Image reconstruction method and device and magnetic resonance imaging system
By acquiring and utilizing the scanning protocol parameters and data acquisition methods of magnetic resonance imaging equipment, the abnormal properties of scanning data in magnetic resonance imaging technology are corrected, the problem of image reconstruction failure caused by data errors is solved, and data integrity and reconstruction success are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2026-03-13
AI Technical Summary
In magnetic resonance imaging (MRI) technology, errors in the properties of scanned data due to system or software limitations can cause the image reconstruction process to fail.
By acquiring the scanning protocol parameters and data acquisition methods of the magnetic resonance imaging (MRI) device, abnormal data attributes in the original scan data are corrected. This includes dividing the data into multiple dimensions and using adjacent data attributes to predict and correct abnormal attributes. Finally, the corrected data is stored and the image is reconstructed.
It accurately corrects anomalous properties of the scanned data, ensuring the success of the image reconstruction process and avoiding data loss and reconstruction failure.
Smart Images
Figure CN121661200A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of image processing technology, and in particular to an image reconstruction method, apparatus and magnetic resonance imaging system. Background Technology
[0002] With the continuous development of medical equipment, magnetic resonance imaging technology is increasingly being used in preclinical examinations and diagnoses of various systems.
[0003] During the scanning process of an MRI machine, due to system or software limitations, some scan data attributes may be entered incorrectly, causing the subsequent image reconstruction process to fail.
[0004] Therefore, there is an urgent need for an image reconstruction method that can correct errors in the properties of scanned data. Summary of the Invention
[0005] Therefore, it is necessary to provide an image reconstruction method, apparatus, and magnetic resonance imaging system that can correct the erroneous properties of scan data in response to the above-mentioned technical problems.
[0006] Firstly, this application provides an image reconstruction method, including:
[0007] Obtain the scanning protocol parameters and data acquisition method of the raw scan data acquired by the magnetic resonance imaging (MRI) device; the raw scan data is the complete scan data acquired by the MRI device with abnormal data attributes;
[0008] Based on the scanning protocol parameters and data acquisition method, correct abnormal data attributes in the original scanning data;
[0009] Image reconstruction is performed based on the original scan data after data attribute correction.
[0010] In one embodiment, based on scanning protocol parameters and data acquisition methods, abnormal data attributes in the original scan data are corrected, including:
[0011] Based on the scanning protocol parameters, the raw scanning data is divided into multi-dimensional scanning data;
[0012] Based on the data acquisition method, abnormal attributes in the scanned data of each dimension are corrected.
[0013] In one embodiment, based on scanning protocol parameters, the raw scan data is divided into multi-dimensional scan data, including:
[0014] Determine the dimensional information of the raw scan data from the scan protocol parameters;
[0015] The original scan data is divided according to the dimensional information to obtain multi-dimensional scan data.
[0016] In one embodiment, the multidimensional scan data includes at least one of the following dimensions: layer number dimension, phase encoding dimension, frequency encoding dimension, layer selection dimension, and cardiac phase encoding dimension.
[0017] In one embodiment, based on the data acquisition method, abnormal attributes in the scan data of each dimension are corrected, including:
[0018] For any dimension of scanned data, obtain the adjacent data attributes of the abnormal attributes in the scanned data;
[0019] Based on adjacent data attributes, determine the predicted attributes corresponding to the abnormal attributes;
[0020] Replace outlier attributes in the scanned data with predicted attributes.
[0021] In one embodiment, the method further includes:
[0022] Obtain the difference between each data attribute and its adjacent data attributes in the original scan data;
[0023] If any difference exceeds a preset threshold, the data attribute corresponding to the difference is determined to be abnormal.
[0024] In one embodiment, the method further includes:
[0025] Based on the data dimensions of the original scan data after data attribute correction, predict the total storage space of the original scan data after data attribute correction.
[0026] Based on the total storage space and splitting rules, the original scanned data after data attribute correction is split;
[0027] The split scan data is stored in the scan database.
[0028] In one embodiment, image reconstruction is performed based on the original scan data after data attribute correction, including:
[0029] The original scan data with corrected data attributes is obtained from the scan database, and the image is reconstructed based on the original scan data with corrected data attributes.
