Magnetic resonance scanning acceleration method and system

Abstract

The embodiment of the invention provides a magnetic resonance scanning acceleration method, system and device and a storage medium, and the method comprises the steps: obtaining a positioning scanning sequence of heart magnetic resonance scanning, and obtaining a plurality of scanning orientations of magnetic resonance positioning scanning in the positioning scanning sequence based on the positioning scanning sequence; determining a corresponding scanning acceleration multiple based on the scanning orientation of magnetic resonance positioning scanning; and carrying out magnetic resonance automatic sequence scanning on the corresponding scanning orientation by adopting the scanning acceleration multiple, and obtaining a magnetic resonance scanning image corresponding to the scanning orientation in an automatic sequence.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging, and in particular to a magnetic resonance scanning acceleration method, system, device and storage medium. Background Art

[0002] Cardiac MRI scanning is the process of generating cardiac MRI scan images using MRI scanning equipment. However, the heart is affected by both respiratory and cardiac movements, so cardiac MRI scan images can only be acquired during the relatively static time (systole and diastole) of the cardiac cycle within a breath-holding period, causing the patient to hold his breath too many times. In addition, the slice positioning of the heart is complex, resulting in a long cardiac MRI scan time.

[0003] Therefore, it is desirable to provide a magnetic resonance scanning acceleration solution that can reduce the scanning time of cardiac magnetic resonance scanning and the number of breath-holding times of the patient, while ensuring the quality of the cardiac magnetic resonance scanning image. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for accelerating magnetic resonance scanning, the method comprising: acquiring a positioning scanning sequence of cardiac magnetic resonance scanning, acquiring scanning positions of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the positioning scanning sequence; determining a corresponding scanning acceleration factor based on the scanning position of the magnetic resonance positioning scan; and performing automatic sequential magnetic resonance scanning on the corresponding scanning position using the scanning acceleration factor, and acquiring magnetic resonance scanning images corresponding to the scanning position in an automatic sequence.

[0005] One or more embodiments of the present specification provide a method for accelerating magnetic resonance scanning, the method comprising: acquiring a diagnostic scanning sequence of cardiac magnetic resonance scanning; and automatically determining scanning positions of multiple magnetic resonance positioning scans in a positioning scanning sequence based on the diagnostic scanning sequence.

[0006] One or more embodiments of the present specification provide a method for accelerating magnetic resonance scanning, the method comprising: manually setting a scanning acceleration factor based on a demand parameter corresponding to a magnetic resonance scanning orientation; and / or automatically determining a scanning acceleration factor based on a demand parameter corresponding to a magnetic resonance scanning orientation. In some embodiments, the demand parameter corresponding to the magnetic resonance scanning orientation comprises at least one of the number of slice groups corresponding to the magnetic resonance scanning orientation and the number of cardiac cycles corresponding to the magnetic resonance scanning orientation.

[0007] One or more embodiments of the present specification provide a method for accelerating magnetic resonance scanning, the method comprising: automatically identifying a magnetic resonance scanning image corresponding to a previous scanning position, and automatically determining scanning parameters of a next scanning position based on the identification result; acquiring a magnetic resonance scanning image corresponding to the next scanning position according to the scanning parameters of the next scanning position; and repeating automatic identification and acquisition of magnetic resonance scanning images based on the magnetic resonance scanning image corresponding to the next scanning position until the magnetic resonance scanning image corresponding to the last scanning position is acquired.

[0008] One or more embodiments of the present specification provide a magnetic resonance scanning acceleration system, the system comprising: a scanning position acquisition module, used to acquire a positioning scanning sequence of cardiac magnetic resonance scanning, and acquire scanning positions of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the positioning scanning sequence; an acceleration factor determination module, used to determine a corresponding scanning acceleration factor based on the scanning position of the magnetic resonance positioning scan; and a scanning image acquisition module, used to perform automatic sequential magnetic resonance scanning of the corresponding scanning position using the scanning acceleration factor, and acquire magnetic resonance scanning images corresponding to the scanning position in an automatic sequence.

[0009] One or more embodiments of the present specification provide a magnetic resonance scanning acceleration system, the system comprising an acceleration factor determination module, further used to: acquire a diagnostic scanning sequence of cardiac magnetic resonance scanning; and automatically determine scanning orientations of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the diagnostic scanning sequence.

[0010] One or more embodiments of the present specification provide a magnetic resonance scanning acceleration system, which includes a scanning image acquisition module, and is further used to: automatically identify the magnetic resonance scanning image corresponding to the previous scanning orientation, and automatically determine the scanning parameters of the next scanning orientation based on the identification result; acquire the magnetic resonance scanning image corresponding to the next scanning orientation according to the scanning parameters of the next scanning orientation; and repeat the automatic identification and acquisition of the magnetic resonance scanning image based on the magnetic resonance scanning image corresponding to the next scanning orientation until the magnetic resonance scanning image corresponding to the last scanning orientation is acquired.

[0011] One or more embodiments of the present specification provide a magnetic resonance scanning acceleration device, the device comprising: at least one storage medium storing computer instructions; and at least one processor executing the computer instructions to implement a method for magnetic resonance scanning acceleration.

[0012] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a magnetic resonance scanning acceleration method.

[0013] One or more embodiments of the present specification adopt different scanning acceleration multiple strategies based on different required parameters (such as the number of cardiac cycles and / or the number of slice groups) to ensure that different cardiac magnetic resonance scanning image quality requirements are met, while improving the scanning time and reducing the number of times the patient holds his breath.

[0014] One or more embodiments of the present specification automatically determine the scanning orientations of multiple magnetic resonance positioning scans in a positioning scanning sequence based on a diagnostic scanning sequence of cardiac magnetic resonance scanning, which can reduce unnecessary magnetic resonance positioning scans based on diagnostic purposes or further strengthen the scanning to improve positioning details, thereby improving the efficiency of cardiac magnetic resonance scanning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0016] Figure 1 is a schematic diagram of an exemplary application scenario of a magnetic resonance scanning acceleration system according to some embodiments of this specification;

[0017] Figure 2 is an exemplary module diagram of a magnetic resonance scanning acceleration device according to some embodiments of this specification;

[0018] Figure 3 is an exemplary flow chart of a magnetic resonance scanning acceleration method according to some embodiments of the present specification;

[0019] Figure 4 is an exemplary flow chart of determining scanning positions of multiple magnetic resonance localization scans based on a diagnostic scanning sequence according to some embodiments of the present specification;

[0020] Figure 5 is an exemplary flow chart of automatic sequential scanning of magnetic resonance according to some embodiments of the present specification;

[0021] Figure 6 is an exemplary schematic diagram of a cardiac cross-sectional slice group according to some embodiments of the present specification;

[0022] Figure 7 is an exemplary schematic diagram of multiple magnetic resonance positioning images corresponding to scanning positions of multiple magnetic resonance positioning scans according to some embodiments of this specification;

[0023] Fig. 8A , Figure 8B and Figure 8C It is a display interface of a terminal device according to some embodiments of this specification;

[0024] Fig. 9 is an exemplary schematic diagram of magnetic resonance scanning acceleration according to some embodiments of the specification. DETAILED DESCRIPTION

[0025] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0026] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0027] As shown in this specification 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 "comprise" and "include" 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] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0029] Figure 1 It is a schematic diagram of an exemplary application scenario of a magnetic resonance scanning acceleration system according to some embodiments of the present specification.

