A method, apparatus, device, medium, and product for detecting the MIT region in brain hemorrhage.

Abstract

This application discloses a method, apparatus, device, medium, and product for detecting the mitochondrial region (MIT) in brain hemorrhage, relating to the field of brain image processing. The method includes dividing the brain imaging region into multiple regions with predetermined angles, using different coil arrays for different regions, acquiring magnetic field and conductivity information for different coil arrays, establishing multiple sample sets using the magnetic field and conductivity information as sample pairs, training stacked autoencoders with the multiple sample sets to obtain multiple MIT prediction models, determining the location of the lesion, and selecting an array from different coil arrays that positions the lesion within the detection region from -n° to n°, acquiring magnetic field information and obtaining phase information using the selected array, selecting the MIT prediction model corresponding to the selected array, and inputting the phase information into this MIT prediction model to predict the conductivity distribution, and completing image reconstruction based on the conductivity distribution. This application can improve the image reconstruction effect.

Description

Technical Field

[0001] This application relates to the field of brain image processing, and in particular to a method, apparatus, device, medium, and product for detecting the MIT region of brain hemorrhage. Background Technology

[0002] Magnetic Induction Tomography (MIT), also known as electromagnetic tomography, is a novel non-contact, radiation-free imaging technique. An MIT system typically consists of an excitation coil, a detection coil, a signal processing system, and a host computer. The MIT system applies an external alternating magnetic field to the coils to excite eddy currents inside an object and measures the electromagnetic signals induced by these eddy currents. Then, in the host computer, an inverse problem algorithm is used to reconstruct the conductivity distribution inside the object, achieving non-invasive conductivity imaging and analysis.

[0003] Currently, MIT (Made in Taiwan) technology shows promising applications in the field of biomedical imaging. Cerebral hemorrhage is a rapidly developing and highly fatal disease; rapid and accurate detection and diagnosis are crucial for patient treatment and recovery. While current methods such as computed tomography (CT) and magnetic resonance imaging (MRI) are highly effective in detecting cerebral hemorrhage, MIT technology's advantages—low cost, no radiation, and real-time monitoring—make it a valuable adjunct method for pre- and post-operative bedside monitoring, supplementing initial diagnostics and demonstrating excellent clinical application prospects.

[0004] Currently, due to space constraints and the desire for greater convenience, the number of coils that can be set up for the MIT system is limited, which means that the imaging information acquired is limited. Furthermore, in practical applications, the signal is easily affected by environmental noise, which in turn seriously affects the image reconstruction effect. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, device, medium, and product for detecting the MIT region in cerebral hemorrhage, which can improve the image reconstruction effect.

[0006] To achieve the above objectives, this application provides the following solution:

[0007] Firstly, this application provides a method for detecting the MIT region in brain hemorrhage, including:

[0008] The brain imaging area is divided into regions with multiple set angles, and different coil arrays are used in different regions to obtain magnetic field information and conductivity information when different coil arrays are used.

[0009] Multiple sample sets are established by using magnetic field and conductivity information of different coil arrays as sample pairs;

[0010] Multiple sample sets are used to train stacked autoencoders until the trained stacked autoencoders meet the set conditions, thus obtaining multiple MIT prediction models.

[0011] Determine the location of the lesion, and based on the location of the lesion, select an array from different coil arrays that positions the lesion in the region from -n° to n° on the detection side;

[0012] Magnetic field information is acquired by using an array that positions the lesion in the region from -n° to n° on the detection side, and phase information is obtained based on the magnetic field information.

[0013] Select the MIT prediction model corresponding to the array that places the lesion in the region from -n° to n° on the detection side, and input the phase information into this MIT prediction model to predict the conductivity distribution;

[0014] Image reconstruction is performed based on the conductivity distribution.

[0015] Optionally, the brain imaging area can be divided into four 90° regions.

[0016] Optionally, n° is 45°.

[0017] Optionally, the location of the lesion can be determined using computed tomography or magnetic resonance imaging.

[0018] Secondly, this application provides a device for detecting the MIT region of brain hemorrhage, comprising:

[0019] A signal generator is used to generate excitation signals;

[0020] An excitation coil, connected to the signal generator, is used to generate a magnetic field under the action of the excitation signal; the magnetic field acts on the brain to be tested.

