A method, apparatus, device and medium for optimizing magnetic resonance imaging

Abstract

The application discloses an optimization method, device, equipment and medium for magnetic resonance imaging, and relates to the field of magnetic resonance imaging. The method comprises the following steps: acquiring a reference longitudinal relaxation time of an imaging magnetic resonance device with a preset main magnetic field strength; constructing a linkage fitting function between TR and TI parameters based on the reference longitudinal relaxation time, taking the maximum difference value between an image signal of a hemorrhagic focus and an image signal of healthy brain parenchyma as a target; determining a target TI according to a target TR and the linkage fitting function; optimizing scanning parameters of the magnetic resonance device by using a minimum effective echo time, the target TR and the target TI; acquiring an initial magnetic resonance image, which is obtained by scanning a stroke patient by using the magnetic resonance device with the optimized parameters; and enhancing the initial magnetic resonance image by using a nonlinear stretching function to obtain a stroke triage enhanced inversion recovery image. The application can improve the image contrast of the magnetic resonance imaging.

Description

Technical Field

[0001] This application relates to the field of magnetic resonance imaging, and in particular to an optimized method, apparatus, device, and medium for magnetic resonance imaging. Background Technology

[0002] In the golden hour of stroke emergency care, every minute of delay means the irreversible death of millions of neurons. Quickly and accurately differentiating between intracerebral hemorrhage (ICH) and ischemic stroke (AIS) is crucial for treatment.

[0003] Currently, while computed tomography (CT) is considered the gold standard for differential diagnosis due to its high sensitivity to hemorrhage, its large size, heavy radiation shielding requirements, and high maintenance costs significantly limit its widespread use in mobile emergency units. In this context, low-magnetic-intensity (≤0.3T) magnetic resonance imaging (MRI) devices, with their advantages of small size, low cost, and no need for a shielded room, are gradually becoming the mainstream imaging equipment in mobile stroke units. However, in the hyperacute phase within 6 hours of onset, the physical characteristics of the hemorrhage point and ischemic area have not yet undergone drastic changes. In conventional T1-weighted imaging sequences or T2-weighted imaging sequences, the signal intensity of the hemorrhage lesion and healthy brain parenchyma highly overlaps, appearing as the same or equal signal. This weak contrast, coupled with background noise interference from the low magnetic field intensity, makes it easy to miss the hemorrhage lesion, resulting in difficulty distinguishing the hemorrhage lesion, healthy brain parenchyma, and background noise in images obtained by low-magnetic-intensity MRI devices, thus posing a significant challenge to clinical diagnosis. Summary of the Invention

[0004] The purpose of this application is to provide an optimized method, apparatus, device, and medium for magnetic resonance imaging, which can improve the image contrast of magnetic resonance imaging, easily and quickly distinguish hemorrhagic foci, healthy brain parenchyma, and background noise, thereby facilitating rapid clinical diagnosis and reducing the difficulty of diagnosis.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] In a first aspect, this application provides an optimization method for magnetic resonance imaging, comprising:

[0007] Obtain the reference longitudinal relaxation time for magnetic resonance imaging with a preset main magnetic field strength;

[0008] Based on the aforementioned baseline longitudinal relaxation time, a linkage fitting function between the TR and TI parameters is constructed with the objective of maximizing the difference between the hemorrhage foci image signal and the healthy brain parenchyma image signal.

[0009] The target TR is determined based on the equipment parameters of the magnetic resonance imaging device, and the target TI is determined based on the target TR and the linkage fitting function;

[0010] Calculate the minimum effective echo time for imaging with a magnetic resonance imaging (MRI) device, and optimize the scanning parameters of the MRI device using the minimum effective echo time, target TR, and target TI.

[0011] Acquire initial magnetic resonance images; wherein, the initial magnetic resonance images are obtained by scanning a stroke patient using a magnetic resonance imaging device with optimized parameters;

[0012] A nonlinear stretching function is constructed based on the background noise signal of the initial magnetic resonance image;

[0013] The initial magnetic resonance image was enhanced using a nonlinear stretching function to obtain an enhanced inversion recovery image for stroke triage.

[0014] Secondly, this application provides an optimized apparatus for magnetic resonance imaging, comprising:

[0015] The data acquisition module is used to acquire the reference longitudinal relaxation time for imaging with a preset magnetic field strength.

[0016] The function fitting module is used to construct a linkage fitting function between TR and TI parameters based on the benchmark longitudinal relaxation time, with the objective of maximizing the difference between the hemorrhage foci image signal and the healthy brain parenchyma image signal.

