Medical image processing method and device, computer device and storage medium

Abstract

The application relates to a medical image processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a scanning image of an imaging area and a corresponding emission field map of the imaging area, calculating an emission field factor according to the emission field map, determining a correction factor according to the imaging sequence parameters corresponding to the scanning image and the emission field factor, and finally correcting the scanning image of the imaging area according to the correction factor. The above method fully considers the source and derivation process of the signal, and only according to the signal distribution of the scanning image and the emission field map, the corresponding data processing method can be used to overcome the problem of poor quality of the scanning image caused by the unevenness of the emission field. Moreover, when the unevenness of the scanning image caused by the unevenness of the emission field is removed, the natural contrast of the scanning image is retained, the imaging error caused by the unevenness of the scanning image is avoided, and accurate image uniformity correction can be realized.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, apparatus, computer device, and storage medium for processing medical images. Background Technology

[0002] The core components of a magnetic resonance imaging (MRI) system include: a magnet, gradient coils, radio frequency (RF) transmit coils, RF receive coils, and a signal processing and reconstruction unit. The RF transmit coils are used to excite specific nuclei of the object being imaged, such as... 1 H, 23 Na, 31 P, 13 C, etc., combines specific parameter combinations with the physical properties of the imaged material itself, and after a certain time evolution, obtains a signal with special contrast. The signal is received by the radio frequency receiving coil, and the signal processing and reconstruction unit completes the signal processing, finally obtaining an image or spectrum signal that can guide clinical applications.

[0003] However, in the actual radio frequency excitation stage, the uniformity of the corresponding region's excitation has a significant impact on the uniformity of the final overall image or spectrum. If the excitation uniformity deviates too much from the theoretical target, it will largely lead to varying degrees of amplitude modulation in different spatial locations of the final image or spectrum, affecting the overall imaging quality. Currently, in schemes for correcting transmission field inhomogeneity, after acquiring the image, conventional image processing algorithms are directly used to perform post-processing based on the image's own grayscale distribution to achieve uniformity correction, without directly addressing the uniformity from the coil's own transmission field distribution. However, in reality, MRI medical images inherently possess natural contrast due to differences in proton density among tissue components, exhibiting characteristics of varying signal control distributions in the image. Directly applying algorithmic uniformity processing to the image may weaken these natural differences, leading to grayscale errors and reducing the quality of the acquired image. Summary of the Invention

[0004] Therefore, it is necessary to provide a medical image processing method, apparatus, computer equipment, and storage medium that can effectively solve the problem of image non-uniformity caused by non-uniformity of the excitation region, thereby improving the quality of the imaging image.

[0005] Firstly, a method for processing medical images, the method comprising:

[0006] Acquire a scanned image of the imaging region and a corresponding emission field map of the imaging region;

[0007] The launch field factor is calculated based on the launch field diagram.

[0008] The correction factor is determined based on the imaging sequence parameters corresponding to the scanned image and the emission field factor;

[0009] The image of the imaging region is corrected according to the correction factor.

[0010] In one embodiment, the emission field map is a low-resolution image, and after obtaining the emission field map corresponding to the imaging region, the method further includes:

[0011] A high-resolution emission field map is obtained from the low-resolution image using an interpolation algorithm;

[0012] The calculation of the launch field factor based on the launch field map includes:

[0013] The launch field factor is calculated based on the high-resolution launch field map.

[0014] In one embodiment,

[0015] At least a portion of the transmission field map is a high signal-to-noise ratio region, and the transmission field factor calculated based on the transmission field map includes:

[0016] The emission field map is input into the correction model to obtain the corrected emission field map; the emission field factor is determined based on the corrected emission field map.

[0017] In one embodiment, determining the correction factor based on the imaging sequence parameters corresponding to the scanned image and the emission field factor includes:

[0018] According to the Bloch equation derivation rules, the theoretical signal distribution intensity without considering the emission field effect is determined based on the imaging sequence parameters corresponding to the scanned image.

[0019] According to the Bloch equation derivation rules, the theoretical signal distribution intensity under the emission field effect is determined based on the imaging sequence parameters corresponding to the scanned image and the emission field factor.

[0020] The ratio of the theoretical signal distribution intensity without considering the transmission field effect to the theoretical signal distribution intensity considering the transmission field effect is determined as the correction factor.

[0021] In one embodiment, the emission field map is obtained by reconstructing signals acquired after applying a double flip-angle sequence or a DREAM sequence to the imaging region.

[0022] In one embodiment, the launch site map is a two-dimensional launch site map or a three-dimensional launch site map.