[0021] A detection coil array is used to acquire magnetic field information;

[0022] A lock-in amplifier, connected to the detection coil array and the signal generator, is used to generate phase information based on the magnetic field information;

[0023] The host computer, connected to the lock-in amplifier, is used to implement the MIT region detection method for cerebral hemorrhage provided above, so as to complete image reconstruction based on the phase information.

[0024] Optionally, the excitation coil and the detection coil array form a coil array.

[0025] Optionally, the excitation coil and the detection coil array are placed 180° apart with the patient's brain as the center; the excitation coil and the detection coil array are rotated at a set angle to obtain magnetic field information at different set angles.

[0026] 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 brain hemorrhage MIT region detection device provided above.

[0027] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned brain hemorrhage MIT region detection device.

[0028] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned brain hemorrhage MIT region detection device.

[0029] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0030] This application provides a method, apparatus, device, medium, and product for detecting the MIT region in cerebral hemorrhage. After determining the location of the lesion, the lesion is always located in the region from -n° to n° on the detection side. The magnetic field signal obtained by the array detection corresponding to the lesion in the region from -n° to n° on the detection side is converted into a phase signal and then input into the MIT prediction model corresponding to the selected array for imaging. Thus, even with limited imaging information, better image reconstruction results can be obtained, and reconstruction accuracy can be improved. Attached Figure Description

[0031] 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.

[0032] Figure 1 This is a flowchart illustrating a method for detecting the MIT region in cerebral hemorrhage according to an embodiment of this application.

[0033] Figure 2 A schematic diagram illustrating the implementation process of a method for detecting the MIT region in cerebral hemorrhage, provided as an embodiment of this application;

[0034] Figure 3 This is a schematic diagram of the structure of a brain hemorrhage MIT region detection device provided in an embodiment of this application;

[0035] Figure 4 A schematic diagram of a model provided for another embodiment of this application;

[0036] Figure 5 A phase difference information curve of the lesion located at (-45, 45) provided for an embodiment of this application;

[0037] Figure 6 A phase difference information curve of the lesion located at (45, 45) provided in an embodiment of this application;

[0038] Figure 7 A phase difference information curve of the lesion located at (-70, 0) provided in an embodiment of this application;

[0039] Figure 8 A phase difference information curve of the lesion located at (0,0) provided in an embodiment of this application;

[0040] Figure 9 A phase difference information curve of the lesion located at (70,0) provided in an embodiment of this application;

[0041] Figure 10 A phase difference information curve of the lesion located at (-45, -45) provided for an embodiment of this application;

[0042] Figure 11 A phase difference information curve of the lesion located at (45, -45) provided in an embodiment of this application;

[0043] Figure 12 Reconstruction results of a lesion located at (-50,0) under different noise conditions, provided for an embodiment of this application;

[0044] Figure 13 Reconstruction results of a lesion located at (50,0) under different noise conditions, provided for another embodiment of this application;

[0045] Figure 14 A reconstruction result diagram of the phantom located on the excitation side, provided for another embodiment of this application;

[0046] Figure 15 A reconstruction result diagram of the phantom located on the detection side, provided for another embodiment of this application;

[0047] Figure 16 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.

[0048] Explanation of reference numerals in the attached figures:

[0049] 101-Signal generator, 102-Lock-in amplifier, 103-Host computer, 104-Excitation coil, 105-Legion, 106-Detection coil array. Detailed Implementation

[0050] 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.

[0051] 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.

[0052] This embodiment provides a method for detecting the MIT region in cerebral hemorrhage, such as Figure 1 and Figure 2 As shown, the method includes:

[0053] Step 100: Divide the brain imaging area into multiple regions with set angles, and use different coil arrays for different regions to obtain magnetic field information and conductivity information for different coil arrays.

[0054] For example, the brain imaging area is divided into four 90° regions, the excitation coil and the detection coil are placed 180° apart, and all coils are moved 90° four times to construct the corresponding coil array and model, and the magnetic field information and conductivity information of different coil arrays are obtained respectively.

