Anatomical measurements using magnetic resonance imaging

Abstract

A medical system (100, 300, 500) is disclosed herein. Execution of the machine executable instructions (112) causes the computing system (104) to: receive (200) a baseline anatomical measurement (114) describing a clinical magnetic resonance image of the subject (318); receiving (202) scan metadata (116) describing a clinical magnetic resonance image of the subject; sending (204) the scan parameters to the low-field magnetic resonance imaging system (301) over the network connection (350); receiving (206) subsequent k-space data (122) from the low-field magnetic resonance imaging system via the network connection in response to transmitting the scan parameter; reconstructing (208) a subsequent magnetic resonance image (124) from the subsequent k-space data; determining (210) a subsequent anatomical measurement (128) in response to inputting the subsequent magnetic resonance image into the segmentation module; and provide (212) a warning signal (132) when the difference of the subsequent anatomical measurements from the baseline anatomical measurements exceeds a predetermined amount.

Description

Technical Field

[0001] The present invention relates to magnetic resonance imaging and, more particularly, to making anatomical measurements. Background Art

[0002] Magnetic resonance imaging (MRI) scanners use large static magnetic fields to align the nuclear spins of atoms as part of the process used to produce images within a patient. The main magnetic field is used to produce a large static magnetic field, called the B0 field or main magnetic field. Various quantities or properties of a subject can be measured spatially and imaged using MRI.

[0003] One difficulty with MRI is that the equipment is expensive. Installing and operating an MRI scanner can be a major expense for a hospital. Costs can be saved by using a main magnet that produces a lower B0 field. However, this may have the effect of reducing the resolution and / or signal-to-noise ratio of the MRI images. Typically, the quality of these low-field MRI images is poor, which is undesirable.

[0004] The journal article “Minimum Field Strength Simulator for Proton Density Weighted MRI” by Wu Z, Chen W, Nayak KS. PLoS one. 2016; 11(5) e0154711 doi: 10.1371 / joumal.pone0154711 PMID: 27136334; PMCID: PMC4852924 discloses a framework for simulating low-field proton density weighted MRI acquisitions based on high-field acquisitions.

[0005] US patent application US2018 / 0025466 relates to accurately acquiring subsequent magnetic resonance data having the same geometry as an earlier baseline image. Summary of the invention

[0006] The invention provides a medical system, a computer program product and a method as described in the independent claims. Embodiments are given in the dependent claims.

[0007] Embodiments may provide a means for performing follow-up tracking of subsequent magnetic resonance imaging scans using a so-called low-field magnetic resonance imaging system. To this end, baseline anatomical measurements obtained from clinical magnetic resonance images and scan metadata describing the baseline anatomical measurements are provided. The scan metadata and the baseline anatomical measurements are used to provide scan parameters that are sent to the low-field magnetic resonance imaging system via a network connection. In response to the scan parameters, subsequent k-space data is received from the low-field magnetic resonance imaging system and used to reconstruct subsequent magnetic resonance images. The scan metadata describes the clinical magnetic resonance image as having a first resolution and a first signal-to-noise ratio. The subsequent magnetic resonance image has a second resolution and a second signal-to-noise ratio. The first signal-to-noise ratio is higher than the second signal-to-noise ratio and / or the first resolution is higher than the second resolution. Subsequent anatomical measurements are then determined by inputting the subsequent magnetic resonance image into a segmentation module. The subsequent anatomical measurements can then be compared with the baseline anatomical measurements. Although the low-field magnetic resonance imaging system may not have a sufficiently strong main magnetic field to produce clinical quality images, it can still be used to provide anatomical information.

[0008] In one aspect, the present invention provides a medical system comprising a memory storing machine executable instructions. The medical system also comprises a computing system. Execution of the machine executable instructions causes the computing system to receive baseline anatomical measurements describing a clinical magnetic resonance image of a subject. Execution of the machine executable instructions also causes the computing system to receive scan metadata describing the clinical magnetic resonance image of the subject. The scan metadata comprises scan coordinates referenced to predetermined anatomical landmarks of the subject. The scan metadata describes the clinical magnetic resonance image having a first resolution and a first signal-to-noise ratio.