[0030] Secondly, this application also provides an image reconstruction apparatus, comprising:
[0031] The acquisition module is used to acquire the scanning protocol parameters and data acquisition method of the raw scan data acquired by the magnetic resonance imaging (MRI) device; the raw scan data is the complete scan data acquired by the MRI device with abnormal data attributes;
[0032] The correction module is used to correct abnormal data attributes in the original scan data based on the scan protocol parameters and data acquisition method.
[0033] The reconstruction module is used to reconstruct images based on the original scan data after data attribute correction.
[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the content of any embodiment of the image reconstruction method in the first aspect.
[0035] Fourthly, this application also provides a magnetic resonance imaging system, which includes a magnetic resonance device and a computer device, wherein the magnetic resonance device is connected to the computer device;
[0036] Magnetic resonance imaging (MRI) equipment is used to acquire data from the scanned object and send the acquired data to a computer.
[0037] Computer equipment is used to acquire complete raw scan data with abnormal data attributes from raw data, and to correct the abnormal data attributes in the raw scan data according to the scanning protocol parameters and data acquisition method of the raw scan data; and to reconstruct the image based on the raw scan data after data attribute correction.
[0038] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the content of any embodiment of the image reconstruction method in the first aspect.
[0039] In a sixth aspect, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the content of any embodiment of the image reconstruction method in the first aspect.
[0040] The aforementioned image reconstruction method, apparatus, and magnetic resonance imaging system acquire the scanning protocol parameters and data acquisition method of the original scan data collected by the magnetic resonance imaging equipment. The original scan data is complete scan data acquired by the magnetic resonance imaging equipment, but with abnormal data attributes. Based on the scanning protocol parameters and data acquisition method, the abnormal data attributes in the original scan data are corrected. Image reconstruction is then performed based on the original scan data with corrected data attributes. For scan data that is complete but has abnormal data attributes, this method can accurately correct abnormal data attributes by acquiring the scanning protocol parameters and data acquisition method during the acquisition process. The corrected data attributes are correct, and the scan data is complete, thus avoiding failure in the image reconstruction process. Attached Figure Description
[0041] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0042] Figure 1 This is a diagram illustrating the application environment of an image reconstruction method in one embodiment;
[0043] Figure 2 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0044] Figure 3 This is a schematic diagram illustrating the composition of the original scan data in one embodiment;
[0045] Figure 4 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0046] Figure 5 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0047] Figure 6 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0048] Figure 7 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0049] Figure 8 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0050] Figure 9 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0051] Figure 10 This is a flowchart illustrating an image reconstruction method in one embodiment;
[0052] Figure 11 This is a structural block diagram of an image reconstruction apparatus in one embodiment. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0054] The image reconstruction method provided in this application embodiment can be applied to, for example... Figure 1The application environment shown is a computer device that can be a server, personal computer, laptop, smartphone, tablet, mobile phone, etc. This computer device may include a processor, memory, and network interface connected via a system bus or wirelessly. The processor provides computing and control capabilities. The memory may include non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data used in the image reconstruction process. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements an image reconstruction method.
[0055] In one exemplary embodiment, such as Figure 2 As shown, an image reconstruction method is provided, which is applied to... Figure 1 The following steps, 201 to 203, are used as an example of computer equipment.
[0056] S201, Obtain the scanning protocol parameters and data acquisition method of the original scan data acquired by the magnetic resonance imaging (MRI) device; the original scan data is the complete scan data acquired by the MRI device with abnormal data attributes.
[0057] The scanning protocol parameters refer to the parameters of the raw scanning data during the acquisition process. For example, scanning protocol parameters may include readout encoding, first phase encoding, second phase encoding, number of coil channels, average count, and repetition count. For instance, scanning protocol parameters could be [176, 108, 110, 3, 4, 35]. The data acquisition method refers to the acquisition method for K-space data.
[0058] Figure 3 This is a schematic diagram of the composition of the original scan data. The original scan data mainly includes the protocol version, protocol length, protocol part, and multiple scan data. Each scan data mainly includes data attributes and data part. Data attributes include data length, data index, and the scan layer where the data is located, etc.