[0030] The magnetic resonance scanning acceleration system 100 can acquire multiple magnetic resonance scanning images using different scanning acceleration multiples by implementing the method and / or process disclosed in this specification, thereby improving the efficiency of cardiac magnetic resonance scanning.

[0031] like Figure 1 As shown, the magnetic resonance scanning acceleration system 100 may include: a scanning device 110 , a processing device 120 , a terminal device 130 , a network 140 and a storage device 150 .

[0032] The scanning device 110 can transmit a signal to a target object or a portion thereof, and collect echo data related to the target object or a portion thereof. In some embodiments, the scanned object can include, but is not limited to, a human body, an organ, a body, a damaged part, a tumor, an object, a phantom, etc. In some embodiments, the scanning device 110 can include a single-modality imaging device. For example, the scanning device 110 can include a magnetic resonance imaging (MRI) device (also referred to as an MR scanner). In some embodiments, the scanning device 110 can include a multi-modality imaging device. For example, a multi-modality imaging device can include a PET-MR device. For illustrative purposes, the present application is described in conjunction with a magnetic resonance imaging (MRI) device.

[0033] The processing device 120 may process data and / or information obtained from the scanning device 110, the terminal device 130, and / or the storage device 150. For example, the number of slice groups and / or the number of cardiac cycles may be determined. For another example, the scanning acceleration factor of the magnetic resonance scanning orientation may be determined. In some embodiments, the processing device 120 may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a system on chip (SoC), a microcontroller unit (MCU), etc. and / or any combination thereof.

[0034] In some embodiments, the processing device 120 may include a computer, a user console, a single server or a server group, etc. The server group may be centralized or distributed. In some embodiments, the processing device 120 may be local or remote. For example, the processing device 120 may access information and / or data stored in the scanning device 110, the terminal device 130 and / or the storage device 150 via the network 140. For another example, the processing device 120 may directly connect the scanning device 110, the terminal device 130 and / or the storage device 150 to access the stored information and / or data. In some embodiments, the processing device 120 may be implemented on a cloud platform. As an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, a cloud-to-cloud, a multi-cloud, etc., or any combination thereof. In some embodiments, the processing device 120 or a portion of the processing device 120 may be integrated into the scanning device 110.

[0035] The terminal device 130 can display images, such as magnetic resonance scan images, to the user. The terminal device 130 can include a mobile device 131, a tablet computer 132, a notebook computer 133, etc., or any combination thereof. In some embodiments, the terminal device 130 can be a part of the processing device 120.

[0036] The network 140 may include any suitable network that facilitates information and / or data exchange of the magnetic resonance scanning acceleration system 100. In some embodiments, one or more components of the magnetic resonance scanning acceleration system 100 (e.g., the scanning device 110, the processing device 120, the storage device 150, the terminal device 130) may communicate information and / or data with one or more other components of the magnetic resonance scanning acceleration system 100 through the network 140. For example, the processing device 120 may obtain a cardiac scanning protocol group (including a positioning scanning sequence and / or a diagnostic scanning sequence) from the scanning device 110 via the network 140. In some embodiments, one or more components of the magnetic resonance scanning acceleration system 100 (e.g., the scanning device 110, the processing device 120, the storage device 150, the terminal device 130) may communicate information and / or data with one or more external resources (e.g., an external database of a third party, etc.). The network 140 may be and / or include a public network, a private network, a wired network, a wireless network, a cellular 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. In some embodiments, the network 140 may include one or more network access points. For example, the network 140 may include wired and / or wireless network access points such as base stations and / or Internet exchange points, and one or more components of the magnetic resonance scanning acceleration system 100 may be connected to the network 140 through these access points to exchange data and / or information.

[0037] The storage device 150 can store data, instructions and / or any other information. In some embodiments, the storage device 150 can store data obtained from the scanning device 110, the terminal device 130 and / or the processing device 120. In some embodiments, the storage device 150 can store data and / or instructions, and the processing device 120 can execute or use the data and instructions to perform the exemplary method / system described in this application. In some embodiments, the storage device 150 may include a large capacity memory, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc. or any combination thereof. In some embodiments, the storage device 150 can be connected to the network 140 to communicate with one or more other components of the magnetic resonance scanning acceleration system 100 (e.g., the scanning device 110, the processing device 120, the storage device 150, the terminal device 130). One or more components of the magnetic resonance scanning acceleration system 100 can access the data or instructions stored in the storage device 150 through the network 140. In some embodiments, the storage device 150 may be directly connected to or communicate with one or more other components (e.g., the scanning device 110, the processing device 120, the storage device 150, the terminal device 130) of the magnetic resonance scanning acceleration system 100. In some embodiments, the storage device 150 may be a part of the processing device 120.

[0038] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, under the guidance of the contents of this specification, various changes and modifications can be made. The features, structures, methods and other features of the exemplary embodiments described in this specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. However, these changes and modifications will not deviate from the scope of this specification.

[0039] Figure 2 is an exemplary module diagram of a magnetic susceptibility imaging device according to some embodiments of this specification. Figure 2 As shown, the magnetic susceptibility imaging device 200 may include a scanning position acquisition module 210 , an acceleration multiple determination module 220 and a scanning image acquisition module 230 .

[0040] The scanning position acquisition module 210 can be used to acquire a positioning scanning sequence of cardiac magnetic resonance scanning, and acquire scanning positions of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the positioning scanning sequence. In some embodiments, the scanning position acquisition module 210 can perform one or more of the following operations: acquire a diagnostic scanning sequence of cardiac magnetic resonance scanning; and automatically determine scanning positions of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the diagnostic scanning sequence.

[0041] The acceleration factor determination module 220 may be used to determine the corresponding scanning acceleration factor based on the scanning orientation of the magnetic resonance positioning scan. In some embodiments, the scanning acceleration factor is determined based on the requirement parameters corresponding to the magnetic resonance scanning orientation. In some embodiments, the acceleration factor determination module 220 may manually set the scanning acceleration factor based on the requirement parameters corresponding to the magnetic resonance scanning orientation; and / or automatically determine the scanning acceleration factor based on the requirement parameters corresponding to the magnetic resonance scanning orientation. In some embodiments, the requirement parameters corresponding to the magnetic resonance scanning orientation include at least one of the number of slice groups corresponding to the magnetic resonance scanning orientation and the number of cardiac cycles corresponding to the magnetic resonance scanning orientation.

[0042] The scanning image acquisition module 230 can be used to perform magnetic resonance automatic sequential scanning of the corresponding scanning position using the scanning acceleration multiple, and automatically acquire the magnetic resonance scanning image corresponding to the scanning position in sequence. In some embodiments, the scanning image acquisition module 230 can perform one or more of the following operations: automatically identify the magnetic resonance scanning image corresponding to the previous scanning position, and automatically determine the scanning parameters of the next scanning position based on the identification result; acquire the magnetic resonance scanning image corresponding to the next scanning position according to the scanning parameters of the next scanning position; based on the magnetic resonance scanning image corresponding to the next scanning position, repeat the automatic identification and acquisition of the magnetic resonance scanning image until the magnetic resonance scanning image corresponding to the last scanning position is acquired.

