Magnetic resonance T1 mapping system and method

Abstract

This application provides a magnetic resonance T1 mapping system and method, the system comprising: at least one storage device storing a set of instructions; and at least one processor communicating with the at least one storage device, characterized in that, when the instructions are executed, the at least one processor is configured to cause the system to perform the following operations: acquiring at least three images of a target during an inversion recovery process, each of the at least three images being acquired during breath-holding within a cardiac cycle of the target; and determining a T1 mapping image of the target based on the at least three images acquired during the inversion recovery process and a trained model.

Description

[0001] Cross-referencing

[0002] This application claims priority to U.S. Application No. US17 / 456,890, filed November 30, 2021, the contents of which are incorporated herein by reference. Technical Field

[0003] This application generally relates to magnetic resonance imaging (MRI), and more specifically, to systems and methods for magnetic resonance T1 mapping. Background Technology

[0004] In magnetic resonance imaging (MRI), the T1 value refers to the longitudinal (or rotating lattice) relaxation time of a tissue. T1 mapping is used to calculate the T1 value of a tissue. The calculated T1 value can be displayed at the element location (e.g., pixel location, voxel location) on a parametric map (e.g., a T1-mapped image). T1 mapping has been applied in clinical practice for the diagnosis of myocardial tissue diseases and risk stratification. Existing T1 mapping methods are time-consuming and have low resolution. For example, during T1 mapping using the improved Look-Locker Inversion Recovery (MOLLI) algorithm, patients typically need to hold their breath for 11 cardiac cycles to acquire 8 images for T1 value calculation. The complex calculations involved in processing such images often lead to inaccurate results. Therefore, there is a need for MRI T1 mapping systems and methods with short scan times and high accuracy. Summary of the Invention

[0005] According to one aspect of this application, a magnetic resonance T1 mapping system is provided. The system may include at least one storage device storing a set of instructions, and at least one processor communicating with the at least one storage device. When the instruction set is executed, the at least one processor causes the system to perform the following operations: acquire at least three images of a target during an inversion recovery process, each of the at least three images being acquired during breath-holding within one cardiac cycle of the target; and determine a T1 mapping image of the target based on the at least three images acquired during the inversion recovery process and a trained model.

[0006] In some embodiments, the operation further includes: obtaining one or more processed images by processing one or more of the at least three images, which includes: obtaining one or more processed images by applying at least one of a motion correction algorithm or a phase correction algorithm to one or more of the at least three images.

[0007] In some embodiments, obtaining one or more processed images by processing one or more of at least three images includes: obtaining one or more processed images by performing at least one of a motion correction algorithm or a phase correction algorithm.

[0008] In some embodiments, the trained model includes a fully connected neural network.

[0009] In some embodiments, determining the T1 mapping image of a target based on at least three images and a trained model includes: obtaining the T1 mapping image of the target by inputting at least three images into a trained model, wherein the T1 mapping image is the output of the trained model.

[0010] In some embodiments, determining the T1 mapping image of a target based on at least three images and a trained model includes: for element positions in the T1 mapping image, inputting the values ​​of at least three elements and the image acquisition time of each of the at least three images into the trained model to determine the T1 value, wherein each of the at least three elements is at a corresponding element position in one of the at least three images; and determining the T1 mapping image based on multiple T1 values ​​for multiple element positions in the T1 mapping image.

[0011] In some embodiments, determining the T1 value for the element position in the T1-mapped image includes: for each of at least three images, identifying the image acquisition time of the image, where the image acquisition time is the time point at which the image was acquired during the inversion recovery process; and identifying the value of the element at each element position in the image.

[0012] In some embodiments, the trained model is determined based on a training process, which includes: acquiring multiple sample sets, wherein each sample set includes multiple sample images, multiple sample image acquisition times, and reference T1 mapping images of the multiple sample images, wherein each of the multiple sample image acquisition times corresponds to one image in the multiple sample images; and training an initial model based on the multiple sample sets to obtain a trained model.

[0013] In some embodiments, acquiring multiple sample sets includes: acquiring multiple sample images for each of the multiple sample sets; determining the acquisition time of each sample image of the multiple sample images; and determining a reference T1 mapping image of the multiple sample images based on the multiple sample images and the corresponding sample image acquisition time.

[0014] In some embodiments, multiple sample images of a sample set are obtained using an improved Look-Locker inversion recovery sequence.

[0015] In some embodiments, a reference T1 mapping image for multiple sample images is determined according to a fitting algorithm.

[0016] According to another aspect of this application, a magnetic resonance T1 mapping method is provided. The method may include: acquiring at least three images of a target during an inversion recovery process, each of the at least three images being acquired during breath-holding of the target in one cardiac cycle; and determining a T1-mapped image of the target based on the at least three images acquired during the inversion recovery process and a trained model.

[0017] According to another aspect of this application, a non-transitory readable medium comprising at least one set of instructions is provided. When executed by at least one processor of a computer device, the system for magnetic resonance T1 mapping, the at least one set of instructions causes the at least one processor to implement a method comprising: acquiring at least three images of a target during an inversion recovery process, each of the at least three images being acquired during breath-holding within one cardiac cycle of the target; and determining a T1 mapping image of the target based on the at least three images acquired during the inversion recovery process and a trained model.

[0018] Some of the additional features of this application can be described in the following description. Some of the additional features of this application will be apparent to those skilled in the art through study of the following description and the corresponding drawings, or through understanding of the production or operation of the embodiments. The features and implementations of this application can be realized and implemented by practicing or using various aspects of the methods, tools, and combinations set forth in the detailed examples discussed below. Attached Figure Description

[0019] This application will be further described through exemplary embodiments. These exemplary embodiments will be described in detail with reference to the accompanying drawings. The drawings are not drawn to scale. These embodiments are non-limiting exemplary embodiments, in which the same numbers in the figures denote similar structures, wherein:

[0020] Figure 1 These are schematic diagrams of exemplary magnetic resonance imaging systems according to some embodiments of this application;

[0021] Figure 2 This is a schematic diagram of an exemplary magnetic resonance imaging scanner according to some embodiments of this application;

[0022] Figure 3 These are schematic diagrams of exemplary hardware and / or software components of a computing device according to some embodiments of this application;

[0023] Figure 4 These are schematic diagrams of exemplary hardware and / or software components of a mobile device according to some embodiments of this application;

[0024] Figure 5A This is a block diagram of an exemplary processing apparatus according to some embodiments of this application;

[0025] Figure 5B This is a block diagram of an exemplary processing apparatus according to some embodiments of this application;

[0026] Figure 6 This is a flowchart illustrating an exemplary process for determining a T1 mapping image according to some embodiments of this application;

[0027] Figure 7 This is a schematic diagram of an exemplary scanning process within a reversal recovery process according to some embodiments of this application;

[0028] Figure 8 This is a flowchart illustrating an exemplary process for determining a T1 mapping image according to some embodiments of this application;

[0029] Figure 9 This is a flowchart illustrating an exemplary process for generating a training model according to some embodiments of this application;

[0030] Figure 10 This is a schematic diagram illustrating an exemplary scanning process using a MOLLI sequence according to some embodiments of this application;

[0031] Figure 11 These are exemplary images obtained according to exemplary scanning procedures using MOLLI sequences as shown in some embodiments of this application; and

[0032] Figure 12 This is a schematic diagram of an exemplary initial model shown according to some embodiments of this application. Detailed Implementation

[0033] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. However, those skilled in the art should understand that this application can be implemented without these details. In other instances, to avoid unnecessarily obscuring various aspects of this application, well-known methods, processes, systems, components, and / or circuits have been described at a higher level. It will be apparent to those skilled in the art that various changes can be made to the disclosed embodiments, and the general principles defined in this application can be applied to other embodiments and application scenarios without departing from the principles and scope of this application. Therefore, this application is not limited to the embodiments shown, but conforms to the broadest scope consistent with the scope of the claims.

[0034] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. However, those skilled in the art should understand that this application can be implemented without these details. In other instances, to avoid unnecessarily obscuring various aspects of this application, well-known methods, processes, systems, components, and / or circuits have been described at a higher level. It will be apparent to those skilled in the art that various changes can be made to the disclosed embodiments, and the general principles defined in this application can be applied to other embodiments and application scenarios without departing from the principles and scope of this application. Therefore, this application is not limited to the embodiments shown, but conforms to the broadest scope consistent with the scope of the claims.

[0035] The terminology used in this application is for the purpose of describing particular exemplary embodiments only and is not restrictive. The singular forms “a,” “an,” and “the” used in this application may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and “including” as used in this specification indicate only the presence of the stated features, integers, steps, operations, components, and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components, parts, and / or combinations thereof.

[0036] It should be understood that the terms "system," "engine," "unit," "cell," "module," and / or "block" are one way to distinguish different levels of parts, elements, components, parts, or assemblies in ascending order. However, these terms can be replaced with other expressions if the same purpose can be achieved.

[0037] Generally, the terms "module," "unit," or "block" as used herein refer to logic embodied in hardware or firmware, or a collection of software instructions. The modules, units, or blocks described herein can be implemented as software and / or hardware and can be stored on any type of non-transitory computer-readable medium or other storage device. In some embodiments, software modules / units / blocks can be compiled and linked into an executable program. It should be understood that software modules can be invoked from other modules / units / blocks or from themselves, and / or can be invoked in response to detected events or interrupts. The software modules / units / blocks configured for execution on a computing device (e.g., such as...) Figure 3The processor 310 shown may be located on a computer-readable medium, such as an optical disc, digital video disc, flash drive, disk, or any other tangible medium, or as a digital download (and may be initially stored in a compressed or installable format that requires installation, decompression, or decryption before execution). The software code herein may be stored, in part or in whole, in the storage device of the computing device performing the operation and applied in the operation of the computing device. Software instructions may be embedded in firmware, such as EPROM. It should also be understood that hardware modules / units / blocks may be included in connected logical components, such as gates and flip-flops, and / or programmable units, such as programmable gate arrays or processors. The modules / units / blocks or computing device functions described herein may be implemented as software modules / units / blocks, but may be represented in hardware or firmware. Generally, the modules / units / blocks described herein refer to logical modules / units / blocks that may be combined with other modules / units / blocks or divided into submodules / subunits / subblocks, although they are physical organization or storage devices. This description may apply to a system, an engine, or a part thereof.