[0059] In this embodiment, all scan data acquired by the MRI machine is stored in a scan database. Scan data that is complete but has abnormal data attributes carries identification information. The computer device can retrieve scan data carrying identification information from the scan database and use the scan data carrying identification information as the original scan data acquired by the MRI machine.
[0060] Optionally, the computer can also send a data acquisition command to the MRI scanner. Upon receiving the command, the MRI scanner begins acquiring raw scan data and sends the acquired data to the computer. Then, it checks whether the acquired scan data is complete and whether there are any anomalies in its attributes. If the scan data is complete and its attributes are not abnormal, the acquired scan data is used as the raw scan data acquired by the MRI scanner.
[0061] Furthermore, once the original scan data is determined, the computer equipment can retrieve the scanning protocol parameters and data acquisition method of the original scan data from the historical settings parameters of the MRI equipment.
[0062] It is important to emphasize that because the raw scan data is complete, its data volume is very large. For example, the raw scan data is 266 gigabytes (GB). Computer devices can use a combination of physical memory and virtual memory to read the raw scan data, thus loading the raw scan data much faster.
[0063] S202 corrects abnormal data attributes in the original scan data based on scan protocol parameters and data acquisition methods.
[0064] In this embodiment, the computer device can input scanning protocol parameters and data acquisition methods into a preset attribute determination model. The attribute determination model analyzes the scanning protocol parameters and data acquisition methods, predicts abnormal data attributes, and outputs predicted data attributes. The predicted data attributes then replace the abnormal data attributes in the original scanning data, thus correcting the overall data attributes.
[0065] Optionally, the computer device can also adjust abnormal data attributes in the original scan data according to a preset step size based on scanning protocol parameters and data acquisition methods. It then determines whether the adjusted data attributes are still abnormal. If abnormalities exist, the adjustment of abnormal data attributes in the original scan data continues until the last adjusted data attributes are free of abnormalities. At this point, the abnormal data attributes in the original scan data have been corrected.
[0066] S203, Reconstruct the image based on the original scan data after data attribute correction.
[0067] In this embodiment, the original scan data after data attribute correction has correct attributes, and the scan data is complete, allowing for direct image reconstruction. Therefore, a computer device can use an image reconstruction algorithm to reconstruct the original scan data after data attribute correction, obtaining a reconstructed magnetic resonance image corresponding to the corrected original scan data. It should be noted that the reconstructed magnetic resonance image is the entire image of the scanned area.
[0068] In the aforementioned image reconstruction method, the scanning protocol parameters and data acquisition method of the original scan data acquired by the magnetic resonance imaging (MRI) device are obtained. The original scan data is complete scan data acquired by the MRI device that contains abnormal data attributes. Based on the scanning protocol parameters and data acquisition method, the abnormal data attributes in the original scan data are corrected. Image reconstruction is then performed based on the original scan data after data attribute correction. For scan data that is complete but contains abnormal data attributes, this method can accurately correct abnormal data attributes by acquiring the scanning protocol parameters and data acquisition method during the acquisition process. The corrected data attributes are correct, and the scan data is complete, thus avoiding failure in the image reconstruction process.
[0069] To avoid failure in the image reconstruction process, the main focus is on correcting abnormal data attributes. Therefore, in one embodiment, such as... Figure 4 As shown, the specific process for correcting abnormal data attributes in the original scan data based on the scan protocol parameters and data acquisition method is explained. This specific process includes the following steps:
[0070] S301 divides the raw scan data into multi-dimensional scan data based on scan protocol parameters.
[0071] The multi-dimensional scan data is related to the definition of scan data dimensions in the user's current protocol file. In one embodiment, the multi-dimensional scan data includes at least one of the following dimensions: layer number dimension, phase encoding dimension, frequency encoding dimension, layer selection dimension, and cardiac phase encoding dimension.
[0072] The following section uses the number of layers as an example to describe the dimension division process. In this embodiment, the scanning protocol parameters include the number of scanning layers in the magnetic resonance imaging (MRI) scan. For example, the number of scanning layers can be 100 or 150. The computer device can divide the scan data of different layers in the original scan data according to the number of scanning layers in the scanning protocol parameters to obtain multi-layer scan data.
[0073] For dimensions other than the number of layers, the division method is the same as that for the number of layers, and will not be elaborated on here.