[0043] In some embodiments, the scanning position acquisition module 210, the acceleration factor determination module 220 and the scanning image acquisition module 230 can be implemented on the same or different processing devices.

[0044] Figure 3 FIG. 3 is an exemplary flow chart of a magnetic resonance scanning acceleration method according to some embodiments of the present specification. In some embodiments, the processing device 120 and / or the magnetic resonance scanning acceleration system 100 may execute process 300. Figure 3 As shown, process 300 may include the following steps.

[0045] Step 310 , obtaining a positioning scan sequence of cardiac magnetic resonance scanning, and obtaining scanning positions of multiple magnetic resonance positioning scans in the positioning scan sequence based on the positioning scan sequence. Specifically, step 310 may be performed by the scanning position obtaining module 210 .

[0046] Cardiac magnetic resonance scanning can be a process of using a magnetic resonance device to transmit radio frequency pulses to a region of interest, converting the energy received from the region of interest into electrical signals, and generating a cardiac magnetic resonance image based on the electrical signals.

[0047] In some embodiments, the cardiac magnetic resonance scan may include multiple magnetic resonance localization scans and multiple magnetic resonance diagnostic scans. For example, the cardiac magnetic resonance scan of patient A may include 7 magnetic resonance localization scans and 5 magnetic resonance diagnostic scans.

[0048] Magnetic resonance localization scanning can be a scanning process of acquiring magnetic resonance localization images, wherein the magnetic resonance localization images are magnetic resonance scanning images used to determine the position and orientation relationship of the patient's internal structure.

[0049] In some embodiments, the format of the magnetic resonance localization image may include Joint Photographic Experts Group (JPEG) image format, Tagged Image File Format (TIFF) image format, Graphics Interchange Format (GIF) image format, Kodak Flash PiX (FPX) image format, Digital Imaging and Communications in Medicine (DICOM) image format, etc.

[0050] In some embodiments, the MRI localization image may be a two-dimensional (2D) image or a three-dimensional (3D) image. In some embodiments, the three-dimensional image may be formed by a sequence of two-dimensional image slices.

[0051] The scanning orientation may be a region of interest and / or anatomical orientation for determining the position and orientation relationship of the patient's internal structure. The region of interest may include but is not limited to the chest, heart, heart chambers, etc., and the anatomical orientation may include but is not limited to the coronal, sagittal, and axial orientations, etc. For example, the scanning orientation "heart transverse position" may be the anatomical orientation "transverse position" of the region of interest "heart". For another example, the scanning orientation "heart three-chamber heart" may be the region of interest "heart three-chamber heart".

[0052] In some embodiments, each magnetic resonance localization scan may correspond to a scanning position. It is understood that the relationship between the multiple scanning positions may be determined based on the magnetic resonance localization images corresponding to the multiple magnetic resonance localization scans.

[0053] The positioning scanning sequence of the cardiac magnetic resonance scanning may be a scanning sequence used for magnetic resonance positioning scanning. In some embodiments, the scanning position acquisition module 210 may acquire the positioning scanning sequence of the cardiac magnetic resonance scanning from the cardiac scanning protocol group.

[0054] In some embodiments, the positioning scan sequence of the cardiac magnetic resonance scan may include multiple positioning scan subsequences corresponding to multiple magnetic resonance positioning scans. For example, the positioning scan sequence of the cardiac magnetic resonance scan may include positioning scan subsequences: T1, T2, T3, T4, T5, T6 and T7.

[0055] In some embodiments, each positioning scan subsequence may include positioning scan information. In some embodiments, the positioning scan information may include the type of the positioning scan subsequence and the scanning position corresponding to the magnetic resonance positioning scan. In some embodiments, the type of the positioning scan subsequence may include but is not limited to a fast spin echo (Fast Spin Echo, FSE) sequence, a gradient echo (Gradient Echo, GRE) sequence, an echo plane (Echo Planar Imaging, EPI) sequence, a gradient spin echo (Gradient And Spin Echo, GRASE) sequence, or the like or a combination thereof.

[0056] Continuing with the above example, T1, T2, T3, T4, T5, T6 and T7 can respectively contain positioning scan information: FSE sequence-chest coronary position, FSE sequence-heart axial position, FSE sequence-heart two-chamber heart, GRE sequence-heart four-chamber heart, EPI sequence-heart short axis, GRE sequence-heart two-chamber heart and GRE sequence-heart three-chamber heart.

[0057] In some embodiments, the scanning orientation acquisition module 210 may adjust the type of the positioning scanning subsequence corresponding to the next scanning orientation based on the magnetic resonance scanning image corresponding to the previous scanning orientation.

[0058] Specifically, the scanning orientation acquisition module 210 may determine the scanning orientations of multiple magnetic resonance positioning scans based on the scanning orientations of multiple positioning scan subsequences in the positioning scan sequence. Figure 7 is an exemplary schematic diagram of a plurality of magnetic resonance positioning images corresponding to the scanning positions of a plurality of magnetic resonance positioning scans shown in some embodiments of this specification, such as Figure 7 As shown, the scanning orientation acquisition module 210 can determine the scanning orientations of multiple magnetic resonance positioning scans based on the scanning orientations of T1, T2, T3, T4, T5, T6 and T7: chest coronal position cor, heart transverse position tra, heart chamber 2ch, heart chamber 4ch, heart short axis SA, heart chamber 2ch and heart chamber 3ch.

[0059] Magnetic resonance diagnostic scanning can be a scanning process for acquiring magnetic resonance diagnostic images. Among them, magnetic resonance diagnostic images are magnetic resonance images used to diagnose and analyze patient diseases. In some embodiments, magnetic resonance diagnostic images can be acquired based on magnetic resonance localization images. For more descriptions of magnetic resonance diagnostic images, please refer to magnetic resonance localization images, which will not be repeated here.

[0060] The diagnostic scanning sequence of the cardiac magnetic resonance scanning may be a scanning sequence for magnetic resonance diagnostic scanning. In some embodiments, the scanning orientation acquisition module 210 may determine the scanning orientations of multiple magnetic resonance localization scans based on the diagnostic scanning sequence. For a detailed description of determining the scanning orientations of multiple magnetic resonance localization scans based on the diagnostic scanning sequence, see Figure 4 And the related description will not be repeated here.

[0061] Step 320 , determining a corresponding scanning acceleration factor based on the scanning orientation of the magnetic resonance localization scanning. Specifically, step 320 may be performed by the acceleration factor determination module 220 .

[0062] The scanning acceleration factor corresponding to the scanning position may be the scanning acceleration factor of the positioning scanning subsequence corresponding to the scanning position. In some embodiments, the scanning acceleration factor may be determined based on the required parameters corresponding to the magnetic resonance scanning position.

[0063] The demand parameters corresponding to the MRI scanning orientation are parameters set based on user and / or patient requirements. In some embodiments, the demand parameters corresponding to the MRI scanning orientation may include at least one of the number of slice groups corresponding to the MRI scanning orientation and the number of cardiac cycles corresponding to the MRI scanning orientation.