[0055] Step 101: Use the magnetic field information and conductivity information of different coil arrays as sample pairs to establish multiple sample sets.

[0056] Step 102: Train stacked autoencoders (SAEs) using multiple sample sets until the trained stacked autoencoders meet the set conditions, thus obtaining multiple MIT prediction models.

[0057] Step 103: Determine the location of the lesion, and select an array from different coil arrays that places the lesion in the detection side from -n° to n° based on the location of the lesion.

[0058] For example, CT, MRI and other methods are used to determine the location of the lesion, and an array is selected from multiple coil arrays to place the lesion in the region from -45° to 45° on the detection side.

[0059] Step 104: Use an array to locate the lesion in the region from -n° to n° on the detection side to obtain magnetic field information, and obtain phase information based on the magnetic field information.

[0060] Step 105: Select the MIT prediction model corresponding to the array that places the lesion in the -n° to n° region on the detection side, and input the phase information into this MIT prediction model to predict the conductivity distribution.

[0061] Step 106: Complete image reconstruction based on conductivity distribution.

[0062] In summary, the SAE-based MIT region detection method for intracerebral hemorrhage provided in this application can achieve better reconstruction results even with a limited number of coils and noise. After initially determining the location of the lesion using methods such as CT and MRI, the coil array is adjusted according to the lesion location to ensure that the lesion is always located in a more sensitive detection area. This results in more distinctive lesion information, enabling the MIT system to achieve better reconstruction results under practical conditions with limited imaging information. This improves reconstruction accuracy while maintaining convenience, and provides an optimized MIT detection method for preoperative and postoperative bedside monitoring, allowing doctors to understand the patient's condition in real time.

[0063] In another exemplary embodiment of this application, a device for detecting the MIT region of brain hemorrhage is provided, such as... Figure 3 The device shown includes: a signal generator 101, an excitation coil 104, a detection coil array 106, a lock-in amplifier 102, and a host computer 103. The excitation coil 104 is connected to the signal generator 101. The lock-in amplifier 102 is connected to both the detection coil array 106 and the signal generator 101. The host computer 103 is connected to the lock-in amplifier 102. The detection coil array 106 includes multiple detection coils. Figure 3 The number 105 represents the lesion.

[0064] The signal generator 101 generates an excitation signal, which, through the excitation coil 104, generates a magnetic field in the imaging domain that acts on the object under test. The magnetic field information is then acquired through the detection coil array 106 and connected to a lock-in amplifier to output phase information to the host computer 103. The host computer 103 implements the aforementioned brain hemorrhage MIT region detection method to complete image reconstruction based on the phase information.

[0065] In another exemplary embodiment of this application, the excitation coil 104 and the detection coil array 106 form a coil array.

[0066] In another exemplary embodiment of this application, the excitation coil 104 and the detection coil array 106 are placed 180° apart from each other with the patient's brain as the center. The excitation coil 104 and the detection coil array 106 are rotated at a set angle to obtain magnetic field information at different set angles.

[0067] In another exemplary embodiment of this application, a brain model is constructed by processing real CT and MRI images using finite element simulation software. The brain model is detected using the excitation coil and detection coil array provided above. Figure 4 As shown, the excitation coil and the detection coil array are placed 180° apart. The brain hemisphere closer to the excitation coil is the excitation side, and the brain hemisphere closer to the detection coil array is the detection side. The brain can be approximated as a circle and divided into four 90° regions. By moving the coil array 90°, the lesion is always positioned within the -45° to 45° region on the detection side. During detection, the excitation coil is energized, generating a variable main magnetic field B0 in the imaging space. Human tissue, under the influence of this main magnetic field, generates a secondary induced magnetic field ΔB. Different pathological tissue morphologies affect the value of ΔB. Meanwhile, the detection coil collects the synthetic magnetic field B0+ΔB around the head by moving its position. According to MIT theory, the phase delay of B0+ΔB relative to B0 is Δφ, which is linearly related to the conductor's conductivity and is expressed as a phase difference.