[0074] S302, based on the data acquisition method, correct abnormal attributes in the scanned data of each dimension.
[0075] In this embodiment, the computer device can predict abnormal attributes in the scanned data of each dimension based on the data acquisition method, and obtain the predicted attribute corresponding to the abnormal attribute. The predicted attribute is then used to replace the abnormal attribute to correct the abnormal attributes in the scanned data of each dimension.
[0076] In the image reconstruction method described above, the original scan data is divided into multi-dimensional scan data based on scan protocol parameters; and abnormal attributes in the scan data of each dimension are corrected according to the data acquisition method. This method can accurately divide the original scan data through scan protocol parameters, and accurately complete the abnormal attribute correction process based on the data acquisition method.
[0077] As can be seen from the above embodiments, the correction of abnormal attributes consists of two parts: one is the division of the original scan data, and the other is the correction process. These two parts will be described in detail below.
[0078] First, in one embodiment, such as Figure 5 As shown, the specific process of dividing the original scan data into multi-dimensional scan data based on the scan protocol parameters includes:
[0079] S401, determine the dimensional information of the raw scan data from the scan protocol parameters.
[0080] In this context, dimensional information refers to the criteria used to divide the raw scan data along different dimensions. For example, regarding the layer count dimension, dimensional information refers to the number of layers scanned by the magnetic resonance imaging (MRI) device during the scanning process. For instance, the number of scanned layers could be 100 or 150.
[0081] In this embodiment, since the scanning protocol parameters include multiple parameters, and dimensional information is one of those parameters, the computer device can determine the value corresponding to the dimensional information in the scanning protocol parameters, thereby determining the dimensional information of the original scan data.
[0082] S402, the original scan data is divided according to the dimensional information to obtain multi-dimensional scan data.
[0083] In this embodiment, the computer device can divide the original scan data into various scan dimensions according to the scan dimensions to obtain multi-dimensional scan data. It should be noted that each scan layer includes multiple scan data.
[0084] In the image reconstruction method described above, the dimensional information of the original scan data is determined from the scanning protocol parameters. The original scan data is then divided based on this dimensional information to obtain multi-dimensional scan data. This method, by acquiring the dimensional information from the scanning protocol parameters, can accurately divide the original scan data based on this information, resulting in more accurate division results. Furthermore, this division method can be used for scan data of different dimensions, meaning it has a wide range of applications.
[0085] The following example illustrates the specific process of correcting abnormal attributes in the scanned data of each dimension based on the data acquisition method. Figure 6 As shown, the specific process includes:
[0086] S501: For scanned data of any dimension, obtain the adjacent data attributes of the abnormal attributes in the scanned data.
[0087] In this embodiment, since the correction process for the data attributes of scanned data in any dimension is the same, for any dimension of scanned data, when it is determined that there is an abnormal attribute in the scanned data of that layer, the computer device can obtain the adjacent data attributes of the abnormal attribute based on the location of the abnormal attribute.
[0088] S502, determine the predicted attribute corresponding to the abnormal attribute based on the adjacent data attributes.
[0089] In this embodiment, the computer device can input adjacent data attributes into a preset attribute prediction model. The attribute prediction model can analyze the features of adjacent data attributes and output the predicted attribute corresponding to the abnormal attribute. It should be noted that, to improve the accuracy of attribute prediction, all data attributes of the scanned data at that layer can also be input into the attribute prediction model. The attribute prediction model can then predict all data attributes of the scanned data at that layer from a global perspective, resulting in higher accuracy of the predicted attribute. Optionally, the computer device can also determine the predicted attribute corresponding to the abnormal attribute based on the patterns between adjacent data attributes. This embodiment does not limit the method used to determine the predicted attribute corresponding to the abnormal attribute.
[0090] S503 uses predicted attributes to replace anomalous attributes in scanned data.
[0091] In this embodiment, after obtaining the predicted attribute corresponding to the abnormal attribute, the computer device can delete the abnormal attribute and fill the corresponding position with the predicted attribute to complete the replacement process. At this time, the correction process for the abnormal attribute has also been completed.
