Transmission of K-space data for remote reconstruction of magnetic resonance images.

Abstract

The medical system includes a local memory (138) storing local machine-executable instructions and pulse sequence commands, a magnetic resonance imaging system, and a local computing system. Execution of the local machine-executable instructions causes the local computing system to transmit metadata describing a magnetic resonance imaging protocol to a remote computing system over a network connection. Execution of the local machine-executable instructions causes the computing system to repeatedly: control the magnetic resonance imaging system with pulse sequence commands to acquire one of a series of discrete k-space acquisitions; compress one of the series of k-space acquisitions using a compression module to construct a compressed k-space acquisition (206); and transmit the compressed k-space acquisition to the remote computing system over the network connection.

Description

[Technical Field]

[0001] The present invention relates to magnetic resonance imaging, and more particularly to magnetic resonance image reconstruction. [Background technology]

[0002] A large static magnetic field is used by magnetic resonance imaging (MRI) scanners to align the nuclear spins of atoms as part of a procedure to generate images of a patient's body. This large static magnetic field is called the B0 field or main magnetic field. A combination of radio frequency signals and magnetic gradients is used to encode the atomic nuclear spins. The nuclear spins emit radio frequency signals in response to this encoding. These radio frequency signals may be sampled and digitally stored. These samples reside in k-space and are referred to herein as k-space data. The k-space data may be Fourier transformed into a magnetic resonance image.

[0003] U.S. Patent Application Publication No. 2021003651A1 discloses a medical data processing device including a processing circuit. The processing circuit receives first data obtained by sparse sampling. The processing circuit multiplies the first data by a set of weighting coefficients and adds the multiplied first data to generate first compressed data portions that are smaller than the first data. The processing circuit performs first processing to output second compressed data portions by applying a trained model to the first compressed data portions, the trained model being trained by receiving the first compressed data portions based on sparse sampling and outputting at least one of the second compressed data portions based on full sampling.

[0004] The present invention provides a medical system, a computer program and a method in the independent claims. Embodiments are given in the dependent claims. Summary of the Invention [Problem to be solved by the invention]

[0005] The amount of data that can be acquired during a magnetic resonance imaging scan can be very large, with the raw data size of the acquired k-space data being hundreds of megabytes or even tens of gigabytes. Once this measured k-space data is acquired, magnetic resonance images can be reconstructed using different methods depending on the magnetic resonance imaging protocol. Some of these reconstruction methods can be computationally intensive, particularly methods that rely on deep learning or optimization processes to perform the reconstruction. Therefore, there is interest in performing image reconstruction on remote or cloud-based platforms where computing power can be provided on demand.

[0006] A difficulty is that transferring large amounts of data to a remote system can result in delays in receiving the reconstructed magnetic resonance image. Embodiments can provide a means to accelerate this. For example, measured k-space data is acquired as a series of discrete k-space acquisitions. As the discrete acquisitions of k-space data are acquired, they are compressed and then transmitted to a remote computing system, where the k-space data is decompressed and then used to reconstruct the magnetic resonance image. This can have several advantages. One potential advantage is that the measured k-space data can reach the remote computing system more quickly, reducing or alleviating data bottlenecks. Another potential advantage is that in some reconstruction techniques, partial data, such as the blades of propeller k-space data or self-navigation data, can be immediately used to perform part of the reconstruction. [Means for solving the problem]

[0007] In one aspect, the present invention provides a medical system comprising a local memory storing local machine-executable instructions and pulse sequence commands. The pulse sequence commands are commands or data that can be converted into commands used to control a magnetic resonance imaging system to acquire k-space data. Typically, the pulse sequence commands are provided in the form of events occurring at different time periods during an acquisition procedure. The medical system further comprises a magnetic resonance imaging system configured to acquire measured k-space data describing a subject within an imaging zone. The pulse sequence commands are configured to control the magnetic resonance imaging system to acquire the measured k-space data as a series of discrete k-space acquisitions according to a magnetic resonance imaging protocol. The measured k-space data is k-space data that can be used to reconstruct a complete image. The series of discrete k-space acquisitions is sometimes referred to as a series of discrete lines or shots of k-space data.

[0008] The medical system further includes a local computing system. Execution of the local machine-executable instructions causes the local computing system to transmit metadata describing a magnetic resonance imaging protocol to the remote computing system via a network connection. Execution of the local machine-executable instructions causes the local computing system to repeatedly control the magnetic resonance imaging system using pulse sequence commands to acquire one of a series of discrete k-space acquisitions. For example, this may be acquiring one line of k-space data. The metadata describes the acquisition and / or sampling aspects of the measured k-space data. Reconstruction of an image from the measured k-space data may be adapted to the acquisition and / or sampling aspects of the measured k-space data. To that end, the metadata is made available in the reconstruction process. This may be implemented by transmitting the compressed k-space data and the metadata together, or the metadata may be transmitted separately or otherwise made available for the reconstruction process. Some examples of acquisition and / or sampling aspects may be simple Cartesian k-space sampling, radial or spiral k-space sampling, blade-wise Cartesian sampling ("multi-vane"), where the blades have different orientations in k-space. Redundant sampling of the central region of k-space can be used for motion correction or the availability of separate motion data that can be used for motion correction of the measured k-space data. In the case of parallel imaging with undersampling of k-space, the metadata can indicate that separate sets of measured k-space data are acquired by specific receiver antennas (receiver coils). The metadata can indicate aspects of undersampling patterns, coil sensitivity profiles, or auto-calibration data that represent coil sensitivity profiles within the measured k-space data. Such aspects can be useful for adapting the reconstruction strategy to the way the k-space data is acquired. The metadata can indicate control parameters for selecting and / or adjusting aspects of the reconstruction, such as a sampling pattern in k-space (or dynamically in (k,t) space, where t represents time) that imposes spatial and / or contrast encoding of the magnetic resonance signals.The reconstruction needs to account for these encoding aspects of the magnetic resonance signals in the reconstruction of a magnetic resonance image from sampled magnetic resonance signals. Furthermore, the metadata can represent motion information related to offsets in the phase of the magnetic resonance signals due to motion. This motion information needs to be taken into account to correct for motion in the reconstruction. The metadata may also represent aspects of the parallel image, such as parallel image acceleration coefficients and spatial coil sensitivity profiles, which need to be taken into account in the development of aliasing in the magnetic resonance signals due to undersampling in k-space.

[0009] Execution of the local machine-executable instructions causes the local computing system to repeatedly build a compressed k-space acquisition as one of a series of compressed k-space acquisitions by compressing one of the series of k-space acquisitions using the compression module. Execution of the local machine-executable instructions further causes the local computing system to repeatedly transmit the compressed k-space acquisition to a remote computing system over a network connection. In these aspects, the magnetic resonance imaging system is controlled to acquire a single discrete k-space acquisition and then compress it into a compressed k-space acquisition. After being compressed using the compression module, it is then transmitted to the remote computing system.