[0064] The slice group corresponding to the magnetic resonance scanning position may be a sequence of magnetic resonance localization images corresponding to each magnetic resonance scanning position. It can be understood that in some embodiments, each magnetic resonance scanning position may correspond to multiple magnetic resonance localization images. For example, Figure 6 is an exemplary schematic diagram of a cardiac cross-sectional slice group according to some embodiments of the present specification, such as Figure 6 As shown, the scanning orientation "heart transverse position tra" can correspond to multiple magnetic resonance positioning images at multiple transverse positions of the heart.

[0065] The number of slice groups corresponding to the magnetic resonance scanning orientation may be the number of magnetic resonance positioning images corresponding to each magnetic resonance scanning orientation. For example, the number of slice groups corresponding to the scanning orientation "coronal position of chest cor" may be the number of magnetic resonance positioning images "2" of the two coronal positions of the heart, and the number of slice groups corresponding to the "transverse position of heart tra" may be the number of magnetic resonance positioning images "5" of the five transverse positions of the heart. Similarly, the number of slice groups corresponding to the scanning orientations "two-chamber heart 2ch", "four-chamber heart 4ch", "short axis heart SA" and "three-chamber heart 3ch" may be 2, 2, 9 and 4 respectively.

[0066] In some embodiments, the acceleration multiple determination module 220 may automatically determine the corresponding number of slice groups based on the scanning position of the magnetic resonance scan. As an example only, the acceleration multiple determination module 220 may store the number of slice groups corresponding to the preset scanning position in the storage device 150, and then obtain the corresponding number of slice groups from the storage device 150 based on the scanning positions of multiple magnetic resonance positioning scans in the positioning scan sequence.

[0067] In some embodiments, the acceleration multiple determination module 220 may automatically determine the number of slice groups for the next scanning position based on the magnetic resonance scanning image corresponding to the previous scanning position. For a description of automatically determining the number of slice groups for the next scanning position based on the magnetic resonance scanning image corresponding to the previous scanning position, see Figure 5 And its description will not be repeated here.

[0068] In some embodiments, the larger the number of slice groups corresponding to the magnetic resonance scanning orientation, the larger the corresponding scanning acceleration factor. It can be understood that when the number of slice groups corresponding to the magnetic resonance scanning orientation is larger, the more scanning time is required for the same scanning speed, and increasing the scanning acceleration factor can reduce the scanning time of the corresponding magnetic resonance positioning scan, thereby controlling the scanning time of each magnetic resonance positioning scan within a certain range, and completing the cardiac magnetic resonance scan within one breath holding time.

[0069] A cardiac cycle may be a process in which a patient's heart completes one physiological movement. For example, one physiological movement of the heart may include one diastolic movement and one systolic movement, and a cardiac cycle may be a process in which one systolic movement and one diastolic movement are completed.

[0070] In some embodiments, the acceleration multiple determination module 220 may determine the time corresponding to a cardiac cycle based on the cardiac motion signal. For example, the acceleration multiple determination module 220 may determine that the time corresponding to a cardiac cycle is 600 milliseconds based on an electrocardiogram (ECG).

[0071] The number of cardiac cycles may be the number of cardiac cycles within a certain period of time. The number of cardiac cycles corresponding to the cardiac magnetic resonance scan may be the number of cardiac cycles within the cardiac magnetic resonance scan time.

[0072] In order to ensure that the patient completes the cardiac magnetic resonance scan within one breath-holding time, in some embodiments, the acceleration multiple determination module 220 can determine the number of cardiac cycles corresponding to the cardiac magnetic resonance scan based on the patient's breath-holding time and the time corresponding to the cardiac cycle. For example, if the patient's breath-holding time is 14400 milliseconds and the time corresponding to the cardiac cycle is 600 milliseconds, the number of cardiac cycles corresponding to the cardiac magnetic resonance scan is INT(14400 / 600)=24.

[0073] The number of cardiac cycles corresponding to the magnetic resonance scanning orientation may be the number of cardiac cycles of the patient during the magnetic resonance positioning scanning stage. In some embodiments, the acceleration multiple determination module 220 may determine the number of cardiac cycles corresponding to the corresponding magnetic resonance scanning orientation based on the number of cardiac cycles corresponding to the cardiac magnetic resonance scanning and the positioning scanning time ratio. The positioning scanning time ratio may represent an estimated ratio of the magnetic resonance positioning scanning time to the cardiac magnetic resonance scanning time. In some embodiments, the positioning scanning time ratio may be a preset default value. For example, 1 / 3. In some embodiments, the positioning scanning time ratio may be determined based on the number of magnetic resonance positioning scans and the number of magnetic resonance diagnostic scans. For example, based on 7 magnetic resonance positioning scans and 5 magnetic resonance diagnostic scans, the positioning scanning time ratio is determined to be 7 / (5+7)=7 / 12.

[0074] As an example only, the acceleration factor determination module 220 may determine that the number of cardiac cycles corresponding to the magnetic resonance scanning orientation is 24*(1 / 3)=8 based on the number of cardiac cycles corresponding to the cardiac magnetic resonance scanning 24 and the positioning scanning time ratio 1 / 3.

[0075] In some embodiments, the acceleration multiple determination module 220 can manually set the scanning acceleration multiple based on the requirement parameters corresponding to the magnetic resonance scanning position. Specifically, the acceleration multiple determination module 220 can send the requirement parameters corresponding to the magnetic resonance scanning position to the display interface of the terminal device 130, and then obtain the scanning acceleration multiple corresponding to the requirement parameters set by the user based on the display interface from the terminal device 130. In some embodiments, the acceleration multiple determination module 220 can obtain the scanning acceleration technology and phase reference line set by the user from the terminal device 130.

[0076] For example, Fig. 8A , Figure 8B and Figure 8C is a display interface of a terminal device according to some embodiments of this specification, such as Fig. 8A , Figure 8B and Figure 8C As shown, the user can select the scanning acceleration technology of slice group 1 as 1D, the scanning acceleration factor as 2, and the phase reference line as 24 through the display interface, select the scanning acceleration technology of slice group 2 as 1D (the first scanning acceleration mode), the scanning acceleration factor as 3, and the phase reference line as 28, and select the scanning acceleration technology of slice group 3 as uCS (the second scanning acceleration mode), the scanning acceleration factor as 3, and the phase reference line as 18.

[0077] Some embodiments of the present specification manually determine the scanning acceleration factor based on the required parameters corresponding to the magnetic resonance scanning orientation, thereby ensuring that the magnetic resonance positioning scan can be completed within multiple cardiac cycles within one breath-holding time based on user experience.

[0078] In some embodiments, the acceleration factor determination module 220 may automatically determine the scanning acceleration factor based on the required parameters corresponding to the magnetic resonance scanning position.

[0079] In some embodiments, the acceleration factor determination module 220 can automatically determine the scanning acceleration factor based on the number of slice groups corresponding to the magnetic resonance scanning orientation. Specifically, the acceleration factor determination module 220 can determine the corresponding scanning acceleration factor based on the number of slice groups corresponding to the magnetic resonance scanning orientation according to the relationship between the number of slice groups and the scanning acceleration factor set in advance.