[0023] In one embodiment, correcting the imaging region image according to the correction factor includes:

[0024] The corrected imaging region image is obtained by multiplying each pixel value of the imaging region image with the correction factor.

[0025] In one embodiment, the imaging sequence parameters corresponding to the scanned image include the type of radio frequency pulse and / or the flip angle of the radio frequency pulse.

[0026] Secondly, a medical image processing apparatus, the apparatus comprising:

[0027] The acquisition module is used to acquire a scanned image of the imaging region and a corresponding emission field map of the imaging region;

[0028] The calculation module is used to calculate the launch field factor based on the launch field diagram;

[0029] The determination module is used to determine the correction factor based on the imaging sequence parameters corresponding to the scanned image and the emission field factor;

[0030] A correction module is used to correct the image of the imaging region according to the correction factor.

[0031] Thirdly, a computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the method described in the first aspect.

[0032] Fourthly, a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0033] The aforementioned medical image processing method, apparatus, computer equipment, and storage medium acquire a scanned image of the imaging region and a corresponding emission field map of the imaging region. They then calculate the emission field factor based on the emission field map, determine a correction factor based on the imaging sequence parameters corresponding to the scanned image and the emission field factor, and finally correct the scanned image of the imaging region based on the correction factor. This method fully considers the source and evolution of the signal. By using appropriate data processing methods based solely on the signal distribution of the scanned image and the emission field map, it can overcome the problem of image quality degradation caused by emission field inhomogeneity. Furthermore, when removing signal inhomogeneity in the scanned image caused by emission field inhomogeneity, this method optimizes the physical values ​​of the excitation source, better preserving the natural contrast of the scanned image. Compared to traditional methods that remove emission field inhomogeneity through image homogenization algorithms, this method avoids imaging errors and achieves accurate image uniformity correction. Attached Figure Description

[0034] Figure 1 This is an application environment diagram of a medical image processing method in one embodiment;

[0035] Figure 2 This is a flowchart illustrating a medical image processing method in one embodiment;

[0036] Figure 3 for Figure 2 A flowchart illustrating one implementation of S103 in the embodiment;

[0037] Figure 4 This is a schematic diagram of a 2D GRE sequence in one embodiment;

[0038] Figure 5A This is a flowchart illustrating a medical image processing method in one embodiment;

[0039] Figure 5B This is a schematic diagram of the process for determining a launch site map based on a scanned image in one embodiment;

[0040] Figure 6 This is a flowchart illustrating a medical image processing method in one embodiment;

[0041] Figure 7 This is a schematic diagram of the structure of a medical image processing device in one embodiment;

[0042] Figure 8 This is a schematic diagram of the structure of a medical image processing device in one embodiment;

[0043] Figure 9 This is a schematic diagram of the structure of a medical image processing device in one embodiment;

[0044] Figure 10 This is a schematic diagram of the structure of a medical image processing device in one embodiment;

[0045] Figure 11 This is a schematic diagram of the structure of a medical image processing device in one embodiment;

[0046] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0047] 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.

[0048] The medical image processing method provided in this application can be applied to, for example... Figure 1In the application environment shown, imaging device 102 is connected to terminal 104 via a network. Imaging device 102 scans objects within the imaging area and transmits the scan data and related signals of the imaging process to terminal 104. Terminal 104 then performs imaging processing on the imaging area based on the scan data and related signals to obtain an image. Imaging device 102 can be various types of imaging devices, such as magnetic resonance imaging (MRI) devices. Terminal 104 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.

[0049] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is merely a block diagram of a partial structure related to the solution of this application, and does not constitute a limitation on the application environment to which the solution of this application is applied. The specific application environment may include more or fewer components than shown in the figure, or a combination of certain components, or different component arrangements.

[0050] In one embodiment, such as Figure 2 As shown, a method for processing medical images is provided, which can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps:

[0051] S101, acquire the scanned image of the imaging area and the emission field map corresponding to the imaging area.

[0052] The scanned image of the imaging region is the initial image obtained after the imaging device scans and images the object to be imaged within the imaging region. For example, after using an MRI scanner to scan and image human tissues and organs, an MRI image of that tissue or organ can be obtained. The scanned image can be a two-dimensional image or a three-dimensional image; this is not limited here. The emission field map corresponding to the imaging region is obtained by reconstructing the emission field map from signals acquired after applying a corresponding test sequence to the imaging region. Optionally, the emission field map is obtained by reconstructing signals acquired after applying a double flip-angle sequence or a double refocusing echo acquisition (DREAM) sequence to the imaging region. The emission field map can be a two-dimensional emission field map or a three-dimensional emission field map; this is not limited here.