[0038] It is understood that, unless the context explicitly states otherwise, when a unit, engine, module, or block is referred to as being "on," "connected," or "coupled to" another unit, engine, module, or block, it may be directly on, connected to, coupled to, or communicate with the other unit, engine, module, or block, or there may be intermediate units, engines, modules, or blocks. In this specification, the term "and / or" may include any one or more of the associated listed items or a combination thereof. The term "image" in this application is used for images of various forms collectively referred to as image data (e.g., scanned data, projected data) and / or images, including two-dimensional (2D) images, three-dimensional (3D) images, four-dimensional (4D) images, etc. The terms "pixel" and "Voxel" in this application are used interchangeably to refer to elements of an image.

[0039] It should be understood that although the terms “first,” “second,” “third,” etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of exemplary embodiments of the invention.

[0040] These and other features, characteristics, functions and operating methods of related structural elements, as well as component assembly and manufacturing economics, will become more apparent from the following description of the accompanying drawings, which form part of this application specification. However, it should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of this application. It should also be understood that the drawings are not drawn to scale.

[0041] As used herein, the term "imaging modality" or "modality" broadly refers to imaging methods or techniques for gathering, generating, processing, and / or analyzing imaging information of a target (or target object). Targets (or target objects) may include biological targets and / or non-biological targets. Biological targets may be humans, animals, plants, or parts thereof (e.g., heart, breast, etc.). In some embodiments, targets may be compositions made of organic and / or inorganic substances, whether living or non-living.

[0042] This document provides systems and methods for non-invasive biomedical imaging, such as for disease diagnosis or research purposes. While the systems and methods disclosed in this application are primarily concerned with magnetic resonance T1 mapping, it should be understood that this is for illustrative purposes only. The systems and methods of this application can be applied to any other type of imaging system. In some embodiments, the imaging system may include a single-modality imaging system and / or a multimodality imaging system. A single-modality imaging system may include, for example, a magnetic resonance imaging system. A multimodality imaging system may include, for example, an X-ray imaging-magnetic resonance imaging (X-MRI) system, a single-photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) system, a digital subtraction angiography-magnetic resonance imaging (DSA-MRI) system, a computed tomography-magnetic resonance imaging (MRI-CT) system, a positron emission tomography-magnetic resonance imaging (PET-MRI) system, and the like.

[0043] One aspect of this application relates to a system and method for magnetic resonance T1 mapping. The system and method can acquire at least three images of a target within a single inversion recovery process and determine a T1-mapped image of the target based on the at least three images acquired during the inversion recovery process and a trained model. Each of the at least three images can be acquired during a breath-hold period within the target's cardiac cycle. In this way, the target can hold their breath for only a few cardiac cycles, thereby improving the target's comfort and the convenience of the imaging process. Simultaneously, reducing the amount of image data acquired during imaging can improve the reliability of the image data, increase the efficiency of the imaging process, improve the efficiency of subsequent image processing, and enhance the accuracy of the T1-mapped image determined from the acquired image data.

[0044] Figure 1 This is a schematic diagram of an exemplary magnetic resonance imaging system 100 according to some embodiments of this application. Figure 1As shown, the magnetic resonance imaging system 100 may include a magnetic resonance imaging scanner 110, a processing device 120, a storage device 130, one or more terminals 140, and a network 150. In some embodiments, the magnetic resonance imaging scanner 110, the processing device 120, the storage device 130, and / or the terminal 140 may be connected to and / or communicate with each other via wireless connections, wired connections, or combinations thereof. The connections between the components in the magnetic resonance imaging system 100 may be variable. For example, the magnetic resonance imaging scanner 110 may be connected to the processing device 120 via the network 150. As another example, the magnetic resonance imaging scanner 110 may be directly connected to the processing device 120.

[0045] The magnetic resonance imaging scanner 110 can be configured to scan a target (or a portion of a target) to obtain image data of the target. In some embodiments, the magnetic resonance imaging scanner 110 may include, for example, a main magnet, gradient coils (or also referred to as spatial coding coils), radio frequency (RF) coils, etc. Figure 2 As shown. In some embodiments, depending on the type of main magnet, the magnetic resonance imaging scanner 110 can be a permanent magnet magnetic resonance imaging scanner, a superconducting magnet magnetic resonance imaging scanner, a superconducting magnet magnetic resonance imaging scanner, or a resistive electromagnet magnetic resonance imaging scanner, etc. In some embodiments, depending on the strength of the magnetic field, the magnetic resonance imaging scanner 110 can be a high magnetic field magnetic resonance imaging scanner, a medium magnetic field magnetic resonance imaging scanner, and a low magnetic field magnetic resonance imaging scanner, etc. Further descriptions of the magnetic resonance imaging scanner 110 can be found elsewhere in this application, such as... Figure 2 And its description.

[0046] The target scanned by the magnetic resonance imaging scanner 110 can be biological or non-biological. For example, the target may include a patient, man-made objects, etc. As another example, the target may include a specific part, organ, tissue, and / or a physical point of the patient. By way of example only, the target may include the head, brain, neck, body, shoulder, arm, chest, heart, stomach, blood vessels, soft tissue, knee joint, foot, etc., or combinations thereof.

[0047] For ease of explanation, Figure 1 The system includes a coordinate system with X, Y, and Z axes. Figure 1 The X and Z axes shown can be horizontal, and the Y axis can be vertical. As shown, when viewed from the front facing the magnetic resonance imaging scanner 110, the positive direction of the X axis can be from the right side of the magnetic resonance imaging scanner 110 to the left side; Figure 1 The positive direction of the Y-axis shown can be from the bottom to the top of the magnetic resonance imaging scanner 110; Figure 1 The positive direction of the Z-axis shown can be the direction in which the target is moved out of the scanning channel (or aperture) of the magnetic resonance imaging scanner 110.

[0048] Processing device 120 can process data and / or information obtained from magnetic resonance imaging scanner 110, storage device 130, and / or terminal 140. For example, after an inversion recovery pulse is applied to the target (but before another inversion recovery pulse is applied), or in a process called an inversion recovery, processing device 120 can acquire at least three images of the target, or image data corresponding to the at least three acquired images. Image data corresponding to each of the at least three images can be acquired during breath-holding within one cardiac cycle of the target. As another example, processing device 120 can determine a T1-mapped image of the target based on at least three images acquired within an inversion recovery process and a trained model. In some embodiments, processing device 120 can be a single server or a group of servers. The server group can be centralized or distributed. In some embodiments, processing device 120 can be local or remotely controlled. For example, processing device 120 can access information and / or data from magnetic resonance imaging scanner 110, storage device 130, and / or terminal 140 via network 150. As another example, processing device 120 can be directly connected to magnetic resonance imaging scanner 110, terminal 140, and / or storage device 130 to access information and / or data. In some embodiments, processing device 120 can be implemented on a cloud platform. For example, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, etc., or combinations thereof. In some embodiments, processing device 120 can be... Figure 3 This is achieved through one or more components of the associated computing device 300.

[0049] Storage device 130 can store data, instructions, and / or any other information. In some embodiments, storage device 130 can store data obtained from magnetic resonance imaging scanner 110, processing device 120, and / or terminal 140. In some embodiments, storage device 130 can store data and / or instructions that processing device 120 can execute or be used to execute the exemplary methods described in this application. In some embodiments, storage device 130 may include mass storage devices, removable storage devices, volatile read-write memory, read-only memory (ROM), etc., or combinations thereof. Exemplary volumetric storage devices may include disks, optical disks, solid-state drives, etc. Exemplary removable storage devices may include flash drives, floppy disks, optical disks, memory cards, zipper disks, magnetic tapes, etc. Exemplary volatile read-write memory may include random access memory (RAM). Exemplary RAM may include dynamic RAM (DRAM), dual date rate synchronous dynamic RAM (DDRSDRAM), static RAM (SRAM), thyristor RAM (T-RAM), zero-capacitance RAM (Z-RAM), etc. Exemplary ROMs may include mask ROMs (MROMs), programmable ROMs (PROMs), erasable programmable ROMs (EPROMs), erasable programmable ROMs (EEPROMs), optical disc ROMs (CD-ROMs), digital multifunction disk ROMs, etc. In some embodiments, storage device 130 may be implemented on a cloud platform, as described elsewhere in this application.

[0050] In some embodiments, storage device 130 may be connected to network 150 to communicate with one or more other components of magnetic resonance imaging system 100 (e.g., magnetic resonance imaging scanner 110, processing device 120, and / or terminal 140). One or more components of magnetic resonance imaging system 100 may access data or instructions stored in storage device 130 via network 150. In some embodiments, storage device 130 may be part of processing device 120 or terminal 140.

[0051] Terminal 140 can be configured to enable interaction between a user and magnetic resonance imaging system 100. For example, terminal 140 can receive instructions from the user to have magnetic resonance imaging scanner 110 scan a target. As another example, terminal 140 can receive processing results (e.g., a T1-mapped image of the target) from processing device 120 and display the processing results to the user. In some embodiments, terminal 140 can be connected to and / or communicate with magnetic resonance imaging scanner 110, processing device 120, and / or storage device 130. In some embodiments, terminal 140 can include mobile device 140-1, tablet computer 140-2, laptop computer 140-3, etc., or combinations thereof. For example, mobile device 140-1 can include mobile phone, personal digital assistant (PDA), gaming device, navigation device, point-of-sale (POS) device, laptop computer, tablet computer, desktop, etc., or combinations thereof. In some embodiments, terminal 140 can include input devices, output devices, etc. Input devices can include alphanumeric and other key mechanisms that can be input via keyboard, touch screen (e.g., with haptic or haptic feedback), voice input, eye-tracking input, brain monitoring system, or any other comparable input. Input information received via an input device can be transmitted to processing device 120 for further processing, for example, via a bus. Other types of input devices may include cursor control devices, such as a mouse, trackball, or arrow keys. Output devices may include a display, speakers, a printer, or combinations thereof. In some embodiments, terminal 140 may be part of processing device 120 or magnetic resonance imaging scanner 110.