[0009] In different examples, the baseline anatomical measurements may take different forms. For example, the baseline anatomical measurements may be distances relative to predetermined anatomical landmark references. In another example, the baseline anatomical measurements may be dimensions, volumes, or other physical quantities describing anatomical structures, such as organs and / or tumors. In some examples, the baseline anatomical measurements may be numerical values. In other examples, the baseline anatomical measurements may be lines or segmentation results within a clinical magnetic resonance image. In the examples, it is not actually necessary to have a clinical magnetic resonance image there, because baseline anatomical measurements are provided along with scan metadata, which provides information such as scan coordinates, a first resolution, and a first signal-to-noise ratio.

[0010] The execution of the machine executable instructions also causes the computing system to send scanning parameters to the low-field magnetic resonance imaging system via a network connection. As used herein, a low-field magnetic resonance imaging system includes a magnetic resonance imaging system having a magnetic field lower than that commonly used for clinical magnetic resonance imaging. For example, a low-field magnetic resonance imaging system can, for example, have a main magnetic field strength less than 0.6 or even 0.2 T. Scanning parameters can be provided from several different sources; they can certainly be standard parameters used by a low-field magnetic resonance imaging system, or they can be scanning parameters optimized for measuring specific baseline anatomical measurements in subsequent images.

[0011] Execution of the machine executable instructions further causes the computing system to receive subsequent k-space data from the low-field magnetic resonance imaging system via a network connection in response to sending the scan parameters. The subsequent k-space data is acquired using the scan parameters sent to the low-field magnetic resonance imaging system. Execution of the machine executable instructions further causes the computing system to reconstruct subsequent magnetic resonance images based on the subsequent k-space data. Execution of the machine executable instructions further causes the computing system to determine subsequent anatomical measurements in response to inputting the subsequent magnetic resonance imaging data into a segmentation module.

[0012] The segmentation module can perform several different tasks. For example, it can be used to perform segmentation or measurement in a subsequent magnetic resonance image. The subsequent magnetic resonance image has a second resolution that can be lower than the first resolution and / or has a signal-to-noise ratio that is lower than the first signal-to-noise ratio. This may be the result of using a low-field magnetic resonance image. The execution of the machine executable instructions also causes the computing system to provide a warning signal when the difference between the subsequent anatomical measurement and the baseline anatomical measurement exceeds a predetermined amount. For example, if the baseline anatomical measurement is a distance, then if the distance changes by more than a certain amount, this can trigger a warning signal. If the anatomical measurement being compared is, for example, a tumor size or other volume measurement, an increase in the size or volume of the object being measured can also be used to trigger a warning signal. This embodiment may be beneficial because it can provide a means of monitoring the anatomical measurements of a subject more cheaply. For example, when a doctor performs a diagnosis or examination on a subject, they may use a clinical magnetic resonance imaging system, which may have a field strength greater than 0.6 or even greater than 1 T, for example. These systems may be more expensive than low-field magnetic resonance imaging systems. For example, in one example, the medical system may provide image reconstruction and other services to various low-field magnetic resonance imaging systems as a cloud service or remote server.

[0013] In different examples, the warning signal can take different forms. In one example, it can be a signal provided to the physician via email or even via a cellular telecommunications system. In other examples, the warning signal can be a message or instruction that is subsequently sent to the low-field magnetic resonance imaging system so as to be received by the subject. For example, this can be an instruction to perform various health tasks, such as instructions for a healthcare provider or instructions for specific changes in the subject's behavior (such as adjusting food consumption or taking other actions). In other examples, the warning signal can be used to send further scanning parameters to the low-field magnetic resonance imaging system to repeat the acquisition of subsequent k-space data. For example, providing a warning signal when the anatomical measurement results indicate that the subject may have a problem or health problem can be used to automatically re-acquire the measurement results to confirm that the subsequent anatomical measurement results are correct.

