Brain image processing method and readable storage medium

Abstract

The present application relates to a brain image processing method, system, readable storage medium and device, belonging to the field of medical imaging technology. When a brain image is obtained, it can be compared with a known brain image, the known image is used as the first brain image, and the obtained brain image is used as the second brain image to be compared. The first brain image and the second brain image are processed respectively to obtain the brain morphological features therein respectively, and the brain morphological features are analyzed and matched. If the features of the two are matched, it can be determined that the second brain image to be compared and the known brain image belong to the same person; the brain image morphological feature is a stable human biological identifier. Through the analysis and matching of the brain morphological feature, multiple brain images of the same patient can be accurately found. At the same time, compared with the distinction method of identification number, certificate number, and medical record number, the scheme of the present application can more accurately and effectively distinguish the brain images of different patients.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a brain image processing method, system, readable storage medium and device. Background Art

[0002] With the popularization of medical imaging equipment and the increasing demand for brain imaging to assist in the diagnosis of brain diseases, the processing of brain images has become increasingly important. When processing the brain images of a large number of patients, an identification number is generally assigned to each patient's brain image to distinguish between different patients.

[0003] In the current related technology, the methods generally used to distinguish brain images of different patients include: 1. Image identification number; 2. Comparison by patient gender and age; 3. Comparison by patient ID number; 4. Comparison by medical record number.

[0004] The above method of distinguishing brain images of different patients will have the following problems: 1. When a patient visits a hospital for treatment, it is necessary to compare the previous database to find the brain images that have been collected; if the recognition design is not perfect, it may not be possible to retrieve the patient's brain image completely or to retrieve the brain images of other patients incorrectly; 2. It is common for a patient to visit different hospitals for treatment, but different hospitals have different recognition definition systems, which will lead to a lack of an effective identification system to determine whether images from different sources belong to the same patient. No effective solution has been proposed for this. Summary of the invention

[0005] Based on this, it is necessary to provide a brain image processing method, system, readable storage medium and device to address the problem of low accuracy of traditional methods of distinguishing brain images of different patients.

[0006] In a first aspect, the present application provides a brain image processing method, comprising the following steps:

[0007] Acquiring a known first brain image and a second brain image to be compared;

[0008] acquiring a first brain morphological feature of the first brain image and a second brain morphological feature of the second brain image;

[0009] If the first brain morphological feature matches the second brain morphological feature, it is determined that the first brain image and the second brain image belong to the same person.

[0010] In a second aspect, the present application provides a brain image processing system, comprising:

[0011] An image acquisition unit, used for acquiring a known first brain image and a second brain image to be compared;

[0012] a feature acquisition unit, configured to acquire a first brain morphological feature of the first brain image and a second brain morphological feature of the second brain image;

[0013] The matching judgment unit is used to determine that the first brain image and the second brain image belong to the same person when the first brain morphological feature matches the second brain morphological feature.

[0014] In a third aspect, the present application provides a readable storage medium having an executable program stored thereon, characterized in that when the executable program is executed by a processor, the steps of any of the above-mentioned brain image processing methods are implemented.

[0015] In a fourth aspect, the present application provides a brain image processing device, comprising a memory and a processor, wherein the memory stores an executable program, and wherein the processor implements the steps of any of the above-mentioned brain image processing methods when executing the executable program.

[0016] Compared with the related art, the brain image processing method, system, readable storage medium and device provided by the present application can compare a brain image with a known brain image when obtaining it. The known image is used as the first brain image, and the obtained brain image is used as the second brain image to be compared. The first brain image and the second brain image are processed respectively to obtain the brain morphological features therein respectively, and the brain morphological features are analyzed and matched. If the features of the two match, it can be determined that the second brain image to be compared and the known brain image belong to the same person. Since the brain already has a complete brain structure when a person is born, the morphological features of brain images are a stable human biological identifier. Through the analysis and matching of brain morphological features, multiple brain images of the same patient can be accurately found. At the same time, compared with the distinction method of identification number, certificate number, and medical record number, the scheme of the present application can more accurately and effectively distinguish brain images of different patients.

[0017] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a schematic diagram of an exemplary medical device 100 in one embodiment;

[0020] Figure 2is a schematic diagram of exemplary hardware and / or software components of an exemplary computing device 200 on which the processing engine 140 is implemented in one embodiment;

[0021] Figure 3 is a schematic diagram of exemplary hardware and / or software components of an exemplary mobile device 300 on which the terminal 130 may be implemented in one embodiment;

[0022] Figure 4 is a flowchart of a brain image processing method in one embodiment;

[0023] Figure 5 is a schematic diagram of a flow chart of MRI brain image processing in one embodiment;

[0024] Figure 6 is a schematic diagram of the structure of a brain image processing system in one embodiment;

[0025] Figure 7 FIG. 4 is a schematic diagram of the structure of a brain image processing system in another embodiment. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present application and do not limit the scope of protection of the present application.

[0027] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0028] Although the present application makes various references to certain modules in the system according to embodiments of the present application, any number of different modules can be used and run on the imaging system and / or processor. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0029] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0030] Figure 1is a schematic diagram of an exemplary medical apparatus 100 for brain image processing according to an embodiment. Figure 1 As shown, the medical device 100 may include a scanner 110, a network 120, one or more terminals 130, a processing engine 140, and a memory 150. All components in the medical device 100 may be interconnected via the network 120.

[0031] The scanner 110 can scan an object and generate brain scan data related to the scanned object. In some embodiments, the scanner 110 can be a medical imaging device, such as a CT device, a PET device, a SPECT device, an MRI device, etc. or any combination thereof (e.g., a PET-CT device or a CT-MRI device). In the present application, the medical imaging device can specifically be an MRI device.

[0032] The "image" mentioned in this application may refer to a 2D image, a 3D image, a 4D image and / or any related data, which is not intended to limit the scope of this application. For those skilled in the art, various modifications and changes can be made under the guidance of this application.

[0033] The scanner 110 may include a support assembly 111 , a detector assembly 112 , a workbench 114 , an electronics module 115 , and a cooling assembly 116 .

[0034] The support assembly 111 can support one or more components of the scanner 110, such as the detector assembly 112, the electronic module 115, the cooling assembly 116, etc. In some embodiments, the support assembly 111 may include a main frame, a frame base, a front cover plate, and a rear cover plate (not shown). The front cover plate can be connected to the frame base. The front cover plate can be perpendicular to the frame base. The main frame can be mounted on the side of the front cover plate. The main frame can include one or more support frames to accommodate the detector assembly 112 and / or the electronic module 115. The main frame can include a circular opening (e.g., a detection area 113) to accommodate the scanning target. In some embodiments, the opening of the main frame can be other shapes, including, for example, an elliptical shape. The rear cover plate can be mounted on the side of the main frame opposite to the front cover plate. The frame base can support the front cover plate, the main frame and / or the rear cover plate. In some embodiments, the scanner 110 may include a housing to cover and protect the main frame.

[0035] The detector assembly 112 can detect radiation events (e.g., radio frequency signals) emitted from the detection area 113. In some embodiments, the detector assembly 112 can receive radiation (e.g., radio frequency signals) and generate electrical signals. The detector assembly 112 can include one or more detector units. One or more detector units can be packaged to form a detector block. One or more detector blocks can be packaged to form a detector box. One or more detector boxes can be installed to form a detection ring. One or more detection rings can be installed to form a detector module.