[0052] Network 150 may include any suitable network that can facilitate the exchange of information and / or data for the magnetic resonance imaging system 100. In some embodiments, one or more components of the magnetic resonance imaging system 100 (e.g., magnetic resonance imaging scanner 110, processing device 120, storage device 130, terminal 140, etc.) may transmit information and / or data with one or more other components of the magnetic resonance imaging system 100 via the network. For example, processing device 120 may obtain image data (e.g., at least three images of a target) from magnetic resonance imaging scanner 110 via network 150. As another example, processing device 120 may obtain user instructions from terminal 140 via network 150. Network 150 may include public networks (e.g., the Internet), private networks (e.g., local area networks (LANs), wide area networks (WANs), etc.), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks, Wi-Fi networks, etc.), cellular networks (e.g., Long Term Evolution (LTE) networks), Frame Relay networks, virtual private networks (“VPNs”), satellite networks, telephone networks, routers, hubs, switches, server computers, etc., or combinations thereof. For example, network 150 may include cable networks, wired networks, fiber optic networks, telecommunications networks, intranets, wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth, etc. TM Network, ZigBee TM Network, near field communication (NFC), or a combination thereof. In some embodiments, network 150 may include one or more network access points. For example, network 150 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 magnetic resonance imaging system 100 may connect to network 150 to exchange data and / or information.

[0053] This description is intended to be illustrative and not to limit the scope of this application. Many alternatives, modifications, and variations will be apparent to those skilled in the art. The features, structures, methods, and characteristics of the exemplary embodiments described herein can be combined in various ways to obtain additional and / or alternative exemplary embodiments. In some embodiments, the magnetic resonance imaging system 100 may include one or more additional components, and one or more of the aforementioned components may be omitted. Additionally or alternatively, two or more components of the magnetic resonance imaging system 100 may be integrated into a single component. For example, processing device 120 may be integrated into magnetic resonance imaging scanner 110. As another example, a component of the magnetic resonance imaging system 100 may be replaced by another component that can perform the function of the component. In some embodiments, storage device 130 may be a data storage, including cloud computing platforms, such as public clouds, private clouds, community clouds, and hybrid clouds. However, these variations and modifications do not depart from the scope of this application.

[0054] Figure 2 This is a schematic diagram of an exemplary magnetic resonance imaging scanner 110 according to some embodiments of this application. Figure 2 The figure shows one or more components of a magnetic resonance imaging scanner 110. As shown, a main magnet 201 can generate a first magnetic field (or main magnetic field) that can be applied to an object (also called a target) exposed within the field. The main magnet 201 can include a resistive magnet or a superconducting magnet, both of which require a power source (not shown) to operate. Alternatively, the main magnet 201 can include a permanent magnet. The main magnet 201 can include an aperture for placing the target inside. The main magnet 201 can also control the uniformity of the generated main magnetic field. Several shimming coils can be present in the main magnet 201. Shimming coils placed in the gaps of the main magnet 201 can compensate for non-uniformity of the magnetic field of the main magnet 201. The shimming coils can be energized by a shim power source.

[0055] Gradient coil 202 may be located within main magnet 201. Gradient coil 202 may generate a second magnetic field (or gradient field, including gradient fields Gx, Gy, and Gz). The second magnetic field may be superimposed on the main magnetic field generated by main magnet 201 and twist the main magnetic field so that the magnetic orientation of the protons of the object changes with their position within the gradient field, thereby encoding spatial information into the echo signal generated by the imaged region. Gradient coil 202 may include an X coil (e.g., configured to generate a gradient field Gx corresponding to the X direction), a Y coil (e.g., configured to generate a gradient field Gy corresponding to the Y direction), and / or a Z coil (e.g., configured to generate a gradient field Gz corresponding to the Z direction). Figure 2(Not shown in the image). In some embodiments, the Z coil may be based on a Maxwell coil design, while the X and Y coils may be based on a Golay coil configuration. The three sets of coils can generate three different magnetic fields for position encoding. Gradient coil 202 allows spatial encoding of the echo signal for image construction. Gradient coil 202 may be connected to one or more of the X gradient amplifier 204, Y gradient amplifier 205, or Z gradient amplifier 206. One or more of the three amplifiers may be connected to waveform generator 216. Waveform generator 216 can generate gradient waveforms applied to the X gradient amplifier 204, Y gradient amplifier 205, and / or Z gradient amplifier 206. The amplifiers can amplify the waveforms. The amplified waveforms can be applied to one of the coils in gradient coil 202 to generate magnetic fields along the X, Y, or Z axes, respectively. Gradient coil 202 may be designed for use in closed-aperture or open-aperture magnetic resonance imaging (MRI) scanners. In some cases, all three sets of coils in gradient coil 202 may be energized, thereby generating three gradient fields. In some embodiments of this application, the X coil and Y coil may be energized to generate gradient fields in the X and Y directions. As used herein, Figure 2 The description of the X-axis, Y-axis, Z-axis, X direction, Y direction, and Z direction is consistent with... Figure 1 The same or similar as described in the text.

[0056] In some embodiments, the radio frequency (RF) coil 203 may be located within the main magnet 201 and serve as a transmitter, receiver, or both. The RF coil 203 may be connected to an RF electronics device 209, which may be configured as or used as one or more integrated circuits (ICs) serving as waveform transmitters and / or waveform receivers. The RF electronics device 209 may be connected to an RF power amplifier (RFPA) 207 and an analog-to-digital converter (ADC) 208.

[0057] When used as a transmitter, the RF coil 203 can generate an RF signal that provides a third magnetic field used to generate an echo signal correlated with the area of ​​the imaged object. The third magnetic field can be perpendicular to the main magnetic field. The waveform generator 216 can generate RF pulses. These RF pulses can be amplified by the RF power amplifier 207, processed by the RF electronics 209, and applied to the RF coil 203 to generate an RF signal in response to a strong current generated by the RF electronics 209 based on the amplified RF pulses.

[0058] When used as a receiver, the RF coil can respond to the detected echo signal. After excitation, the echo signal generated by the object can be sensed by the RF coil 203. The receiver amplifier can then receive the sensed echo signal from the RF coil 203, amplify the sensed echo signal, and provide the amplified echo signal to the analog-to-digital converter 208. The analog-to-digital converter 208 can convert the echo signal from an analog signal to a digital signal. The digital echo signal can then be sent to the processing device 120 for sampling.

[0059] In some embodiments, gradient coil 202 and radio frequency coil 203 may be circumferentially positioned relative to the object. Those skilled in the art will understand that the main magnet 201, gradient coil 202, and radio frequency coil 203 may be located in various configurations around the object.

[0060] In some embodiments, the RF power amplifier 207 can amplify RF pulses (e.g., the power and voltage of the RF pulses), and the amplified RF pulses are used to drive the RF coil 203. The RF power amplifier 207 may include a transistor-based RF power amplifier, a vacuum tube-based RF power amplifier, or any combination thereof. A transistor-based RF power amplifier may include one or more transistors. A vacuum tube-based RF power amplifier may include transistors, tetrodes, klystrons, or any combination thereof. In some embodiments, the RF power amplifier 207 may include a linear RF power amplifier or a non-linear RF power amplifier. In some embodiments, the RF power amplifier 207 may include one or more RF power amplifiers.

[0061] In some embodiments, the magnetic resonance imaging scanner 110 may further include an object positioning system (not shown). The object positioning system may include an object holder and a transport device. The object may be placed on the object holder and positioned within the aperture of the main magnet 201 by the transport device.

[0062] Magnetic resonance imaging (MRI) systems (e.g., MRI system 100 disclosed herein) are typically used to obtain internal images of specific regions of interest (ROIs) from a patient, which may be used for purposes such as diagnosis, treatment, or a combination thereof. An MRI system includes a master magnet assembly (e.g., master magnet 201) for providing a strong, uniform master magnetic field to align individual magnetic moments of hydrogen atoms within the patient's body. In this process, hydrogen atoms oscillate around their magnetic poles at their characteristic Larmor frequencies. If tissue is subjected to an additional magnetic field tuned to the Larmor frequency, the hydrogen atoms absorb additional energy, thereby rotating the net alignment torque of the hydrogen atoms. The additional magnetic field may be provided by a radio frequency excitation signal (e.g., an RF signal generated by radio frequency coil 203). When the additional magnetic field is removed, the magnetic moments of the hydrogen atoms rotate back to alignment with the master magnetic field, thereby emitting an echo signal. The echo signal is received and processed to form an MRI image. T1 relaxation can be the process of net magnetization increasing / recovering to its initial maximum value parallel to the master magnetic field. T1 can be the time constant for longitudinal (e.g., along the master magnetic field) magnetization regeneration. T2 relaxation can be a process of magnetization transverse component decay or dephase. T2 can be the time constant of transverse magnetization decay / dephase.

[0063] If the main magnetic field is uniformly distributed throughout the patient's body, the radio frequency excitation signal may non-selectively excite all hydrogen atoms in the object. Therefore, in order to image a specific body part of the patient, magnetic field gradients Gx, Gy, and Gz in the x, y, and z directions (e.g., generated by gradient coil 202) can be superimposed on the uniform magnetic field. These magnetic field gradients have specific time, frequency, and phase, such that the radio frequency excitation signal excites hydrogen atoms in the desired slice of the patient's body, and based on the position of the hydrogen atoms in the "image slice," unique phase and frequency information is encoded in the echo signal.