[0092] In the image reconstruction method described above, for scanned data in any dimension, the neighboring data attributes of the abnormal attributes in the scanned data are obtained; based on the neighboring data attributes, the predicted attribute corresponding to the abnormal attribute is determined; and the abnormal attribute in the scanned data is replaced with the predicted attribute. During the data attribute correction process, this method, by obtaining the neighboring data attributes of the abnormal attributes and based on these neighboring data attributes, can accurately predict the attributes, thus making the data attribute correction results more accurate.
[0093] Raw scan data refers to data that is complete but contains anomalies in its attributes. The following example illustrates the specific process for determining if data attributes are abnormal. Figure 7 As shown, the specific process includes:
[0094] S601, obtain the difference between each data attribute of the original scan data and its adjacent data attributes.
[0095] Because there are certain relationships between the data attributes of multiple scan data in each scan layer of the original scan data. This relationship can be that the difference in the data attributes of adjacent scan data is fixed. For example, the difference in the data attributes of adjacent scan data might be 1. Therefore, whether the data attributes are abnormal can be determined by whether there are abrupt changes in the data attributes of adjacent scan data.
[0096] In this embodiment of the application, the computer device can divide the original scan data into multi-dimensional scan data according to the scan protocol parameters of the original scan data. For example, if the scan layer in the scan protocol parameters is 100 layers, the corresponding number of layers in the scan data is 100 layers.
[0097] For each dimension of the scan data, the computer device can calculate the difference between the previous and next adjacent scan data in that layer of scan data, and use this difference as the difference between adjacent data attributes.
[0098] S602, if any difference is greater than a preset threshold, it is determined that the data attribute corresponding to the difference is abnormal.
[0099] The preset threshold can be the average of the remaining differences after removing the highest and lowest jump differences, or it can be the difference with the most occurrences. For example, if the difference with the most occurrences is 1, the preset threshold can be set to 1.
[0100] In this embodiment, the computer device can compare multiple differences in the scan data of each dimension with a preset threshold. If all differences are less than the preset threshold, it indicates that the data attributes corresponding to the original scan data are not abnormal. In this case, image reconstruction can be directly performed on the original scan data to obtain a reconstructed magnetic resonance image. If at least one difference is greater than the preset threshold, it indicates that the data attributes of the scan data corresponding to that difference are abnormal, thus confirming that the data attributes corresponding to the difference are abnormal.
[0101] It should be noted that the difference refers to the difference between adjacent scan data. If this difference is greater than a preset threshold, it is impossible to determine which of the adjacent scan data is abnormal. In this case, the data attributes of the next adjacent scan data are checked to determine the data attribute with the abnormality. For example, if the data attribute of the current scan data is 30 and the data attribute of the previous scan data is 20, there is a jump between the two. Then, the data attribute of the next scan data can be obtained. If the data attribute of the next scan data is 22, then it is determined that the data attribute of the current scan data is abnormal.
[0102] In the image reconstruction method described above, the difference between each data attribute of the original scan data and its adjacent data attributes is obtained. If any difference is greater than a preset threshold, the data attribute corresponding to the difference is determined to be abnormal. By comparing the differences between adjacent data attributes with the preset threshold, this method can accurately filter out data attributes with large differences from the original scan data, thereby accurately determining whether there are any abnormalities in the data attributes.
[0103] In scientific research settings, magnetic resonance imaging (MRI) devices generate enormous amounts of scan data during long-duration or advanced sequence scans, typically reaching tens or even hundreds of gigabytes (GB). Furthermore, the original scan data in this application is complete scan data, which is even larger in volume. Such large amounts of scan data are easily limited by computer hardware resources during reading and parsing. To address this issue, embodiments of this application can split and store the scan data, thus facilitating the reading and parsing of the scan data during subsequent image reconstruction.
[0104] In one embodiment, such as Figure 8 As shown, the process of splitting storage includes the following:
[0105] S701, based on the data dimensions of the original scan data after data attribute correction, predicts the total storage space of the original scan data after data attribute correction.
[0106] In this embodiment of the application, the computer device can obtain the variable types of the original scan data after data attribute correction, and estimate the total storage space required for the original scan data after data attribute correction based on the data dimensions and variable types of the original scan data after data attribute correction.
[0107] S702 splits the original scan data after data attribute correction based on the total storage space and splitting rules.
[0108] The dimensions for splitting the target scan data can be the average number of scans, the number of scan layers, and other data dimensions.