[0036] The scanning bed 114 can support the object to be detected and position the object to be detected at a desired position in the detection area 113. In some embodiments, the object to be detected can lie on the scanning bed 114. The scanning bed 114 can move and reach a desired position in the detection area 113. In some embodiments, the scanner 110 can have a relatively long axial field of view, such as a 2-meter axial field of view. Accordingly, the scanning bed 114 can move in a wide range (e.g., greater than 2 meters) along the axial direction.

[0037] The electronic module 115 can collect and / or process the electrical signals generated by the detector assembly 112. The electronic module 115 can include one or a combination of adders, multipliers, subtractors, amplifiers, driver circuits, differential circuits, integration circuits, counters, filters, analog-to-digital converters, lower limit detection circuits, constant coefficient discriminator circuits, time-to-digital converters, coincidence circuits, etc. The electronic module 115 can convert analog signals related to the energy of the radiation received by the detector assembly 112 into digital signals. The electronic module 115 can compare multiple digital signals, analyze multiple digital signals, and determine image data by the energy of the radiation received in the detector assembly 112. In some embodiments, if the detector assembly 112 has a large axial field of view (e.g., 0.75 meters to 2 meters), the electronic module 115 can have a high data input rate from multiple detector channels. For example, the electronic module 115 can process tens of billions of events per second. In some embodiments, the data input rate can be related to the number of detector units in the detector assembly 112.

[0038] The cooling assembly 116 can generate, transfer, transmit, conduct or circulate a cooling medium in the scanner 110 to absorb the heat generated by the scanner 110 during the imaging process. In some embodiments, the cooling assembly 116 can be fully integrated into the scanner 110 and become a part of the scanner 110. In some embodiments, the cooling assembly 116 can be partially integrated into the scanner 110 and associated with the scanner 110. The cooling assembly 116 can allow the scanner 110 to maintain a suitable and stable operating temperature (e.g., 25°C, 30°C, 35°C, etc.). In some embodiments, the cooling assembly 116 can control the temperature of one or more target components of the scanner 110. The target component can include the detector assembly 112, the electronic module 115 and / or any other component that generates heat during operation. The cooling medium can be a gas, a liquid (e.g., water), etc., or a combination of several thereof. In some embodiments, the gaseous cooling medium can be air.

[0039] The network 120 may include any suitable network that can facilitate the exchange of information and / or data between the medical device 100. In some embodiments, one or more components of the medical device 100 (e.g., the scanner 110, the terminal 130, the processing engine 140, the memory 150, etc.) may communicate information and / or data with one or more other components of the medical device 100 via the network 120. For example, the processing engine 140 may obtain image data from the scanner 110 via the network 120. As another example, the processing engine 140 may obtain a user instruction from the terminal 130 via the network 120. The network 120 may include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN), a wide area network (WAN), etc.), a wired network (e.g., Ethernet), a wireless network (e.g., an 802.11 network, a Wi-Fi network, etc.), a cellular network (e.g., a long term evolution (LTE) network), a frame relay network, a virtual private network (“VPN”), a satellite network, a telephone network, a router, a hub, a switch, a server computer, and / or any combination thereof. By way of example only, the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunication network, an intranet, a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 120 may include one or more network access points. For example, the network 120 may include wired and / or wireless network access points, such as base stations and / or Internet exchange points, through which one or more components of the medical device 100 may connect to the network 120 to exchange data and / or information.

[0040] One or more terminals 130 include a mobile device 131, a tablet computer 132, a laptop computer 133, etc., or any combination thereof. In some embodiments, the mobile device 131 may include a smart home device, a wearable device, a mobile device, a virtual reality device, an augmented reality device, etc., or any combination thereof. In some embodiments, the smart home device may include a smart lighting device, a control device for smart appliances, a smart monitoring device, a smart TV, a smart camera, an interconnected phone, etc., or any combination thereof. In some embodiments, the wearable device may include a bracelet, shoes and socks, glasses, a helmet, a watch, clothing, a backpack, a smart accessory, etc., or any combination thereof. In some embodiments, the mobile device 131 may include a mobile phone, a personal digital assistant (PDA), a gaming device, a navigation device, a point of sale (POS) device, a laptop computer, a tablet computer, a desktop computer, etc., or any combination thereof. In some embodiments, the virtual reality device and / or the augmented reality device may include a virtual reality helmet, virtual reality glasses, virtual reality goggles, an augmented reality helmet, augmented reality glasses, augmented reality goggles, etc., or any combination thereof. For example, the virtual reality device and / or the augmented reality device may include Google Glass, Oculus Rift, Hololens, Gear VR, etc. In some embodiments, the terminal 130 may be part of the processing engine 140.

[0041] The processing engine 140 can process data and / or information obtained from the scanner 110, the terminal 130 and / or the memory 150. In some embodiments, the processing engine 140 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processing engine 140 can be local or remote. For example, the processing engine 140 can access the information and / or data stored in the scanner 110, the terminal 130 and / or the memory 150 through the network 120. As another example, the processing engine 140 can be directly connected to the scanner 110, the terminal 130 and / or the memory 150 to access the stored information and / or data. In some embodiments, the processing engine 140 can be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an interconnected cloud, multiple clouds, etc. or any combination thereof. In some embodiments, the processing engine 140 can be implemented by Figure 2 The computing device 200 shown in FIG. 1 may be implemented with one or more components.

[0042] The memory 150 may store data, instructions, and / or any other information. In some embodiments, the memory 150 may store data obtained from the terminal 130 and / or the processing engine 140. In some embodiments, the memory 150 may store data and / or instructions, and the processing engine 140 may execute or use the data and / or instructions to perform the exemplary methods described in the present application. In some embodiments, the memory 150 may include a mass storage device, a removable storage device, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid-state drives, etc. Exemplary removable memories may include flash drives, floppy disks, optical disks, memory cards, compressed disks, tapes, etc. Exemplary volatile read-write memories may include random access memories (RAM). Exemplary RAMs may include dynamic RAMs (DRAM), double data rate synchronous dynamic RAMs (DDR SDRAM), static RAMs (SRAM), thyristor RAMs (T-RAMs), and zero capacitor RAMs (Z-RAMs), etc. Exemplary ROMs may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital versatile disk ROM, etc. In some embodiments, the memory 150 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an interconnected cloud, multiple clouds, etc., or any combination thereof.

[0043] In some embodiments, the memory 150 may be connected to the network 120 to communicate with one or more other components in the medical device 100 (e.g., the processing engine 140, the terminal 130, etc.). One or more components in the medical device 100 may access data or instructions stored in the memory 150 through the network 120. In some embodiments, the memory 150 may be directly connected to or communicate with one or more other components in the medical device 100 (e.g., the processing engine 140, the terminal 130, etc.). In some embodiments, the memory 150 may be part of the processing engine 140.

[0044] Figure 2 is a schematic diagram of exemplary hardware and / or software components of an exemplary computing device 200 on which processing engine 140 may be implemented, according to one embodiment. Figure 2 As shown, computing device 200 may include an internal communication bus 210 , a processor 220 , a read-only memory (ROM) 230 , a random access memory (RAM) 240 , a communication port 250 , an input / output component 260 , a hard disk 270 , and a user interface device 280 .