[0010] Execution of the local machine-executable instructions further causes the local computing system to transmit at least a portion of the series of compressed k-space acquisitions over a network connection before completing acquisition of the measured k-space data. This embodiment can be advantageous because it provides a highly efficient and rapid means of transmitting the measured k-space data to the remote computing system. This can, for example, enable more rapid reconstruction of magnetic resonance images than would be possible if all of the measured k-space data were acquired, compressed, and then transmitted to the remote computing system.

[0011] In another embodiment, the medical system further comprises a remote memory storing remote machine-executable instructions. The medical system further comprises a remote computing system. Execution of the remote machine-executable instructions causes the remote computing system to receive metadata describing a magnetic resonance imaging protocol over a network connection. Execution of the remote machine-executable instructions further causes the remote computing system to repeatedly receive compressed k-space acquisitions over the network connection. Execution of the remote machine-executable instructions further causes the remote computing system to repeatedly acquire one of the series of discrete k-space acquisitions by decompressing the compressed k-space acquisition with a decompression module.

[0012] Execution of the machine-executable instructions further causes the remote computing system to reconstruct a magnetic resonance image from at least a portion of the measured k-space data according to the magnetic resonance imaging protocol specified in the metadata. This can take different forms in different embodiments. In some cases, the system may wait for all of the compressed k-space acquisitions to arrive so that the fully measured k-space data can be reconstructed. In this case, the system receives the measured k-space data more quickly than if it were acquired and then transmitted. In other examples, for example, in parallel imaging or when there is self-navigation, such as in propeller magnetic resonance imaging techniques, it may be beneficial to perform individual, discrete acquisitions earlier. For example, if the discrete acquisitions of k-space are the blades of a propeller k-space data, the system can begin motion compensation even before the fully measured k-space data is received. This can therefore enable faster reconstruction of the magnetic resonance image.

[0013] In another embodiment, the medical system further comprises a motion detection system for acquiring motion data describing the motion of the subject. In some examples, the motion detection system may be a sensor system such as a camera, a breathing belt, or other sensor system. In other examples, the motion detection system may operate using motion detection by the magnetic resonance imaging system itself. For example, there may be fiducial markers placed on the surface of the subject, there may be self-navigation, or there may be navigation measurements used to acquire the motion data.

[0014] Execution of the local machine-executable instructions causes the local computing system to control the motion detection system to acquire motion data during acquisition of the measured k-space data. Execution of the local machine-executable instructions further causes the local computing system to trigger a motion alert if the motion data indicates subject motion above a predetermined motion threshold. For example, if the subject is moving too frequently or if the subject repositions their body during acquisition of the measured k-space data, the trigger may indicate that motion correction may be necessary.

[0015] Execution of the local machine-executable instructions further causes the local computing system to initiate construction of a compressed k-space acquisition and transmission of the compressed k-space acquisition to the remote computing system over a network connection when a motion alert is triggered, and the metadata includes a motion compensated reconstruction request for the measured k-space data when a motion alert is triggered.

[0016] The motion alert may indicate subject motion that is occurring or has occurred during a portion of the acquisition of the measured k-space data, which then requests a remote computing system to perform a reconstruction that performs motion compensation.

[0017] As described above, motion detection using a motion detection system can be detected not only explicitly, such as using a latent hardware-based motion sensor such as a camera, but also in the acquired raw k-space data or image itself. This embodiment is beneficial because motion compensation can be very computationally intensive. The ability to detect subject motion and then trigger remote reconstruction can allow a more powerful computing system to be used to perform the reconstruction.

[0018] In another embodiment, the compression module is implemented as a neural network. Implementing the compression module as a neural network can be beneficial because neural networks process data very quickly and with very low computational demands. Thus, the use of a neural network can enable compression of discrete k-space acquisitions more quickly, and potentially with lower computational requirements and power.

[0019] This approach may have one or more of the following advantages: 1. Compression of data in k-space does not require lossy data pre-processing and therefore allows full utilization of the coding capacity of the compression neural network used. 2. Compression of MR 1D phase encoding (k-space data) allows data from the scanner to be compressed and transmitted independently, which allows for multi-threaded compression and data transmission, improving throughput. 3. Compression of 1D signals (k-space data) allows the use of smaller coding networks, reducing encoding and decoding runtimes. In cases where it may be beneficial or necessary to send compressed neural network weights along with the compressed data, the use of smaller networks also improves the rate-distortion tradeoff.

[0020] In another embodiment, the compression module is formed from the encoder portion of the autoencoder. The compressed k-space data acquisitions are the latent space vectors of the autoencoder. The decoder can then be formed from the decoder portion of the autoencoder. This can be beneficial because the k-space data can be accurately transmitted using the latent space vectors.

[0021] Phase-encoded MR profiles (k-space data) can be arbitrarily defined in 2D or 3D k-space, up to specific physiological and scan parameter constraints. Common choices for sampling trajectories are along Cartesian, radial, or spiral coordinates. Regardless of the trajectory design, the phase encoding can be linearly projected from 2D or 3D space to 1D space. The 1D signal is then processed by an encoding neural network structure, which nonlinearly projects it onto a lower-dimensional underlying 1D space, thereby achieving compression. The resulting signal can then be transmitted to the receiver and decoded by a decoding neural network.

[0022] Encoding and decoding networks can be trained offline by solving an autoencoder optimization task. Given a training dataset assumed to represent the data to be compressed, the autoencoder optimizes neural network parameters so that the autoencoder's output is as close as possible to the network's input for all samples in the training dataset. This task can be solved efficiently using stochastic gradient descent or its extensions, and the metric used to evaluate the reconstruction fidelity can be defined sample-by-sample in either an L2 or L1 sense.

[0023] Different embodiments of the present invention can modify the encoding-decoding pipeline. Examples of these include: 1. A single autoencoder is applied independently to all phase encodings. 2. Different autoencoders are used for the individual phase encoding. 3. A single autoencoder is used for all phase encoding, but is adapted for individual phase encoding with transmission of additional information captured during encoding of each phase encoding.

[0024] In another embodiment, the autoencoder used as the encoder and decoder portions is derived from a vector quantization variational autoencoder (VQ-VAE). Vector quantization variational autoencoders have been shown to be useful for compressing images, as shown in Razavi et al., "Generating diverse high-fidelity images with vq-vae-2," in Advances in Neural Information Processing Systems, pp. 14866-14876, 2019. These same techniques can be used to compress k-space data. Applying a VQ-VAE can be beneficial because the data can be accurately restored after decompression, the VQ-VAE can be simpler, and it can use fewer computational resources to compress the image.