[0109] In this embodiment, the computer device can split the original scan data after data attribute correction according to the splitting dimension of the average number of scans, and determine the storage space under the average splitting dimension. Furthermore, the computer device can also split the original scan data after data attribute correction according to the splitting dimension of the scan layer, and determine the storage space under the scan layer splitting dimension. The storage space under the average splitting dimension is compared with the storage space under the scan layer splitting dimension, and the splitting result of the splitting dimension with the smaller storage space is taken as the splitting result of the original scan data after data attribute correction.
[0110] S703 stores the split scan data into the scan database.
[0111] In this embodiment of the application, if the total storage space is less than the storage space of the computer device, the computer device can store the split scan data into the corresponding scan database of the computer device.
[0112] In the image reconstruction method described above, the total storage space of the original scan data after data attribute correction is predicted based on the data dimensions of the original scan data; the original scan data after data attribute correction is then split according to the total storage space and splitting rules; and the split scan data is stored in the scan database. This method splits the original scan data after data attribute correction by data splitting, which facilitates the storage of large amounts of data.
[0113] After the original scan data with corrected data attributes is stored, the subsequent image reconstruction process can be performed. In one embodiment, the specific process of image reconstruction based on the original scan data with corrected data attributes is described, and this specific process may include the following steps:
[0114] The original scan data with corrected data attributes is obtained from the scan database, and the image is reconstructed based on the original scan data with corrected data attributes.
[0115] In this embodiment, after the original scan data with corrected data attributes is split and saved in the scan database, when image reconstruction is required, the computer device can obtain the original scan data with corrected data attributes from the scan database and preprocess it (e.g., noise reduction, filtering, etc.) to reduce signal noise caused by system factors. Then, the preprocessed scan data is reconstructed using a corresponding image reconstruction algorithm to obtain the reconstructed image.
[0116] Furthermore, computer devices can also write reconstructed images into Digital Imaging and Communications in Medicine (DICOM) images.
[0117] In the image reconstruction method described above, the original scan data after data attribute correction is obtained from the scan database, and image reconstruction is performed based on the original scan data after data attribute correction. Since the original scan data after data attribute correction is stored in a split manner, the reading and parsing process of this scan data is more convenient, thus facilitating the image reconstruction process.
[0118] As a specific embodiment of this application, processes such as abnormal data attribute correction and image reconstruction both belong to the image reconstruction process, which will be described in detail below. In one embodiment, such as Figure 9 As shown, image reconstruction methods include:
[0119] S801, obtain the scanning protocol parameters and data acquisition method of the original scan data acquired by the magnetic resonance imaging (MRI) device; the original scan data is the complete scan data acquired by the MRI device with abnormal data attributes;
[0120] S802, determine the dimensional information of the raw scan data from the scan protocol parameters;
[0121] S803 divides the original scan data according to the dimensional information to obtain multi-dimensional scan data;
[0122] S804: For scanned data of any dimension, obtain the adjacent data attributes of abnormal attributes in the scanned data;
[0123] S805, determine the predicted attribute corresponding to the abnormal attribute based on the adjacent data attributes;
[0124] S806, replaces anomalous attributes in scanned data with predicted attributes;
[0125] S807, based on the data dimensions of the original scan data after data attribute correction, predict the total storage space of the original scan data after data attribute correction;
[0126] S808 splits the original scan data after data attribute correction based on the total storage space and splitting rules;
[0127] S809 stores the split scan data into the scan database;
[0128] S810 retrieves the original scan data after data attribute correction from the scan database and performs image reconstruction based on the original scan data after data attribute correction.
[0129] Figure 10 The diagram below illustrates the process of an image reconstruction method, which includes: S901, acquiring scan data collected by a magnetic resonance imaging (MRI) device; S902, determining whether there are any abnormalities in the data attributes of the scan data; if there are abnormalities, proceeding to step S903; if there are no abnormalities, proceeding to step S904; S903: correcting the abnormal data attributes to obtain scan data without abnormalities; S904: splitting the scan data without abnormalities and saving it to a scan database; S905: reading the corrected original scan data from the scan database and performing image reconstruction based on the corrected original scan data.