[0045] The internal communication bus 210 may enable data communication among the components of the computing device 200 .

[0046] The processor 220 can execute computer instructions (e.g., program code) and perform the functions of the processing engine 140 according to the techniques described herein. The computer instructions may include, for example, routines, programs, scan objects, components, data structures, processes, modules, and functions that perform specific functions described herein. For example, the processor 220 can process image data obtained from the scanner 110, the terminal 130, the memory 150, and / or any other component of the medical device 100. In some embodiments, the processor 220 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a central processing unit (CPU), a graphics processing unit (GPU), a physical processing unit (PPU), a microcontroller unit, a digital signal processor (DSP), a field programmable gate array (FPGA), an advanced RISC machine (ARM), a programmable logic device (PLD), any circuit or processor capable of performing one or more functions, etc. or any combination thereof.

[0047] For illustration purposes only, only one processor 220 is described in the computing device 200. However, it should be noted that the computing device 200 in the present application may also include multiple processors, and thus the operations and / or method steps performed by one processor described in the present application may also be performed jointly or separately by multiple processors.

[0048] The read-only memory (ROM) 230 and the random access memory (RAM) 240 may store data / information obtained from the scanner 110, the terminal 130, the memory 150, and / or any other component of the medical device 100. The read-only memory (ROM) 230 may include a mask ROM (MROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a compact disk ROM (CD-ROM), and a digital versatile disk ROM, etc. The random access memory (RAM) 240 may include a dynamic RAM (DRAM), a double data rate synchronous dynamic RAM (DDR SDRAM), a static RAM (SRAM), a thyristor RAM (T-RAM), and a zero capacitor RAM (Z-RAM), etc. In some embodiments, the read-only memory (ROM) 230 and the random access memory (RAM) 240 may store one or more programs and / or instructions for executing the exemplary methods described in the present application.

[0049] The communication port 250 can be connected to a network (e.g., network 120) to assist in data communication. The communication port 250 can establish a connection between the processing engine 140 and the scanner 110, the terminal 130 and / or the memory 150. The connection can be a wired connection, a wireless connection, any other communication connection that can realize data transmission and / or reception, and / or any combination of these connections. The wired connection may include, for example, a cable, an optical cable, a telephone line, etc., or any combination thereof. The wireless connection may include, for example, a Bluetooth link, a Wi-Fi link, a WiMax link, a WLAN link, a ZigBee link, a mobile network link (e.g., 3G, 4G, 5G, etc.), etc., or a combination thereof. In some embodiments, the communication port 250 may include a standardized communication port, such as RS232, RS485, etc. In some embodiments, the communication port 250 may be a specially designed communication port. For example, the communication port 250 may be designed according to the Digital Imaging and Communications in Medicine (DICOM) protocol.

[0050] The input / output assembly 260 supports input / output data flow between the computing device 200 and other components. In some embodiments, the input / output assembly 260 may include input devices and output devices. Examples of input devices may include a keyboard, a mouse, a touch screen, a microphone, etc. or a combination thereof. Examples of output devices may include a display device, a speaker, a printer, a projector, etc. or a combination thereof. Examples of display devices may include a liquid crystal display (LCD), a display based on a light emitting diode (LED), a flat panel display, a curved screen, a television device, a cathode ray tube (CRT), a touch screen, etc. or a combination thereof.

[0051] The computing device 200 may also include different forms of program storage units and data storage units, such as a hard disk 270 , which can store various data files used for computer processing and / or communication, and possible program instructions executed by the processor 220 .

[0052] The user interface device 280 can enable interaction and information exchange between the computing device 200 and the user.

[0053] Figure 3 is a schematic diagram of exemplary hardware and / or software components of an exemplary mobile device 300 on which terminal 130 may be implemented according to one embodiment. Figure 3As shown, the mobile device 300 may include an antenna 310, a display 320, a graphics processing unit (GPU) 330, a central processing unit (CPU) 340, an input and output unit (I / O) 350, a memory 360, and a storage 390. In some embodiments, the mobile device 300 may also include any other suitable components, including but not limited to a system bus or a controller (not shown). In some embodiments, a mobile operating system 370 (e.g., iOS, Android, Windows Phone, etc.) and one or more applications 380 may be loaded from the storage 390 into the memory 360 for execution by the CPU 340. The application 380 may include a browser or any other suitable mobile application for receiving and drawing information related to image processing or other information from the processing engine 140. The user's interaction with the information stream may be implemented through the I / O 350 and provided to the processing engine 140 and / or other components of the medical device 100 through the network 120.

[0054] In order to realize the various modules, units and functions thereof described in the present application, a computer hardware platform can be used as the hardware platform of one or more elements described herein. A computer with a user interface element can be used as a personal computer (PC) or any other type of workstation or terminal device. If suitable programming is performed, the computer can also serve as a server. Brain image processing methods, systems, etc. can be implemented in medical equipment 100.

[0055] See also Figure 4 FIG. 1 is a flow chart of a brain image processing method according to an embodiment of the present application. The brain image processing method in this embodiment includes the following steps:

[0056] Step S410: obtaining a known first brain image and a second brain image to be compared;

[0057] In this step, the known first brain image can be obtained from the memory 150, and a database can be set in the memory 150 to store the first brain image. The second brain image to be compared can also be obtained from the memory 150, or it can be a new brain image currently scanned and photographed. The specific process is that the object to be scanned can be placed on the workbench 114 of the medical equipment scanner 110, enter the detection area 113 of the scanner 110, scan and photograph the brain image, and obtain the second brain image to be compared;

[0058] Step S420: acquiring a first brain morphological feature of the first brain image and a second brain morphological feature of the second brain image;

[0059] In this step, the morphological outline of the brain can be displayed in the first brain image and the second brain image, from which corresponding brain morphological features can be obtained, and the acquisition process can be executed by the processing engine 140.

[0060] Step S430: If the first brain morphological feature matches the second brain morphological feature, it is determined that the first brain image and the second brain image belong to the same person.

[0061] In this step, since the brain already has a complete brain structure when a person is born, the morphological characteristics of brain images are a stable human biological marker. Over time, the brain morphological characteristics do not change much, and each person's brain morphological characteristics are unique. Therefore, if the brain morphological characteristics of two brain images match, it can be more accurately determined that the two belong to the same person.

[0062] In this embodiment, when a brain image is obtained, it can be compared with a known brain image, the known image is used as the first brain image, and the obtained brain image is used as the second brain image to be compared. The first brain image and the second brain image are processed respectively to obtain the brain morphological features therein respectively, and the brain morphological features are analyzed and matched. If the features of the two match, it can be determined that the second brain image to be compared and the known brain image belong to the same person; because the brain already has a complete brain structure when a person is born, the morphological features of brain images are a stable human biological marker. Through the analysis and matching of brain morphological features, multiple brain images of the same patient can be accurately found. At the same time, compared with the distinction method of identification number, certificate number, and medical record number, the solution of the present application can more accurately and effectively distinguish brain images of different patients.

[0063] It should be noted that the above-mentioned brain image processing method can be executed on the console of the medical device, or on the post-processing workstation of the medical device, or on an exemplary computing device 200 that implements a processing engine on a terminal 130 that can communicate with the medical device, and is not limited to this and can be changed and adjusted according to the needs of actual applications.