[0017] The target parameter determination module is used to determine the target TR based on the equipment parameters of the magnetic resonance device, and to determine the target TI based on the target TR and the linkage fitting function;

[0018] The parameter optimization module is used to calculate the minimum effective echo time for imaging with magnetic resonance imaging equipment, and to optimize the scanning parameters of magnetic resonance imaging equipment using the minimum effective echo time, target TR, and target TI.

[0019] An initial image acquisition module is used to acquire an initial magnetic resonance image; wherein, the initial magnetic resonance image is obtained by scanning a stroke patient using a magnetic resonance imaging device with optimized parameters;

[0020] A nonlinear stretching function construction module is used to construct a nonlinear stretching function based on the background noise signal of the initial magnetic resonance image;

[0021] The image optimization module is used to enhance the initial magnetic resonance image using a nonlinear stretching function to obtain an enhanced inversion recovery image for stroke triage.

[0022] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the optimized method for magnetic resonance imaging as described above.

[0023] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the optimized method for magnetic resonance imaging described above.

[0024] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0025] This application provides an optimization method, apparatus, device, and medium for magnetic resonance imaging (MRI). It constructs a linkage fitting function between the TR and TI parameters of the MRI device with a preset main magnetic field strength, and determines the target TI based on this function. The scanning parameters of the MRI device are optimized based on the minimum effective echo time, the target TR, and the target TI to maximize the image contrast between the hemorrhage and healthy brain parenchyma in the obtained initial MRI image. The minimum effective echo time is used to eliminate interference caused by T2 attenuation. Subsequently, a nonlinear stretching function is used to further optimize the initial MRI image, eliminating residual background noise and increasing the difference between the hemorrhage image signal and the background noise signal, preventing missed detection of the hemorrhage. Through the above process, the contrast of the enhanced inversion recovery image for stroke triage is greatly improved, facilitating rapid differentiation between the hemorrhage, healthy brain parenchyma, and background noise, significantly reducing the difficulty of clinical diagnosis. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is an application environment diagram of a magnetic resonance imaging method according to an embodiment of this application.

[0028] Figure 2 This is a schematic flowchart of a magnetic resonance imaging method provided in an embodiment of this application.

[0029] Figure 3 This is a schematic flowchart of another magnetic resonance imaging method provided in an embodiment of this application.

[0030] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] The specific principle behind the difficulty in distinguishing between lesions (called hemorrhages), normal brain tissue (called healthy brain parenchyma), and background noise in images obtained by low-field magnetic resonance imaging (MRI) equipment is as follows:

[0033] According to the physical laws of magnetic resonance imaging (MRI), the T1 value of brain tissue is positively correlated with the main magnetic field strength B0 of the MRI scanner. If this fixed parameter combination of main magnetic field strength B0 and T1 value is directly applied to other low-magnetic-field-strength MRI scanners, such as those with a main magnetic field strength of 0.28T, the T1 value of normal brain tissue is prolonged at 0.28T. The original zero-crossing T1 time point cannot achieve this signal zero-crossing, leading to ineffective suppression of normal brain tissue. The resulting high background signal severely masks potential hemorrhages and reduces contrast. Furthermore, since low-magnetic-field-strength MRI scanners often use permanent magnets, the static magnetic field uniformity is low and susceptible to environmental temperature drift interference, making it difficult to maintain a stable signal zero-crossing point during imaging, thus reducing the suppression effect of the sequence on normal brain tissue. Current technologies relying solely on sequence parameters for physical suppression cannot effectively suppress the image signal of normal brain tissue, nor can they eliminate the problems of residual local background noise and high image grayscale noise caused by magnetic field inhomogeneity. This mismatch in multi-parameter coupling leads to low image contrast, making it difficult to distinguish between hemorrhagic lesion image signals, healthy brain parenchyma image signals, and background noise signals. This not only reduces the sensitivity of diagnosis but may also lead to false negative results in the differential diagnosis during the hyperacute phase, delaying the golden window for treatment.

[0034] The purpose of this application is to provide an optimized method for magnetic resonance imaging that enhances the contrast between the image signal of the hemorrhage lesion and the image signal of healthy brain parenchyma, as well as the contrast between the image signal of the hemorrhage lesion and the background noise signal, so that the image signal of the hemorrhage lesion, the image signal of healthy brain parenchyma and the background noise signal can be easily distinguished, so as to facilitate rapid clinical diagnosis.