[0053] In this embodiment, an imaging device, such as a nuclear magnetic resonance imaging device, can be used to scan the object to be imaged in the imaging area to obtain the scanning data of the imaging area and the signal corresponding to the test sequence of the emission field, such as the signal corresponding to the conventional double flip angle sequence or DREAM sequence. Then, the scanning data and the signal corresponding to the test sequence are transmitted to the terminal. The terminal performs image reconstruction based on the scanning data to obtain the scanned image of the imaging area. At the same time, it performs image reconstruction based on the signal corresponding to the test sequence to obtain the emission field map of the imaging area.

[0054] In one embodiment, the scanned image of the imaging region and / or the emission field map corresponding to the imaging region employs a double flip-angle sequence. This double flip-angle sequence includes a first RF pulse and a second RF pulse following the first RF pulse. The flip angle of the first RF pulse is θ, and the flip angle of the second RF pulse is 2θ, where θ = γB1T, B1 is the intensity of the RF field, and T represents the duration of the first RF pulse. The magnetic resonance signal of the detected object after applying the first RF pulse can be expressed as Mxy(θ), and the magnetic resonance signal of the detected object after applying the second RF pulse can be expressed as Mxy(2θ). Therefore, θ can be approximately expressed as:

[0055] θ=arccos(Mxy(2θ) / 2 Mxy(θ))

[0056] The intensity at each location in the RF field can be determined using the above formula.

[0057] In one embodiment, the transmit field pattern can also be achieved by employing a stimulated echo (STEAM) sequence comprising three radio frequency pulses, the three radio frequency pulses corresponding to flip angles of respectively... , , And satisfy The intensity of spin echo and stimulus echo signals within the imaging region of the detected object can be expressed as follows:

[0058]

[0059] in, T1 represents the longitudinal magnetization, T2 is the longitudinal relaxation time of the hydrogen proton, and τ1 and τ2 are the time intervals between the radio frequency pulse and the acquisition window. This is combined with the spin echo signal intensity S... SE and stimulus echo signal intensity S STE The flip angle can then be determined, thereby determining the emission field map corresponding to the imaging area.

[0060] S102, the launch field factor is calculated based on the launch field map.

[0061] When the terminal acquires the emission field map corresponding to the imaging area, such as the B1 emission field map, the emission field factor can be calculated based on the signal distribution intensity of the emission field map. In one application, the emission field map can be input into a correction model to obtain a corrected emission field map; the emission field factor is then determined based on the corrected emission field map. In this embodiment, the emission field factor represents the intensity of the RF field formed by an RF pulse sensed at any location in space.

[0062] S103, determine the correction factor based on the imaging sequence parameters and emission field factor corresponding to the scanned image.

[0063] The imaging sequence parameters corresponding to the scanned image include the type of radio frequency (RF) pulse and / or the flip angle of the RF pulse. When the terminal obtains the type of RF pulse and the emission field factor, it can further simulate the signal evolution process corresponding to that type of RF pulse using the Bloch evolution rule. Combined with the emission field factor under the influence of actual emission field inhomogeneity, a correction factor can be calculated to optimize the uniformity of spatial signal distribution and the uniformity of pixel value distribution in the scanned image of the imaging area. When the terminal obtains the flip angle and emission field factor of the RF pulse, it can further substitute these parameters into the Bloch equation representing the Bloch evolution rule to calculate the signal distribution intensity, and then calculate the correction factor based on the signal distribution intensity.

[0064] S104, corrects the scanned image of the imaging area according to the correction factor.

[0065] When the terminal needs to correct the scanned image of the imaging area, it can correct the gray value or pixel value of each pixel in the scanned image of the imaging area according to the correction factor, so that the gray value or pixel value of each pixel in the corrected scanned image can be basically consistent with the gray value or pixel value of each pixel in the scanned image after imaging without the influence of emission field inhomogeneity, so as to remove the non-uniformity of pixel value or gray value of each pixel in the scanned image caused by emission field inhomogeneity.

[0066] In the aforementioned medical image processing method, a scanned image of the imaging region and the corresponding emission field map are acquired. An emission field factor is calculated based on the emission field map, and a correction factor is determined based on the imaging sequence parameters and emission field factor of the scanned image. Finally, the scanned image of the imaging region is corrected using the correction factor. This method fully considers the source and evolution of the signal. By using appropriate data processing methods based solely on the signal distribution of the scanned image and the emission field map, it can overcome the quality degradation of the scanned image caused by emission field inhomogeneity. Moreover, when removing signal inhomogeneity in the scanned image caused by emission field inhomogeneity, this method optimizes the physical values ​​of the excitation source, better preserving the natural contrast of the scanned image. Compared to traditional methods that remove emission field inhomogeneity through image homogenization algorithms, this method avoids imaging errors and achieves accurate image uniformity correction.