[0064] In one embodiment, the step of acquiring a first brain morphological feature of a first brain image and a second brain morphological feature of a second brain image comprises the following steps:

[0065] Inputting the first brain image and the second brain image into a preset brain spherical mapping network respectively, obtaining a first unfolded spherical image corresponding to the first brain image and a second unfolded spherical image corresponding to the second brain image;

[0066] Restoring the first unfolded spherical image to a first standard spherical image, and extracting a first brain morphological feature from the first standard spherical image;

[0067] The second unfolded spherical image is restored to a second standard spherical image, and a second brain morphological feature is extracted from the second standard spherical image.

[0068] In this embodiment, since the human brain is of irregular shape, and the brain image obtained by scanning and photographing presents an approximately spherical shape, the features of the brain image can be mapped onto the unfolded sphere by inputting the brain image into a preset brain spherical mapping network to obtain an unfolded spherical image, and then the unfolded spherical image is restored to a standard spherical image. The standard spherical image has corresponding positions for comparison, and the brain morphological features of the brain image are extracted from the standard spherical image, which is convenient for feature comparison in combination with the position of the standard spherical image.

[0069] Furthermore, the structure of the brain spherical mapping network can adopt the network design of VNet or other types of network designs, and be pre-trained and stored in the processing engine 140. The brain spherical mapping network has preset mapping rules, through which the input brain image can be mapped into an unfolded spherical image, and the unfolded spherical image can be restored through the inverse process of the mapping rule to obtain a standard spherical image. At this time, the features of the brain image are mapped onto the standard sphere; when extracting the brain morphological features of the brain image from the standard spherical image, the spherical Harris feature point extraction method with high accuracy and repeatability can be used to achieve the extraction of feature points.

[0070] In one embodiment, before the step of inputting the first brain image and the second brain image into a preset brain spherical mapping network, the following steps are also included:

[0071] The first brain image and the second brain image are preprocessed respectively, and the preprocessing includes at least one of rotation, resampling, resizing, skull removal, image non-uniformity correction, histogram matching, and grayscale normalization.

[0072] In this embodiment, before the brain image is input into the brain spherical mapping network, one or more preprocessing steps may be performed on the brain image, such as rotation, resampling, resizing, skull removal, image non-uniformity correction, histogram matching, grayscale normalization, etc. Through the preprocessing process, the brain image can be preliminarily adjusted to remove unnecessary interference factors, so that the first brain image and the second brain image can be compared under the same conditions as much as possible, thereby improving the matching accuracy of the brain images.

[0073] In one embodiment, after the step of preprocessing the first brain image and the second brain image respectively, the following steps are further included:

[0074] Gray matter segmentation and cortex reconstruction are performed on the preprocessed first brain image and the second brain image respectively, and after the cortex reconstruction, they are respectively input into the brain spherical mapping network.

[0075] In this embodiment, since the human brain already has complete cerebral sulci and gyri features at birth, subsequent growth is only an increase in brain volume, a pruning process of gray matter thickness on the sulci and gyri, and a myelination process of white matter. The cerebral sulci and gyri refer to the numerous folds formed in the cerebral cortex. By performing gray matter segmentation on the brain image, the gray matter part that may change can be removed, and then the cortex is reconstructed to retain the characteristics of the cerebral sulci, such as the position, width, depth, etc. of the cerebral sulci, thereby making the characteristics of the brain image more obvious.

[0076] In one embodiment, the brain image processing method further comprises the following steps:

[0077] Obtain an initialized spherical mapping network, and obtain multiple brain sample images and corresponding spherical images;

[0078] Using multiple brain sample images as training input samples, and using the corresponding spherical images output by the spherical mapping network as training supervision samples, the spherical mapping network is trained;

[0079] After training with training input samples and training supervision samples, a brain spherical mapping network is obtained.

[0080] In this embodiment, a plurality of sample brain images can be used to train the initialized spherical mapping network, thereby obtaining a brain spherical mapping network; a mapping standard can be pre-set for the spherical mapping network, and the mapping standard is used as supervision to perform mapping training on the sample brain images. Here, the mapping standard can be the mapping process of the freesurfer spherical image corresponding to the sample brain image, that is, during the training process, the freesurfer spherical image corresponding to the sample brain image also obtains an unfolded spherical image according to the same mapping rule, and the unfolded spherical image of the freesurfer spherical image is used as a training supervision sample to train the spherical mapping network, so that the spherical mapping network adapts to the relationship between the brain image and the unfolded spherical image, thereby obtaining a brain spherical mapping network.

[0081] Specifically, during training, a freesurfer spherical image corresponding to a sample brain image can be obtained, and the dice loss function of the spherical mapping network can be used. The dice loss function is optimized to converge the mapping result of the brain image so that the mapping result of the freesurfer spherical image is as consistent as possible. Then, the converged dice loss function value is used to configure the parameters of the spherical mapping network so that the spherical mapping network becomes a brain spherical mapping network to meet the needs of brain image mapping.

[0082] It should be noted that the brain sample image can be a historical brain image that has been taken, or a simulated sample image, etc., and has a corresponding freesurfer spherical image. Freesurfer is a tool for processing 3D structural image data of the brain and performing automatic cortical and subcutaneous nuclei segmentation. The tool is used to process the brain scanning data to obtain the corresponding freesurfer spherical image. In addition, the freesurfer spherical image is only one of many spherical images. The present application can use other types of spherical images, and the specific application process is similar to the application process of the freesurfer spherical image.

[0083] In one embodiment, if the first brain morphological feature matches the second brain morphological feature, the step of determining that the first brain image and the second brain image belong to the same person comprises the following steps:

[0084] If the number of feature points matching the first brain morphological feature and the second brain morphological feature is greater than or equal to a first preset value, it is determined that the first brain image and the second brain image belong to the same person.

[0085] In this embodiment, when matching the brain morphological features of brain images, feature points can be used to extract brain morphological feature points from the first brain image and the second brain image respectively. After the matching process, the number of matched feature points is obtained. Since each person's brain is unique, when the number of feature points is greater than or equal to a first preset value, it can be determined that the two brain images belong to the same person. The relationship between the first brain image and the second brain image can be quickly determined by matching the number of feature points.

[0086] It should be noted that the first preset value can be adjusted according to actual needs; during the matching process, a feature matching algorithm can be used, such as the FLANN algorithm, the K-nearest neighbor algorithm (KNN), the brute force matching algorithm, etc.

[0087] In one embodiment, the step of acquiring a first brain morphological feature of a first brain image and a second brain morphological feature of a second brain image comprises the following steps:

[0088] Inputting the first brain image and the second brain image into a preset brain segmentation model respectively, and obtaining a plurality of functional brain region maps corresponding to the first brain image and a plurality of functional brain region maps corresponding to the second brain image;

[0089] extracting a first brain morphological feature from a plurality of functional brain area maps of the first brain image;

[0090] A second brain morphological feature is extracted from a plurality of functional brain area maps of the second brain image.