[0025] VQ-VAEs and other autoencoders can be trained to compress data by using previously acquired k-space data as training data for the autoencoder.

[0026] In another embodiment, a magnetic resonance imaging system includes a magnetic resonance imaging coil including a digitizer circuit for measuring a series of discrete k-space acquisitions. A local computing system includes the digitizer circuit. The digitizer circuit is configured to construct a compressed k-space acquisition as one of the series of k-space acquisitions is measured. This embodiment can be advantageous because it can be used to compress a discrete k-space acquisition as it is acquired. Many magnetic resonance imaging techniques use so-called parallel imaging, where multiple receive coils are used. When the digitizer circuit for each of these receive coils separately compresses the discrete k-space acquisitions, compression and transmission are performed in a parallel manner. This can significantly accelerate transmission of the measured k-space data to the remote computing system.

[0027] It should be noted that using neural networks can be very beneficial when digitizer circuits are used to construct compressed k-space acquisitions. This is because neural networks, such as variational autoencoders, have very low computational overhead. This means that the digitizer requires less computation and can use less power. This can be a concern because digitizer circuits may be located within magnetic resonance imaging systems, and it is typically not possible to provide them with large amounts of power. This is because the wires entering the magnetic resonance imaging system can pick up some of the radio frequencies and energy used to execute the magnetic resonance imaging protocol. Therefore, reducing the power usage of digitizer circuits is very beneficial.

[0028] In another embodiment, execution of the machine-executable instructions further causes the computing system to determine a predicted correlation in a discrete k-space acquisition from previously acquired k-space data. The metadata includes the predicted correlation. Execution of the machine-executable instructions causes the computing system to decorrelate one of the series of discrete k-space acquisitions using the predicted correlation prior to compression into a compressed k-space acquisition. Performing this decorrelation essentially reduces the amount of data that needs to be compressed. This can reduce the size of the data transmitted to the remote computing system.

[0029] In the remote computing system, once the k-space data is decompressed, the receiver can reconstruct the k-space data using metadata regarding correlations between the k-space data.

[0030] In another embodiment, the previously acquired k-space data originates from a survey scan of the subject or from a previously compressed one of a series of discrete k-space acquisitions, which may be beneficial because it may contain information about how the k-space data can be effectively decorrelated, both in the case of a survey scan or this previously acquired acquisition.

[0031] In one example, the previously acquired data may be a localized entire scout image, a topogram image, or a survey image. From these correlations between points and k-space data, a transform can be calculated to decorrelate the data before using a compression technique. This method is similar to the imaging technique GRAPPA, in which the actual acquisition is modified to avoid measuring redundant data. For example, samples in k-space are omitted, and these can be estimated by neighboring measurements.

[0032] Another example is using information from previous measurements of the patient to better improve the compression ratio of the next transmitted data portion.

[0033] In another example, previously transmitted k-space measurements already present at the receiver are used to decorrelate the next data to be compressed and transmitted. For this purpose, the compression method is further supplied with previously transmitted data while compressing the current k-space data being compressed. The decoder at the receiving end acts in a complementary or complementary manner, using the history of decompressed chunks to also decompress the current k-space data.

[0034] In another aspect, the present invention provides a medical system including a remote memory storing remote machine-executable instructions. The medical system further includes a remote computing system. Execution of the remote machine-executable instructions causes the computing system to receive, via a network connection, metadata describing the acquisition of measured k-space data as a series of discrete k-space acquisitions according to a magnetic resonance imaging protocol. Execution of the remote machine-executable instructions further causes the remote computing system to repeatedly receive compressed k-space data acquisitions via the network connection and acquire one of the series of discrete k-space data acquisitions by decompressing the compressed k-space data acquisitions with a decompression module. The aforementioned compression module is complementary to and functions in conjunction with the decompression module.

[0035] Execution of the machine-executable instructions further causes the computing system to reconstruct a magnetic resonance image from at least a portion of the series of discrete k-space acquisitions in accordance with the magnetic resonance imaging protocol specified in the metadata. As mentioned above, this part or this medical system forms a receiver that functions complementary to the transmitter part detailed above. This receiver part can receive k-space data more quickly, thereby starting computationally intensive magnetic resonance imaging reconstruction while still receiving, or can receive complete measured k-space data more quickly and then start reconstruction sooner.

[0036] In another embodiment, execution of the remote machine-executable instructions causes the remote computing system to begin reconstruction of a magnetic resonance image before the complete measured k-space data has been received. As noted above, it is highly beneficial to begin reconstruction as early as possible so that the magnetic resonance image is available sooner.

[0037] In another embodiment, the magnetic resonance imaging protocol is a parallel imaging magnetic resonance imaging protocol. This embodiment can be advantageous because discrete k-space acquisitions can represent images from individual coils. This allows a remote computing system to begin magnetic resonance image reconstruction before the complete measured k-space data is received.

[0038] In another embodiment, execution of the remote machine-executable instructions causes a remote computing system to begin reconstruction of a magnetic resonance image before complete measured k-space data has been received. The magnetic resonance imaging protocol is a propeller magnetic resonance imaging protocol. In propeller, magnetic resonance images of k-space data are acquired. The discrete k-space acquisitions may be blades of k-space data. The so-called blades are used to reconstruct undersampled blade images that can be used for motion correction. This embodiment may be advantageous because it may allow motion correction to begin before complete measured k-space data has arrived.

[0039] In another embodiment, execution of the remote machine-executable instructions causes the remote computing system to begin reconstruction of a magnetic resonance image before complete measured k-space data is received. The magnetic resonance imaging protocol is a self-navigation magnetic resonance imaging protocol. This embodiment may be advantageous because each individual acquisition of k-space data may include self-navigation data. This embodiment may also allow motion correction to be calculated before complete measured k-space data is received.

[0040] In another embodiment, execution of the remote machine-executable instructions causes a remote computing system to begin magnetic resonance image reconstruction after the complete measured k-space data has been received, which may be useful, for example, for highly computationally intensive magnetic resonance imaging protocols in which reconstruction has a large computational overhead.

[0041] In another embodiment, the magnetic resonance imaging protocol is a magnetic resonance fingerprinting magnetic resonance imaging protocol, which is an example that may be beneficial because it has a large computational overhead and the system may wait until the completed measured k-space data is received, but receives the complete measured k-space data faster.

[0042] In another embodiment, the magnetic resonance imaging protocol is a motion-compensated magnetic resonance imaging protocol. This may be, for example, a magnetic resonance imaging protocol in which the self-consistency of the motion correction is checked with the originally measured k-space data. This may also have a large computational overhead. Therefore, even if reconstruction does not begin until the complete measured k-space data is received, a remote computing system may still be advantageous because it can begin this computationally intensive reconstruction earlier.