[0067] In one embodiment, one implementation of S103 above is provided, such as... Figure 3 As shown, the above-mentioned S103 "determines the correction factor based on the imaging sequence parameters and emission field factor corresponding to the scanned image" includes:

[0068] S201, according to the Bloch equation evolution rule, the theoretical signal distribution intensity without considering the emission field effect is determined based on the imaging sequence parameters corresponding to the scanned image.

[0069] The Bloch equation derivation rules can be expressed using the Bloch equation, and different types of radio frequency pulses correspond to different Bloch derivation results. The theoretical signal distribution intensity refers to the regional signal intensity distribution calculated using the Bloch equation under the corresponding sequence parameters and an ideal transmit-receive field.

[0070] In this embodiment, when the terminal obtains the imaging sequence parameters corresponding to the scanned image, it directly analyzes the imaging sequence parameters according to the Bloch equation evolution rules to obtain the theoretical signal distribution intensity corresponding to the actual transmission field without considering the transmission field effect. In practical applications, the imaging sequence parameters are directly substituted into the Bloch equation as calculation parameters to calculate the signal intensity, which is the theoretical signal distribution intensity without considering the transmission field effect.

[0071] S202, according to the Bloch equation evolution rule, based on the imaging sequence parameters and emission field factor corresponding to the scanned image, the theoretical signal distribution intensity considering the emission field effect is determined.

[0072] The theoretical signal distribution intensity under the transmission field effect refers to the distribution intensity of the signal partition corresponding to the actual transmission field after signal modulation, calculated using the Bloch equation relative to the actual imaging sequence parameters and the actual imaging sequence parameters after being modulated by the transmission field factor.

[0073] In this embodiment, when the terminal obtains the imaging sequence parameters and emission field factor corresponding to the scanned image, it directly analyzes the imaging sequence parameters and emission field factor according to the Bloch equation evolution rules to obtain the theoretical signal distribution intensity under the emission field effect. In practical applications, the imaging sequence parameters and emission field factor are directly substituted into the Bloch equation as calculation parameters for calculation, and the obtained signal intensity is the theoretical signal distribution intensity under the emission field effect.

[0074] S203, the ratio of the theoretical signal distribution intensity without considering the transmission field effect to the theoretical signal distribution intensity considering the transmission field effect is determined as the correction factor.

[0075] When the terminal calculates the theoretical signal distribution strength without considering the transmission field and the theoretical signal distribution strength with considering the transmission field, it can perform a ratio calculation on the two signal strength values ​​and determine the final ratio as the correction factor.

[0076] The method described in S201-S203 is illustrated by way of example. Figure 4Taking the 2D GRE sequence as an example, if the transmission field (B1 field) is ideal, the signal will generate a transverse magnetization vector after RF excitation. And the transverse magnetization vector It can be obtained through the following relation (1):

[0077] (1);

[0078] In the above formula, This indicates that a transverse magnetization vector will be generated after the signal is excited by RF. Represents the quantum density distribution matrix of a volumetric space; This indicates the RF excitation flip angle.

[0079] After a period of time of After attenuation, based on the Bloch equation derivation rules, the theoretical signal distribution intensity corresponding to this sequence, without considering the emission field effect, can be expressed by the relationship (2):

[0080] (2);

[0081] In the above formula, This represents the theoretical signal distribution intensity without considering the transmission field effect; Indicates duration; This represents the pixel spatial distribution matrix.

[0082] When considering the influence of non-uniformity in the actual launch field, the flip angle of different space voxels... Will be affected by launch field factor Modulation, becoming the corresponding Therefore, based on the Bloch equation derivation rules, the theoretical signal distribution intensity corresponding to this sequence can be expressed by the relation (3):

[0083] (3);

[0084] In the above formula, This represents the theoretical signal distribution intensity considering the transmission field effect.

[0085] The theoretical signal distribution intensity after adjustment by the actual launch site is obtained. Theoretical signal distribution intensity that is not adjusted by the transmission field Then, the ratio can be calculated to obtain the correction factor. For example, the correction factor can be determined by the following relationship (4):

[0086] (4);

[0087] In the above formula, This represents the correction factor.