[0091] In this embodiment, the brain morphological features of the brain image can be obtained in another way. The brain image is input into a preset brain segmentation model. The brain segmentation model segments the brain area in the brain image to obtain images of multiple functional brain areas. Then, the brain morphological features are extracted from the images of the multiple functional brain areas respectively. Since the functional brain areas of the human brain are generally fixed, brain morphological features are extracted from each functional brain area respectively. After combining the brain morphological features in each functional brain area, the morphological features of the entire brain can be represented. Moreover, the morphological features are distributed in all functional brain areas of the brain, and the features are relatively complete. Compared with extracting multiple morphological features from the entire brain image, the number of features can be reduced while ensuring feature specificity.

[0092] It should be noted that the first brain morphological feature and the second brain morphological feature obtained by segmenting and extracting the brain region are different from the first brain morphological feature and the second brain morphological feature obtained by spherical mapping and extracting.

[0093] Furthermore, the brain area can be divided into five areas: frontal lobe, temporal lobe, parietal lobe, occipital lobe and subcortical brain. It can also be further subdivided, such as dividing the brain surface into 68 parts based on the brain sulci.

[0094] Furthermore, the brain image processing method further comprises the following steps:

[0095] Obtain an initialized segmentation model and obtain multiple brain sample images;

[0096] Using multiple brain sample images as training input samples, doctors annotate the brain regions of the brain sample images, and use the partition annotation results as training target samples to train the initialized segmentation model;

[0097] After training with training input samples and training target samples, a brain segmentation model is obtained.

[0098] In one embodiment, the step of extracting the first brain morphological feature from the plurality of functional brain area maps of the first brain image comprises the following steps:

[0099] Extracting at least one of the relative volume, surface area, ratio of surface area to relative volume, and long axis length of the brain region structure in each functional brain region map from the plurality of functional brain region maps of the first brain image;

[0100] Alternatively, using multiple functional brain area maps of the first brain image as mask images respectively, mapping the mask images to corresponding areas of the first brain image, and extracting at least one of grayscale average value, texture, grayscale histogram, and variance peak value of the mapped first brain image;

[0101] Alternatively, at least one of the relative volume, surface area, ratio of surface area to relative volume, and long axis length of the brain region structure in each functional brain region map of the first brain image is combined with at least one of the grayscale average value, texture, grayscale histogram, and variance peak value of the mapped first brain image;

[0102] The step of extracting the second brain morphological feature from the plurality of functional brain area maps of the second brain image comprises the following steps:

[0103] Extracting at least one of the relative volume, surface area, ratio of surface area to relative volume, and long axis length of the brain region structure in each functional brain region map from the plurality of functional brain region maps of the second brain image;

[0104] Alternatively, using multiple functional brain area maps of the second brain image as mask images respectively, mapping the mask images to corresponding areas of the second brain image, and extracting at least one of grayscale average value, texture, grayscale histogram, and variance peak value of the mapped second brain image;

[0105] Alternatively, at least one of the relative volume, surface area, ratio of surface area to relative volume, and major axis length of the brain area structure in each functional brain area map of the second brain image is combined with at least one of the grayscale mean, texture, grayscale histogram, and variance peak of the mapped second brain image.

[0106] In this embodiment, brain morphological features can be extracted from multiple functional brain area maps of a brain image in a variety of ways, such as extracting at least one of the relative volume, surface area, ratio of surface area to relative volume, and major axis length of the brain area structure in each functional brain area map, and matching them by comparing the various parameters of each functional brain area image; or, taking any functional brain area map as a mask image and mapping it to the corresponding area of ​​the corresponding brain image, extracting at least one of the grayscale mean, texture, grayscale histogram, and variance peak of the remaining functional brain area after mask mapping, and matching them by comparing the various parameters of the brain area image after mask mapping; or, combining the above two methods and matching them by comparing the combined parameters; the above multiple methods can use different parameters to realize the extraction of brain morphological features, realize diversified matching of brain images, and adapt to various matching needs.

[0107] It should be noted that when the above two methods are combined, the parameters of relative volume, surface area, ratio of surface area to relative volume, and major axis length of the first method can be one or more, and the grayscale average, texture, grayscale histogram, and variance peak of the remaining functional brain area after mask mapping of the second method can also be one or more to achieve various combinations.

[0108] In one embodiment, if the first brain morphological feature matches the second brain morphological feature, the step of determining that the first brain image and the second brain image belong to the same person comprises the following steps:

[0109] The similarity between the first brain morphological feature and the second brain morphological feature is obtained, and if the similarity is greater than or equal to a second preset value, it is determined that the first brain image and the second brain image belong to the same person.

[0110] In this embodiment, when matching the brain morphological features of the brain images, the similarity of the brain morphological features can be compared. After extracting the brain morphological features from the first brain image and the second brain image respectively, the similarity between the two is obtained. Since each person's brain is unique, when the similarity is greater than or equal to the second preset value, it can be determined that the two brain images belong to the same person. By judging the brain morphological similarity, the relationship between the first brain image and the second brain image can be quickly determined.

[0111] It should be noted that when comparing similarities, the first brain image and the second brain image use the same method for collecting brain morphological features, such as both using at least one of the relative volume, surface area, ratio of surface area to relative volume, and major axis length of the brain structure described above, or both using at least one of the grayscale average, texture, grayscale histogram, and variance peak of the remaining functional brain area after mask mapping, or both using any combination of the above two methods; in addition, the second preset value can be adjusted according to actual needs.

[0112] In one embodiment, the brain image processing method further comprises the following steps:

[0113] If the similarity is less than a second preset value, the first brain image and the second brain image are respectively input into a preset brain spherical mapping network to obtain a first unfolded spherical image corresponding to the first brain image and a second unfolded spherical image corresponding to the second brain image;

[0114] restoring the first unfolded spherical image to a first standard spherical image, and extracting a third brain morphological feature of the first brain image from the first standard spherical image;

[0115] restoring the second unfolded spherical image to a second standard spherical image, and extracting a fourth brain morphological feature of the second brain image from the second standard spherical image;

[0116] If the third brain morphological feature matches the fourth brain morphological feature, it is determined that the first brain image and the second brain image belong to the same person.

[0117] In this embodiment, after extracting brain morphological features by segmenting functional brain areas using brain images, if the corresponding similarity is less than a second preset value, the brain morphological features can be further extracted by brain spherical mapping, and the brain image can be matched and analyzed. This can avoid accidental errors in segmenting functional brain areas using brain images, and further improve the accuracy of brain image matching.

[0118] It should be noted that when determining whether the third brain morphological feature matches the fourth brain morphological feature, a processing process similar to the processing process of the first brain morphological feature and the second brain morphological feature in the above-mentioned spherical mapping can be adopted.

[0119] In one embodiment, the brain image processing method further comprises the following steps:

[0120] If the number of matched feature points is less than a first preset value, the first brain image and the second brain image are respectively input into a preset brain segmentation model to obtain a plurality of functional brain area maps corresponding to the first brain image and a plurality of functional brain area maps corresponding to the second brain image;

[0121] extracting a third brain morphological feature of the first brain image from a plurality of functional brain area maps of the first brain image;

[0122] extracting a fourth brain morphological feature of the second brain image from a plurality of functional brain area maps of the second brain image;

[0123] If the third brain morphological feature matches the fourth brain morphological feature, it is determined that the first brain image and the second brain image belong to the same person.