[0035] To make the objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] The optimized method for magnetic resonance imaging provided in this application can be applied to, for example... Figure 1 The application environment shown is illustrated. Terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be set up independently, integrated into server 102, or placed in the cloud or on another server. Terminal 101 can send the reference longitudinal relaxation time of the magnetic resonance imaging (MRI) device with a preset main magnetic field strength to server 102. Server 102 receives the reference longitudinal relaxation time of the MRI device and, based on this reference longitudinal relaxation time, constructs a linkage fitting function between TR and TI parameters with the objective of maximizing the difference between the hemorrhage lesion image signal and the healthy brain parenchyma image signal. It determines the target TR based on the MRI device parameters and the target TI based on the target TR and the linkage fitting function. It calculates the minimum effective echo time of the MRI device and optimizes the scanning parameters of the MRI device using the minimum effective echo time, target TR, and target TI. It acquires an initial MRI image, obtained by scanning a stroke patient using the optimized MRI device. A nonlinear stretching function is constructed based on the background noise signal of the initial MRI image. The nonlinear stretching function is used to enhance the initial MRI image to obtain a stroke triage augmented inversion recovery (STAIR) image. Server 102 can then feed the obtained stroke triage augmented inversion recovery image back to terminal 101. In addition, in some embodiments, the optimization method for magnetic resonance imaging can also be implemented by the server 102 or the terminal 101 alone. For example, the terminal 101 can directly optimize the reference longitudinal relaxation time of the magnetic resonance device with a preset main magnetic field strength, or the server 102 can obtain the reference longitudinal relaxation time of the magnetic resonance device with a preset main magnetic field strength from the data storage system and perform optimization processing.

[0037] The terminal 101 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 102 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0038] In one exemplary embodiment, such as Figure 2 and Figure 3As shown, an optimization method for magnetic resonance imaging is provided. This method is executed by a computer device, specifically a terminal or server, or both. In this embodiment, the method is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps 201 to 207. Wherein:

[0039] Step 201: Obtain the reference longitudinal relaxation time for magnetic resonance imaging with a preset main magnetic field strength.

[0040] In this embodiment, the preset main magnetic field strength is less than or equal to 0.3T, and the range of the main magnetic field strength covers 0.05T to 0.3T.

[0041] Step 202: Based on the baseline longitudinal relaxation time, construct a linkage fitting function between TR and TI parameters with the objective of maximizing the difference between the hemorrhage foci image signal and the healthy brain parenchyma image signal.

[0042] Step 203: Determine the target TI based on the equipment parameters of the magnetic resonance device and the target TR and the linkage fitting function.

[0043] Step 204: Calculate the minimum effective echo time for imaging with the magnetic resonance imaging device, and optimize the scanning parameters of the magnetic resonance imaging device using the minimum effective echo time, target TR, and target TI.

[0044] Step 205: Obtain an initial magnetic resonance image; wherein the initial magnetic resonance image is obtained by scanning a stroke patient using a magnetic resonance imaging device with optimized parameters.

[0045] Step 206: Construct a nonlinear stretching function based on the background noise signal of the initial magnetic resonance image.

[0046] Step 207: Enhance the initial magnetic resonance image using a nonlinear stretching function to obtain a stroke triage enhanced inversion recovery image.

[0047] By implementing steps 201 to 207 above, the contrast of the image generated by the magnetic resonance imaging device with the preset main magnetic field strength can be improved, thereby making it easier to distinguish healthy brain parenchyma, hemorrhage foci and background noise in the image, which is convenient for rapid clinical diagnosis.

[0048] In an exemplary embodiment, step 201 specifically includes steps 10-12:

[0049] Step 10: Using magnetic resonance imaging equipment with different preset parameter combinations, acquire image signals of the region of interest to obtain multiple sets of healthy brain parenchyma image signals and hemorrhage foci image signals; the region of interest includes the healthy brain parenchyma region and the hemorrhage foci region.

[0050] Specifically, healthy volunteers and a pig brain hemorrhage model were selected, and the IR-SE (Inversion Recovery Spin Echo) sequence was used. IR-SE is a magnetic resonance imaging (MRI) pulse sequence, which is characterized by applying a 180° inversion pulse before the standard spin echo (SE) sequence.

[0051] The repetition time (TR) was fixed at 4000ms, and the inversion time (TI) was set to 100, 400, 800, 200, and 2000ms. The IR value and each TI value were combined to obtain multiple sets of preset parameter combinations. Each set of preset parameter combinations was set as the parameters of the magnetic resonance imaging (MRI) device during operation. The MRI device with the set parameters was used to scan healthy volunteers and pig brain hemorrhage models to obtain multiple images of healthy brain parenchyma and hemorrhage lesion areas. A region of interest (ROI) was selected in each healthy brain parenchyma image and hemorrhage lesion area image to obtain the ROI corresponding to each healthy brain parenchyma image and hemorrhage lesion area image. The image signal of each ROI was acquired, thereby obtaining multiple sets of healthy brain parenchyma image signals and hemorrhage lesion area image signals.