[0080] For example, the relationship between the preset number of slice groups and the scanning acceleration multiple may include: when the number of slice groups (the number of slices in a slice group) is less than or equal to 2, the scanning acceleration multiple is 2 times; when the number of slice groups is greater than 2 and less than or equal to 6, the scanning acceleration multiple is 3 times; when the number of slice groups is greater than 6, the scanning acceleration multiple is 4 times; the acceleration multiple determination module 220 can determine the corresponding scanning acceleration multiples of 2 times, 3 times, 2 times, 2 times, 4 times and 3 times respectively based on the slice group numbers 2, 5, 2, 2, 9 and 4 corresponding to "coronary position cor", "transverse position tra", "two chambers of heart 2ch", "four chambers of heart 4ch" and "short axis of heart SA"

[0081] Some embodiments of the present specification determine the scanning acceleration factor based on the number of slice groups corresponding to the magnetic resonance scanning orientation, so that different scanning acceleration factors can be used based on the quality requirements of different magnetic resonance positioning images corresponding to different magnetic resonance scanning orientations, thereby improving the speed of the magnetic resonance positioning scanning while ensuring the quality of the magnetic resonance positioning image corresponding to each scanning orientation.

[0082] In some embodiments, the acceleration factor determination module 220 can automatically determine the scanning acceleration factor based on the number of cardiac cycles corresponding to the magnetic resonance scanning orientation. Specifically, the acceleration factor determination module 220 can determine the number of slice groups included in each cardiac cycle based on the number of cardiac cycles and the number of slice groups corresponding to the magnetic resonance scanning orientation, and then determine the scanning acceleration factor corresponding to each cardiac cycle based on the number of slice groups included in each cardiac cycle, the time corresponding to each cardiac cycle, and the slice scanning time. The slice scanning time can be the scanning time required for each slice group before the magnetic resonance positioning scanning is accelerated.

[0083] Continuing with the above example, the acceleration multiple determination module 220 can determine that the number of slice groups included in each cardiac cycle is 3 or 4 based on the ratio of the number of slice groups "2+5+2+2+9+4+2=26" corresponding to the 7 magnetic resonance scanning positions to the number of cardiac cycles 8, which is 3.25. For example, the first 6 cardiac cycles each contain 3 slice groups, and the last 2 cardiac cycles each contain 4 slice groups. Then, based on the number of slice groups 3 and 4 in each of the first 6 cardiac cycles, the acceleration multiple determination module 220 can determine that the number of slice groups included in each of the first 6 cardiac cycles is 3 and 4 in each of the last 2 cardiac cycles. The time corresponding to each cardiac cycle is 600 milliseconds and the slice scanning time is 200 milliseconds, and the scanning acceleration factor of each cardiac cycle in the first 6 cardiac cycles is determined to be 200×3 / 600=1; based on the number of slice groups 4 contained in each cardiac cycle in the last 2 cardiac cycles, the time corresponding to each cardiac cycle is 600 milliseconds and the slice scanning time is 200 milliseconds, the scanning acceleration factor of each cardiac cycle in the last 2 cardiac cycles is determined to be 200×4 / 600=1.34.

[0084] Some embodiments of the present specification further determine the scanning acceleration factor based on the number of cardiac cycles corresponding to the magnetic resonance scanning position, so as to complete the magnetic resonance positioning scan within multiple cardiac cycles within one breath-holding time, while ensuring that the number of slice groups corresponding to each magnetic resonance scanning position completes the scan, that is, the magnetic resonance positioning image quality corresponding to each magnetic resonance scanning position.

[0085] Step 330 , using the scanning acceleration multiple to perform magnetic resonance automatic sequential scanning on the corresponding scanning position, and automatically sequentially acquiring magnetic resonance scanning images corresponding to the scanning position. Specifically, step 330 may be executed by the scanning image acquisition module 230 .

[0086] The automatic sequential magnetic resonance scanning may scan the region of interest of the patient based on the sequence of scanning sequences (including positioning scanning sequences and / or diagnostic scanning sequences) in the cardiac scanning protocol group.

[0087] The magnetic resonance scanning image may include a magnetic resonance localization image and a magnetic resonance diagnostic image. For a detailed description of the magnetic resonance localization image, please refer to the relevant description of step 310, and for a relevant description of the magnetic resonance diagnostic image, please refer to the relevant description of step 320, which will not be repeated here.

[0088] Specifically, in some embodiments, the scanning image acquisition module 230 can scan the patient's area of ​​interest based on the order of multiple positioning scanning subsequences in the positioning scanning sequence, using acceleration multiples corresponding to multiple slice groups and / or multiple cardiac cycles, and acquire corresponding magnetic resonance positioning images.

[0089] As an example only, the scanning image acquisition module 230 can be based on the order of the positioning scanning subsequences T1, T2, T3, T4, T5, T6 and T7, and use scanning acceleration multiples of 2 times, 3 times, 2 times, 2 times, 9 times, 2 times and 4 times corresponding to the corresponding slice groups to respectively acquire the corresponding magnetic resonance positioning images of the chest coronal position cor, heart transverse position tra, heart chamber 2ch, heart chamber 4ch, heart short axis SA, heart chamber 2ch and heart chamber 3ch.

[0090] As another example, the scanning image acquisition module 230 can be based on the order of the positioning scan subsequences T1, T2, T3, T4, T5, T6 and T7, using a scanning acceleration multiple of 1 in the first 6 cardiac cycles and a scanning acceleration multiple of 1.34 in the last 2 cardiac cycles, to acquire the corresponding magnetic resonance positioning images of the chest coronal position cor, heart transverse position tra, heart chamber 2ch, heart chamber 4ch, heart short axis SA, heart chamber 2ch and heart chamber 3ch.

[0091] In some embodiments, the scanning image acquisition module 230 can acquire the magnetic resonance scanning image corresponding to the next scanning position based on the magnetic resonance scanning image corresponding to the previous scanning position. For a detailed description of acquiring the magnetic resonance scanning image corresponding to the next scanning position based on the magnetic resonance scanning image corresponding to the previous scanning position, please refer to Figure 5 And the related description will not be repeated here.

[0092] Specifically, in some embodiments, the scanning image acquisition module 230 can scan the patient's area of ​​interest based on the order of multiple diagnostic scanning subsequences in the diagnostic scanning sequence and use acceleration multiples corresponding to multiple slice groups and / or multiple cardiac cycles to acquire corresponding magnetic resonance diagnostic images.

[0093] Among them, the acceleration multiples corresponding to the multiple slice groups and / or multiple cardiac cycles of the magnetic resonance diagnostic scan can be referred to the magnetic resonance positioning scan, which will not be described in detail here.

[0094] Some embodiments of the present specification adopt different scanning acceleration multiple strategies for different required parameters (for example, the number of cardiac cycles and / or the number of slice groups), so as to ensure that different cardiac magnetic resonance scanning image quality requirements are met, while improving the scanning time and reducing the number of times the patient holds his breath.

[0095] Figure 4 400 is an exemplary flow chart of determining the scanning positions of multiple magnetic resonance positioning scans based on a diagnostic scanning sequence according to some embodiments of the present specification. In some embodiments, the processing device 120, the magnetic resonance scanning acceleration system 100 and / or the scanning position acquisition module 210 executes the process 400. Figure 4 As shown, process 400 may include the following steps.

[0096] Step 410, obtaining a diagnostic scan sequence of cardiac magnetic resonance scanning.