[0064] Typically, the patient's body is scanned through a series of measurement cycles to visualize the area to be imaged, where the radiofrequency excitation signal and magnetic field gradients Gx, Gy, and Gz vary according to the MRI imaging protocol being used. Protocols can be designed for one or more tissues, diseases, and / or clinical scenarios to be imaged. Protocols may include a number of pulse sequences targeting different planes and / or with different parameters. These pulse sequences may include spin echo sequences, gradient echo sequences, diffusion sequences, inversion recovery sequences, etc., or any combination thereof. For example, spin echo sequences may include fast spin echo (FSE) pulse sequences, turbine spin echo (TSE) pulse sequences, fast capture with relaxation enhancement (RARE) pulse sequences, half-Fourier acquisition single-excitation turbine spin echo (HASTE) pulse sequences, turbine gradient spin echo (TGSE) pulse sequences, etc., or any combination thereof. As another example, gradient echo sequences may include equilibrium steady-state free precession (bSSFP) pulse sequences, scrambled gradient echo (GRE) pulse sequences, echo-plane imaging (EPI) pulse sequences, steady-state free precession (SSFP), etc., or any combination thereof. The protocol may also include information regarding image contrast and / or ratio, ROI, slice thickness, imaging type (e.g., T1-weighted imaging, T2-weighted imaging, proton density-weighted imaging, etc.), T1, T2, echo type (spin echo, fast spin echo (FSE), fast recovery FSE, single-shot FSE, gradient echo, fast imaging with steady-state processing, etc.), flip angle, acquisition time (TA), echo time (TE), repetition time (TR), echo sequence length (ETL), number of phases, number of excitations (NEX), inversion time, bandwidth (e.g., RF receiver bandwidth, RF transmitter bandwidth, etc.), etc., or any combination thereof. For each MRI scan, the generated echo signals can be digitized and processed to reconstruct an image according to the MRI imaging protocol used.

[0065] Figure 3 This is a schematic diagram of exemplary hardware and / or software components of a computing device 300 according to some embodiments of this application. The computing device 300 can be used to implement any component of the magnetic resonance imaging system 100 as described herein. For example, processing device 120 and / or terminal 140 can be implemented on the computing device 300 respectively through their hardware, software programs, firmware, or combinations thereof. Although only one such computing device is shown for convenience, the computer functions associated with the magnetic resonance imaging system 100 described herein can be implemented in a distributed manner on at least two similar platforms to distribute the processing load. Figure 3 As shown, the computing device 300 may include a processor 310, a storage device 320, an input / output device 330, and a communication port 340.

[0066] Processor 310 can execute computer instructions (e.g., program code) and perform the functions of processing device 120 according to the techniques described herein. Computer instructions may include, for example, routines, programs, objects, components, data structures, procedures, modules, and functions that perform the specific functions described herein. For example, processor 310 can process image data obtained from magnetic resonance imaging scanner 110, terminal 140, storage device 130, and / or any other component of magnetic resonance imaging system 100. In some embodiments, processor 310 may include one or more hardware processors, such as microcontrollers, microprocessors, reduced instruction set computers (RISC), application-specific integrated circuits (ASICs), application-specific instruction set processors (ASIPs), central processing units (CPUs), graphics processing units (GPUs), physical processing units (PPUs), microcontroller units, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), advanced RISC machines (ARMs), programmable logic devices (PLDs), any circuit or processor capable of performing one or more functions, or any combination thereof.

[0067] For illustrative purposes only, only one processor is described in computing device 300. However, it should be noted that computing device 300 in this application may also include multiple processors, and therefore the operations and / or methods performed by one processor as described in this application may also be performed jointly or individually by multiple processors. For example, if in this application, the processor of computing device 300 performs operations A and B, it should be understood that operations A and B may also be performed jointly or individually by two or more different processors in the computing device as shown in FIG300 (e.g., the first processor performs operation A and the second processor performs operation B, or the first and second processors jointly perform operations A and B).

[0068] Storage device 320 may store data / information obtained from magnetic resonance imaging scanner 110, terminal 140, storage device 130, and / or any other component of magnetic resonance imaging system 100. In some embodiments, storage device 320 may include mass storage device, removable storage device, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. In some embodiments, storage device 320 may store one or more programs and / or instructions to perform the exemplary methods described in this application. For example, storage device 320 may store a program for processing device 120 to perform SMS multitasking imaging.

[0069] Input device / output device 330 can input and / or output signals, data, information, etc. In some embodiments, input device / output device 330 allows a user to interact with processing device 120. In some embodiments, input device / output device 330 may include input devices and output devices. The input device may include alphanumeric keys or other keys, which may be input via a keyboard, a touchscreen (e.g., with haptic or haptic feedback), voice input, eye-tracking input, brain monitoring system, or any other similar input mechanism. Input information received through the input device may be transmitted via, for example, a bus to another component (e.g., processing device 120) for further processing. Other types of input devices may include cursor control devices, such as a mouse, trackball, or cursor arrow keys. Output devices may include displays (e.g., liquid crystal displays (LCDs), light-emitting diode (LED) based displays, flat panel displays, curved screens, television sets, cathode ray tube (CRT) displays, touchscreens), speakers, printers, etc., or combinations thereof.

[0070] Communication port 340 can be connected to a network (e.g., network 150) to facilitate data communication. Communication port 340 can establish a connection between processing device 120 and magnetic resonance imaging scanner 110, terminal 140, and / or storage device 130. This connection can be a wired connection, a wireless connection, any other communication connection capable of data transmission and / or reception, and / or any combination of these connections. Wired connections can include, for example, cables, optical fibers, telephone lines, etc., or any combination thereof. Wireless connections can include, for example, Bluetooth. TM Connectivity, Wi-Fi TM Connectivity, WiMax TM Connectivity, WLAN connectivity, ZigBee TM The communication port 340 may be a connection, a mobile network connection (e.g., 3G, 4G, 5G), or a combination thereof. In some embodiments, the communication port 340 may be / include a standardized communication port, such as RS232, RS485, etc. In some embodiments, the communication port 340 may be a specially designed communication port. For example, the communication port 340 may be designed according to the Digital Imaging and Medical Communications (DICOM) protocol.

[0071] Figure 4 This is a schematic diagram of exemplary hardware and / or software components of a mobile device 400 according to some embodiments of this application. In some embodiments, one or more components of a magnetic resonance imaging system 100 (e.g., terminal 140 and / or processing device 120) may be implemented on the mobile device 400.

[0072] like Figure 4As shown, the mobile device 400 may include a communication platform 410, a display 420, a graphics processing unit (GPU) 430, a central processing unit 440, an input / output device 450, memory 460, and storage 490. In some embodiments, any other suitable components, including but not limited to a system bus or controller (not shown), may also be included in the mobile device 400. In some embodiments, a mobile operating system 470 (e.g., iOS) may be included. TM Android TM Windows Phone TM One or more applications 480 are loaded from memory 490 into memory 460 for execution by central processing unit 440. Application 480 may include a browser or any other suitable mobile application for receiving and presenting information relating to magnetic resonance imaging system 100. User interaction with the information flow may be implemented via input / output device 450 and provided via network 150 to processing device 120 and / or other components of magnetic resonance imaging system 100.

[0073] To implement the various modules, units, and functions described in this application, a computer hardware platform may be used as the hardware platform for one or more of the components described herein. A computer with user interface elements may be used to implement a personal computer (PC) or any other type of workstation or terminal device. If the computer is properly programmed, it may also be used as a server.

[0074] Figure 5A and 5B These are block diagrams of exemplary processing devices 120A and 120B according to some embodiments of this application.

[0075] Processing devices 120A and 120B can be Figure 1 The exemplary processing device 120 is described above. In some embodiments, processing device 120A may be configured to apply one or more machine learning models when generating an artifact-corrected image of the original image. Processing device 120B may be configured to generate one or more machine learning models. In some embodiments, processing devices 120A and 120B may be respectively in a processing unit (e.g., Figure 3 The processor 310 shown is or Figure 4 The central processing unit 440 shown is implemented as described. By way of example only, processing device 120A can be implemented on the central processing unit 440 of the terminal device, and processing device 120B can be implemented on the computing device 300. Alternatively, processing devices 120A and 120B can be implemented on the same computing device 300 or the same central processing unit 440. For example, processing devices 120A and 120B can be implemented on the same computing device 300.

[0076] like Figure 5A As shown, the processing device 120A may include an acquisition module 502 and a determination module 504.

[0077] The acquisition module 502 can be configured to acquire at least three images of the target, or image data corresponding to the at least three images, during an inversion recovery process. That is, image data can be acquired after applying one inversion recovery pulse and before applying the next inversion recovery pulse.

[0078] The determination module 504 can be configured to determine the T1-mapped image of a target based on at least three images acquired during a reversal recovery process and a trained model. For example, the determination module 504 can determine the T1 value by inputting the values ​​of at least three elements and the image acquisition time of each of the at least three images into the trained model, where each of the three elements corresponds to a corresponding element position in the at least three images. As another example, the determination module 504 can determine the T1-mapped image based on multiple T1 values ​​for multiple element positions in the T1-mapped image. Further description of determining the T1-mapped image can be found elsewhere in this application. See, for example... Figure 6 And its description.

[0079] like Figure 5B As shown, the processing device 120B may include an acquisition module 506 and a model generation module 508.

[0080] The acquisition module 506 can be configured to acquire data for training the model. For example, the acquisition module 506 can acquire multiple sample sets. Each sample set may include multiple sample images and the acquisition time of each sample image. The acquisition time of each sample image corresponds to one of the multiple sample images, as well as a reference T1 mapping image of the multiple sample images.