[0052] The baseline longitudinal relaxation time includes the longitudinal relaxation time of healthy brain parenchyma and the longitudinal relaxation time of hemorrhagic lesions.

[0053] Step 11: Using multiple sets of healthy brain parenchyma image signals and corresponding preset parameter combinations, the longitudinal relaxation time of healthy brain parenchyma is calculated using a three-parameter fitting formula.

[0054] Healthy brain parenchyma image signals refer to Under specific parameter values, an MRI scanner scans healthy brain parenchyma to obtain image signals. The preset parameter combination refers to the TI and IR parameters. Using multiple sets of obtained healthy brain parenchyma image signals and their corresponding TI and IR values, a three-parameter fitting formula is employed to determine the optimal parameters. The three parameters are TR, TI, and longitudinal relaxation time of healthy brain parenchyma. The longitudinal relaxation time of healthy brain parenchyma is denoted as .

[0055] The expression for the three-parameter fitting formula is:

[0056] ;

[0057] in, In order to be in The image signal obtained under the parameter values, The balancing magnetization vector signal is a constant; A is the inversion efficiency factor, which is also a constant.

[0058] Step 12: Using the image signal of the bleeding lesion area and the corresponding preset parameter combination, the longitudinal relaxation time of the bleeding lesion is calculated using a three-parameter fitting formula.

[0059] The process for calculating the longitudinal relaxation time of the hemorrhage is the same as step 11 above, and will not be repeated here. The obtained longitudinal relaxation time of the hemorrhage is denoted as... .

[0060] In an exemplary embodiment, step 202 specifically includes steps 21-24:

[0061] Step 21: Construct a coupling equation for background suppression and lesion enhancement with the goal of maximizing the difference between the hemorrhage image signal and the healthy brain parenchyma image signal; wherein the hemorrhage image signal and the healthy brain parenchyma image signal are calculated by the longitudinal relaxation time of the hemorrhage and the longitudinal relaxation time of the healthy brain parenchyma, respectively.

[0062] Based on the longitudinal relaxation analytical solution of the Bloch equation under the IR-SE pulse sequence, a coupling equation for background suppression and lesion enhancement is constructed with the objective of maximizing the difference between the hemorrhagic lesion image signal and the healthy brain parenchyma image signal.

[0063] The expression for the coupling equation between background suppression and lesion enhancement is:

[0064] ;

[0065] And, when At that time, the difference between the image signal of the hemorrhagic lesion and the image signal of the healthy brain parenchyma was the largest.

[0066] in, The magnetization intensity, For the longitudinal relaxation time of healthy brain parenchyma, For the repetition time, This is for reversing time.

[0067] Longitudinal relaxation time of healthy brain parenchyma obtained in step 201 And preset the repetition time. By solving the coupling equation between background suppression and lesion enhancement, the corresponding TI parameter value was calculated. This TI parameter value is the theoretical zero-crossing reversal time of the background tissue. Also known as the zero point of background suppression, the zero-point inversion time is obtained by solving the coupling equation between background suppression and lesion enhancement. The expression is represented as:

[0068] ;

[0069] Will and Substituting the hemorrhage contrast function into the image signal, specifically, the image signal is calculated using the three-parameter fitting formula obtained above. The parameter values ​​and the corresponding longitudinal relaxation time of healthy brain parenchyma or hemorrhage longitudinal relaxation time are used to calculate the image signals of the healthy brain parenchyma region and the hemorrhage lesion region. Based on this, the hemorrhage contrast is calculated. Specifically, the expression for the hemorrhage contrast function is:

[0070] ;

[0071] in, For contrast of bleeding, In order to be in Image signals of the bleeding lesion area obtained under the parameter values, In order to be in Image signals of healthy brain parenchyma regions obtained under parameter values, In order to be in Image signal of the bleeding lesion area obtained under parameter values.

[0072] Step 22: Based on the longitudinal relaxation time of the healthy brain parenchyma and multiple preset repetition times, solve the coupling equation of background inhibition and lesion enhancement to obtain multiple zero-crossing reversal times.