[0068] The phase difference data comparison results when the lesion is located in seven different locations are as follows: Figures 5 to 11 As shown. From Figure 5 to... Figure 11 As can be seen, compared to lesions located on the excitation coil side, the phase difference information curve of lesions on the detection coil array side exhibits more pronounced valley characteristics, with the valleys appearing near the detection coils close to the lesion. When the lesion is located at (-45, 45) and (45, 45), the phase difference valleys are approximately at the 85th and 65th detection points, respectively. When the lesion moves to any of the three X-axis positions, the phase difference valley moves to the 50th detection point, while when the lesion is located at (-45, -45) and (45, -45), the phase difference valley moves again to the 15th and 35th detection points. The change in lesion location corresponds to a change in the phase difference curve, indicating that it contains lesion location information, and the phase difference information characteristics of lesions on the detection coil array side are more pronounced. Since the information characteristics contained in lesions at different locations and in different regions differ, the image reconstruction effect and the degree of noise influence will also vary.

[0069] Based on the above description, the SAE neural network algorithm is used in the image reconstruction process. In this embodiment, one excitation coil and seven detection coils are placed 180° opposite each other. The lesion position is continuously changed to build a sample set for network training and conduct SAE training. The MIT prediction model is established. The MIT prediction model takes phase difference information as input and conductivity distribution as output, and is finally used to reconstruct the image.

[0070] For example, if the brain is roughly considered as a circle, the location of the lesion can be divided into different regions, such as... Figure 4 As shown, the brain model is divided into an excitation side and a detection side based on the positions of the excitation coil and the detection coil. Compared with the error results of all lesion reconstructions under superimposed noise conditions, the average relative error of lesion reconstruction in the -45° to 45° region on the excitation side is the largest, while the average relative error of lesion reconstruction in the -45° to 45° region on the detection side is the smallest. The reconstruction results of lesions located in the above two regions under different noise conditions are shown below. Figure 12 and Figure 13 As shown in the figure, the lesion at (-50,0) on the excitation side already showed some shift and blurring under 40dB noise conditions. When the noise increased to 35dB, the lesion at (-50,0) could not be reconstructed well. When the noise increased to 25dB, the lesion at (50,0) on the detection side could still be reconstructed well. Under 20dB noise conditions, the lesion at (50,0) also showed some shift. Figure 12 Part (a) is an actual schematic diagram. Figure 12 Part (b) is a schematic diagram of the reconstruction of the lesion located at (-50,0) under 40dB noise conditions. Figure 12 Part (c) is a schematic diagram of the reconstruction of the lesion located at (-50,0) under 35dB noise conditions. Figure 12 Part (d) is a schematic diagram of the reconstruction of the lesion located at (-50,0) under 30dB noise conditions. Figure 12 Part (e) is a schematic diagram of the reconstruction of the lesion located at (-50,0) under 25dB noise conditions. Figure 12 Part (f) is a schematic diagram of the reconstruction of the lesion located at (-50,0) under 20dB noise conditions. Figure 13 Part (a) is an actual schematic diagram. Figure 13 Part (b) is a schematic diagram of the reconstruction of the lesion located at (50,0) under 40dB noise conditions. Figure 13 Part (c) is a schematic diagram of the reconstruction of the lesion located at (50,0) under 35dB noise conditions. Figure 13 Part (d) is a schematic diagram of the reconstruction of the lesion located at (50,0) under 30dB noise conditions. Figure 13 Part (e) is a schematic diagram of the reconstruction of the lesion located at (50,0) under 25dB noise conditions. Figure 13Part (f) is a schematic diagram of the reconstruction of the lesion located at (50,0) under 20dB noise conditions.

[0071] To further verify the simulation results, a phantom experiment was conducted using the aforementioned brain hemorrhage MIT region detection device. Phase information was acquired using the device when the aluminum rod was located in the -45° to 45° region on the excitation side and the -45° to 45° region on the detection side. The results are as follows: Figure 14 and Figure 15 As shown, artifacts appear in the reconstruction results of the aluminum rod on the excitation coil side, while the aluminum rod on the detection coil side is reconstructed better, with higher reconstruction accuracy. Among these, Figure 14 Part (a) is a schematic diagram of the actual situation where the phantom is located on the excitation side. Figure 14 Part (b) is a schematic diagram of the reconstruction of the phantom located on the excitation side. Figure 15 Part (a) is a schematic diagram of the actual situation where the phantom is located on the detection side. Figure 15 Part (b) is a schematic diagram of the reconstruction of the phantom located on the detection side.