[0088] In practical applications, non-uniformity of the transmission field only affects the signal strength generated during radio frequency transmission and has no additional impact on spatial coding. Therefore, for spatially coded signals, after Fourier transform and conversion into corresponding spatial pixel signals, the signal strength at the corresponding spatial position is adjusted according to the transmission field factor and the radio frequency type and flip angle in the corresponding sequence time, which can improve the data uniformity problem caused by non-uniformity of the transmission field. Based on this idea, the spatial excitation non-uniformity caused by non-uniformity of the transmission field can be eliminated by using the Bloch equation derivation rule to calculate the correction factor according to the relationship (4) between the theoretical signal distribution intensity without considering the transmission field distribution and the theoretical signal distribution intensity considering the transmission field distribution. Then, the correction factor is used to perform reverse compensation adjustment on the gray values ​​of each pixel in the obtained actual imaging image, which can eliminate the influence of non-uniformity of the B1 transmission field.

[0089] In practical applications, the emission field map in S101 above is usually a low-resolution image acquired in a short, fast sequence. Based on this, Figure 2 The method described in this embodiment further includes the step of: obtaining a high-resolution emission field map from the low-resolution image using an interpolation algorithm, and then calculating the emission field factor based on the high-resolution emission field map. Optionally, the terminal can also pre-train a conversion network based on the low-resolution emission field map, enabling the conversion network to convert the low-resolution emission field map into a high-resolution emission field map. In practical applications, the trained conversion network is directly used to convert the acquired emission field map to obtain the corresponding high-resolution emission field map. It should be noted that, in this embodiment, a low-resolution image refers to an image whose resolution is less than a first preset threshold, and a high-resolution image refers to an image whose resolution is greater than or equal to a second preset threshold; that is, a low-resolution image has a relatively low resolution compared to a high-resolution image.

[0090] In one embodiment, the launch field map can also be obtained from a neural network model. This neural network model is obtained by training the neural network with multiple pairs of prior scan images and prior B1 launch field maps, such as... Figure 5B As shown, during the training phase, the input of the neural network model includes a low-resolution water film positioning image / initial scan image, and the output of the neural network model is the B1 emission field map (B1 field map) of the RF field corresponding to the aforementioned water film positioning image / initial scan image. By continuously optimizing the parameters of the neural network, the neural network model can be obtained.

[0091] During the usage phase, only the scanned image of the imaging area can be acquired. This scanned image can be a rapid localization image, a pre-scanned image, etc. Inputting it into a neural network model yields the emission field map corresponding to the imaging area. In this embodiment, it is unnecessary to use a test sequence to detect the emission field map corresponding to the imaging area, which reduces the absorption of radio frequency energy by the object being detected, saves scanning time, and improves scanning efficiency.

[0092] In practical applications, the emission field map in S101 above represents a high signal-to-noise ratio (SNR) region. Therefore, the emission field factor in the low SNR region near the high SNR region may not be accurate, requiring correction of the emission field map. For example, the emission field map can be input into a correction model to obtain a corrected emission field map; the emission field factor can then be determined based on the corrected emission field map. The emission field map is affected by the different proton density distribution and tissue structure within the detected object. In regions with low proton density (e.g., bone or lung regions), the emission field map corresponds to a low SNR, i.e., a low SNR region; while in regions with high proton density, the emission field map corresponds to a high SNR, i.e., a high SNR region. Optionally, low SNR regions are often located around or near high SNR regions. Theoretically, the radio frequency field intensity experienced by the two regions is approximately the same, i.e., the emission field factors of the two regions are the same or approximately the same. Optionally, the correction model can be a correction network obtained based on machine learning methods, or a mathematical model obtained using a fitting algorithm.

[0093] In one embodiment, one implementation of S102 above is provided, such as... Figure 5A As shown, the method includes:

[0094] S301, the first launch field factor is calculated based on the high signal-to-noise ratio (SNR) regions in the launch field map. Of course, low SNR regions also exist in the launch field map, and these low SNR regions are located around the high SNR regions.

[0095] The first transmission field factor is calculated based on the high signal-to-noise ratio region of the transmission field map. When the terminal acquires the transmission field map corresponding to the imaging area, the first transmission field factor can be calculated based on the signal distribution intensity of the transmission field map.

[0096] S302, input the emission field map into the correction model to obtain the corrected emission field map, and determine the second emission field factor of the low signal-to-noise ratio region based on the corrected emission field map.

[0097] The second emission field factor is the emission field factor corrected for the low signal-to-noise ratio (SNR) region image. In this embodiment, the terminal can pre-train a correction network based on the emission field map using machine learning methods. This correction network can obtain a corrected emission field map based on the input emission field map, and the pixels in the low SNR region of the corrected emission field map are corrected and are equal to or able to connect with the pixels in the high SNR region of the emission field map.