[0081] The model generation module 508 can be configured to generate a model. For example, the model generation module 508 can generate a trained model by training an initial model based on multiple sample sets obtained from the acquisition module 506. Further description of model training can be found elsewhere in this application. See, for example... Figure 9 And its description.

[0082] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, these changes and modifications do not depart from the scope of this application. In some embodiments, processing devices 120A and / or 120B may share two or more modules, and any module may be divided into two or more units. For example, processing devices 120A and 120B may share the same acquisition module; that is, acquisition module 502 and acquisition module 506 are the same module. In some embodiments, processing devices 120A and / or 120B may include one or more additional modules, such as a storage module (not shown) for storing data. In some embodiments, processing devices 120A and 120B may be integrated into a single processing device 120.

[0083] Figure 6 This is a flowchart illustrating an exemplary process 600 for determining a T1-mapped image according to some embodiments of this application. In some embodiments, process 600 may be performed by magnetic resonance imaging system 100. For example, process 600 may implement a set of instructions (e.g., an application program) stored in a storage device (e.g., storage device 130, storage device 320, and / or memory 490). In some embodiments, processing device 120A (e.g., processor 310 of computing device 300, central processing unit 440 of mobile device 400, and / or...) Figure 5A One or more modules shown can execute this set of instructions and can be instructed to perform process 600 accordingly. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 600 can be accomplished by one or more additional operations not described, and / or one or more operations not discussed. Additionally, as Figure 6 The order of operations in process 600 shown is not restrictive.

[0084] In step 602, the processing device 120A (e.g., acquisition module 502) can acquire at least three images of the target, or image data corresponding to the at least three images, during a reversal recovery process. That is, the image data can be acquired after applying one reversal recovery pulse and before applying the next.

[0085] In some implementations, the target may include biological and / or non-biological targets. For example, the target may include a target or specific part of the body (e.g., chest, heart, etc.). In some embodiments, image data corresponding to at least three images may be obtained from a magnetic resonance imaging scanner (e.g., magnetic resonance imaging scanner 110). For example, magnetic resonance imaging scanner 110 may scan the target to generate image data corresponding to at least three images. As used herein, the image data or image data corresponding to the images refers to image data generated by means of image reconstruction or other image processing algorithms or methods. During the scan, the target may be required to hold their breath for multiple cardiac cycles. In some embodiments, magnetic resonance imaging scanner 110 may acquire image data in a reverse recovery process. After the target begins to hold his / her breath (and remains still), magnetic resonance imaging scanner 110 may apply a reverse recovery pulse to the target to perform the reverse recovery process. In the reverse recovery process, magnetization within the target may be reversed after a 180° out-of-phase pulse is applied to the target. As used herein, the reverse recovery pulse may be a conventional spin echo sequence following a 180° out-of-phase pulse. For example, an inversion recovery pulse generated by the waveform generator 216 of the magnetic resonance imaging scanner 110 can be applied to the RF coil 230, and the RF coil 230 can generate an RF signal of a third magnetic field used to generate an echo signal associated with the scanned target. In some embodiments, an electrocardiogram (ECG) recording can be performed simultaneously during the scan. Image data of each of at least three images can be acquired during a single breath-hold of the target within a cardiac cycle. Figure 7 This is a schematic diagram of an exemplary scanning process in a reversal recovery process according to some embodiments of this application. Figure 7 As shown, ECG recording was performed simultaneously during the scan. When the target held their breath and a reverse recovery pulse was applied, image data for five images were acquired at time points A, B, C, D, and E. According to the ECG recordings, each of the five time points A, B, C, D, and E represents one cardiac cycle of the target. It should be noted that... Figure 7 For illustrative purposes only, the magnetic resonance imaging scanner 110 may acquire an additional number of images, including at least three images, during a single inversion recovery process. For example, the number of images, including at least three images, may be three, four, five, six, seven, eight, nine, ten, etc.

[0086] In some embodiments, image data of each of at least three images can be acquired when the target is in a specific state within each cardiac cycle. This specific state can be detected based on the ECG recording. For example, when an R wave is detected in an ECG recording within a cardiac cycle, image data corresponding to each of at least three images can be acquired. In some embodiments, image data corresponding to each of at least three images can be acquired at a specific time point within each cardiac cycle. For example, within each 100ms cardiac cycle, image data corresponding to each of the at least three images can be acquired at 60ms after the start of a 100ms cardiac cycle. In some embodiments, the processing device 120A can determine whether the target's heartbeat is regular and periodic (or the cardiac cycle is the same). In response to determining that the target's heartbeat is regular and periodic, the processing device 120A can acquire image data of each of at least three images at a specific time point within each cardiac cycle. Otherwise, the processing device 120A can acquire image data of each of at least three images when the target is in a specific state within each cardiac cycle.

[0087] In some embodiments, each of the at least three images can be marked with an image acquisition time. The image acquisition time can be a point in time when the image data of the image was acquired during the inversion recovery process. For example, such as... Figure 7 As shown, after the inversion recovery pulse is applied at time point 0, image data of the first image of at least three images is acquired at time point A. The first image of at least three images can be marked with time point A. The image acquisition time can provide information about the relative time point within the inversion recovery process relative to a reference time point (e.g., the start time of the inversion recovery pulse).

[0088] In some embodiments, at least three images may be original images (e.g., 2D or 3D images) based on image data acquired directly from the magnetic resonance imaging scanner 110. For example, at least three images may be reconstructed based on image data acquired from the magnetic resonance imaging scanner 110. In some embodiments, at least three images may be processed original images. For example, processing device 120A may process one or more of the at least three original images to obtain one or more processed images. In some embodiments, one or more processed images may be obtained by correcting artifacts in one or more of the at least three original images. For example, processing device 120A may correct artifacts caused by the motion of a target (e.g., heartbeat) during scanning by using a motion correction algorithm on one or more of the at least three original images. Exemplary motion correction algorithms may include iterative convergence algorithms, contour tracking algorithms, minimum entropy-based algorithms, and any combination thereof. As another example, the processing device 120A can correct artifacts caused by hardware (e.g., non-uniform magnetic fields, eddy currents) in the magnetic resonance imaging scanner 110 by performing a phase correction algorithm on one or more of at least three original images. Exemplary phase correction algorithms may include spectral peak location algorithms, peak curve fitting algorithms, entropy-based algorithms, peak regularization minimization algorithms, or any combination thereof. In some embodiments, the magnetic resonance imaging scanner 110 can perform inverse Fourier transforms on the real and imaginary parts of the image data, respectively, to obtain real and imaginary images of the image. For example, the image may correspond to image data having real and imaginary parts. Inverse Fourier transforms can be performed on the real and imaginary parts of the image data, respectively, to obtain real and imaginary images of the image. The processing device 120A can register the real image with other real images of at least three original images, and register the imaginary image with other imaginary images of at least three original images, respectively (e.g., by performing a phase correction algorithm). The registered real and imaginary parts of the same original image are fused or combined to obtain the processed image.

[0089] In some embodiments, the processing device 120A can process each of at least three original images to obtain at least three processed images. In some embodiments, the processing device 120A can select one or more images from the at least three original images for processing. For example, the processing device 120A can identify the type of artifact in the original image and process the original image by correcting the artifacts of the identified artifact type. For example, if the artifact in the original image is periodic, the processing device 120A can determine that the artifact may be caused by the heartbeat of the target, and the processing device 120A can process the original image according to a motion correction algorithm. As another example, if the artifact in the original image is moiré fringes, the processing device 120A can determine that the artifact may be caused by the non-uniform magnetic field of the magnetic resonance imaging scanner 110, and the processing device 120A can process the original image using a phase correction algorithm. In some embodiments, the processing device 120A can apply at least one of a motion correction algorithm or a phase correction algorithm to one or more of the at least three images. For example, processing device 120A can process one or more of the at least three original images by executing a phase correction algorithm and a motion correction algorithm. Alternatively, processing device 120A can process each of the at least three original images by executing the phase correction algorithm, and select one or more of the processed images from the at least three original images to further execute the motion correction algorithm. It should be noted that the phase correction algorithm and / or motion correction algorithm are for illustrative purposes only, and other algorithms can also be used to process one or more of the at least three images.

[0090] In some embodiments, the image count of at least three images can be associated with the cycle count of multiple cardiac cycles during the target's breath-holding period. In some embodiments, the magnetic resonance imaging scanner 110 can acquire image data of one of the at least three images within one cardiac cycle. For example, during the target's breath-holding period, the image count of at least three images can be less than or equal to the cycle count of multiple cardiac cycles. For example, if the target holds their breath in the visceral circulation for four cardiac cycles during the scan, the image count of at least three images can be four. Each of the four images can be acquired within each of the four cardiac cycles. As another example, if the target holds their breath for four cardiac cycles during the scan, the image count of at least three images can be three. The processing device 120A can select three cardiac cycles from the four cardiac cycles, wherein a specific state is detected in each cardiac cycle. Each of the three images can be acquired within each of the three selected cardiac cycles.

[0091] In some embodiments, at least three images may be generated based on image data acquired by magnetic resonance imaging scanner 110 and stored in a storage device (e.g., storage device 130, storage device 320, storage 490, or an external source). Processing device 120A may retrieve at least three images directly from the storage device.

[0092] In 604, the processing device 120A (e.g., the determination module 504) can determine the T1 mapping image of the target based on at least three images acquired during the inversion recovery process and a trained model.