[0014] The present invention relates to generating subsequent k-space data after a clinical magnetic resonance image. The subsequent k-space data is collected at a magnetic field strength lower than the magnetic field strength associated with the clinical magnetic resonance image. This enables a follow-up study of the patient to be examined after the lesion is identified in the (original) clinical magnetic resonance image. To this end, a baseline anatomical measurement result from the clinical magnetic resonance image is received. For example, this may involve the size and shape of the lesion. Also received are associated scan metadata of the clinical magnetic resonance image, which represent the (first) spatial resolution and signal-to-noise ratio of the clinical diagnostic image. Scan parameters of the subsequent k-space data are available for use by a low-field magnetic resonance imaging system. These scan parameters are associated with the (second) spatial resolution and signal-to-noise ratio of the subsequent magnetic resonance image reconstructed from the subsequent k-space data. A segmentation module returns subsequent anatomical measurements of the reconstructed subsequent magnetic resonance image corresponding to the baseline anatomical measurements, because these measurements involve the same anatomical lesions. The segmentation module can be implemented as a conceptual algorithm, an expert system, a simple but extensive lookup table, or can be based on artificial intelligence, for example in the form of a trained neural network. Finally, based on the comparison between the baseline anatomical measurement results and the subsequent anatomical measurement results, a warning signal is issued to alert the user when the change exceeds a predetermined threshold.

[0015] Subsequent k-space data is collected by a low-field magnetic resonance imaging system, the main magnetic field strength of which is significantly lower than the main magnetic field strength associated with the clinical magnetic resonance images, and the baseline anatomical measurements are derived from the clinical magnetic resonance images. In the context of the present invention, "significantly" refers to the extent to which the field strength is so low that the contrast appearance of the subsequent magnetic resonance images is substantially different from that of the clinical magnetic resonance images. Compared with magnetic resonance images of the same object collected by various magnetic resonance imaging systems with equal nominal main magnetic field strengths, the subsequent magnetic resonance images and the clinical diagnostic images are less similar and have obvious differences. These differences are attributed to the dependence on the main magnetic field strength of the relaxation parameters (1 / T1, 1 / T2, 1 / (T2*)) and the signal-to-noise ratio of the reconstructed image. For example, significantly lower field strengths are associated with relaxation times (Ti(B0)), that is, the values ​​of the main magnetic field strength associated with the clinical magnetic resonance images differ by more than 10%. For example, relaxation times typically differ by about 25% between the main magnetic field strengths of 1.5T and 3.0T, respectively, or by a factor of 2 between the main magnetic field strengths of 0.3T and 3.0T.

[0016] The segmentation module is used to perform segmentation and / or measurements on subsequent magnetic resonance images, and the subsequent anatomical measurements correspond to the baseline anatomical measurements. In addition, the segmentation module performs identification of predetermined anatomical landmarks in the subsequent magnetic resonance images, and the predetermined anatomical landmarks in the subsequent magnetic resonance images correspond to predetermined anatomical landmarks associated with the baseline anatomical measurements. When implemented in artificial intelligence, the trained neural network returns the subsequent anatomical measurements in response to the baseline anatomical measurements and the subsequent magnetic resonance images.

[0017] On the other hand, the medical system also includes a low-resolution magnetic resonance imaging system. The low-resolution magnetic resonance imaging system includes a local memory and a controller. The local memory stores survey scan pulse sequence commands and measurement pulse sequence commands. The local memory also stores controller commands. The execution of the controller commands causes the controller to receive scan parameters via a network connection. The execution of the controller commands also causes the controller to acquire survey scan k-space data by controlling the low-resolution magnetic resonance imaging system with the survey scan pulse sequence commands. The execution of the controller commands also causes the controller to reconstruct a survey scan image based on the survey scan k-space data. The execution of the controller commands further causes the controller to detect the position of a predetermined anatomical landmark of the subject in the survey scan image.