[0073] By iteratively adjusting the value of TR, multiple preset repetition times are obtained, and the system is synchronously updated based on each preset repetition time. Finally, to compensate for the impact of non-uniformity of the B1 magnetic field (radio frequency magnetic field) on the background suppression effect, a fine-tuning strategy was introduced.

[0074] Step 23: For each zero-crossing reversal time, calculate the optimal reversal time based on the zero-crossing reversal time, and obtain multiple optimal reversal times.

[0075] The optimal reversal time is calculated by multiplying the zero-crossing reversal time by a correction factor of 1.1. Multiple optimal reversal times are obtained by multiplying the zero-crossing reversal time by the correction factor.

[0076] Step 24: Use a quadratic polynomial fitting algorithm to fit multiple sets of preset repetition times and corresponding optimal reversal times to obtain the linkage fitting function between TR and TI parameters.

[0077] Based on the TR value set in step 22, the corresponding optimal reversal time is calculated by executing steps 21-23. The TR value and the corresponding optimal reversal time are used as a set of optimal TR and TI parameter combinations, thus obtaining multiple sets of TR and TI parameter combinations, denoted as ( ), representing the i-th group of TR and TI parameter combinations.

[0078] A quadratic polynomial fitting algorithm is used to fit multiple combinations of TR and TI parameters, generating parameter fitting curves. This transforms discrete combinations of TR and TI parameters into continuous parameter fitting curves, yielding a linkage fitting function between the TR and TI parameters. In this embodiment, the quadratic polynomial fitting algorithm employs the least squares method.

[0079] The expression for the linkage fitting function between the TR and TI parameters is:

[0080] ;

[0081] Specifically, when the main magnetic field strength of the magnetic resonance imaging (MRI) device is 0.28T, that is, when the preset main magnetic field strength is 0.28T, the longitudinal relaxation time of healthy brain parenchyma is measured. For 460ms, multiple TR values ​​are selected within the range of 800ms to 2000ms. The zero-point inversion time is obtained by solving the coupling equation between background suppression and lesion enhancement using the values ​​of TR and , respectively. Then, based on step 23, the corresponding optimal reversal time is obtained, and thus multiple sets are obtained ( , ).

[0082] Using multiple groups ( , By performing a least-squares fit on the linkage function between the TR and TI parameters, we obtain A=0.00058, B=0.82, and C=55. Therefore, when the preset main magnetic field strength of the magnetic resonance imaging device is 0.28T, the expression for the linkage function between the TR and TI parameters is:

[0083] ;

[0084] in, For the repetition time, This is for reversing time.

[0085] In the specific implementation process, the linkage fitting function between the fitted TR and TI parameters is embedded in the scanning protocol of the magnetic resonance equipment. When in use, the user sets the value of TR according to the equipment parameters of the magnetic resonance equipment. At this time, the value of TI is automatically matched by the pre-embedded linkage fitting function between TR and TI parameters. The set value of TR and the automatically matched value of TI are used as the parameters for the magnetic resonance equipment to perform imaging.

[0086] In one exemplary embodiment, step 203 specifically includes:

[0087] In this embodiment, the equipment parameters of the magnetic resonance imaging device include, but are not limited to, the maximum gradient field strength and the gradient switching rate. The physical duration boundary of the imaging sequence is defined based on the equipment parameters. For example, under a main magnetic field strength of 0.28T, the physical duration boundary of the imaging sequence is first defined based on the equipment parameters. Then, based on the physical duration boundary, the range of TR is determined to be 800ms to 2000ms. Finally, combined with the specific requirements of clinical diagnosis for scanning efficiency, the target TR value is determined from the range of 800ms to 2000ms.

[0088] In one exemplary embodiment, step 204 specifically includes:

[0089] By disabling unnecessary gradients such as flow compensation and retaining only the slice selection and readout gradients, the minimum effective echo time for magnetic resonance imaging (MRI) is calculated using the formula for minimum effective echo time. The calculation formula is as follows:

[0090] ;

[0091] in, To minimize the effective echo time, and These are the durations of the 90° excitation pulse and the 180° inversion pulse, respectively. For gradient climbing time, This is the signal readout window width.

[0092] In one exemplary embodiment, step 205 specifically includes:

[0093] The initial magnetic resonance images of stroke patients were obtained by scanning them using a magnetic resonance imaging (MRI) device with optimized parameters. The image contrast of the initial MRI images has been preliminarily optimized by optimizing the scanning parameters of the MRI device.

[0094] In an exemplary embodiment, step 206 specifically includes steps 61-62:

[0095] Step 61: Calculate the background noise suppression threshold based on the background noise signal of the initial magnetic resonance image.