[0043] In another aspect, the present invention provides a computer program comprising local machine-executable instructions for execution by a local computing system configured to control a magnetic resonance imaging system. The computer program can also include pulse sequence commands. The magnetic resonance imaging system is configured to acquire measured k-space data describing a subject within an imaging zone. The pulse sequence commands are configured to control the magnetic resonance imaging system to acquire the measured k-space data as a series of discrete k-space acquisitions in accordance with a magnetic resonance imaging protocol.

[0044] Execution of the local machine-executable instructions causes the local computing system to transmit metadata describing a magnetic resonance imaging protocol to a remote computing system via a network connection. Execution of the local machine-executable instructions causes the local computing system to repeatedly control the magnetic resonance imaging system using pulse sequence commands to acquire one of a series of discrete k-space acquisitions. Execution of the local machine-executable instructions further causes the local computing system to repeatedly build a compressed k-space acquisition as one of a series of compressed k-space acquisitions by compressing one of the series of k-space acquisitions using a compression module. Execution of the local machine-executable instructions further causes the local computing system to repeatedly transmit the compressed k-space acquisition to the remote computing system via the network connection. Execution of the local machine-executable instructions further causes the local computing system to transmit at least a portion of the series of compressed k-space acquisitions via the network connection before acquisition of measured k-space data is complete.

[0045] In another aspect, the present invention provides a method of operating a medical system. The medical system comprises a local memory storing machine-executable instructions and pulse sequence commands. The method further comprises a remote memory storing remote machine-executable instructions. The medical system further comprises a magnetic resonance imaging system configured to acquire measured k-space data describing a subject within an imaging zone. The pulse sequence commands are configured to control the magnetic resonance imaging system to acquire the measured k-space data as a series of discrete k-space acquisitions according to a magnetic resonance imaging protocol. The medical system further comprises a local computing system. The medical system further comprises a remote computing system.

[0046] Execution of the local machine-executable instructions causes the local computing system to transmit metadata describing a magnetic resonance imaging protocol to the remote computing system over a network connection.

[0047] Execution of the remote machine-executable instructions causes the remote computing system to receive the metadata over a network connection.

[0048] Execution of the local machine-executable instructions causes the local computing system to repeatedly control the magnetic resonance imaging system with pulse sequence commands to acquire one of a series of discrete k-space acquisitions. Execution of the local machine-executable instructions further causes the local computing system to repeatedly build a compressed k-space acquisition as one of a series of compressed k-space acquisitions by compressing one of the series of k-space acquisitions using a compression module. Execution of the local machine-executable instructions further causes the local computing system to repeatedly transmit the compressed k-space acquisition to a remote computing system via a network connection.

[0049] Execution of the local machine-executable instructions further causes the local computing system to transmit at least a portion of the series of compressed k-space acquisitions over a network connection before acquisition of the measured k-space data is complete.

[0050] Execution of the remote machine-executable instructions further causes the remote computing system to repeatedly receive the compressed k-space acquisitions via a network connection. Execution of the remote machine-executable instructions further causes the remote computing system to repeatedly acquire one of the series of discrete k-space acquisitions by decompressing the compressed k-space acquisitions with a decompression module. Execution of the machine-executable instructions further causes the remote computing system to reconstruct a magnetic resonance image from at least a portion of the series of discrete k-space acquisitions according to a magnetic resonance imaging protocol identified in the metadata.

[0051] It is understood that one or more of the above-described embodiments of the present invention may be combined, provided that the combined embodiments are not mutually exclusive.

[0052] As will be appreciated by one of skill in the art, aspects of the present invention may be embodied as an apparatus, a method, or a computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be referred to generally herein as a "circuit," "module," or "system." Further, aspects of the present invention may take the form of a computer program product embodied in one or more computer-readable medium(s) having computer-executable code embodied thereon.

[0053] Any combination of one or more computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" encompasses any tangible storage medium capable of storing instructions executable by a processor or computing system of a computing device. The computer-readable storage medium may also be referred to as a computer-readable non-transitory storage medium. The computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, the computer-readable storage medium may also be capable of storing data that can be accessed by the computing system of a computing device. Examples of computer-readable storage media include, but are not limited to, floppy disks, magnetic hard disk drives, solid-state hard disks, flash memory, USB thumb drives, random access memory (RAM), read-only memory (ROM), optical disks, magneto-optical disks, and computing system register files. Examples of optical disks include compact discs (CDs) and digital versatile discs (DVDs), such as CD-ROM, CD-RW, CD-R, DVD-ROM, DVD-RW, or DVD-R discs. The term computer-readable storage medium also refers to various types of storage media that can be accessed by a computer device over a network or communications link. For example, data may be retrieved via a modem, over the Internet, or over a local area network. Computer-executable code embodied on a computer-readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wireline, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

[0054] A computer-readable signal medium may include, for example, a propagated data signal having computer-executable code embodied therein, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium is not a computer-readable storage medium but may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0055] "Computer memory" or "memory" is an example of a computer-readable storage medium. Computer memory is any memory directly accessible to a computing system. "Computer storage" or "storage" is a further example of a computer-readable storage medium. Computer storage is any non-volatile memory computer-readable storage medium. In some embodiments, computer storage may be computer memory, and vice versa.

[0056] As used herein, a "computing system" encompasses electronic components capable of executing programs, machine-executable instructions, or computer-executable code. References to a computing system, including examples of a "computing system," should be interpreted as including two or more computing systems or processing cores, as the case may be. A computing system may be, for example, a multi-core processor. A computing system may also refer to a collection of computing systems within a single computer system or distributed among multiple computer systems. The term computing system should also be interpreted as referring to a collection or network of computing devices, possibly each comprising a processor or computing system. Machine-executable code or instructions may be executed by multiple computing systems or processors, which may be within the same computing device or distributed across multiple computing devices.

[0057] Machine-executable instructions or computer-executable code may comprise instructions or programs that cause a processor or other computing system to perform aspects of the present invention. Computer-executable code for performing operations for aspects of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages, and compiled into machine-executable instructions. In some cases, the computer-executable code may be in the form of a high-level language or in pre-compiled form and may be used in conjunction with an interpreter that generates machine-executable instructions on the fly. In other cases, the machine-executable instructions or computer-executable code may form a program for a programmable logic gate array.

[0058] The computer executable code may run entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be to an external computer (e.g., via the Internet using an Internet Service Provider).

[0059] Aspects of the present invention will be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block or portion of a block in the flowcharts, diagrams, and / or block diagrams, where applicable, can be implemented by computer program instructions in the form of computer-executable code. Furthermore, it should be noted that combinations of blocks in different flowcharts, diagrams, and / or block diagrams can be combined, if not mutually exclusive. These computer program instructions can be provided to a general-purpose computer, special-purpose computer, or other programmable data processing device computing system to generate a machine, such that the instructions, executed via the computer or other programmable data processing device computing system, create means for performing the functions / acts identified in the flowchart and / or block diagram block or blocks.