[0018] For example, a segmentation module that identifies predetermined anatomical landmarks of the subject may be used to provide the location. Other things such as segmentation modules (such as deformable shape models) may also be used to determine the location of predetermined anatomical landmarks. Execution of the controller command also causes the controller to adjust the acquisition pulse sequence command using the location of the predetermined anatomical landmark of the subject in the survey scan image, the second resolution, and the scan coordinates of the predetermined anatomical landmark of the reference subject. Execution of the controller command also causes the controller to acquire subsequent k-space data by controlling the low-resolution magnetic resonance imaging system with the acquisition pulse sequence command. Execution of the controller command also causes the controller to send subsequent k-space data to the computing system via a network connection. This embodiment may be beneficial because it may provide a means for automatically acquiring magnetic resonance images remotely.

[0019] In another embodiment, the low-resolution magnetic resonance imaging system includes a main magnet configured to generate a main magnetic field. The main magnetic field has an intensity of 0.6T or less. In another embodiment, the main magnetic field preferably has an intensity of 0.2T or less. Using a main magnet with a field strength of 0.6T can have the advantage of much lower construction and operating costs. Therefore, a magnet with a field strength of 0.2T or less has lower construction and maintenance costs. The disadvantage of using a magnet with such a low field strength is that the signal-to-noise ratio may be lower, and it may be more difficult to measure with the same resolution.

[0020] In another embodiment, the controller is configured to automatically perform acquisition of subsequent k-space data upon receiving the scan parameters and send the subsequent k-space data to the computing system.This embodiment may be advantageous because it may eliminate the need for a trained operator of the low-field magnetic resonance imaging system.

[0021] In another embodiment, the memory further stores a scan parameter configuration module. The scan parameter configuration module is configured to output scan parameters in response to receiving the second resolution and / or the second signal-to-noise ratio, the scan coordinates, and the baseline anatomical measurements. Execution of the machine executable instructions further causes the computing system to receive the scan parameters in response to inputting the second resolution and / or the second signal-to-noise ratio, the scan coordinates, and the baseline anatomical measurements into the scan parameter configuration module. This embodiment may be beneficial because the scan parameter configuration module may be used to automatically generate scan parameters that enable the low-field magnetic resonance imaging system to accurately measure anatomical measurements despite having a lower field and potentially lower quality than the clinical magnetic resonance imaging system used to obtain the baseline anatomical measurements.

[0022] In another embodiment, the scan parameter configuration module is implemented at least in part as a lookup table, a neural network, or an expert system. Over time, as the system is used for an increasing number of examinations, data about appropriate scan parameters for a particular configuration and baseline anatomical measurements can be stored and then used later. In other examples, a neural network can be trained for this purpose. Likewise, data acquired through repeated use can be encoded in an expert system that can be used to automatically provide scan parameters.

[0023] In another embodiment, the scan parameters include the selection of a pulse sequence type. The baseline anatomical measurements may be derived from a clinical magnetic resonance image having a particular weighting or image type. For example, the image type may be stored in the scan metadata and then may be used to select a pulse sequence type for acquisition of subsequent k-space data on a low-field magnetic resonance imaging system.

[0024] In another embodiment, the computing system is implemented as a cloud computing system. This may be beneficial because it may enable the computing system to serve a large number of low field MRI systems. For example, if the low field MRI systems are located in a smaller clinic or stored in a distributed manner. The use of a cloud computing system enables a single or very few medical systems to provide reconstruction and determination of subsequent anatomical measurements.

[0025] In another embodiment, the segmentation module is implemented as a neural network. The neural network can be, for example, a U-net or a ResNet. The training of the neural network may be ad hoc in several embodiments. The baseline anatomical measurements are taken from a clinical magnetic resonance image having a first resolution and a first signal-to-noise ratio. When subsequent magnetic resonance images are used to determine subsequent anatomical measurements, the data comes from a magnetic resonance imaging system that may have a lower magnetic field and / or image quality. In order to properly train the neural network, a training image can be taken and then the image can be automatically or manually segmented to provide a baseline anatomical measurement. The training anatomical measurement can then be used as part of the training data. The training magnetic resonance image can then be resampled, and a lower resolution and a lower signal-to-noise ratio can then be simulated to produce an image, which can then be input into the neural network during training. The lower resolution image can be input into the neural network, and the segmentation or anatomical measurement derived from the original image can then be used as the baseline truth data. In this way, the neural network can be trained to produce anatomical measurements just as if the measurements were made on a higher resolution image.