[0096] By using the air regions at the four corners of the initial magnetic resonance image as a reference for background noise signals, background noise is calculated, thereby achieving dynamic background modeling. Specifically, each corner point of the initial magnetic resonance image is extracted. The region, where N is a positive number, represents the size of the selected image corner region, where the image corner region is the region of interest at the four corners of the initial magnetic resonance image; calculate the region of interest for each image corner. regional signal mean and standard deviation The background noise suppression threshold is calculated based on the signal mean and standard deviation.

[0097] ;

[0098] in, The background noise suppression threshold. The value range is 3-5, and should be selected according to the actual situation.

[0099] Step 62: Construct a nonlinear stretching function based on the background noise suppression threshold.

[0100] Build with The sigmoid function is used as the anchor point to perform nonlinear remapping of the pixel grayscale of the initial magnetic resonance image. In this embodiment, the sigmoid function is used as the sigmoid function.

[0101] by The S-shaped transfer function with anchor points is called a nonlinear stretching function, and its specific expression is:

[0102] ;

[0103] in, The output value of the image signal. The maximum value of the image signal. The input value is the image signal. and For nonlinear mapping coefficients, Set as This ensures that the residual background is located in the "bottom dead zone" of the S-curve, while the hemorrhage signal is located in the "linear rising zone". The degree of contrast stretching is controlled. In this embodiment, the output value of the image signal is used as the image signal of the STAIR image, and the image signal of the initial magnetic resonance image is used as the input value of the image signal.

[0104] By constructing a nonlinear stretching function, the image signal of the initial magnetic resonance image that is below the background noise suppression threshold is forcibly compressed to near 0 (pure black), suppressing the residual background noise signal, while the image signal of the hemorrhage lesion that is above the background noise suppression threshold is stretched and enhanced, thus enhancing the image signal of the hemorrhage lesion.

[0105] Steps 206-207 above are based on the initial optimization. Dynamic background modeling and nonlinear stretching are used to enhance the image, and the initial magnetic resonance image is optimized again to obtain the final optimized STAR image.

[0106] This application has the following beneficial effects:

[0107] 1. This application establishes a linkage fitting function between TR and TI parameters based on the Bloch equation in magnetic resonance physics under different main magnetic field strengths. Only the value of TR needs to be input to generate a suitable function. The value is significant. Compared to existing technologies that can only be used on specific models, this application has broad applicability.

[0108] 2. Existing technologies suffer from incomplete background suppression after changes in the main magnetic field strength. This application ensures that the healthy brain parenchyma image signal is suppressed to its lowest point by precisely calculating the zero-point reversal time, while the hemorrhage image signal is at its high point during the recovery period, forming a physically high contrast. Combined with the algorithm enhancement in step 206, background noise is suppressed, significantly improving image contrast and making the hemorrhage easily distinguishable, thereby significantly reducing the probability of missed hemorrhage and misjudgment due to background noise.

[0109] 3. By introducing a nonlinear mapping algorithm, residual background noise in low magnetic field environments is removed from the image. Through the stretching effect of the S-curve, a large visual contrast is formed between the image signal of the bleeding lesion and the background, thus achieving full display of the bleeding lesion area.

[0110] Based on the same inventive concept, this application also provides an apparatus for implementing the above-described optimization method for magnetic resonance imaging. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the optimization apparatus for magnetic resonance imaging provided below can be found in the limitations of the optimization method for magnetic resonance imaging described above, and will not be repeated here.

[0111] In one exemplary embodiment, an optimized apparatus for magnetic resonance imaging is provided, comprising:

[0112] The data acquisition module is used to acquire the reference longitudinal relaxation time for magnetic resonance imaging with a preset magnetic field strength.

[0113] The function fitting module is used to construct a linkage fitting function between TR and TI parameters based on the benchmark longitudinal relaxation time, with the objective of maximizing the difference between the hemorrhage foci image signal and the healthy brain parenchyma image signal.

[0114] The target parameter determination module is used to determine the target TR based on the equipment parameters of the magnetic resonance device, and to determine the target TI based on the target TR and the linkage fitting function.

[0115] The parameter optimization module is used to calculate the minimum effective echo time for imaging with magnetic resonance imaging equipment, and to optimize the scanning parameters of magnetic resonance imaging equipment using the minimum effective echo time, target TR, and target TI.

[0116] An initial image acquisition module is used to acquire an initial magnetic resonance image; wherein, the initial magnetic resonance image is obtained by scanning a stroke patient using a magnetic resonance device with optimized parameters.