[0093] In some embodiments, the T1-mapped image may be a parametric map that displays the T1 values ​​of the target at element locations (e.g., pixel locations, voxel locations) in the parametric-mapped image. In some embodiments, the T1 values ​​may correspond to elements (e.g., pixels, voxels) at element locations (e.g., pixel locations, voxel locations) in each of at least three images. For example, for at least three elements at the same element location in each of at least three images, the T1-mapped image may contain the T1 values ​​of a portion of the T1-mapped image at the same element location as the image. As used herein, the same element location in different images of the target or in the same image and the corresponding T1-mapped image represents the same physical point or target location. In some embodiments, the T1-mapped image may include T1 values ​​in an array of components arranged in the same array dimension at the elements of each of at least three images. For example, each of at least three images includes elements (e.g., pixels) arranged in an array dimension of M×N, where M and N are integers equal to or greater than 1. Therefore, the T1-mapped image may include T1 values ​​in an array dimension of M×N. The T1 value of the element position (P, Q) of the T1-mapped image can correspond to (e.g., determined based on) the value of the element (e.g., pixel) at the element position (P, Q) in each of at least three images, where P is an integer, 1 ≤ p ≤ m, and q is an integer, 1 ≤ q ≤ n.

[0094] In some embodiments, the trained model can be a program or algorithm for processing at least three images to obtain a T1-mapped image of the target. In some embodiments, the trained model can include a fully connected neural network (FNN), a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a feature pyramid network (FPN), a generative adversarial neural network (GAN), a CycleGAN model, a pix2pix model, etc., or any combination thereof. In some embodiments, it can be based on other parts of this application (e.g., Figure 9 The machine learning algorithm described in the description is used to generate a trained model.

[0095] In some embodiments, processing device 120A can obtain a trained model from one or more components of magnetic resonance imaging system 100 (e.g., storage device 130, storage device 320, memory 490) or from an external source via a network (e.g., network 150). For example, the trained model can be first trained by a computing device (e.g., processing device 120B) and stored in the storage device of magnetic resonance imaging system 100 (e.g., storage device 130, storage device 320, memory 490, or an external source). Processing device 120A can access the storage device and obtain the trained model.

[0096] In some embodiments, the trained model may include a process or algorithm for processing at least three images and determining a T1-mapped image of a target. For example, an initial model can be trained using multiple sample sets to generate the trained model. Each sample set in the multiple sample sets may include multiple sample images (also referred to as original sample images) and multiple reference T1-mapped images of the sample images. In some embodiments, the processing device 120A can obtain the T1-mapped image of the target by inputting at least three images into the trained model. For example, the processing device 120A may input at least three images into the trained model, and the trained model may directly output the T1-mapped image. In some embodiments, each sample set in the multiple sample sets may further include a sample image acquisition time. The sample image acquisition time may be the acquisition time of each sample image of the multiple sample images during the sample inversion recovery process. During the sample inversion recovery process, a sample inversion recovery pulse is applied to the sample target. The processing device 120A may input each of the at least three images and the image acquisition time of each of the at least three images into the trained model, and the trained model may output the T1-mapped image.

[0097] In some embodiments, the processing device 120A can directly determine the T1 value at each element position of the T1 mapping image based on the trained model, and determine the T1 mapping image based on the T1 values ​​at multiple element positions. In some embodiments, the T1 mapping image can be determined according to other parts of this application (e.g., Figure 8 The instance process described in the description is used to determine this.

[0098] It should be noted that the above description of process 600 is for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, these changes and modifications do not depart from the scope of this application. In some embodiments, process 600 may be performed by one or more additional operations not described and / or one or more operations not discussed. For example, process 600 may include the additional operation of sending a T1-mapped image to a terminal device (e.g., a doctor's terminal device 140).

[0099] Figure 8 This is a flowchart illustrating an exemplary process 800 for determining a T1-mapped image according to some embodiments of this application. In some embodiments, process 800 may be performed by magnetic resonance imaging system 100. For example, process 800 may be implemented as a set of instructions (e.g., an application program) stored in a storage device (e.g., storage device 130, storage device 320, and / or memory 490). In some embodiments, processing device 120A (e.g., processor 310 of computing device 300, central processing unit 440 of mobile device 400, and...) Figure 5A One or more modules shown can execute this set of instructions and can accordingly execute process 800. The operation of the process shown below is for illustrative purposes only. In some embodiments, process 800 can be accomplished with one or more additional operations not described and / or one or more operations not discussed. Additionally, as Figure 8 The order of operations in process 800 shown and described below is not restrictive.

[0100] In step 802, for the element positions in the T1-mapped image, the processing device 120A (e.g., determination module 504) can input the values ​​of at least three elements and the image acquisition time of each of the at least three images into a trained model to determine the T1 value. Each of the at least three elements is located at a corresponding element position in one of the at least three images.

[0101] In some embodiments, the trained model may include a process or algorithm for determining T1 values ​​for multiple element locations of a T1-mapped image. For example, a trained model can be generated by training an initial model using multiple sample sets. Each of the multiple sample sets may include multiple sample values ​​(e.g., sample pixel values, sample voxel values, sample grayscale values, etc.) for sample element locations (e.g., sample pixels, sample voxels) in multiple sample images and a reference T1 value for the multiple sample values. When the multiple sample values ​​are input to the trained model, the reference T1 value may be the expected output of the trained model. In some embodiments, each of the multiple sample sets may further include a sample image acquisition time for acquiring each of the multiple sample images during the sample inversion retrieval process. During the sample inversion retrieval process, a sample inversion retrieval pulse is applied to the sample target. Further description of model training can be found elsewhere in this application. For example, see [link to relevant documentation]. Figure 9 And its description.

[0102] In some embodiments, the T1-mapped image may include multiple components (e.g., T1 values) arranged at multiple element locations. To determine the T1-mapped image, the component (e.g., T1 value) at each element location can be determined. In some embodiments, the processing device 120A can obtain the T1 value at the element location by inputting at least three values ​​of an element into a trained model, which can output T1 values. These at least three values ​​are at the corresponding element locations in each of at least three images. For example, for each of the at least three images, the processing device 120A can identify the value of an element (e.g., pixel, voxel) at each element location (e.g., pixel location, voxel location) in the image. The processing device 120A can input at least three values ​​(e.g., pixel values) of an element (e.g., pixel) at each element location (e.g., p, q) in each of the at least three images into the trained model. The trained model can output the T1 value at element location (p, q) of the T1-mapped image.

[0103] In some embodiments, the input to the training model may further include the image acquisition time of each of at least three images. For example, the processing device 120A can identify the image acquisition time of each of the at least three images. In some embodiments, the image acquisition time of an image may be the time point at which image data of an image is acquired during a reversal recovery process. In some embodiments, the processing device 120 may input at least three values ​​of elements at at least three corresponding element positions in one of the at least three images and the image acquisition time of each of the at least three images into the trained model, and then the trained model outputs a T1 value. For example, if the image count of the at least three images is N, the input count in the trained model may be 2N, where N is an integer equal to or greater than 3. In the 2N input counts, the input includes the image acquisition times of N images, and the other N inputs include N values ​​of an element, each element being at the same element position in one of the N images.

[0104] In 804, the processing device 120A (e.g., determination module 504) can determine the T1 mapping image based on multiple T1 values ​​of multiple element positions in the T1 mapping image.

[0105] In some embodiments, the processing device 120A can generate a T1-mapped image by each of a plurality of T1 values ​​at element positions in a plurality of element locations. For example, for at least three elements at the same element position in one of at least three images, the T1-mapped image can include the T1 values ​​at the same element positions in the T1-mapped image. For example, each of the at least three images includes elements (e.g., pixels) located in an array dimension of M×N, where each M and N is an integer equal to or greater than 1. Therefore, the T1-mapped image can include T1 values ​​arranged in an array dimension of M×N. The T1 value at element position (p, q) in the T1-mapped image can correspond to the value of the element (e.g., pixel) at element position (p, q) in each of the at least three images (e.g., determined based on), where P is an integer, 1 ≤ p ≤ m, and q is an integer, 1 ≤ q ≤ n.

[0106] It should be noted that the above description of process 800 is for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, these changes and modifications do not depart from the scope of this application. In some embodiments, process 800 may be accomplished by one or more additional operations not described and / or without one or more operations discussed above. For example, process 800 may include additional operations for sending T1-mapped images to a terminal device (e.g., a doctor's terminal device 140).

[0107] Figure 9 This is a flowchart illustrating an exemplary process 900 for generating a trained model according to some embodiments of this application. In some embodiments, process 900 may be performed by magnetic resonance imaging system 100. For example, process 900 may be implemented as a set of instructions (e.g., an application program) stored in a storage device (e.g., storage device 130, storage device 320, and / or memory 490). In some embodiments, processing device 120B (e.g., processor 310 of computing device 300, central processing unit 440 of mobile device 400, and / or...) Figure 5B One or more modules shown can execute this set of instructions and are accordingly instructed to execute process 900. In some embodiments, process 900 can be used to obtain information related to... Figure 6 The associated trained model in operation 604. In some embodiments, process 900 may be performed by another device or system other than magnetic resonance imaging system 100, such as, for example, the device or system of a supplier or the manufacturer of the trained model. For ease of illustration, process 900 implemented by processing device 120B is described as an example.

[0108] In some embodiments, the trained model can be trained offline. For example, the trained model can be trained and stored in the storage device of the magnetic resonance imaging system 100 (e.g., storage device 130, storage device 320, and / or memory 490). The processing device 120B can access the storage device to obtain the trained model to determine the T1 mapping image. Alternatively, the trained model can be trained in real time. For example, when the trained model is needed to generate a T1 map, the processing device 120B can train to obtain the trained model.

[0109] In 902, the processing device 120B (e.g., acquisition module 506) can acquire multiple sample sets.

[0110] In some embodiments, each sample set may include multiple sample images, an acquisition time for each sample image corresponding to one of a series of sample images, and a reference T1 mapping image for the multiple sample images. The reference T1 mapping image can be determined based on the multiple sample images and the multiple sample image acquisition times within the sample set. In some embodiments, each sample set may include values ​​of multiple sample elements located at sample element positions in one of the multiple sample images, a sample image acquisition time corresponding to each image in the sample images, and a reference T1 value corresponding to the sample element position. The reference T1 value can be determined based on the multiple sample elements and the multiple sample image acquisition times within the sample set.