[0130] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0131] Based on the same inventive concept, this application also provides a magnetic resonance imaging system, which includes a magnetic resonance device and a computer device, wherein the magnetic resonance device is connected to the computer device;
[0132] Magnetic resonance imaging (MRI) equipment is used to acquire data from the scanned object and send the acquired data to a computer.
[0133] Computer equipment is used to acquire complete raw scan data with abnormal data attributes from raw data, and to correct the abnormal data attributes in the raw scan data according to the scanning protocol parameters and data acquisition method of the raw scan data; and to reconstruct the image based on the raw scan data after data attribute correction.
[0134] Among these, the magnetic resonance equipment can be an animal magnetic resonance imaging (MRI) device, primarily used for MRI scans of animals. Alternatively, the MRI device can also be a high-magnetic-field MRI device, for example, the magnetic field strength of which can be 7 Tesla (T), 9.4T, 11T, etc. Or, the MRI device can also be a preclinical research MRI device.
[0135] The aforementioned magnetic resonance imaging (MRI) system includes an MRI scanner and a computer, with the MRI scanner connected to the computer. The MRI scanner acquires data from the scanned object and sends the acquired raw data to the computer. The computer retrieves complete raw scan data with anomalous data attributes from the raw data and corrects the anomalous data attributes based on the scanning protocol parameters and data acquisition method of the raw scan data. Image reconstruction is then performed based on the corrected raw scan data. In this MRI system, the computer can filter out complete raw scan data with anomalous data attributes from the raw data acquired by the MRI scanner. By acquiring the scanning protocol parameters and data acquisition method during the acquisition process, it can accurately correct the anomalous data attributes of this raw scan data. The corrected data attributes are correct, and the scan data is complete, thus preventing image reconstruction failure.
[0136] Based on the same inventive concept, this application also provides an image reconstruction apparatus for implementing the image reconstruction method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more image reconstruction apparatus embodiments provided below can be found in the limitations of the image reconstruction method described above, and will not be repeated here.
[0137] In one exemplary embodiment, such as Figure 11 As shown, an image reconstruction apparatus is provided, comprising: an acquisition module 11, a correction module 12, and a reconstruction module 13, wherein:
[0138] The acquisition module 11 is used to acquire the scanning protocol parameters and data acquisition method of the original scan data acquired by the magnetic resonance imaging device; the original scan data is the complete scan data acquired by the magnetic resonance imaging device with abnormal data attributes;
[0139] Correction module 12 is used to correct abnormal data attributes in the original scan data based on scan protocol parameters and data acquisition method;
[0140] The reconstruction module 13 is used to reconstruct the image based on the original scan data after data attribute correction.
[0141] In one embodiment, the above-mentioned correction module includes: a division unit and a correction unit, wherein:
[0142] The partitioning unit is used to divide the raw scan data into multi-dimensional scan data based on the scan protocol parameters;
[0143] The multidimensional scan data includes at least one of the following dimensions: layer number dimension, phase encoding dimension, frequency encoding dimension, layer selection dimension, and cardiac phase encoding dimension.
[0144] The correction unit is used to correct abnormal attributes in the scanned data of each dimension according to the data acquisition method.
[0145] In one embodiment, the aforementioned partitioning unit is further configured to determine the dimensional information of the original scan data from the scan protocol parameters; and to partition the original scan data according to the dimensional information to obtain multi-dimensional scan data.
[0146] In one embodiment, the correction unit is further configured to, for any dimension of scan data, obtain adjacent data attributes of the abnormal attribute in the scan data; determine the predicted attribute corresponding to the abnormal attribute based on the adjacent data attributes; and replace the abnormal attribute in the scan data with the predicted attribute.
[0147] In one embodiment, the image reconstruction apparatus further includes: a difference acquisition module and an anomaly detection module, wherein:
[0148] The difference acquisition module is used to acquire the difference between each data attribute and its adjacent data attributes in the original scan data.
[0149] The anomaly detection module is used to determine that the data attribute corresponding to any difference is abnormal if any difference is greater than a preset threshold.
[0150] In one embodiment, the image reconstruction apparatus further includes: a prediction module, a segmentation module, and a storage module, wherein:
[0151] The prediction module is used to predict the total storage space of the original scan data after data attribute correction based on the data dimensions of the original scan data after data attribute correction.