[0060] These machine-executable instructions or computer program instructions may be stored on a computer-readable medium that can instruct a computer, other programmable data processing apparatus, or other device to function in a particular manner, such that the instructions stored on the computer-readable medium produce an article of manufacture including instructions that implement the function / acts identified in a block or blocks of the flowcharts and / or block diagrams.

[0061] The machine-executable instructions or computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps executed on the computer, other programmable apparatus, or other device to be executed on the computer, creating a computer-implemented process such that the instructions executing on the computer or other programmable apparatus provide a process for implementing the functions / operations identified in the flowchart and / or block diagram blocks or blocks.

[0062] As used herein, a "user interface" is an interface that allows a user or operator to interact with a computer or computer system. A "user interface" is sometimes referred to as a "human interface device," and a user interface can provide information or data to an operator and / or receive information or data from an operator. A user interface can allow input from an operator to be received by a computer and can provide output from the computer to a user. In other words, a user interface can allow an operator to control or manipulate a computer, and an interface can allow a computer to show the effects of the operator's control or manipulation. The display of data or information on a display or graphical user interface is an example of providing information to an operator. Receiving data via a keyboard, mouse, trackball, touchpad, pointing stick, graphics tablet, joystick, gamepad, webcam, headset, pedals, wired gloves, remote control, and accelerometer are all examples of user interface components that allow information or data to be received from an operator.

[0063] As used herein, a "hardware interface" encompasses an interface that allows a computer system to interact with and / or control external computing devices and / or equipment. A hardware interface may allow a computer system to send control signals or instructions to external computing devices and / or equipment. A hardware interface may also allow a computing system to exchange data with external computing devices and / or equipment. Examples of hardware interfaces include, but are not limited to, a universal serial bus, an IEEE 1394 port, a parallel port, an IEEE 1284 port, a serial port, an RS-232 port, an IEEE-488 port, a Bluetooth connection, a wireless local area network connection, a TCP / IP connection, an Ethernet connection, a control voltage interface, a MIDI interface, an analog input interface, and a digital input interface.

[0064] As used herein, "display" or "display device" encompasses an output device or user interface adapted to display images or data. A display can output visual, audio, and / or tactile data.

[0065] Examples of displays include computer monitors, television screens, touch screens, tactile electronic displays, Braille screens, cathode ray tubes (liquid), memory tubes, bi-stable displays, electronic paper, vector displays, flat panel displays, vacuum fluorescent displays (VF), light emitting diode (LED) displays, electroluminescent displays (ELD), plasma display panels (PDP), liquid crystal displays (LCD), organic light emitting diode displays (OLED), and projectors.

[0066] K-space data is defined herein as the recorded measurements of radio frequency signals emitted by atomic spins using the antenna of a magnetic resonance machine during a magnetic resonance imaging scan. Magnetic resonance data is an example of tomographic image data.

[0067] A magnetic resonance image or MR image is defined herein as a reconstructed two-dimensional or three-dimensional visualization of anatomical data contained within magnetic resonance imaging data, which visualization can be performed using a computer.

[0068] In the following, preferred embodiments of the invention will be described, by way of example only, with reference to the drawings, in which: [Brief explanation of the drawings]

[0069] [Figure 1] 1 shows an example of a medical system. [Figure 2] 2 shows a flowchart illustrating a method of using the medical system of FIG. 1. [Figure 3] 1 shows an example of a radio frequency coil having multiple coil elements. [Figure 4] 1 illustrates an example of an autoencoder that can be used to compress k-space data. [Figure 5] Examples of image domain and k-space domain compression are given. [Figure 6] A timing diagram for the example shown in FIG. 5 is shown. DETAILED DESCRIPTION OF THE INVENTION

[0070] Like numbered elements in these figures are equivalent elements or perform the same function. An element as described above is not necessarily discussed in a subsequent figure if there is functional equivalence.

[0071] 1 shows an example of a medical system 100 comprising a transmitter portion 101 and a receiver portion 102. The transmitter portion 101 is shown as being formed from a magnetic resonance imaging system 103 and a local computer 130. The receiver portion is shown as being formed from a remote computer 130′.

[0072] The magnetic resonance imaging system 103 includes a magnet 104. The magnet 104 is a superconducting cylindrical magnet with a bore 106. Different types of magnets can be used, including split cylindrical magnets and so-called open magnets. Split cylindrical magnets are similar to standard cylindrical magnets except that the cryostat is divided into two sections to allow access to the magnet's equal surface. Such magnets can be used, for example, in conjunction with charged particle beam therapy. Open magnets have two magnet sections, one above the other, with a space between them large enough to accommodate the subject, i.e., an arrangement of the two sections similar to the area of ​​a Helmholtz coil. Open magnets are popular because they provide less subject confinement. Inside the cryostat of a cylindrical magnet is a collection of superconducting coils.

[0073] Within the bore 106 of the cylindrical magnet 104 is an imaging zone 108 where the magnetic field is strong and sufficiently uniform to perform magnetic resonance imaging. A field of view 109 is shown within the imaging zone 108. Magnetic resonance data that would typically be acquired for the field of view 109. A subject 118 is shown supported by a subject support 120 such that at least a portion of the subject 118 is within the imaging zone 108 and the predetermined region of interest 109.

[0074] Also within the magnet bore 106 are a set of magnetic field gradient coils 110 used for preliminary magnetic resonance data acquisition to spatially encode magnetic spins within the imaging zone 108 of the magnet 104. The gradient coils 110 are connected to a gradient coil power supply 112. The magnetic field gradient coils 110 are intended to be representative. Typically, the magnetic field gradient coils 110 include three separate coil sets for spatial encoding in three orthogonal spatial directions. The gradient power supply supplies current to the gradient coils. The current supplied to the magnetic field gradient coils 110 is controlled as a function of time and can be ramped or pulsed.

[0075] Adjacent to the imaging zone 108 is a radio frequency coil 114 for manipulating the orientation of magnetic spins within the imaging zone 108 and for receiving radio frequency transmissions from the spins within the imaging zone 108. The radio frequency antenna may include multiple coil elements. The radio frequency antenna may also be referred to as a channel or antenna. The radio frequency coil 114 is connected to a radio frequency transceiver 116. The radio frequency coil 114 and the radio frequency transceiver 116 may be replaced by separate transmit and receive coils, as well as separate transmitters and receivers. It is understood that the radio frequency coil 114 and the radio frequency transceiver 116 are representative. The radio frequency coil 114 is also intended to represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 116 may also represent a separate transmitter and receiver. The radio frequency coil 114 may also have multiple receive / transmit elements, and the radio frequency transceiver 116 may have multiple receive / transmit channels. For example, when a parallel imaging technique, such as sensing, is performed, the radio frequency coil 114 may have multiple coil elements.