[0097] As can be seen from the foregoing, the diagnostic scanning sequence of cardiac magnetic resonance scanning can be a scanning sequence used for magnetic resonance diagnostic scanning. In some embodiments, the scanning orientation acquisition module 210 can acquire the diagnostic scanning sequence of cardiac magnetic resonance scanning from the cardiac scanning protocol group.

[0098] In some embodiments, the diagnostic scan sequence of the cardiac magnetic resonance scan may include multiple diagnostic scan subsequences corresponding to multiple magnetic resonance diagnostic scans. For example, the diagnostic scan sequence of the cardiac magnetic resonance scan may include three diagnostic scan subsequences: T8, T9, and T10.

[0099] In some embodiments, each diagnostic scan subsequence may include diagnostic scan information. In some embodiments, the diagnostic scan information may include the type of the diagnostic scan subsequence and the target position corresponding to the magnetic resonance diagnostic scan.

[0100] The types of the diagnostic scanning subsequences can refer to the types of the positioning scanning subsequences, which will not be described in detail here.

[0101] The target position corresponding to the magnetic resonance diagnostic scan may be a region of interest and / or anatomical position for diagnosing and analyzing a patient's disease. For example, the target position may include "left ventricular outflow tract LVOT", "tricuspid valve" and "aortic valve".

[0102] In some embodiments, each magnetic resonance diagnostic scan may correspond to a target position. It is understood that, according to different diagnostic purposes, analysis features of regions of interest of multiple target positions may be determined based on magnetic resonance diagnostic images corresponding to multiple magnetic resonance diagnostic scans.

[0103] Just as an example, based on the patient's previous medical consultation results, the doctor wants to determine whether the patient's aortic valve has cardiovascular blockage, so the target location may include "aortic valve".

[0104] Step 420: automatically determine the scanning positions of multiple magnetic resonance localization scans in the localization scan sequence based on the diagnostic scan sequence.

[0105] In some embodiments, the scanning orientation acquisition module 210 may acquire the target orientations of multiple magnetic resonance diagnostic scans in the diagnostic scan sequence based on the diagnostic scan sequence. Specifically, the scanning orientation acquisition module 210 may determine the target orientations of multiple magnetic resonance diagnostic scans based on the target orientations of multiple diagnostic scan subsequences in the diagnostic scan sequence. For example, based on the target orientations of T8, T9, T10, T11, and T12, it is determined that the target orientations of multiple magnetic resonance diagnostic scans include: left ventricular outflow tract LVOT, tricuspid valve, and aortic valve.

[0106] In some embodiments, the scanning orientation acquisition module 210 may determine the scanning orientations of multiple magnetic resonance localization scans in the localization scanning sequence based on the target orientations of multiple magnetic resonance diagnostic scans. Specifically, the scanning orientation acquisition module 210 may determine the corresponding diagnostic purposes based on the target orientations of multiple magnetic resonance diagnostic scans, and then automatically determine the scanning orientations of multiple magnetic resonance localization scans in the localization scanning sequence based on the diagnostic purposes.

[0107] In some embodiments, the scanning orientation acquisition module 210 may determine the scanning orientations of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the target orientations of multiple magnetic resonance diagnostic scans according to a preset "target orientation-diagnostic purpose-scanning orientation" relationship table.

[0108] In some embodiments, the scanning orientation acquisition module 210 can determine the scanning orientation of a magnetic resonance localization scan based on the trained scanning orientation model. Specifically, the scanning orientation model can output corresponding scanning orientations of multiple magnetic resonance localization scans based on the input target orientations of multiple magnetic resonance diagnostic scans.

[0109] In some embodiments, the scanning orientation model can be obtained by training a large number of training samples with labels. Specifically, the training samples with labels are input into the initial scanning orientation model, and the parameters of the initial scanning orientation model are updated through training, thereby obtaining a trained scanning orientation model.

[0110] In some embodiments, the training samples may be sample target positions of multiple magnetic resonance diagnostic scans. In some embodiments, the identifiers may be sample scan positions corresponding to multiple magnetic resonance localization scans that are manually annotated. In some embodiments, multiple corresponding magnetic resonance localization scans may be acquired based on multiple magnetic resonance diagnostic scans, and then multiple corresponding sample scan positions may be acquired based on multiple magnetic resonance localization scans.

[0111] As an example only, based on the target orientation "aortic valve", the diagnostic purpose can be determined to be "determining whether there is vascular blockage in the aortic valve", and then based on this diagnostic purpose, the scanning orientation can be determined to include "heart chamber 2ch", and it is not necessary to include "heart chamber 4ch".

[0112] Some embodiments of the present specification automatically determine the scanning orientations of multiple magnetic resonance positioning scans in a positioning scanning sequence based on a diagnostic scanning sequence of cardiac magnetic resonance scanning, which can reduce unnecessary magnetic resonance positioning scans based on diagnostic purposes or further strengthen the scanning to improve positioning details, thereby improving the efficiency of cardiac magnetic resonance scanning.

[0113] Figure 5 500 is an exemplary flow chart of automatic sequential magnetic resonance scanning according to some embodiments of the present specification. In some embodiments, the processing device 120, the magnetic resonance scanning acceleration system 100 and / or the scanning image acquisition module 230 execute the process 500. Figure 5 As shown, process 500 may include the following steps.

[0114] Step 510: automatically identify the magnetic resonance scan image corresponding to the previous scan position, and automatically determine the scan parameters of the next scan position based on the identification result.

[0115] The scanning parameters may be parameters of the magnetic resonance imaging device during the scanning process. In some embodiments, the scanning parameters may include but are not limited to the type of the positioning scanning subsequence corresponding to the scanning orientation, the number of slice groups, and the scanning angle.

[0116] The recognition result of the magnetic resonance scan image may include the image quality, positioning information and / or diagnostic information of the magnetic resonance scan image. The image quality of the magnetic resonance scan image may be represented by signal-to-noise ratio, resolution and contrast, etc. The positioning information and diagnostic information of the magnetic resonance scan image may represent image features in the magnetic resonance scan image that have positioning significance and diagnostic significance, respectively.

[0117] Specifically, the scanning image acquisition module 230 can extract the feature information of the magnetic resonance scanning image corresponding to the last scanning position, and then determine the recognition result of the corresponding magnetic resonance scanning image based on the feature information of the magnetic resonance scanning image corresponding to the last scanning position. In some embodiments, the feature information of the magnetic resonance scanning image may include but is not limited to local image features, shape features and / or texture features.

[0118] As an example only, the scanning image acquisition module 230 can extract the characteristic information of the magnetic resonance scanning image corresponding to the first magnetic resonance scanning image "chest coronal position cor", and then based on the characteristic information, determine that the resolution of the heart A area in the magnetic resonance scanning image corresponding to the "chest coronal position" is low.

[0119] Further, the scanning image acquisition module 230 can determine the part that needs to adjust the scanning mode according to the recognition result of the magnetic resonance scanning image corresponding to the previous scanning position, and then determine the scanning parameters corresponding to the next scanning position based on the part that needs to adjust the scanning mode. In some embodiments, the scanning image acquisition module 230 can determine the slice group corresponding to the part that needs to adjust the scanning mode in the next scanning position, and then adjust the scanning parameters corresponding to the slice group.