[0152] The splitting module is used to split the original scanned data after data attribute correction based on the total storage space and splitting rules;
[0153] The storage module is used to store the split scan data into the scan database.
[0154] In one embodiment, the reconstruction module 13 includes: a reconstruction unit, wherein:
[0155] The reconstruction unit is used to obtain the original scan data after data attribute correction from the scan database and to reconstruct the image based on the original scan data after data attribute correction.
[0156] Each module in the aforementioned image reconstruction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.
[0157] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the content of any of the embodiments of the above-described image reconstruction methods.
[0158] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the content of any of the embodiments of the above-described image reconstruction methods.
[0159] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the content of any one of the embodiments of the image reconstruction method described above.
[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0163] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. An image reconstruction method, characterized in that, The method includes: The scanning protocol parameters and data acquisition method for acquiring raw scan data from the magnetic resonance imaging (MRI) device are obtained; the raw scan data is complete scan data acquired by the MRI device that has abnormal data attributes. Based on the scanning protocol parameters and data acquisition method, abnormal data attributes in the original scanning data are corrected; Image reconstruction is performed based on the original scan data after data attribute correction.
2. The method according to claim 1, characterized in that, The process of correcting abnormal data attributes in the original scan data based on scan protocol parameters and data acquisition methods includes: Based on the scanning protocol parameters, the original scanning data is divided into multi-dimensional scanning data; Based on the data acquisition method described above, abnormal attributes in the scanned data of each dimension are corrected.
3. The method according to claim 2, characterized in that, The process of dividing the original scan data into multi-dimensional scan data based on the scan protocol parameters includes: The dimensional information of the original scan data is determined from the scan protocol parameters; The original scan data is divided according to the dimensional information to obtain the multi-dimensional scan data.
4. The method according to claim 2, characterized in that, The step of correcting abnormal attributes in the scanned data for each dimension, based on the data acquisition method, includes: For any dimension of scanned data, obtain the adjacent data attributes of the abnormal attributes in the scanned data; Based on the adjacent data attributes, determine the predicted attribute corresponding to the abnormal attribute; The predicted attributes are used to replace the abnormal attributes in the scanned data.
5. The method according to any one of claims 2-4, characterized in that, The multidimensional scan data includes at least one of the following dimensions: layer number dimension, phase encoding dimension, frequency encoding dimension, layer selection dimension, and cardiac phase encoding dimension.
6. The method according to any one of claims 1-4, characterized in that, The method further includes: Obtain the difference between each data attribute and its adjacent data attributes in the original scan data; If any difference is greater than a preset threshold, it is determined that the data attribute corresponding to the difference is abnormal.
7. The method according to any one of claims 1-4, characterized in that, The method further includes: Based on the data dimensions of the original scan data after data attribute correction, predict the total storage space of the original scan data after data attribute correction. Based on the total storage space and the splitting rules, the original scan data after the data attributes were corrected is split; The split scan data is stored in the scan database.
8. The method according to claim 7, characterized in that, The image reconstruction based on the original scan data after data attribute correction includes: The original scan data after data attribute correction is obtained from the scan database, and image reconstruction is performed based on the original scan data after data attribute correction.
9. An image reconstruction apparatus, characterized in that, The device includes: The acquisition module is used to acquire the scanning protocol parameters and data acquisition method of the original scan data collected by the magnetic resonance imaging device; the original scan data is the complete scan data collected by the magnetic resonance imaging device that has abnormal data attributes; The correction module is used to correct abnormal data attributes in the original scan data based on the scan protocol parameters and data acquisition method. The reconstruction module is used to reconstruct images based on the original scan data after data attribute correction.
10. A magnetic resonance imaging system, characterized in that, The magnetic resonance imaging system includes a magnetic resonance device and a computer device, wherein the magnetic resonance device is connected to the computer device; The magnetic resonance imaging device is used to acquire data from the scanned object and send the acquired data to the computer device. The computer device is used to acquire complete raw scan data with abnormal data attributes from the raw data, and correct the abnormal data attributes in the raw scan data according to the scanning protocol parameters and data acquisition method of the raw scan data; and perform image reconstruction based on the raw scan data after data attribute correction.