[0098] It should be noted that this embodiment does not impose specific restrictions on the method of obtaining the second emission field factor in the low signal-to-noise ratio region. In other embodiments, it can also be obtained directly by interpolation: determine the low signal-to-noise ratio region in the emission field map, determine the first emission field factor corresponding to the pixels located around the low signal-to-noise ratio region and belonging to the high and low signal-to-noise ratio regions, and determine the second emission field factor by linear interpolation based on the first emission field factor corresponding to the pixels located around the low signal-to-noise ratio region and belonging to the high and low signal-to-noise ratio regions.

[0099] S303, determine the launch field factor based on the first launch field factor and the second launch field factor.

[0100] Once the terminal obtains the first and second transmission field factors, it can obtain the transmission field factors for all transmission fields. For low signal-to-noise ratio (SNR) regions in the transmission field map, the initial and second transmission field factors calculated from the transmission field map can be further averaged or weighted and summed, and the final result can be used as the transmission field factor for the low SNR region. Similarly, for all transmission fields, the average of the first and second transmission field factors can be used as the transmission field factor.

[0101] In one embodiment, when the computer device executes the above S104, it specifically performs the following: multiplying each pixel value of the scanned image of the imaging region with the correction factor to obtain the corrected imaging region image.

[0102] This embodiment relates to a specific method for using a correction factor to correct a scanned image of an imaging region. When the correction factor is calculated by the ratio of the theoretical signal distribution intensity to the actual signal distribution intensity, the pixel values ​​of the scanned image can be multiplied by the correction factor to obtain the corrected imaging region image. When the correction factor is calculated by the ratio of the actual signal distribution intensity to the theoretical signal distribution intensity, the pixel values ​​of the scanned image can be multiplied by the reciprocal of the correction factor to obtain the corrected imaging region image.

[0103] Based on all the above embodiments, a method for processing medical images is provided, such as... Figure 6 The method includes:

[0104] S401, acquire the scanned image of the imaging area.

[0105] S402 obtains the emission field map of the imaging region by reconstructing the signal acquired after applying a double flip angle sequence or a DREAM sequence to the imaging region.

[0106] S403, the launch field factor is calculated based on the launch field map.

[0107] S404, according to the Bloch equation evolution rule, determines the theoretical signal distribution intensity without considering the emission field effect based on the imaging sequence parameters corresponding to the scanned image.

[0108] S405, according to the Bloch equation evolution rule, the theoretical signal distribution intensity considering the emission field effect is determined based on the imaging sequence parameters and emission field factor corresponding to the scanned image.

[0109] S406, the ratio of the theoretical signal distribution intensity without considering the transmission field effect to the theoretical signal distribution intensity considering the transmission field effect is determined as the correction factor.

[0110] S407, multiply each pixel value of the imaging region image with the correction factor to obtain the corrected imaging region image.

[0111] In existing schemes for correcting high-field B1 emission field inhomogeneity (excitation inhomogeneity), after image acquisition, conventional image processing algorithms are directly used to post-process the image based on its own grayscale distribution to achieve uniformity correction, without directly addressing the uniformity from the coil's own emission field distribution. However, conventional image processing algorithms do not consider the signal source and evolution process; they only rely on the image's own signal distribution and use data processing algorithms to make the image approximate a more uniform overall distribution. In reality, MRI medical images inherently possess natural contrast due to differences in proton density and T1 or T2 properties of tissue components, exhibiting spatially varying signal distributions. Directly applying algorithmic uniformity processing to the image may weaken these natural differences, leading to errors. The medical image processing method provided in this embodiment is based on Bloch simulation signal evolution to obtain correction factors, achieving optimized spatial signal uniformity distribution correction while preserving as much of the original signal contrast as possible.

[0112] It should be understood that, although Figure 2-6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2-6 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0113] In one embodiment, such as Figure 7 As shown, a medical image processing apparatus is provided, comprising:

[0114] The acquisition module 11 is used to acquire the scanned image of the imaging area and the emission field map corresponding to the imaging area.

[0115] The calculation module 12 is used to calculate the launch field factor based on the launch field map.

[0116] The determination module 13 is used to determine the correction factor based on the imaging sequence parameters corresponding to the scanned image and the emission field factor.

[0117] The correction module 14 is used to correct the scanned image of the imaging area according to the correction factor.