[0026] In another embodiment, the neural network is trained by repeatedly receiving training clinical magnetic resonance images or training clinical k-space data. The training clinical magnetic resonance images have a first resolution and / or a first signal-to-noise ratio. The neural network is further trained by repeatedly receiving training anatomical measurements describing baseline anatomical measurements about the training clinical magnetic resonance images. As previously described, this can be performed, for example, manually or by a segmentation module. The neural network is further trained by repeatedly calculating simulated subsequent magnetic resonance images having a second resolution and / or a second signal-to-noise ratio. This can be training clinical magnetic resonance images or training clinical k-space data. The neural network is further trained by repeatedly constructing training data from pairs of simulated subsequent magnetic resonance images and training anatomical measurements. The neural network is further trained by repeatedly training the neural network using the training data. For example, this can be performed using a deep learning algorithm.

[0027] In another embodiment, the medical system further comprises a clinical magnetic resonance imaging system. The clinical magnetic resonance imaging system is configured to acquire clinical magnetic resonance images of the subject and determine baseline anatomical measurements based on the clinical magnetic resonance images. The baseline anatomical measurements may be provided automatically by an algorithm or neural network, or may be provided by data received by a physician or operator of the clinical magnetic resonance imaging system. The clinical magnetic resonance imaging system is further configured to provide the baseline anatomical measurements to the computing system. For example, it may provide the data via a network or other connection.

[0028] In another aspect, the present invention provides a medical imaging method. The method includes receiving baseline anatomical measurements describing a clinical magnetic resonance image of a subject. The method also includes receiving scan metadata describing the clinical magnetic resonance image of the subject. The scan metadata includes scan coordinates referenced to predetermined anatomical landmarks of the subject. The scan metadata describes the clinical magnetic resonance image having a first resolution and / or a first signal-to-noise ratio. The method also includes sending scan parameters to a low-field magnetic resonance imaging system via a network connection. The scan parameters include a second resolution and / or a second signal-to-noise ratio. The scan parameters also include scan coordinates referenced to predetermined anatomical landmarks of the subject. The first resolution is higher than the second resolution. The first signal-to-noise ratio is higher than the second signal-to-noise ratio. The method also includes receiving subsequent k-space data from the low-field magnetic resonance imaging system via a network connection in response to sending the scan parameters.

[0029] The method also includes reconstructing a subsequent magnetic resonance image based on the subsequent k-space data. The method also includes determining a subsequent anatomical measurement in response to inputting the subsequent magnetic resonance image into the segmentation module. The method also includes providing a warning signal when the subsequent anatomical measurement differs from the baseline anatomical measurement by more than a predetermined amount.

[0030] In another embodiment, the medical system also includes a low-resolution magnetic resonance imaging system. The method also includes receiving scanning parameters via a network connection. The method also includes acquiring survey scan k-space data by controlling the low-resolution magnetic resonance imaging system with a survey scan pulse sequence command. The method also includes reconstructing a survey scan image based on the survey scan k-space data. The method also includes detecting the position of a predetermined anatomical landmark of the subject in the survey scan image. For example, this can be done using a segmentation algorithm. The method also includes adjusting the acquisition pulse sequence command using the position of the predetermined anatomical landmark of the subject in the survey scan image, the second resolution, and the scanning coordinates of the predetermined anatomical landmark of the reference subject. The method also includes acquiring subsequent k-space data by controlling the low-resolution magnetic resonance imaging system with an acquisition pulse sequence command. The method also includes sending the subsequent k-space data to the computing system via a network connection.

[0031] In another aspect, the present invention provides a computer program product comprising machine executable instructions for execution by a computing system controlling a medical system. Execution of the machine executable instructions causes the computing system to receive baseline anatomical measurements describing a clinical magnetic resonance image of a subject. Execution of the machine executable instructions also causes the computing system to receive scan metadata describing the clinical magnetic resonance image of the subject. The scan metadata includes scan coordinates referenced to predetermined anatomical landmarks of the subject. The scan metadata describes the clinical magnetic resonance image having a first resolution and / or a first signal-to-noise ratio.