[0124] In this embodiment, after extracting brain morphological features by means of brain spherical mapping, if the number of matching feature points is less than a first preset value, the brain morphological features can be further extracted by means of brain image segmentation of functional brain areas, and the brain image can be matched and analyzed. This can avoid accidental errors caused by brain spherical mapping and further improve the accuracy of brain image matching.

[0125] It should be noted that the third brain morphological feature and the fourth brain morphological feature obtained by brain region segmentation and extraction are different from the third brain morphological feature and the fourth brain morphological feature obtained by spherical mapping and extraction; when judging whether the third brain morphological feature matches the fourth brain morphological feature, a processing process similar to the processing process of the first brain morphological feature and the second brain morphological feature in the above-mentioned brain region segmentation can be adopted; the above-mentioned brain spherical mapping method and the brain image segmentation functional brain area method can be used alone or in combination, and there is no restriction on the order of use when used in combination.

[0126] Specifically, the brain image processing method can be applied in the brain scanning imaging process of medical equipment, and the image features can be extracted through morphological methods, and used to compare two images to determine whether they belong to the same patient. This method can be used as an auxiliary to the traditional identity comparison method, automatically search the database, provide supplements for images missed by traditional methods, and identify and remove images mistakenly found by traditional methods.

[0127] Studies have shown that the human brain already has complete cerebral sulci and gyri at birth, and subsequent growth is only an increase in brain volume, a pruning process of gray matter thickness on the sulci and gyri, and a myelination process of white matter. In other words, if we extract the morphological characteristics of the brain from a 5-year-old child, when she grows to 25 years old, we can still find her image in the brain image library by comparing it with the 5-year-old image. Compared with personal information such as name and age, which may be subjectively misreported or misreported during input, as well as the reproducibility of fingerprints and changes caused by external forces, the morphological characteristics of brain images are a stable human biomarker.

[0128] Specifically, brain morphology can refer to the analysis of neural images obtained by performing MRI scans, PET scans or CT scans on the human brain to extract representative features. Brain sulci refer to the numerous folds formed in the cerebral cortex, which is the basis of higher neural activity and is closely related to human intelligence. In this application, brain sulci are used as an important feature. According to the features in the neural images, such as the position, width and depth of the brain sulci, each person's features are unique, just like a person's fingerprint circuit. The scanned neural images are quantitatively analyzed and evaluated using a deep learning algorithm, and used as an advanced auxiliary method for biometric identification.

[0129] At the same time, the cerebral sulci divide the brain into different lobes, such as the frontal lobe, temporal lobe, parietal lobe, occipital lobe, etc. If it is further subdivided, the surface of the brain can be divided into 68 parts according to the gyrus. In the case of space-occupying lesions in the brain or surgical lesion removal, each lobe or sulcus can be compared separately. If there is a significant match in most areas, it can be considered that the image is from the same patient.

[0130] In this application, the cerebral cortex is regarded as a highly folded curved surface, which is projected onto a fixed sphere through conformal mapping, and then a series of feature points are extracted on the sphere for the subsequent feature matching. In addition, a standard characteristic feature vector is constructed based on the neuroimaging of the brain. We first segment the whole brain and divide the brain into five regions: frontal lobe, temporal lobe, parietal lobe, occipital lobe and subcortical brain. After segmenting the brain region, neuroimaging features can be extracted from different brain regions as another effective feature for matching. By verifying the features extracted after the cerebral cortex is mapped to the sphere, it can be determined whether the test object is the same person; on the other hand, the degree of matching of the features of each functional area of ​​the human brain can also be used to identify the individual. It is worth mentioning that if, when comparing the features of each functional brain area, the features of a certain functional area cannot be matched, while other functional areas can be matched, it cannot be easily determined that the identity identification is inconsistent, and the functional area may have changed due to lesions.

[0131] In specific applications, brain structure image pairs obtained by MRI scanning equipment, such as T1 and T2 weighted images, can be used.

[0132] After acquiring the image, a unified preprocessing operation flow can be performed on all MRI image data pairs: rotation, resampling, resizing, skull removal, image non-uniformity correction, histogram matching, grayscale normalization, etc., so that all images are converted to a size of 256×256×256mm. 3 The directions are all standard Cartesian LPI coordinate systems, and the grayscale ranges are all standard images in the interval (-1, 1).

[0133] After obtaining the standard image, gray matter segmentation and cortical reconstruction can also be performed.

[0134] There are two different ways to match identities:

[0135] 1. Identity verification system based on spherical mapping and feature matching

[0136] For the input image pair, the two images are mapped to the sphere (i.e. Figure 5 The cortical surface mapping in the sphere is then used to extract features based on the sphere. In this regard, an identity verification system based on spherical mapping and feature matching is designed. The specific framework is described as follows:

[0137] The system mainly consists of three modules: spherical mapping network, feature point extraction and feature point matching. Figure 5 shown.

[0138] The structure of the spherical mapping network draws on the network design of VNet. First, the original grayscale image after preprocessing is input to the network, and the output of the network is a sphere unfolded according to a specific one-to-one mapping rule f. During the training process, the freesurfer spherical image corresponding to the training data is unfolded according to the same rule f as supervision information. For the output of the spherical mapping network, the output is restored to a standard sphere according to the inverse process of f, and the sulci and gyri are mapped to the standard sphere.

[0139] Next, a more accurate and repeatable spherical Harris feature point extraction method is used to extract feature points on the standard sphere. After the feature points are extracted, a matching method is used to pair the feature points to see if there are enough feature points to match. If so, it proves that the identity of the object has been successfully identified.

[0140] 2. Identity verification system based on brain segmentation

[0141] The preprocessed brain MRI images can be divided into training data and test data. The data are labeled by professional doctors, and the segmentation model is used to segment the 5 functional brain areas of the brain structure as the gold standard for segmentation.

[0142] During training, the training data and labels are resized to 256*256*256 and then input into the segmentation model. When the loss function converges, a suitable model is selected as the final segmentation model. This application chooses to use the Vnet network as the segmentation model.

[0143] Then, feature extraction is performed based on the segmented model. Feature extraction can be divided into two parts: one part is that after the model segments the image, the relative volume, surface area, surface area to volume ratio, long axis length, etc. of each substructure can be output. The other part is to use the segmented substructures as masks and then map them to the corresponding areas on the MRI image, and then extract the grayscale mean, texture, grayscale histogram, variance peak and other features of the image after mask mapping. The two parts of the feature can be used separately, or they can be connected to form a new feature.

[0144] Finally, by calculating the similarity of the feature vectors of each brain region of the two control samples, the consistency of the sample pair can be determined, and whether lesions occur in each functional area can also be observed.

[0145] The feature matching algorithm used in this application is the FLANN algorithm, which can be replaced by other feature matching algorithms, such as the K-nearest neighbor algorithm (KNN), the brute force matching algorithm, etc. There are a variety of different algorithms to choose from. Secondly, the present invention divides the image into 5 functional brain areas, and can also be further divided into more refined partitions. At the same time, the segmentation network can also select networks other than Vnet, such as FCN networks such as Unet. Finally, this application mainly uses the information of the cerebral cortex layer for judgment, and then identifies the imaging features of the brain area after segmentation; the order of the two can also be swapped, or the two can be combined to obtain the final identification result.