[0118] In one embodiment, if the emission field map is a low-resolution image acquired via a short-time, fast sequence, such as... Figure 8 As shown, the above-mentioned device also includes:

[0119] Interpolation module 15 is used to obtain a high-resolution emission field map based on the low-resolution image using an interpolation algorithm;

[0120] Correspondingly, the aforementioned calculation module 12 is specifically used to calculate the launch field factor based on the high-resolution launch field map.

[0121] In one embodiment, such as Figure 9 As shown, if the transmission field map is a high signal-to-noise ratio transmission field map, then the above-mentioned calculation module 12 includes:

[0122] The calculation unit 121 is used to calculate the first transmission field factor based on the high signal-to-noise ratio region of the transmission field map. There is also a low signal-to-noise ratio region in the transmission field map, and the low signal-to-noise ratio region is located around the high signal-to-noise ratio region.

[0123] The correction unit 122 is used to input the emission field map into the correction model to obtain the corrected emission field map, and to determine the second emission field factor of the low signal-to-noise ratio region based on the corrected emission field map;

[0124] The factor determination unit 123 is used to determine the emission field factor based on the first emission field factor and the second emission field factor.

[0125] In one embodiment, such as Figure 10 As shown, the aforementioned determining module 13 includes:

[0126] The first determining unit 131 is used to determine the theoretical signal distribution intensity based on the imaging sequence parameters corresponding to the scanned image according to the Bloch derivation rule.

[0127] The second determining unit 132 is used to determine the actual signal distribution intensity based on the imaging sequence parameters corresponding to the scanned image and the emission field factor in accordance with the Bloch derivation rule.

[0128] The third determining unit 133 is used to determine the ratio of the theoretical signal distribution intensity to the actual signal distribution intensity as the correction factor.

[0129] In one embodiment, the emission field map is obtained by reconstructing signals acquired after applying a double flip-angle sequence or a DREAM sequence to the imaging region.

[0130] In one embodiment, the launch site map is a two-dimensional launch site map or a three-dimensional launch site map.

[0131] In one embodiment, such as Figure 11 As shown, the above-mentioned medical image processing apparatus further includes:

[0132] The calculation module 15 is used to perform interpolation calculations on the launch field map to obtain a high-resolution launch field map;

[0133] Correspondingly, the aforementioned calculation module 12 is specifically used to calculate the launch field factor based on the high-resolution launch field map.

[0134] In one embodiment, the correction module 14 is specifically used to multiply each pixel value of the imaging region image with the correction factor to obtain the corrected imaging region image.

[0135] In one embodiment, the imaging sequence parameters corresponding to the scanned image include the type of radio frequency pulse and / or the flip angle of the radio frequency pulse.

[0136] Specific limitations regarding the medical image processing device can be found in the limitations of the medical image processing method described above, and will not be repeated here. Each module in the aforementioned medical image processing 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 in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0137] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for processing medical images. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad located on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0138] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0139] In one 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 perform the following steps:

[0140] Acquire a scanned image of the imaging region and a corresponding emission field map of the imaging region;

[0141] The launch field factor is calculated based on the launch field diagram.

[0142] The correction factor is determined based on the imaging sequence parameters corresponding to the scanned image and the emission field factor;

[0143] The scanned image of the imaging region is corrected according to the correction factor.

[0144] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0145] A high-resolution emission field map is obtained from the low-resolution image using an interpolation algorithm;

[0146] The calculation of the launch field factor based on the launch field map includes:

[0147] The launch field factor is calculated based on the high-resolution launch field map.

[0148] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0149] The emission field map is input into the correction model to obtain the corrected emission field map; the emission field factor is determined based on the corrected emission field map.

[0150] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0151] According to the Bloch equation derivation rules, the theoretical signal distribution intensity without considering the emission field effect is determined based on the imaging sequence parameters corresponding to the scanned image.

[0152] According to the Bloch equation derivation rules, the theoretical signal distribution intensity under the emission field effect is determined based on the imaging sequence parameters corresponding to the scanned image and the emission field factor.

[0153] The ratio of the theoretical signal distribution intensity without considering the transmission field effect to the theoretical signal distribution intensity considering the transmission field effect is determined as the correction factor.

[0154] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0155] The corrected imaging region image is obtained by multiplying each pixel value of the imaging region image with the correction factor.

[0156] The computer device provided in the above embodiments has a similar implementation principle and technical effect to the above method embodiments, and will not be described again here.

[0157] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0158] Acquire a scanned image of the imaging region and a corresponding emission field map of the imaging region;

[0159] The launch field factor is calculated based on the launch field diagram.

[0160] The correction factor is determined based on the imaging sequence parameters corresponding to the scanned image and the emission field factor;

[0161] The scanned image of the imaging region is corrected according to the correction factor.