[0117] The nonlinear stretching function construction module is used to construct a nonlinear stretching function based on the background noise signal of the initial magnetic resonance image.

[0118] The image optimization module is used to enhance the initial magnetic resonance image using a nonlinear stretching function to obtain an enhanced inversion recovery image for stroke triage.

[0119] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes 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 the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database contains data related to the optimization method for magnetic resonance imaging. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. The computer program is executed by the processor to implement the optimization method for magnetic resonance imaging.

[0120] Those skilled in the art will understand that Figure 4The 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.

[0121] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0122] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0123] 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.

[0124] 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 above methods. Any references to memory, 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, 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).

[0125] 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, etc., and are not limited to these.

[0126] 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.

[0127] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An optimization method for magnetic resonance imaging, characterized in that, include: The baseline longitudinal relaxation time for imaging with a magnetic resonance imaging (MRI) device at a preset main magnetic field strength is obtained. Specifically, this includes: acquiring image signals of the region of interest (ROI) using MRI devices with different preset parameter combinations, resulting in multiple sets of healthy brain parenchyma image signals and hemorrhage foci image signals; the ROI includes both healthy brain parenchyma and hemorrhage foci; using multiple sets of healthy brain parenchyma image signals and corresponding preset parameter combinations, a three-parameter fitting formula is used to calculate the longitudinal relaxation time of the healthy brain parenchyma; using the hemorrhage foci image signals and corresponding preset parameter combinations, a three-parameter fitting formula is used to calculate the longitudinal relaxation time of the hemorrhage foci; the expression for the three-parameter fitting formula is: ;in, In order to be in The image signal obtained under the parameter values, To balance the magnetization vector signal, A is the inversion efficiency factor, and the reference longitudinal relaxation time includes the longitudinal relaxation time of healthy brain parenchyma and the longitudinal relaxation time of hemorrhage lesions. Based on the aforementioned baseline longitudinal relaxation time, a linkage fitting function between TR and TI parameters is constructed with the objective of maximizing the difference between the hemorrhage image signal and the healthy brain parenchyma image signal. Specifically, this includes: constructing a coupling equation between background suppression and lesion enhancement with the objective of maximizing the difference between the hemorrhage image signal and the healthy brain parenchyma image signal; wherein the hemorrhage image signal and the healthy brain parenchyma image signal are calculated using the longitudinal relaxation time of the hemorrhage and the longitudinal relaxation time of the healthy brain parenchyma, respectively; based on the longitudinal relaxation time of the healthy brain parenchyma and multiple preset repetition times, the coupling equation between background suppression and lesion enhancement is solved to obtain multiple zero-crossing reversal times; for each zero-crossing reversal time, an optimal reversal time is calculated based on the zero-crossing reversal time, resulting in multiple optimal reversal times; wherein the optimal reversal time is calculated by multiplying the zero-crossing reversal time by a correction coefficient; a quadratic polynomial fitting algorithm is used to fit multiple sets of preset repetition times and corresponding optimal reversal times to obtain the linkage fitting function between TR and TI parameters; the expression of the coupling equation between background suppression and lesion enhancement is: ； And, when At that time, the difference between the image signal of the hemorrhagic lesion and the image signal of healthy brain parenchyma was the largest; among them, The magnetization intensity, For the longitudinal relaxation time of healthy brain parenchyma, For the repetition time, To reverse time; The target TR is determined based on the equipment parameters of the magnetic resonance imaging device, and the target TI is determined based on the target TR and the linkage fitting function; Calculate the minimum effective echo time for imaging with a magnetic resonance imaging (MRI) device, and optimize the scanning parameters of the MRI device using the minimum effective echo time, target TR, and target TI. Acquire initial magnetic resonance images; wherein, the initial magnetic resonance images are obtained by scanning a stroke patient using a magnetic resonance imaging device with optimized parameters; Constructing a nonlinear stretching function based on the background noise signal of the initial magnetic resonance image; specifically including: calculating a background noise suppression threshold based on the background noise signal of the initial magnetic resonance image; and constructing a nonlinear stretching function based on the background noise suppression threshold; The formula for calculating the background noise suppression threshold is: ; The background noise suppression threshold. The value range is 3-5; The specific expression for the nonlinear stretching function is: ； in, The output value of the image signal. The maximum value of the image signal. The input value is the image signal. and These are nonlinear mapping coefficients; The initial magnetic resonance image was enhanced using a nonlinear stretching function to obtain an enhanced inversion recovery image for stroke triage.