[0111] In some embodiments, for one sample set of multiple sample sets, the processing device 120B can determine a reference T1 mapping image based on multiple sample images of the sample set and the acquisition time of the multiple sample images. For example, for a sample set, the processing device 120B can acquire multiple sample images of a sample target. Multiple sample images can be generated based on sample image data acquired by an example magnetic resonance imaging scanner. In some embodiments, sample image data of multiple sample images of the sample set is acquired using an improved Look-Locker inversion recovery sequence. In some embodiments, different sample sets can be obtained from different sample magnetic resonance imaging scanners. In some embodiments, the sample magnetic resonance imaging scanner can be one that acquires and... Figure 6 The image data corresponding to at least three images described herein are from a magnetic resonance imaging scanner of the same device (or the same product model).

[0112] Figure 10 This is a schematic diagram illustrating an exemplary scanning process using the MOLLI sequence according to some embodiments of this application. Figure 10 As shown, ECG recording is performed simultaneously during the scan. During the scan, the target sample can be required to be in multiple cardiac cycles (e.g., such as...). Figure 10 (11 cardiac cycles are shown) Breathing is held. After the sample target begins to hold its breath (and remains still), a first sample inversion recovery pulse can be applied to the sample to perform the first sample inversion recovery process. During the first sample inversion recovery process, while the sample target holds its breath and the first sample inversion recovery pulse is applied, sample image data for five sample images can be acquired at time points A', B', C', D', and E', respectively, while the sample target is held. Each of the five time points A'-E' can be within one cardiac cycle of the sample target recorded according to the ECG. After acquiring five images during the first sample inversion recovery process, a recovery process of three cardiac cycles can be performed. During the recovery process, the magnetization within the sample target can be restored to a magnetized state before the first sample inversion recovery pulse is applied to the sample target. Then, a second sample inversion recovery pulse can be applied to the sample target to perform the second sample inversion recovery process. In the second sample inversion recovery process, sample image data for three sample images can be acquired at time points F', G', and H' after the recovery process. Each of the three time points F'-H' falls within one cardiac cycle of the sample target as recorded by electrocardiogram. In each sample inversion recovery process, the magnetization within the sample target can be reversed after a 180° out-of-phase pulse is applied to the sample target. As used herein, the sample inversion recovery pulse can be a conventional spin echo sequence following the 180° out-of-phase pulse. Figure 10As shown, sample image data for eight sample images can be obtained during the two-sample inversion recovery process. It should be noted that... Figure 10 This is for illustrative purposes only and is not intended to limit the scope of this application. For example, during a scan using the MOLLI sequence, sample image data of other image counts (e.g., 9, 10, 11, 12, etc.) of the sample image can be obtained. As another example, more than two inversion recovery pulses can be applied during the scan, and the sample image data of the image counts of the sample image obtained after each inversion recovery pulse can be one, two, three, four, five, etc.

[0113] In some embodiments, sample image data for each of multiple sample images can be acquired when the sample target is in a specific state within each cardiac cycle (e.g., the R wave in an ECG recording) or at a specific time within each cardiac cycle. For example, during a first sample inversion recovery process, sample image data for each of five sample images can be acquired at time point TI1 (e.g., 60 ms) within each cardiac cycle (e.g., 100 ms). During a second sample inversion recovery process, sample image data for each of three sample images can be acquired at time point TI2 (e.g., 70 ms) within each cardiac cycle. In some embodiments, time point TI1 may differ from time point TI2. For example, time point TI2 may be later than time point TI1. In some embodiments, the time difference between time points TI1 and TI2 can be determined depending on the application scenario. For example, during a scan, the time difference between time points TI1 and TI2 may differ when the sample target is injected with contrast agent compared to when no contrast agent is injected. As another example, different sample MR scanners may correspond to different time differences between time points TI1 and TI2.

[0114] In some embodiments, for one sample set of multiple sample sets, the processing device 120B can identify the sample image acquisition time of each of the multiple sample images. For example, each of the multiple sample images can be marked with a sample image acquisition time. The sample image acquisition time can be a point in time in the sample image data acquired after the inversion recovery pulse is applied to the sample target. For example, as... Figure 10As shown, a first inversion recovery pulse is applied at time point 0, and sample image data of sample image a' from a plurality of sample images is acquired at time point A'. The sample image acquisition time of sample image a' is time point A'. After a second inversion recovery pulse is applied at time point 0, sample image data of sample image f' from a plurality of sample images is acquired at time point F'. The sample image acquisition time of sample image f' is time point F'. In some embodiments, the plurality of sample images in the sample set may be arranged in the order of sample image acquisition time and cardiac cycle after the inversion recovery pulse is applied to the sample object, wherein the sample image acquisition time gradually decreases. In some embodiments, the sample image acquisition time may be a relative time point during the inversion recovery process relative to a reference time point (e.g., the start of the inversion recovery pulse). For example, see... Figure 11 The arrangement of sample images in the image.

[0115] Figure 11 These are exemplary images acquired during an exemplary scanning process using the MOLLI sequence, as shown in some embodiments of this application. As described above, during the first sample inversion recovery process, five sample images a'-e' can be acquired at time point TI1 within each cardiac cycle, and during the second sample inversion recovery process, three sample images f'-h' can be acquired at time point TI2 within each cardiac cycle. Time point TI2 (e.g., 70 ms) can be later than time point TI1 (e.g., 60 ms). Figure 10 and Figure 11 As shown, the eight sample images can be arranged in the order of sample image a', sample image f', sample image b', sample image g', sample image c', sample image h', sample image d', and sample image e'.

[0116] In some embodiments, the sample image may be the original sample image obtained by image reconstruction from sample image data acquired from a sample magnetic resonance imaging scanner. In some embodiments, the sample image may be a processed sample image of the original sample image. Algorithms for processing sample images may be used elsewhere in this application (e.g., Figure 6 As described in the relevant descriptions.

[0117] In some embodiments, for one sample set in a plurality of sample sets, the processing device 120B can determine a reference T1 mapping image for the plurality of sample images based on the plurality of sample images and the corresponding sample image acquisition time. For example, the processing device 120B can determine the reference T1 mapping image based on a fitting algorithm (e.g., least squares algorithm, interpolation algorithm, etc.). In some embodiments, the processing device 120B can select sample elements at the same sample element position from each of the plurality of images in the sample set, and determine a reference T1 value at the same sample element position in the reference T1 mapping image. For example, the processing device 120B can select sample elements at the same sample element position from (from Figure 10 In the scanning process shown, a sample element is selected at sample element position (p', q') in each of the eight sample images acquired. The sample value (e.g., sample pixel value) of each sample element (e.g., sample pixel) at sample element position (p', q') can be determined, and the sample image acquisition time of each of the eight sample images can be determined. The processing device 120B can determine the reference T1 value of sample element position (p', q') according to the fitted curve shown in equation (1) below:

[0118]

[0119] Where TI represents the sample image acquisition time when acquiring sample image data for a sample image in the sample set. s(TI) represents the sample value of the sample element at the sample element position in the sample image that has already acquired sample image data at sample image acquisition time TI. 1* Let T1 represent the reference value to be determined, and A and B represent two unknown constants. By inputting the sample image acquisition time of the sample images in the sample set and the corresponding sample value at the sample element position in each sample image into equation (1), the reference T1 value, constant A, and constant B corresponding to the sample element position can be determined.

[0120] In some embodiments, the processing device 120B can determine a plurality of reference T1 values ​​for a sample set and generate a T1 mapping image by setting each of the plurality of reference T1 values ​​at the position of a sample element in the reference T1 mapping image. In some embodiments, the process of generating a reference T1 mapping image based on a plurality of reference T1 values ​​can be integrated with other parts of this application (e.g., Figure 8 The process of generating a T1 mapping image based on multiple T1 values ​​is the same as or similar to that of operation 804).

[0121] In 904, the processing device 120B (e.g., model generation module 508) can obtain a trained model by training an initial model based on multiple sample sets.

[0122] In some embodiments, the initial model refers to the process, algorithm, or model to be trained. The initial model may be found elsewhere in this application (e.g., Figure 6 Any type of model (e.g., a machine learning model) as described in the relevant description. In some embodiments, the processing device 120B may acquire an initial model from one or more components of the magnetic resonance imaging system 100 (e.g., storage device 130, storage device 320, memory 490, or an external source via a network (e.g., network 150)).

[0123] The initial model may include multiple model parameters. For example, the initial model may be an FNN model, and exemplary model parameters of the initial model may include the number (or count) of layers, the number (or count) of kernels, the kernel size, stride, padding for each convolutional layer, etc., or any combination thereof. Before training, the model parameters of the initial model may each have their own initial values. For example, the processing device 120B may initialize the parameter values ​​of the model parameters of the initial model.

[0124] In some embodiments, training the initial model may include one or more iterations to iteratively update the model parameters of the initial model based on multiple sample sets until a termination condition is met in some iteration. An exemplary termination condition may be that the value of the loss function obtained in some iterations is less than a threshold, that is, after a certain number of iterations, the loss function converges, such that the difference between the loss function value obtained in the previous iteration and the loss function value in the current iteration is within a threshold.

[0125] As an example, an updated initial model generated in previous iterations can be evaluated in the current iteration. A loss function can be used to measure the difference between the predicted T1-mapped image output by the updated initial model in the current iteration and a reference T1-mapped image. For example, each sample set may include sample images and a reference T1-mapped image. Sample images from a sample set can be fed into the updated initial model, and the updated initial model can output a predicted T1-mapped image. A loss function can be used to measure the difference between the predicted T1-mapped image and the reference T1-mapped image for each sample set. As another example, each sample set may include the values ​​of sample elements at each sample element location of multiple sample images and a reference T1 value. The values ​​of the sample elements can be fed into the updated initial model, and the updated initial model can output a predicted T1 value. A loss function can be used to measure the difference between the predicted T1 value and the reference T1 value for each sample set. Exemplary loss functions may include normalized exponential functions, focus loss functions, log loss functions, cross-entropy loss functions, variance loss functions, Dice loss functions, L1 loss functions, L2 loss functions, etc.