[0076] The transmitter portion 101 is further shown as comprising a local computer 130. The transceiver 116 and gradient controller 112 are shown as connected to a hardware interface 134 of the local computer system 130. The local computer 130 is intended to represent one or more computers located near the magnetic resonance imaging system 103. The local computer 130 comprises a local computing system 132. The local computing system 132 is intended to represent one or more computational or computing cores. The local computing system 132 is shown in communication with a hardware interface 134 that allows the local computing system 132 to communicate with and control the magnetic resonance imaging system 103 and receive k-space data. The local computing system 132 is further shown in communication with a local network connection 136 and a local memory 138. The local network connection 136 allows the local computer 130 to communicate with a remote computer 130' via a network interface 137.

[0077] Local memory 138 is intended to represent various types of memory accessible to local computing system 132. Local memory 138 is shown as storing local machine-executable instructions 140. Local machine-executable instructions 140 enable local computing system 132 to perform various computational, data processing, and image processing tasks. Local memory 138 is further shown as containing pulse sequence commands 142. Pulse sequence commands are commands or data that can be converted into commands that enable local computing system 132 to control and operate magnetic resonance imaging system 103 via hardware interface 134.

[0078] Memory 138 is further shown as containing metadata 144 describing pulse sequence commands 142. The metadata is used by remote computer 130' to determine which magnetic resonance imaging protocol to use when reconstructing a magnetic resonance image. Local memory 138 is further shown as containing one of a series of discrete k-space acquisitions 146 acquired when controlling magnetic resonance imaging system 103 with pulse sequence commands 142. Memory 138 is further shown as containing a compressed k-space acquisition 148 that was a compression of one of the series of discrete k-space acquisitions 146 compressed by compression module 150. Compression module 150 is shown as being stored by local memory 138.

[0079] The receiver portion 102 is shown to comprise a remote computer 130′. The remote computer 130′ is shown to include a remote computing system 132′. The remote computer 130′ may be, for example, an implementation of a cloud-based reconstruction service for the magnetic resonance imaging system 103. The remote computing system 132′ is shown to be in communication with a remote memory 138′ and a remote network interface 136′. The remote network interface 136′ is used to form a network connection 137 with the local network interface 136. The network connection 137 may be, for example, a local area network, an internet connection, or wireless data communication. The remote memory 138 is intended to represent various types of memory accessible to the remote computing system 132′.

[0080] The remote memory 138' is shown as containing remote machine-executable instructions 160. These include commands that enable the remote computing system 132' to perform basic data processing and numerical and image processing tasks. The remote memory 138' is further shown as containing a compressed k-space acquisition received over the network connection 137. The remote memory 138' is further shown as containing one of a series of discrete k-space acquisitions 146 obtained by decompressing the compressed k-space acquisition 148 with a decompression module 162. The remote memory 138' is further shown as containing a series of discrete k-space acquisitions 164, which in this case are equivalent to measured k-space data. The memory 138' is further shown as containing a magnetic resonance image 166 reconstructed from the series of discrete k-space acquisitions 164 or the measured k-space data.

[0081] 2 is a flowchart illustrating a method of operating the medical system of FIG. 1. First, in step 200, the local computing system 132 transmits metadata 144 to the remote computing system 132′ via the network connection 137. Next, in step 202, the remote computing system 132′ receives the metadata 144 via the network connection 137. Next, in step 204, the local computing system 132 controls the magnetic resonance imaging system 103 using pulse sequence commands 142 to acquire a series of discrete k-space acquisitions 146. The magnetic resonance imaging system does this serially. Steps 204, 206, and 208 can be performed in parallel, as they are capable of being performed. Next, in step 206, a compressed k-space acquisition 148 is constructed by compressing one of the series of discrete k-space acquisitions 146 using the compression module 150. After this compressed k-space acquisition 148 is constructed, step 208 is performed.

[0082] In step 208, the local computing system 132 transmits the compressed k-space acquisition 148 to the remote computing system 132' via the network interface 137. After step 208 is performed, the magnetic resonance imaging system can continuously acquire k-space data. This is indicated by the arrow returning to step 204. While this is occurring, the method can also proceed to step 210, which represents what happens after one compressed k-space acquisition 148 has been transmitted. Next, in step 210, the remote computing system 132' receives the compressed k-space acquisition 148 via the network connection 137. Steps 210 and 212, as well as after step 212, can be performed in parallel, such that one of a series of discrete k-space acquisitions 148 is acquired by decompressing the compressed k-space acquisition 148 with the decompression module 162.

[0083] The method then returns to step 210 and also to step 214. The return to step 210 illustrates how the system can continuously receive and decompress compressed k-space data. In some cases, the system waits for a series of discrete k-space acquisitions 164 or measured k-space data to be received, and then step 214 is performed in which the system reconstructs a magnetic resonance image 166 from at least a portion of the series of discrete k-space acquisition data 164. In other examples, there may be techniques such as motion compensation or parallel imaging that allow the remote computing system 132′ to begin reconstructing the magnetic resonance image 166 before all of the series of discrete k-space acquisitions 164 have been received. In this case, step 214 can proceed as steps 210 and 212 are continuously performed.

[0084] FIG. 3 illustrates one embodiment of the radio frequency coil 114. In this example, there are multiple coil elements 300 that independently receive k-space data. The coil elements include an optical connection 302 to the hardware interface 134 and a digitizer 304 or DSP circuit used to measure the k-space data. The digitizer 304 receives the measured k-space data and then compresses it into compressed k-space acquisitions 148. These are sent directly to the local computing system 132 via the optical connection 302 and transferred to the remote computing system 132' via the network connection 137. A possible advantage of the system illustrated in FIG. 3 is that the k-space data is compressed on the fly and in parallel. Note that in FIG. 3, one possible implementation of the compression module 150 is to use a neural network. This may be particularly advantageous as it requires less computational overhead and may reduce power requirements on the digitizer 304.

[0085] 4 shows an example of how an autoencoder 400 can be used to form a compression module 150 and a decompression module 162. In this embodiment, the compression module 150 is the encoder portion of the autoencoder 400, and the decompression module 162 is the decoder portion of the autoencoder. The encoder portion or compression module 150 receives a discrete k-space acquisition 146 as an input and then outputs a latent space vector or compressed k-space acquisition 148. The compressed k-space acquisition 148 can be transmitted via a network interface 137 and then input to a decompression module 162, which is the decoder portion of the autoencoder 400. In response to receiving the compressed k-space acquisition 148, the decompression module 162 outputs the discrete k-space acquisition 146.