[0120] Continuing with the above example, the scanning image acquisition module 230 can determine that region A needs further enhanced scanning based on the low resolution of region A in the magnetic resonance scanning image corresponding to the "chest coronal position", and determine the slice group corresponding to region A in the next scanning orientation "heart transverse position", and then increase the number of slices in the slice group corresponding to region A and adjust the corresponding scanning acceleration multiple to improve the resolution of region A in the magnetic resonance image corresponding to the "heart transverse position", adjust the scanning angle corresponding to the slice group and / or modify the type of positioning scanning subsequence corresponding to the scanning orientation.

[0121] For example, the number of slice groups of the "heart cross-section" is increased from 5 to 9, and the corresponding scanning acceleration multiple is adjusted from "3 times" to "4 times".

[0122] Step 520: Acquire a magnetic resonance scan image corresponding to the next scanning position according to the scanning parameters of the next scanning position.

[0123] Specifically, the scanning image acquisition module 230 may scan the next scanning position according to the scanning parameters of the next scanning position, so as to acquire the magnetic resonance scanning image corresponding to the next scanning position.

[0124] Continuing with the above example, the scanning image acquisition module 230 can acquire the magnetic resonance scanning image or magnetic resonance positioning image corresponding to the "heart transverse position" according to the scanning parameters of the "heart transverse position" "number of slice groups 9" and the scanning acceleration multiple "4 times".

[0125] Step 530, based on the magnetic resonance scanning image corresponding to the next scanning orientation, repeatedly automatically identify and acquire the magnetic resonance scanning image until the magnetic resonance scanning image corresponding to the last scanning orientation is acquired.

[0126] Continuing with the above example, the scanning image acquisition module 230 can automatically identify the magnetic resonance scanning image corresponding to the “heart transverse position” based on the magnetic resonance scanning image corresponding to the “heart transverse position”, and determine the scanning parameters of the “two heart chambers” based on the identification result, and then acquire the magnetic resonance scanning image corresponding to the “two heart chambers” according to the scanning parameters corresponding to the “two heart chambers”; … until the last magnetic resonance scanning image is acquired.

[0127] In some embodiments, the scanning image acquisition module 230 can further input multiple magnetic resonance scanning images corresponding to multiple scanning orientations into a pre-constructed machine learning model, and generate a whole-heart multi-phase positioning image of the patient's heart through the machine learning model.

[0128] In some embodiments, the whole-heart multi-phase positioning image may include cross-sectional positioning images of the heart in different cardiac phases, for example, long-axis, two-chamber, three-chamber, four-chamber or short-axis and other clinically used cross-sectional images in various cardiac motion phases of the heart, which may also include but are not limited to positioning cross-sectional images of the heart in cardiac systole and / or cardiac diastole.

[0129] In some embodiments, the scanning image acquisition module 230 can input multiple magnetic resonance scanning images corresponding to multiple scanning orientations into a pre-built machine learning model, and generate a whole-heart multi-phase positioning image of the patient's heart through the machine learning model.

[0130] Specifically, the scanning image acquisition module 230 can extract features from multiple magnetic resonance scanning images corresponding to multiple scanning positions through a machine learning model to obtain corresponding feature data. In some embodiments, the processing device 120 can perform convolution and down-sampling processing on multiple magnetic resonance scanning images corresponding to multiple scanning positions input through a machine learning model to obtain corresponding multiple feature maps, that is, to obtain feature data. Further, the scanning image acquisition module 230 can perform image reconstruction processing on the feature data to obtain a dynamic image of the whole heart. Furthermore, the processing device 120 can identify positioning images corresponding to each cardiac phase from the dynamic image of the whole heart, such as positioning images corresponding to the long axis, two chambers, three chambers, four chambers and short axis, or the expiratory and inspiratory states, to obtain a multi-phase positioning image of the whole heart.

[0131] In some embodiments, the full cardiac phase localization image includes cross-sectional localization images of the heart at different cardiac phases. The processing device 120 can determine the corresponding target phase localization image based on the needs of the actual application and perform subsequent scanning processing without the need to collect and locate each different cardiac phase, thereby reducing data processing time and improving data processing efficiency.

[0132] In the above-mentioned whole-heart multi-phase phase positioning image generation method, multiple magnetic resonance scan images corresponding to multiple scanning positions are input into a pre-constructed machine learning model, and a whole-heart multi-phase phase positioning image of the heart of the corresponding patient is generated through the machine learning model. Thus, after obtaining multiple magnetic resonance scan images corresponding to multiple scanning positions of the patient, a whole-heart multi-phase phase positioning image of the corresponding patient can be constructed through machine learning and other methods based on different cardiac phases of different cardiac sections in the multiple magnetic resonance scan images corresponding to the multiple scanning positions. Compared with the traditional method of collecting data through multiple breath holdings and performing manual calibration, the present application scheme can improve the intelligent level of data processing, and can reduce the time of data collection, thereby improving the efficiency of data processing.

[0133] The machine learning model may be a neural network model based on deep learning, including but not limited to VGGNet, AlexNet, LeNet5, etc. It will be appreciated by those skilled in the art that this is only an example, and in other embodiments, other models may also be used, and this application does not limit this.

[0134] In some embodiments, the machine learning model is a pre-built model, and the processing device 120 can obtain training data in advance and train the constructed initial machine learning model to obtain the machine learning model. Specifically, the processing device 120 can annotate the training data and divide the annotated training data into a training data set and a test training set. In some embodiments, the processing device 120 can iteratively train the constructed initial machine learning model through the training data set, and after the training is completed, test it through the test data set. In some embodiments, when the processing device 120 performs model training, the model loss of the initial machine learning model can be determined based on the training results output by the model and the input training data set, and the model parameters of the initial machine learning model can be updated based on the model loss. Further, the processing device 120 can iteratively train the initial neural network model after the model parameters are updated until the training is completed. In some embodiments, the processing device 120 can pre-set the test pass rate, and indicate that the model test has passed when the test pass rate reaches a preset threshold. In some embodiments, the training data may include data in different phase states, for example, data in the exhalation state, data in the inhalation state, or different data such as long axis, two chambers, three chambers, four chambers and short axis.

[0135] In some embodiments, the processing device 120 may perform anti-aliasing processing on a plurality of magnetic resonance scan images corresponding to a plurality of under-sampled scanning positions by means of inter-layer aliasing to obtain a multi-phase localization image of the patient's whole heart.

[0136] In some embodiments, reconstruction processing is performed through artificial intelligence machine learning (ML), and the section positioning of multiple cardiac phases can be obtained, such as long axis, two-chamber, three-chamber, four-chamber or short axis, and other clinically used sections in various cardiac motion phases of the heart, that is, movie imaging, including or not limited to the positioning section of the cardiac systole and / or diastole. This has very significant clinical significance, and provides direct positioning assistance for other applications of cardiac magnetic resonance imaging, greatly increasing the positioning coverage. For example, clinical applications need to be based on the cardiac systole period, while some clinical applications need to be based on the cardiac diastole period. Positioning images for positioning or acquisition, in clinical application scenarios, can be selected and applied according to specific cardiac applications to collect positioning images of specific phases as the positioning basis for subsequent scanning.