2. The optimized method for magnetic resonance imaging according to claim 1, characterized in that, The formula for calculating the minimum effective echo time is: ； in, To minimize the effective echo time, and These are the durations of the 90° excitation pulse and the 180° inversion pulse, respectively. For gradient climbing time, This is the signal readout window width.

3. The optimized method for magnetic resonance imaging according to claim 1, characterized in that, When the preset main magnetic field strength of the magnetic resonance imaging (MRI) device is 0.28T, the expression for the linkage fitting function between the TR and TI parameters is: ； in, For the repetition time, This is for reversing time.

4. An optimized device for magnetic resonance imaging, characterized in that, include: The data acquisition module is used to acquire the baseline longitudinal relaxation time of magnetic resonance imaging (MRI) at a preset main magnetic field strength. Specifically, it includes: acquiring image signals of the region of interest (ROI) using MRI with different preset parameter combinations, obtaining multiple sets of healthy brain parenchyma image signals and hemorrhage foci image signals; the ROI includes the healthy brain parenchyma region and the hemorrhage foci region; using the multiple sets of healthy brain parenchyma image signals and corresponding preset parameter combinations, a three-parameter fitting formula is used to calculate the longitudinal relaxation time of the healthy brain parenchyma; using the hemorrhage foci image signals and corresponding preset parameter combinations, a three-parameter fitting formula is used to calculate the longitudinal relaxation time of the hemorrhage foci; the expression of the three-parameter fitting formula is: ;in, In order to be in The image signal obtained under the parameter values, To balance the magnetization vector signal, A is the inversion efficiency factor, and the reference longitudinal relaxation time includes the longitudinal relaxation time of healthy brain parenchyma and the longitudinal relaxation time of the hemorrhage lesion. The function fitting module is used to construct a linkage fitting function between TR and TI parameters based on the benchmark longitudinal relaxation time, with the objective of maximizing the difference between the hemorrhage image signal and the healthy brain parenchyma image signal. Specifically, it includes: constructing a coupling equation between background suppression and lesion enhancement with the objective of maximizing the difference between the hemorrhage image signal and the healthy brain parenchyma image signal; wherein the hemorrhage image signal and the healthy brain parenchyma image signal are calculated using the longitudinal relaxation time of the hemorrhage and the longitudinal relaxation time of the healthy brain parenchyma, respectively; based on the longitudinal relaxation time of the healthy brain parenchyma and multiple preset repetition times, solving the coupling equation between background suppression and lesion enhancement yields multiple zero-crossing reversal times; for each zero-crossing reversal time, calculating the optimal reversal time, resulting in multiple optimal reversal times; wherein the optimal reversal time is calculated by multiplying the zero-crossing reversal time by a correction coefficient; and using a quadratic polynomial fitting algorithm to fit multiple sets of preset repetition times and corresponding optimal reversal times to obtain the linkage fitting function between TR and TI parameters; the expression of the coupling equation between background suppression and lesion enhancement is: ； And, when At that time, the difference between the image signal of the hemorrhagic lesion and the image signal of healthy brain parenchyma was the largest; among them, The magnetization intensity, For the longitudinal relaxation time of healthy brain parenchyma, For the repetition time, To reverse time; The target parameter determination module is used to determine the target TR based on the equipment parameters of the magnetic resonance device, and to determine the target TI based on the target TR and the linkage fitting function; The parameter optimization module is used to calculate the minimum effective echo time for imaging with magnetic resonance imaging equipment, and to optimize the scanning parameters of magnetic resonance imaging equipment using the minimum effective echo time, target TR, and target TI. An initial image acquisition module is used to acquire an initial magnetic resonance image; wherein, the initial magnetic resonance image is obtained by scanning a stroke patient using a magnetic resonance imaging device with optimized parameters; A nonlinear stretching function construction module is used to construct a nonlinear stretching function based on the background noise signal of the initial magnetic resonance image; specifically, it includes: calculating a background noise suppression threshold based on the background noise signal of the initial magnetic resonance image; and constructing a nonlinear stretching function based on the background noise suppression threshold. The formula for calculating the background noise suppression threshold is: ; The background noise suppression threshold. The value range is 3-5; The specific expression for the nonlinear stretching function is: ； in, The output value of the image signal. The maximum value of the image signal. The input value is the image signal. and These are nonlinear mapping coefficients; The image optimization module is used to enhance the initial magnetic resonance image using a nonlinear stretching function to obtain an enhanced inversion recovery image for stroke triage.

5. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the optimized method for magnetic resonance imaging according to any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the optimized method for magnetic resonance imaging as described in any one of claims 1-3.

Images