[0086] FIG. 5 illustrates methods for image domain compression 500 and k-space domain compression 502 for transmitting magnetic resonance imaging data, such as k-space data, to a remote computing system. FIG. 5 provides a high-level comparison of MR compression in the image domain 500 and the proposed framework in the k-space domain 502 for a single-slice brain scan of dimensions N×N. Compression in the image domain requires all phase encoding profiles to be acquired before preprocessing, domain transformation, and encoding can be applied. In contrast, encoding individual k-space phase encoding allows for multi-threaded encoding, transmission (Tx / Rx), and decoding of raw data. Image domain compression 500 begins with acquisition 504 and, after all data has been acquired, proceeds to perform a Fourier transform 506 which results in a magnetic resonance image 508. Then there is an NxN encoder or compression 510 which is performed. Note that all data is acquired before the image 508 is reconstructed. This is then transmitted 512 and received by a remote computing system and input through an NxN decoder 514. The NxN decoder is a decompression algorithm which is then fed to reconstruction 516.

[0087] The k-space domain compression 502 works differently. Acquisition 504 occurs, but as various bits of k-space data become available, they are encoded parallel 518 and then immediately transmitted 520 over the network interface 137. As they are received, they are decoded or decompressed 522, either in parallel or asynchronously. Once the data is completely or partially received, reconstruction 516 proceeds.

[0088] FIG. 6 is used to illustrate the advantages of k-space domain compression 502 over image domain compression 500. FIG. 6 shows a thread diagram for encoding, transmission, and decoding in the image domain 500 and k-space domain 502. Compression in the k-space domain allows for independent processing of raw data in phase encoding. Thus, data can be encoded, transmitted (Tx / Rx), and decoded before acquisition is complete, allowing cloud-based reconstruction to benefit from higher data transmission throughput. FIG. 6 shows a timing diagram for image domain compression 500 and k-space domain compression 502. In image domain compression 500, acquisition 504 is performed, and after this is fully completed, pre-processing or Fourier transform 506 is performed. After this is completed, encoding 510 is performed, which is then transmitted (512), and then decoded (514). Each of these processes is performed serially and in parallel.

[0089] In contrast, k-space domain compression performs many tasks in parallel or simultaneously. As acquisition 504 occurs, various bits of k-space data are available, which are then encoded 518. Once encoded, they are transmitted 520 as soon as they are available. Decoding 522 also occurs partially as packets of k-space data are still being transmitted. It can be seen that decoding 522 is completely completed for k-space domain compression much sooner than image domain compression 500. This is illustrated by the time savings 600.

[0090] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive, and the invention is not limited to the disclosed embodiments.

[0091] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. A computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, together with or supplied as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be construed as limiting the scope. [Explanation of symbols]

[0092] 100 Medical Systems 101 Transmitter 102 Receiving unit 103 Magnetic Resonance Imaging System 104 Magnet 106 Magnet Bore 108 Imaging Zones 109 Field of view 110 magnetic field gradient coil 112 Gradient magnetic field coil power supply 114 High Frequency Coil 116 Transceiver 118 Subject 120 Subject support unit 130 Local Computer 130' Remote Computer 132 Local Computing System 132' Remote Computing System 134 Local Hardware Interface 136 Local Network Connections 136' Remote Network Connection 137 Network Connections 138 Local Memory 138' Remote Memory 140 local machine executable instructions 142 Pulse Sequence Commands 144 Metadata 146 One of a series of discrete k-space acquisitions 148 Compressed k-space acquisitions 150 Compression Modules 160 Remote Machine Executable Instructions 162 Decompression Module 164 series of discrete k-space acquisitions (measured k-space data) 166 Magnetic Resonance Imaging (MRI) 200 local computing system: transmitting metadata describing the magnetic resonance imaging protocol to a remote computing system via a network connection 202 remote computing system: receiving metadata describing the acquisition of measured k-space data as a series of discrete k-space acquisitions according to a magnetic resonance imaging protocol via a network connection; 204 Local Computation System: Controls the magnetic resonance imaging system using pulse sequence commands to acquire one of a series of discrete k-space acquisitions. 206 Local Computation System: Compressing one of the series of k-space acquisitions using a compression module to construct a compressed k-space acquisition as one of the series of compressed k-space acquisitions. 208 Local Computing System: Transmits compressed k-space acquisitions to a remote computing system via a network connection 210 Remote Computing System: Receives compressed k-space acquisitions via a network connection 212 Remote Computing System: Acquire one of a series of discrete k-space acquisitions by decompressing the compressed k-space acquisition with a decompression module. 214 Remote Computing System: Reconstructing Magnetic Resonance Images from at Least a Portion of a Series of Discrete k-Space Acquisitions 300 coil elements 302 Optical Connection 304 Digitizer (DSP) 400 Autoencoder 500 Image Area Compression 502 k-space domain compression 504 Acquisition 506 Fourier Transform 508 Magnetic Resonance Imaging (MRI) 510 N×N Encoder 512 Send 514 NxN decoder 516 Reconstruction 518 parallel encoding 520 Send 522 Parallel Decoding

Claims

1. 1. A medical system comprising: a local memory for storing local machine executable instructions and pulse sequence commands; a magnetic resonance imaging system configured to acquire measured k-space data describing a subject within an imaging zone, the pulse sequence commands being configured to control the magnetic resonance imaging system to acquire the measured k-space data as a series of discrete k-space acquisitions in accordance with a magnetic resonance imaging protocol; a local computing system, wherein execution of the local machine-executable instructions causes the local computing system to perform the steps of transmitting metadata describing the magnetic resonance imaging protocol and representing control parameters for selecting and / or adjusting aspects of reconstruction to a remote computing system over a network connection; controlling the magnetic resonance imaging system using the pulse sequence commands to acquire one of the series of discrete k-space acquisitions; constructing the compressed k-space acquisition as one of a series of compressed k-space acquisitions by compressing one of the series of k-space acquisitions using a compression module; transmitting the compressed k-space acquisition to the remote computing system via the network connection; Repeatedly execute Execution of the local machine-executable instructions causes the local computing system to perform the step of transmitting at least a portion of the series of compressed k-space acquisitions over the network connection before acquisition of the measured k-space data is completed. Local computing system and A medical system having:

2. The medical system further comprises: a remote memory storing remote machine executable instructions; a remote computing system, wherein execution of the remote machine-executable instructions causes the remote computing system to perform the steps of receiving metadata describing the magnetic resonance imaging protocol over the network connection, and wherein execution of the remote machine-executable instructions further causes the remote computing system to: receiving the compressed k-space acquisition over the network connection; acquiring one of the series of discrete k-space acquisitions by decompressing the compressed k-space acquisition using a decompression module; Repeatedly execute Execution of the machine-executable instructions further causes the remote computing system to perform the step of reconstructing a magnetic resonance image from at least a portion of the measured k-space data in accordance with a magnetic resonance imaging protocol specified in the metadata. Remote computing systems and The medical system of claim 1 , comprising:

3. The medical system further comprises a motion detection system for acquiring motion data describing motion of the subject, and execution of the local machine executable instructions causes the local computing system to: controlling a motion detection system to acquire the motion data during acquisition of the measured k-space data; triggering a motion alert if the motion data indicates subject motion above a predetermined motion threshold; initiating construction of the compressed k-space acquisition and transmission of the compressed k-space acquisition to a remote computing system via the network connection if the motion alert is triggered, wherein the metadata comprises a motion compensated reconstruction request for the measured k-space data if the motion alert is triggered; The medical system according to claim 1 or 2, wherein the medical system executes the following.