[0137] Fig. 9 FIG. 1 is an exemplary schematic diagram of magnetic resonance scanning acceleration according to some embodiments of the specification. Fig. 9 The whole process of magnetic resonance scanning acceleration is described as an example. Fig. 9As shown, first, the magnetic resonance scanning acceleration system 100 can load the cardiac scanning protocol group, then obtain the "positioning scanning sequence" from the cardiac scanning protocol group, and perform scanning based on the scanning parameters corresponding to the first scanning orientation cor in the "positioning scanning sequence", and obtain the first magnetic resonance positioning image corresponding to cor; and automatically add scanning parameters corresponding to other scanning orientations (tra, 2ch, 4ch, etc.) in the "positioning scanning sequence", and extract the scanning parameters corresponding to the target orientation in the "diagnosis scanning sequence" from the cardiac scanning protocol group. Further, the magnetic resonance scanning acceleration system 100 can adjust the scanning parameters corresponding to the second scanning orientation tra in the "positioning scanning sequence" according to the first magnetic resonance positioning image corresponding to cor, and then perform scanning based on the scanning parameters corresponding to the second scanning orientation tra, and obtain the second magnetic resonance positioning image corresponding to tra. Furthermore, the magnetic resonance scanning acceleration system 100 can adjust the scanning parameters corresponding to the third scanning position 2ch in the "positioning scanning sequence" according to the second magnetic resonance positioning image corresponding to the scanning position tra, and then perform scanning based on the scanning parameters corresponding to the third scanning position 2ch, and obtain the third magnetic resonance positioning image corresponding to 2ch. Similarly, the magnetic resonance scanning acceleration system 100 can adjust the scanning parameters corresponding to the fourth scanning position 4ch in the "positioning scanning sequence" according to the third magnetic resonance positioning image corresponding to the scanning position 2ch, and then perform scanning based on the scanning parameters corresponding to the fourth scanning position 4ch, and obtain the fourth magnetic resonance positioning image corresponding to 4ch, ... until the last magnetic resonance positioning image is obtained, and adjust the scanning parameters corresponding to the first target position in the "diagnosis scanning sequence" according to the last magnetic resonance positioning image, and repeat the above operation until the last magnetic resonance diagnostic image is obtained.

[0138] In some implementations of the present specification, a magnetic resonance scanning image corresponding to a next scanning position is obtained based on a magnetic resonance scanning image corresponding to a previous scanning position, so that the magnetic resonance scanning image at the next scanning position can timely compensate for the quality problems of the magnetic resonance scanning image at the previous scanning position, thereby improving the quality of the magnetic resonance scanning image.

[0139] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) adopting different scanning acceleration multiple strategies based on different demand parameters (such as the number of cardiac cycles and / or the number of slice groups) to ensure that different cardiac magnetic resonance scanning image quality requirements are met, while improving the scanning time and reducing the number of times the patient holds his breath; (2) automatically determining the scanning orientations of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the diagnostic scanning sequence of the cardiac magnetic resonance scanning, which can reduce unnecessary magnetic resonance positioning scans based on diagnostic purposes or further strengthen the scanning to improve the positioning details, thereby improving the efficiency of cardiac magnetic resonance scanning.

[0140] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0141] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0142] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0143] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0144] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0145] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0146] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A magnetic resonance scanning acceleration method, characterized in that: The method comprises: Acquire a positioning scan sequence of cardiac magnetic resonance scanning, and acquire scanning positions of multiple magnetic resonance positioning scans in the positioning scan sequence based on the positioning scan sequence; Determining a corresponding scanning acceleration factor based on the scanning orientation of the magnetic resonance positioning scan; and The scanning acceleration multiple is used to perform automatic sequential magnetic resonance scanning corresponding to the scanning orientation, and a magnetic resonance scanning image corresponding to the scanning orientation is acquired in the automatic sequence.

2. The method according to claim 1, characterized in that The method comprises: Acquire diagnostic scan sequences of cardiac magnetic resonance scans; Based on the diagnostic scanning sequence, scanning positions of a plurality of magnetic resonance localization scans in the localization scanning sequence are automatically determined.

3. The method according to claim 1, characterized in that The scanning acceleration factor is determined based on the required parameters corresponding to the magnetic resonance scanning position, including: Manually setting the scanning acceleration factor based on the required parameters corresponding to the magnetic resonance scanning position; and / or The scanning acceleration factor is automatically determined based on the required parameters corresponding to the magnetic resonance scanning orientation.

4. The method according to claim 3, characterized in that The required parameter corresponding to the magnetic resonance scanning orientation includes at least one of the number of slice groups corresponding to the magnetic resonance scanning orientation and the number of cardiac cycles corresponding to the magnetic resonance scanning orientation.

5. The method according to claim 1, characterized in that The method of using the scanning acceleration multiple to perform magnetic resonance automatic sequential scanning corresponding to the scanning position, and acquiring magnetic resonance scanning images corresponding to the scanning position in the automatic sequence, comprises: Automatically identify the magnetic resonance scan image corresponding to the previous scan position, and automatically determine the scan parameters of the next scan position based on the recognition result; acquiring a magnetic resonance scanning image corresponding to the next scanning position according to the scanning parameters of the next scanning position; Based on the magnetic resonance scanning image corresponding to the next scanning orientation, the automatic identification and the acquisition of the magnetic resonance scanning image are repeatedly performed until the magnetic resonance scanning image corresponding to the last scanning orientation is acquired.

6. A magnetic resonance scanning acceleration system, the system comprising: A scanning position acquisition module, used for acquiring a positioning scanning sequence of cardiac magnetic resonance scanning, and acquiring scanning positions of multiple magnetic resonance positioning scans in the positioning scanning sequence based on the positioning scanning sequence; An acceleration factor determination module, used to determine a corresponding scanning acceleration factor based on a scanning orientation of the magnetic resonance positioning scan; as well as The scanning image acquisition module is used to perform magnetic resonance automatic sequential scanning on the corresponding scanning position using the scanning acceleration multiple, and to acquire the magnetic resonance scanning image corresponding to the scanning position in the automatic sequence.

7. The system according to claim 6, characterized in that The acceleration multiple determination module is further used for: Acquire diagnostic scan sequences of cardiac magnetic resonance scans; Based on the diagnostic scanning sequence, scanning positions of a plurality of magnetic resonance localization scans in the localization scanning sequence are automatically determined.

8. The system according to claim 6, characterized in that The scanning image acquisition module is further used for: Automatically identify the magnetic resonance scan image corresponding to the previous scan position, and automatically determine the scan parameters of the next scan position based on the recognition result; acquiring a magnetic resonance scanning image corresponding to the next scanning position according to the scanning parameters of the next scanning position; Based on the magnetic resonance scanning image corresponding to the next scanning orientation, the automatic identification and the acquisition of the magnetic resonance scanning image are repeatedly performed until the magnetic resonance scanning image corresponding to the last scanning orientation is acquired.

9. A magnetic resonance scanning accelerator, characterized in that: The device comprises: at least one storage medium storing computer instructions; At least one processor executes the computer instructions to implement the method according to any one of claims 1 to 5.

10. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions, the computer executes the magnetic resonance scanning acceleration method according to any one of claims 1 to 5.

Images