[0126] If the termination condition is not met in the current iteration, the processing device 120B can further update the updated initial model according to, for example, a backpropagation algorithm, for use in the next iteration. If the termination condition is met in the current iteration, the processing device 120B can designate the updated initial model in the current iteration as the trained model.

[0127] It should be noted that the above description of process 900 is for illustrative purposes only and is not intended to limit the scope of this application. Various changes and modifications can be made by those skilled in the art based on the description of this application. However, these changes and modifications do not depart from the scope of this application. In some embodiments, process 900 may be accomplished by one or more additional operations not described and / or without one or more of the operations discussed above. For example, process 900 may include additional operations for storing the training model in a storage device (e.g., storage device 130, storage device 320, and / or memory 490).

[0128] Figure 12 This is a schematic diagram of an exemplary initial model 1200 according to some embodiments of this application. For example... Figure 12 As shown, the initial model 1200 may include an input layer 1201, one or more hidden layers 1202, and an output layer 1203. In some embodiments, the layers of the initial model 1200 may be connected in a feedforward manner, and the output of the i-th layer may be used as the input of the (i+1)-th layer, where i is an integer equal to or greater than 1. Optionally or additionally, the output of the (i+1)-th layer may be passed back to the i-th layer according to a chain rule.

[0129] In some embodiments, in the initial model 1200, the input layer 1201 may be configured to receive inputs to the initial model 1200 (e.g., with...). Figure 9 (The sample set described in relation to operation 902 in the text). Each hidden layer 1202 can perform a specific function, including, for example, convolution, pooling, normalization, matrix multiplication, nonlinear activation, etc. The output layer 1203 can receive input from the previous layer and perform one or more transformations on the received input values ​​to generate the prediction result of the initial model 1200 (e.g., predicting a T1 mapping image or predicting a T1 value).

[0130] For ease of illustration, hidden layer 1202 may include multiple hidden layers 1202-1, 1202-2, ..., 1202-n. For example, hidden layer 1202 may include convolutional layers, batch normalization layers, pooling layers, fully connected layers, loss layers, etc., or any combination thereof. In some embodiments, the output of the convolutional layer may be processed by the batch normalization layer and the pooling layer and then input into the convolutional layer. The convolutional layer can be used to extract and / or map feature information from a sample set. Exemplary feature information may include low-level feature information (e.g., edge features, texture features), high-level feature information, or complex features. The batch normalization layer may be configured to receive and normalize the output of the convolutional layer (e.g., feature maps). Normalizing the data by the batch normalization layer can accelerate the convergence of the initial model and improve the stability of the initial model during training. For example, the batch normalization layer can make the input values ​​of neurons in each layer of the initial model 1200 follow a standard normal distribution with a mean of 0 and a variance of 1. The batch normalization layer can also make the input values ​​of nonlinear functions (representing the initial model 1200) fall into the input-sensitive region, so that small changes in the input values ​​can lead to large changes in the loss function, thus avoiding the low-level gradient vanishing problem of the initial model 1200. This can improve the convergence speed during the training of the initial model 1200. Each pooling layer can be used to sample the batch normalization layer to reduce the computational load of data processing and accelerate data processing. Fully connected layers can be connected to pooling layers. Fully connected layers can be used to perform improvement operations to reduce the loss of feature information. The loss layer can be used to evaluate the loss function based on the correction result predicted by the initial model and the corresponding reference T1 mapping image (or reference T1 value). The loss function can be used to measure the difference between the prediction result output by the updated initial model (e.g., predicted T1 mapping image or predicted T1 value) and the reference T1 mapping image (or reference T1 value). Further descriptions of the loss function can be found elsewhere in this application, for example, see [link to relevant documentation]. Figure 9 The 904 error and its related description are described in the documentation. It should be noted that... Figure 12 The initial model 1200 described herein is for illustrative purposes only and is not intended to limit the scope of this application. An initial model with any other structure can be used to generate a trained model.

[0131] The basic concepts have been described above. Obviously, for those skilled in the art who have read this application, the above disclosure is merely illustrative and does not constitute a limitation of this application. Various modifications, improvements, and corrections may be made, and these modifications, improvements, and corrections are intended for those skilled in the art, although not explicitly stated herein. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0132] Furthermore, this application uses specific terms to describe its embodiments. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be appropriately combined.

[0133] Furthermore, those skilled in the art will understand that aspects of this application can be described and illustrated through several patentable types or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Therefore, aspects of this invention can be implemented entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or a combination of software and hardware, which are generally referred to herein as “units,” “modules,” or “systems.” Furthermore, aspects of this application can take the form of computer program products embodied in one or more computer-readable media, on which computer-readable program code is embodied.

[0134] A computer-readable signal medium may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. Such propagated signals can take many forms, including electromagnetic, optical, and any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer-readable signal medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency, and any combination of the above.

[0135] The computer program code that performs the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc.; traditional procedural programming languages ​​such as the "C" programming language, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP; dynamic programming languages ​​such as Python, Ruby, and Groovy, or other programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer as a standalone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (e.g., via the Internet through an Internet service provider) or in a cloud computing environment, or provided as a service, such as Software as a Service (SaaS).

[0136] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this application are not intended to limit the order of the processes and methods of this application. Although some currently considered useful embodiments of the invention have been discussed in the foregoing disclosure by way of various examples, it should be understood that such details are for illustrative purposes only, and the additional claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments of this application. For example, although the implementations of the various components described above can be implemented in hardware devices, they can also be implemented as software-only solutions, such as installations on existing servers or mobile devices.

[0137] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, the method of the present application should not be construed as reflecting an intention that the claimed object to be scanned requires more features than expressly recited in each claim. Rather, the subject of the invention should possess fewer features than in any single embodiment described above.

[0138] In some embodiments, the numbers used to describe and claim certain embodiments of the present application in terms of expressive quality or characteristics should be understood to be modified in certain circumstances by the terms "about," "approximately," or "substantially." For example, unless otherwise stated, "about," "approximately," or "substantially" can represent a range of ±1%, ±5%, ±10%, or ±20% of the numerical value they describe. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the desired characteristics of individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of the present application are approximate values, in specific embodiments, such numerical values ​​are set as precisely as feasible.

[0139] For each patent, patent application, patent application publication, and other material cited herein, such as articles, books, specifications, publications, and documents, the entire contents are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this document, as well as documents that limit the broadest scope of the claims of this application (currently or subsequently appended herein). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the appended materials and the content herein, the descriptions, definitions, and / or terminology used herein shall prevail.

[0140] Finally, it should be understood that the embodiments described in this application are merely illustrative of the principles of the embodiments of this application. Other modifications may also fall within the scope of this application. Therefore, alternative configurations of the embodiments of this application are considered as examples and not limitations, and are regarded as consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly described and illustrated in this application.

Claims

1. A magnetic resonance T1 mapping method, comprising: Acquire at least three images of the target during a reversal recovery process, each of the at least three images being acquired during breath-holding within one cardiac cycle of the target, and the image count of the at least three images being less than or equal to the cycle count of a plurality of cardiac cycles; as well as Based on the at least three images acquired during the inversion recovery process and the trained model, the T1 mapping image of the target is determined, including: obtaining the T1 mapping image of the target by inputting the at least three images into the trained model, wherein the T1 mapping image is the output of the trained model.

2. The method according to claim 1, characterized in that, Further includes: One or more processed images are obtained by processing one or more of the at least three images; as well as Based on the one or more processed images and the trained model, determine the T1 mapping image of the target.

3. The method according to claim 2, characterized in that, The process of obtaining one or more processed images by processing one or more images of at least three images includes: The one or more processed images are obtained by applying at least one of motion correction algorithms or phase correction algorithms to one or more of the at least three images.

4. The method according to claim 1, characterized in that, The trained model includes a fully connected neural network.

5. The method according to claim 1, characterized in that, Determining the T1 mapping image of the target based on the at least three images and the trained model includes: For the element positions in the T1 mapped image, the values ​​of at least three elements and the image acquisition time of each of the at least three images are input into the trained model to determine the T1 value, where each of the at least three elements is located at its corresponding element position in one of the at least three images; and The T1 mapping image is determined based on the plurality of T1 values ​​of the plurality of element positions in the T1 mapping image.

6. The method according to claim 5, characterized in that, Determining the T1 value for the element position in the T1 mapping image includes: For each of the at least three images, Identify the image acquisition time of the image, wherein the image acquisition time is the time point at which the image was acquired during the inversion recovery process; and Identify the value of the element at each element location in the image.

7. The method according to claim 1, characterized in that, The trained model is determined based on the training process, which includes: Acquire multiple sample sets, each sample set including multiple sample images, multiple sample image acquisition times, and reference T1 mapping images of the multiple sample images, wherein each of the multiple sample image acquisition times corresponds to one image among the multiple sample images; and The initial model is trained based on the multiple sample sets to obtain a trained model.

8. The method according to claim 7, characterized in that, The acquisition of multiple sample sets includes: For each of the plurality of sample sets, Acquire the multiple sample images; Determine the acquisition time of each of the plurality of sample images; and Based on the plurality of sample images and the corresponding sample image acquisition time, a reference T1 mapping image for the plurality of sample images is determined.

9. A magnetic resonance T1 mapping system, comprising: At least one storage device for storing a set of instructions; as well as At least one processor communicating with the at least one storage device, characterized in that, when executing the instructions, the at least one processor is configured to cause the system to perform the method as described in any one of claims 1-8.

Images