4. The medical system of claim 1 , 2 or 3 , wherein the compression module is implemented as a neural network.

5. 5. The medical system of claim 4, wherein the compression module is formed from an encoder portion of an autoencoder, and the compressed k-space acquisitions are latent space vectors of the autoencoder.

6. 6. The medical system of claim 1, wherein the magnetic resonance imaging system comprises a magnetic resonance imaging coil with a digitizer circuit for measuring the series of discrete k-space acquisitions, and the local computing system comprises the digitizer circuit, the digitizer circuit configured to construct the compressed k-space acquisition when one of the series of k-space acquisitions is measured.

7. Execution of the machine-executable instructions further causes the computing system to: determining predicted correlations in discrete acquisitions of k-space from previously acquired k-space data, said metadata comprising said predicted correlations; decorrelating one of the series of discrete k-space acquisitions using the predicted correlation prior to compression into the compressed k-space acquisition; The medical system according to claim 1 , wherein the medical system executes the following steps:

8. 8. The medical system of claim 7, wherein the previously acquired k-space data originates from a survey scan of the subject or from a previously compressed one of the series of discrete k-space acquisitions.

9. a remote memory storing remote machine executable instructions; 1. A remote computing system, wherein execution of the remote machine-executable instructions causes the computing system to perform the steps of receiving metadata representing an acquisition of measured k-space data as a series of discrete k-space acquisitions according to a magnetic resonance imaging protocol over a network connection, the execution of the remote machine-executable instructions further causing the remote computing system to: receiving the compressed k-space acquisition via the network connection; acquiring one of the series of discrete k-space acquisitions by decompressing the compressed k-space acquisition using a decompression module; A remote computing system that repeatedly executes and Execution of the machine-executable instructions further causes the computing system to perform the step of reconstructing a magnetic resonance image from at least a portion of the series of discrete k-space acquisitions according to a magnetic resonance imaging protocol specified in the metadata. Medical systems.

10. 10. The medical system of claim 9, wherein execution of the remote machine-executable instructions causes the remote computing system to perform the step of initiating reconstruction of the magnetic resonance image before the complete measured k-space data is received.

11. the magnetic resonance imaging protocol is a parallel imaging magnetic resonance imaging protocol; the magnetic resonance imaging protocol is a propeller magnetic resonance imaging protocol; or the magnetic resonance imaging protocol is a self-navigation magnetic resonance imaging protocol; The medical system of claim 10.

12. 10. The medical system of claim 9, wherein execution of the remote machine-executable instructions causes the remote computing system to perform the step of initiating reconstruction of the magnetic resonance image after the complete measured k-space data is received.

13. the magnetic resonance imaging protocol is a magnetic resonance fingerprinting magnetic resonance imaging protocol; or the magnetic resonance imaging protocol is a motion compensated magnetic resonance imaging protocol; The medical system of claim 12.

14. 1. A computer program having local machine-executable instructions for execution by a local computing system configured to control a magnetic resonance imaging system configured to acquire measured k-space data describing a subject within an imaging zone, the pulse sequence commands configured to control the magnetic resonance imaging system to acquire the measured k-space data as a series of discrete k-space acquisitions in accordance with a magnetic resonance imaging protocol; Execution of the local machine executable instructions causes the local computing system to perform the steps of transmitting metadata describing the magnetic resonance imaging protocol and representing control parameters for selecting and / or adjusting aspects of the reconstruction to a remote computing system via a network connection, controlling the magnetic resonance imaging system using the pulse sequence commands to acquire one of the series of discrete k-space acquisitions; compressing one of the series of k-space acquisitions using a compression module to construct the compressed k-space acquisition as one of the series of compressed k-space acquisitions; transmitting the compressed k-space acquisition to the remote computing system via the network connection; Repeatedly execute Execution of the local machine-executable instructions causes the local computing system to perform the step of transmitting at least a portion of the series of compressed k-space acquisitions over the network connection before acquisition of the measured k-space data is completed. Computer program.

15. 1. A method of operating a medical system, the medical system comprising: a local memory for storing local machine executable instructions and pulse sequence commands; a remote memory storing remote machine executable instructions; a magnetic resonance imaging system configured to acquire measured k-space data describing a subject within an imaging zone, the pulse sequence commands being configured to control the magnetic resonance imaging system to acquire the measured k-space data as a series of discrete k-space acquisitions in accordance with a magnetic resonance imaging protocol; a local computing system; Remote computing systems and and Execution of the local machine-executable instructions causes the local computing system to perform the steps of transmitting metadata describing the magnetic resonance imaging protocol and representing control parameters for selecting and / or adjusting aspects of the reconstruction to the remote computing system via a network connection; Execution of the remote machine-executable instructions causes the remote computing system to perform the steps of receiving the metadata over the network connection; Execution of the local machine executable instructions on the local computing system includes: controlling the magnetic resonance imaging system using the pulse sequence commands to acquire one of the series of discrete k-space acquisitions; compressing one of the series of k-space acquisitions using a compression module to construct the compressed k-space acquisition as one of a series of compressed k-space acquisitions; transmitting the compressed k-space acquisition to the remote computing system via the network connection; Repeatedly execute Execution of the local machine-executable instructions causes a local computing system to perform the steps of transmitting at least a portion of the series of compressed k-space acquisitions over the network connection before acquisition of the measured k-space data is completed; Execution of the remote machine-executable instructions further comprises: receiving the compressed k-space acquisition over the network connection; acquiring one of the series of discrete k-space acquisitions by decompressing the compressed k-space acquisition using a decompression module; Repeatedly execute Execution of the machine-executable instructions further causes the remote computing system to perform the step of reconstructing a magnetic resonance image from at least a portion of the series of discrete k-space acquisitions according to a magnetic resonance imaging protocol identified in the metadata. method.

Images