[0162] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0163] A high-resolution emission field map is obtained from the low-resolution image using an interpolation algorithm;

[0164] The calculation of the launch field factor based on the launch field map includes:

[0165] The launch field factor is calculated based on the high-resolution launch field map.

[0166] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0167] Based on the high signal-to-noise ratio region of the launch site map, the first launch site factor is calculated. There is also a low signal-to-noise ratio region in the launch site map, and the low signal-to-noise ratio region is located around the high signal-to-noise ratio region.

[0168] Input the emission field map into the correction model to obtain the corrected emission field map, and determine the second emission field factor of the low signal-to-noise ratio region based on the corrected emission field map;

[0169] The launch field factor is determined based on the first launch field factor and the second launch field factor.

[0170] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0171] According to the Bloch equation derivation rules, the theoretical signal distribution intensity without considering the emission field effect is determined based on the imaging sequence parameters corresponding to the scanned image.

[0172] According to the Bloch equation derivation rules, the theoretical signal distribution intensity under the emission field effect is determined based on the imaging sequence parameters corresponding to the scanned image and the emission field factor.

[0173] The ratio of the theoretical signal distribution intensity without considering the transmission field effect to the theoretical signal distribution intensity considering the transmission field effect is determined as the correction factor.

[0174] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0175] The corrected imaging region image is obtained by multiplying each pixel value of the imaging region image with the correction factor.

[0176] The computer-readable storage medium provided in the above embodiments has a similar implementation principle and technical effect to the above method embodiments, and will not be described again here.

[0177] 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, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0178] 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 specification.

[0179] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. 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 patent application should be determined by the appended claims.

Claims

1. A processing method of a medical image, characterized by, The method comprises: acquiring a scan image of an imaging region and a transmit field map corresponding to the imaging region; calculating a transmit field factor according to the transmit field map; determining, according to a Bloch equation derivation rule, a theoretical signal distribution intensity without considering a transmit field effect based on an imaging sequence parameter corresponding to the scan image; determining, according to the Bloch equation derivation rule, a theoretical signal distribution intensity considering the transmit field effect based on the imaging sequence parameter corresponding to the scan image and the transmit field factor; determining a correction factor as a ratio of the theoretical signal distribution intensity without considering the transmit field effect to the theoretical signal distribution intensity considering the transmit field effect; the imaging sequence parameter comprises a type of radio frequency pulse and / or a flip angle of the radio frequency pulse; correcting the scan image of the imaging region according to the correction factor.

2. The method of claim 1, wherein, The transmit field map is a low-resolution image, and after acquiring the transmit field map corresponding to the imaging region, the method further comprises: obtaining a high-resolution transmit field map from the low-resolution image through an interpolation algorithm; The calculating of the transmit field factor according to the transmit field map comprises: calculating the transmit field factor according to the high-resolution transmit field map.

3. The method of claim 1, wherein, At least part of the transmit field map is a high signal-to-noise ratio region, and the calculating of the transmit field factor according to the transmit field map comprises: inputting the transmit field map into a correction model to obtain a corrected transmit field map, and determining the transmit field factor according to the corrected transmit field map.

4. The method of claim 1, wherein, The transmit field map is obtained through signal reconstruction after a double flip angle sequence or a DREAM sequence is applied to the imaging region.

5. The method of claim 1, wherein, The transmit field map is a two-dimensional transmit field map or a three-dimensional transmit field map.

6. The method of claim 4, wherein, The correcting of the scan image of the imaging region according to the correction factor comprises: performing a product operation on each pixel value of the scan image of the imaging region and the correction factor to obtain a corrected scan image of the imaging region.

7. A medical image processing apparatus characterized by comprising: The device comprises: an acquisition module configured to acquire a scan image of an imaging region and a transmit field map corresponding to the imaging region; a calculation module configured to calculate a transmit field factor according to the transmit field map; a determination module configured to determine, according to a Bloch equation derivation rule, a theoretical signal distribution intensity without considering a transmit field effect based on an imaging sequence parameter corresponding to the scan image, and determine, according to the Bloch equation derivation rule, a theoretical signal distribution intensity considering the transmit field effect based on the imaging sequence parameter corresponding to the scan image and the transmit field factor, and determine a correction factor as a ratio of the theoretical signal distribution intensity without considering the transmit field effect to the theoretical signal distribution intensity considering the transmit field effect; the imaging sequence parameter comprises a type of radio frequency pulse and / or a flip angle of the radio frequency pulse; a correction module configured to correct the scan image of the imaging region according to the correction factor. 8.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.

Images