[0146] This application can map the preprocessed sample pair input image to a standard sphere, extract feature points and perform feature point matching, and then identify whether the sample pair comes from the same person; use the brain segmentation model to obtain the volume, texture, grayscale and other features of different brain regions, and perform quantitative analysis on the functional brain regions corresponding to the sample pairs.

[0147] According to the above-mentioned brain image processing method, the embodiment of the present application further provides a brain image processing system. The embodiment of the brain image processing system is described in detail below.

[0148] See also Figure 6 FIG. 1 is a schematic diagram of the structure of a brain image processing system according to an embodiment. The brain image processing system according to this embodiment includes:

[0149] An image acquisition unit 510, used for acquiring a known first brain image and a second brain image to be compared;

[0150] A feature acquisition unit 520, configured to acquire a first brain morphological feature of the first brain image and a second brain morphological feature of the second brain image;

[0151] The matching judgment unit 530 is used to determine that the first brain image and the second brain image belong to the same person when the first brain morphological feature matches the second brain morphological feature.

[0152] In this embodiment, the brain image processing system includes an image acquisition unit 510, a feature acquisition unit 520 and a matching judgment unit 530; when the image acquisition unit 510 obtains a brain image, it can compare it with a known brain image, the known image is used as the first brain image, and the obtained brain image is used as the second brain image to be compared, the feature acquisition unit 520 processes the first brain image and the second brain image respectively, and obtains the brain morphological features therein respectively, and the matching judgment unit 530 analyzes and matches them, and if the features of the two match, it can be determined that the second brain image to be compared and the known brain image belong to the same person; because the brain has a complete brain structure when a person is born, the morphological features of brain images are a stable human biological identifier, and through the analysis and matching of brain morphological features, multiple brain images of the same patient can be accurately found. At the same time, compared with the distinction method of identification number, certificate number, and medical record number, the solution of the present application can more accurately and effectively distinguish brain images of different patients.

[0153] In one embodiment, the feature acquisition unit 520 is used to input the first brain image and the second brain image into a preset brain spherical mapping network, respectively, to obtain a first unfolded spherical image corresponding to the first brain image, and a second unfolded spherical image corresponding to the second brain image; to restore the first unfolded spherical image to a first standard spherical image, and to extract a first brain morphological feature from the first standard spherical image; and to restore the second unfolded spherical image to a second standard spherical image, and to extract a second brain morphological feature from the second standard spherical image.

[0154] In one embodiment, the feature acquisition unit 520 is further used to preprocess the first brain image and the second brain image respectively, and the preprocessing includes at least one of rotation, resampling, resizing, skull removal, image non-uniformity correction, histogram matching, and grayscale normalization.

[0155] In one embodiment, the feature acquisition unit 520 is further used to perform gray matter segmentation and cortical reconstruction on the preprocessed first brain image and the second brain image, respectively, and input them into the brain spherical mapping network after the cortical reconstruction.

[0156] In one embodiment, Figure 7 As shown, the brain image processing system also includes a network training unit 540, which is used to obtain an initialized spherical mapping network, and obtain multiple brain sample images and corresponding spherical images; use the multiple brain sample images as training input samples, and use the corresponding spherical images in the unfolded spherical images output by the spherical mapping network as training supervision samples to train the spherical mapping network; after training with the training input samples and the training supervision samples, a brain spherical mapping network is obtained.

[0157] In one embodiment, the matching judgment unit 530 is used to determine that the first brain image and the second brain image belong to the same person when the number of feature points matching the first brain morphological feature and the second brain morphological feature is greater than or equal to a first preset value.

[0158] In one embodiment, the feature acquisition unit 520 is used to input the first brain image and the second brain image into a preset brain segmentation model, respectively, to obtain multiple functional brain area maps corresponding to the first brain image, and multiple functional brain area maps corresponding to the second brain image; to extract the first brain morphological feature from the multiple functional brain area maps of the first brain image; and to extract the second brain morphological feature from the multiple functional brain area maps of the second brain image.

[0159] In one embodiment, the feature acquisition unit 520 is used to extract at least one of the relative volume, surface area, ratio of surface area to relative volume, and long axis length of the brain region structure in each functional brain region map from the multiple functional brain region maps of the first brain image;

[0160] Alternatively, the feature acquisition unit 520 is used to use the multiple functional brain area maps of the first brain image as mask images, map the mask images to corresponding areas of the first brain image, and extract at least one of the grayscale average value, texture, grayscale histogram, and variance peak value of the mapped first brain image;

[0161] Alternatively, the feature acquisition unit 520 is used to combine at least one of the relative volume, surface area, ratio of surface area to relative volume, and long axis length of the brain region structure in each functional brain region map of the first brain image with at least one of the grayscale average value, texture, grayscale histogram, and variance peak value of the mapped first brain image;

[0162] In addition, the feature acquisition unit 520 is further used to extract at least one of the relative volume, surface area, ratio of surface area to relative volume, and long axis length of the brain region structure in each functional brain region map from the multiple functional brain region maps of the second brain image;

[0163] Alternatively, the feature acquisition unit 520 is further configured to use the plurality of functional brain region maps of the second brain image as mask images, respectively, map the mask images to corresponding regions of the second brain image, and extract at least one of a grayscale average value, a texture, a grayscale histogram, and a variance peak value of the mapped second brain image;

[0164] Alternatively, the feature acquisition unit 520 is also used to combine at least one of the relative volume, surface area, ratio of surface area to relative volume, and major axis length of the brain area structure in each functional brain area map of the second brain image with at least one of the grayscale mean, texture, grayscale histogram, and variance peak of the mapped second brain image.

[0165] In one embodiment, the matching judgment unit 530 is used to obtain the similarity between the first brain morphological feature and the second brain morphological feature, and if the similarity is greater than or equal to a second preset value, it is determined that the first brain image and the second brain image belong to the same person.

[0166] In one embodiment, when the matching judgment unit 530 judges that the similarity is less than the second preset value, the feature acquisition unit 520 is further used to input the first brain image and the second brain image into a preset brain spherical mapping network respectively, to obtain a first unfolded spherical image corresponding to the first brain image, and a second unfolded spherical image corresponding to the second brain image; to restore the first unfolded spherical image to a first standard spherical image, and to extract a third brain morphological feature of the first brain image from the first standard spherical image; to restore the second unfolded spherical image to a second standard spherical image, and to extract a fourth brain morphological feature of the second brain image from the second standard spherical image;

[0167] The matching judgment unit 530 is further configured to determine that the first brain image and the second brain image belong to the same person when the third brain morphological feature matches the fourth brain morphological feature.

[0168] In one embodiment, when the matching judgment unit 530 determines that the number of matching feature points is less than a first preset value, the feature acquisition unit 520 is further used to input the first brain image and the second brain image into a preset brain segmentation model, respectively, to obtain a plurality of functional brain area maps corresponding to the first brain image, and a plurality of functional brain area maps corresponding to the second brain image; extract a third brain morphological feature of the first brain image from the plurality of functional brain area maps of the first brain image; extract a fourth brain morphological feature of the second brain image from the plurality of functional brain area maps of the second brain image;

[0169] The matching judgment unit 530 is further configured to determine that the first brain image and the second brain image belong to the same person when the third brain morphological feature matches the fourth brain morphological feature.