[0072] In summary, this application uses the SAE neural network algorithm for image reconstruction in inverse problem reconstruction. By placing the coil array according to the lesion location, the imaging area can be divided into four 90° regions. The coil array is adjusted by simultaneously rotating the excitation and detection coil arrays by 90°, resulting in four corresponding array configurations. Four corresponding MIT prediction models are constructed. Once the lesion location is determined, the coil array is adjusted again, and the corresponding MIT prediction model is applied for imaging, ensuring the lesion is always located in the -45° to 45° region on the detection side. This allows the brain hemorrhage MIT region detection device to obtain better reconstructed images and reconstruction noise resistance with fewer coil configurations, achieving better reconstruction results and improving reconstruction accuracy even with limited imaging information.

[0073] 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 16As 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 stores imaging results of the MIT region detection in brain hemorrhage. 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. When the computer program is executed by the processor, it implements a method for detecting the MIT region of brain hemorrhage.

[0074] Those skilled in the art will understand that Figure 16 The structures shown are merely block diagrams of some structures related to the present application and do 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 shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0075] 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.

[0076] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0077] 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.

[0078] 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).

[0079] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0080] 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.

[0081] 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. A method for detecting the MIT region in cerebral hemorrhage, characterized in that, The method for detecting the MIT region in cerebral hemorrhage includes: The brain imaging area is divided into regions with multiple set angles, and different coil arrays are used in different regions to obtain magnetic field information and conductivity information when different coil arrays are used. Multiple sample sets are established by using magnetic field and conductivity information of different coil arrays as sample pairs; Multiple sample sets are used to train stacked autoencoders until the trained stacked autoencoders meet the set conditions, thus obtaining multiple MIT prediction models. The location of the lesion is determined, and based on the location of the lesion, an array is selected from different coil arrays to place the lesion in the region from -n° to n° on the detection side; n° is 45°. Magnetic field information is acquired by using an array that positions the lesion in the region from -n° to n° on the detection side, and phase information is obtained based on the magnetic field information. Select the MIT prediction model corresponding to the array that places the lesion in the region from -n° to n° on the detection side, and input the phase information into this MIT prediction model to predict the conductivity distribution; Image reconstruction is performed based on the conductivity distribution.

2. The method for detecting the MIT region in cerebral hemorrhage according to claim 1, characterized in that, The brain imaging area was divided into four 90° regions.

3. The method for detecting the MIT region in cerebral hemorrhage according to claim 1, characterized in that, The location of the lesion is determined using computed tomography or magnetic resonance imaging.

4. A device for detecting the MIT region in cerebral hemorrhage, characterized in that, The brain hemorrhage MIT region detection device includes: A signal generator is used to generate excitation signals; An excitation coil, connected to the signal generator, is used to generate a magnetic field under the action of the excitation signal; the magnetic field acts on the brain to be tested. A detection coil array is used to acquire magnetic field information; A lock-in amplifier, connected to the detection coil array and the signal generator, is used to generate phase information based on the magnetic field information; A host computer, connected to the lock-in amplifier, is used to implement the brain hemorrhage MIT region detection method as described in any one of claims 1-3, to complete image reconstruction based on the phase information.

5. The brain hemorrhage MIT region detection device according to claim 4, characterized in that, The excitation coil and the detection coil array form a coil array.

6. The brain hemorrhage MIT region detection device according to claim 4, characterized in that, The excitation coil and the detection coil array are placed 180° apart with the patient's brain as the center; the excitation coil and the detection coil array are rotated at a set angle to obtain magnetic field information at different set angles.

7. 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 brain hemorrhage MIT region detection method according to any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the brain hemorrhage MIT region detection method as described in any one of claims 1-3.

9. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the brain hemorrhage MIT region detection method as described in any one of claims 1-3.

Images