

[0078] Obtaining image acquisition data;

[0079] Inputting the image acquisition data into a pre-trained preprocessing mode prediction model to obtain a preprocessing mode corresponding to the image acquisition data;

[0080] Based on the preprocessing algorithm corresponding to the preprocessing mode, a preprocessing operation on the image acquisition data is performed.

[0081] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing an image preprocessing method provided by an embodiment of the present invention.

[0082] Of course, those skilled in the art can understand that the processor can also implement the technical solution of an image preprocessing method provided by any embodiment of the present invention.

[0083] Embodiment 4

[0084] Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, an image preprocessing method provided in the embodiment of the present invention is implemented. The method includes:

[0085] Obtaining image acquisition data;

[0086] Inputting the image acquisition data into a pre-trained preprocessing mode prediction model to obtain a preprocessing mode corresponding to the image acquisition data;

[0087] Based on the preprocessing algorithm corresponding to the preprocessing mode, a preprocessing operation on the image acquisition data is performed.

[0088] Of course, the computer program stored in a computer-readable storage medium provided by an embodiment of the present invention is not limited to the above method operations, but can also execute related operations in an image preprocessing method provided by any embodiment of the present invention.

[0089] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with 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 this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, system or device or used in combination with it.

[0090] Computer-readable signal media may include image acquisition data, preprocessing patterns, preprocessing algorithms, etc., which carry computer-readable program codes. Such propagated image acquisition data, preprocessing patterns, preprocessing algorithms, etc. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, system or device.

[0091] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0092] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate 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, including 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).

[0093] It is worth noting that in the embodiment of the above-mentioned image preprocessing device, the various modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0094] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An image preprocessing method, characterized in that: include: Obtaining image acquisition data; Inputting the image acquisition data into a pre-trained pre-processing mode prediction model to obtain a pre-processing mode corresponding to the image acquisition data; The preprocessing mode is determined according to the image type of the image acquisition data, the image acquisition part and the preprocessing algorithm included in the preprocessing mode; Based on the preprocessing algorithm corresponding to the preprocessing mode, performing a preprocessing operation on the image acquisition data; The training method of the preprocessing mode prediction model comprises: Acquire sample collection data and a sample preprocessing mode, wherein the sample collection data includes at least one of basic user information, collection device related information, and image related information; The sample collection data is input into the original prediction model to obtain a prediction preprocessing mode; wherein, before the sample collection data is input into the original prediction model, it also includes judging whether the data volume of the sample collection data reaches the training sample volume, and if so, inputting the sample collection data into the original prediction model; Adjust the network parameters of the original prediction model according to the prediction preprocessing mode and the sample preprocessing mode to obtain the preprocessing mode prediction model; The performing of a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode includes: Determine a label of the preprocessing mode according to the image type of the image acquisition data, the image acquisition part, and the preprocessing algorithm included in the preprocessing mode, determine an application name, an application mode, and a preference sequence corresponding to the preprocessing mode according to the label, select the preprocessing algorithm, and perform a preprocessing operation according to the processing logic of the preprocessing algorithm; The step of inputting the image acquisition data into a pre-trained pre-processing mode prediction model to obtain a pre-processing mode corresponding to the image acquisition data includes: Extracting a region of interest from the image acquisition data based on the preprocessing mode prediction model; Determining, according to the image information of each pixel point of the region of interest, a label of a preprocessing mode corresponding to the image acquisition data and a probability of each of the labels; A preprocessing mode corresponding to the image acquisition data is determined according to the probability of each of the labels.

2. The method according to claim 1, characterized in that Before inputting the sample collection data into the original prediction model, the method further includes: The sample collection data is decentralized using a principal component analysis method, and a covariance matrix of the decentralized sample collection data is calculated; Performing eigenvalue decomposition on the covariance matrix, extracting a set number of eigenvectors from the eigenvalue decomposition result, projecting the sample collection data onto the eigenvectors, and obtaining a feature sequence of the sample collection data.

3. The method according to claim 1, characterized in that The performing of a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode includes: Determining at least one of an application name, an application mode, and a preference sequence corresponding to the preprocessing mode according to the label carried by the preprocessing mode; A preprocessing operation on the image acquisition data is performed based on the processing logic of the preprocessing algorithm, wherein the preprocessing operation includes at least one of a denoising algorithm, a filtering algorithm, and a parameter setting processing algorithm.

4. The method according to claim 1, characterized in that: The image acquisition data is any one or a combination of ultrasound images, magnetic resonance images, computer tomography images, digital X-ray photography scan images, and molecular images.

5. The method according to claim 1, characterized in that Also includes: The preprocessed image acquisition data is subjected to at least one post-processing operation of data rearrangement, part segmentation, and feature information extraction to obtain a reconstructed image corresponding to the image acquisition data.

6. An image preprocessing device, characterized in that: include: An image acquisition data acquisition module is used to acquire image acquisition data; A preprocessing mode determination module, used for inputting the image acquisition data into a pre-trained preprocessing mode prediction model to obtain a preprocessing mode corresponding to the image acquisition data; The preprocessing mode is determined according to the image type of the image acquisition data, the image acquisition part and the preprocessing algorithm included in the preprocessing mode; A preprocessing execution module, used for executing a preprocessing operation on the image acquisition data based on a preprocessing algorithm corresponding to the preprocessing mode; A preprocessing mode prediction model training module is used to obtain sample acquisition data and sample preprocessing mode, wherein the sample acquisition data includes at least one of user basic information, acquisition device related information and image related information; input the sample acquisition data into the original prediction model to obtain the prediction preprocessing mode; adjust the network parameters of the original prediction model according to the prediction preprocessing mode and the sample preprocessing mode to obtain the preprocessing mode prediction model; wherein, before inputting the sample acquisition data into the original prediction model, it also includes judging whether the data volume of the sample acquisition data reaches the training sample volume, and if so, inputting the sample acquisition data into the original prediction model; adjusting the network parameters of the original prediction model according to the prediction preprocessing mode and the sample preprocessing mode to obtain the preprocessing mode prediction model; The performing of the preprocessing operation on the image acquisition data based on the preprocessing algorithm corresponding to the preprocessing mode includes: determining the label of the preprocessing mode according to the image type of the image acquisition data, the image acquisition part and the preprocessing algorithm included in the preprocessing mode, determining the application name, application mode and preference sequence corresponding to the preprocessing mode according to the label, selecting the preprocessing algorithm, and performing the preprocessing operation according to the processing logic of the preprocessing algorithm; The preprocessing mode determination module is also used to extract the region of interest of the image acquisition data based on the preprocessing mode prediction model; Determining, according to the image information of each pixel point of the region of interest, a label of a preprocessing mode corresponding to the image acquisition data and a probability of each of the labels; A preprocessing mode corresponding to the image acquisition data is determined according to the probability of each of the labels.

7. An image preprocessing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the image preprocessing method according to any one of claims 1 to 5 is implemented.

8. A storage medium containing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, the image preprocessing method according to any one of claims 1 to 5 is implemented.

Images