[0170] The brain image processing system of the embodiment of the present application corresponds one-to-one to the above-mentioned brain image processing method, and the technical features and beneficial effects described in the embodiment of the above-mentioned brain image processing method are applicable to the embodiment of the brain image processing system.

[0171] A readable storage medium stores an executable program, which implements the steps of the above-mentioned brain image processing method when executed by a processor.

[0172] The above-mentioned readable storage medium, through the executable program stored therein, can achieve that when a brain image is obtained, it can be compared with a known brain image, the known image is used as the first brain image, and the obtained brain image is used as the second brain image to be compared, the first brain image and the second brain image are processed respectively, the brain morphological features therein are obtained respectively, and the brain morphological features are analyzed and matched. If the features of the two match, it can be determined that the second brain image to be compared and the known brain image belong to the same person; because the brain already has a complete brain structure when a person is born, the morphological features of brain images are a stable human biological identifier. Through the analysis and matching of brain morphological features, multiple brain images of the same patient can be accurately found. At the same time, compared with the distinction method of identification number, certificate number, and medical record number, the solution of the present application can more accurately and effectively distinguish brain images of different patients.

[0173] A brain image processing device comprises a memory and a processor. The memory stores an executable program. When the processor executes the executable program, the steps of the above-mentioned brain image processing method are implemented.

[0174] The above-mentioned brain image processing device, by running an executable program on a processor, can achieve that when a brain image is obtained, it can be compared with a known brain image, the known image is used as the first brain image, and the obtained brain image is used as the second brain image to be compared, the first brain image and the second brain image are processed respectively, the brain morphological features thereof are obtained respectively, and the brain morphological features are analyzed and matched, and if the features of the two match, it can be determined that the second brain image to be compared and the known brain image belong to the same person; because the brain already has a complete brain structure when a person is born, the morphological features of brain images are a stable human biological identifier, and through the analysis and matching of brain morphological features, multiple brain images of the same patient can be accurately found. At the same time, compared with the distinction method of identification number, certificate number, and medical record number, the solution of the present application can more accurately and effectively distinguish brain images of different patients.

[0175] The brain image processing device may be provided in the medical device 100 , or may be provided in the terminal 130 or the processing engine 140 .

[0176] Those skilled in the art can understand that the implementation of all or part of the processes in the brain image processing method in the above embodiment can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. For example, in the embodiment, the program can be stored in the storage medium of the computer system and executed by at least one processor in the computer system to implement the process including the embodiment of the brain image processing method as described above. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0177] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described 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.

[0178] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program. The program can be stored in a readable storage medium. When the program is executed, it includes the steps described in the above-mentioned method. The storage medium includes: ROM / RAM, disk, optical disk, etc.

[0179] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A brain image processing method, characterized in that: The method comprises the following steps: Acquiring a known first brain image and a second brain image to be compared; Acquiring a first brain morphological feature of the first brain image and a second brain morphological feature of the second brain image; If the first brain morphological feature matches the second brain morphological feature, determining that the first brain image and the second brain image belong to the same person; The step of acquiring the first brain morphological feature of the first brain image and the second brain morphological feature of the second brain image comprises the following steps: Inputting the first brain image and the second brain image into a preset brain spherical mapping network respectively, to obtain a first unfolded spherical image corresponding to the first brain image and a second unfolded spherical image corresponding to the second brain image; Restoring the first unfolded spherical image to a first standard spherical image, and extracting the first brain morphological feature from the first standard spherical image; The second unfolded spherical image is restored to a second standard spherical image, and the second brain morphological feature is extracted from the second standard spherical image.

2. The brain image processing method according to claim 1, characterized in that: Before the step of inputting the first brain image and the second brain image into a preset brain spherical mapping network respectively, the method further includes the following steps: Preprocessing the first brain image and the second brain image respectively, wherein the preprocessing includes at least one of rotation, resampling, resizing, skull removal, image non-uniformity correction, histogram matching, and grayscale normalization; Gray matter segmentation and cortex reconstruction are performed on the preprocessed first brain image and the second brain image respectively, and after the cortex reconstruction, they are respectively input into the brain spherical mapping network.

3. The brain image processing method according to claim 1, characterized in that: The method further comprises the following steps: Obtain an initialized spherical mapping network, and obtain multiple brain sample images and corresponding spherical images; Using the plurality of brain sample images as training input samples, using the unfolded spherical images of the corresponding spherical images output by the spherical mapping network as training supervision samples, and training the spherical mapping network; After training with the training input samples and the training supervision samples, the brain spherical mapping network is obtained.

4. The brain image processing method according to claim 1, characterized in that: The step of determining that the first brain image and the second brain image belong to the same person if the first brain morphological feature matches the second brain morphological feature comprises the following steps: If the number of feature points that match the first brain morphological feature and the second brain morphological feature is greater than or equal to a first preset value, it is determined that the first brain image and the second brain image belong to the same person.

5. The brain image processing method according to claim 4, characterized in that: The method further comprises the following steps: If the number of the matched feature points is less than the first preset value, the first brain image and the second brain image are respectively input into a preset brain segmentation model to obtain a plurality of functional brain area maps corresponding to the first brain image and a plurality of functional brain area maps corresponding to the second brain image; extracting a third brain morphological feature of the first brain image from a plurality of functional brain area maps of the first brain image; extracting a fourth brain morphological feature of the second brain image from a plurality of functional brain area maps of the second brain image; If the third brain morphological feature matches the fourth brain morphological feature, it is determined that the first brain image and the second brain image belong to the same person.

6. A brain image processing method, characterized in that: The method comprises the following steps: Acquiring a known first brain image and a second brain image to be compared; Acquiring a first brain morphological feature of the first brain image and a second brain morphological feature of the second brain image; If the first brain morphological feature matches the second brain morphological feature, determining that the first brain image and the second brain image belong to the same person; The step of acquiring the first brain morphological feature of the first brain image and the second brain morphological feature of the second brain image comprises the following steps: Inputting the first brain image and the second brain image into a preset brain segmentation model respectively, and obtaining a plurality of functional brain area maps corresponding to the first brain image and a plurality of functional brain area maps corresponding to the second brain image; extracting the first brain morphological feature from a plurality of functional brain area maps of the first brain image; extracting the second brain morphological feature from a plurality of functional brain area maps of the second brain image; The step of determining that the first brain image and the second brain image belong to the same person if the first brain morphological feature matches the second brain morphological feature comprises the following steps: Obtaining a similarity between the first brain morphological feature and the second brain morphological feature, and if the similarity is greater than or equal to a second preset value, determining that the first brain image and the second brain image belong to the same person; If the similarity is less than the second preset value, the first brain image and the second brain image are respectively input into a preset brain spherical mapping network to obtain a first unfolded spherical image corresponding to the first brain image and a second unfolded spherical image corresponding to the second brain image; Restoring the first unfolded spherical image to a first standard spherical image, and extracting a third brain morphological feature of the first brain image from the first standard spherical image; restoring the second unfolded spherical image to a second standard spherical image, and extracting a fourth brain morphological feature of the second brain image from the second standard spherical image; If the third brain morphological feature matches the fourth brain morphological feature, it is determined that the first brain image and the second brain image belong to the same person.

7. A readable storage medium having an executable program stored thereon, characterized in that: When the executable program is executed by a processor, the steps of the brain image processing method according to any one of claims 1 to 6 are implemented.

Images