[0032] The execution of the machine executable instructions also causes the computing system to send scanning parameters to the low-field magnetic resonance imaging system via a network connection. The scanning parameters include a second resolution and / or a second signal-to-noise ratio. The scanning parameters also include scanning coordinates with reference to predetermined anatomical landmarks of the subject. The first resolution is higher than the second resolution and / or the first signal-to-noise ratio is higher than the second signal-to-noise ratio. The execution of the machine executable instructions also causes the computing system to receive subsequent k-space data from the low-field magnetic resonance imaging system via a network connection in response to sending the scanning parameters. The execution of the machine executable instructions also causes the computing system to reconstruct subsequent magnetic resonance images based on the subsequent k-space data. The execution of the machine executable instructions also causes the computing system to determine subsequent anatomical measurements in response to inputting the subsequent magnetic resonance images into the segmentation module. The execution of the machine executable instructions also causes the computing system to provide a warning signal when the difference between the subsequent anatomical measurements and the baseline anatomical measurements exceeds a predetermined amount.

[0033] It should be understood that one or more of the aforementioned embodiments of the present invention may be combined as long as the combined embodiments are not mutually exclusive.

[0034] As will be appreciated by those skilled in the art, aspects of the present invention may be embodied as an apparatus, method, or computer program product. Thus, aspects of the present invention may take the form of a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, which may all be generally referred to herein as a "circuit," "module," or "system." In addition, aspects of the present invention may take the form of a computer program product contained in one or more computer-readable media, which contain computer executable code.

[0035] Any combination of one or more computer-readable media can be utilized. Computer-readable media can be computer-readable signal media or computer-readable storage media. As used herein, "computer-readable storage media" encompasses any tangible storage media that can store instructions that can be executed by a processor or computing system of a computing device. Computer-readable storage media can be referred to as computer-readable non-temporary storage media. Computer-readable storage media can also be referred to as tangible computer-readable media. In some embodiments, computer-readable storage media can also store data that can be accessed by a 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 memories (RAM), read-only memories (ROM), optical disks, magneto-optical disks, and register files of computing systems. Examples of optical disks include compact disks (CDs) and digital versatile disks (DVDs), such as CD-ROMs, CD-RWs, CD-Rs, DVD-ROMs, DVD-RWs, or DVD-R disks. The term computer-readable storage media also refers to various types of recording media that can be accessed by a computer device via a network or communication link. For example, data can be retrieved via a modem, the Internet, or a local area network. Computer executable code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0036] A computer readable signal medium may include a propagated data signal with computer executable code embodied therein, for example, 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 may be any computer readable medium that is not a computer readable storage medium and may communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0037] "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 another example of a computer-readable storage medium. Computer storage is any non-volatile computer-readable storage medium. In some embodiments, computer storage may also be computer memory and vice versa.

[0038] As used herein, "computing system" encompasses an electronic component capable of executing a program or machine executable instructions or computer executable code. References to computing systems including examples of "computing system" should be interpreted as possibly including multiple computing systems or processing cores. A computing system may, for example, be 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 possibly referring to a collection or network of computing devices, each of which includes 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 may even be distributed across multiple computing devices.

[0039] Machine executable instructions or computer executable code may include instructions or programs that cause a processor or other computing system to perform an aspect of the present invention. Computer executable code for performing operations of various 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++, etc.) and conventional procedural programming languages ​​(such as "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 a precompiled 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 be a programming form of a programmable logic gate array.

[0040] The computer executable code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0041] Aspects of the present invention are described with reference to the flow chart and / or block diagram of the method, device (system) and computer program product according to an embodiment of the present invention. It should be understood that each frame or a part of a frame of a flow chart, diagram and / or block diagram can be implemented by a computer program instruction in the form of a computer executable code when applicable. It should also be understood that when not mutually exclusive, the combination of frames in different flow charts, diagrams and / or block diagrams can be combined. These computer program instructions can be provided to a computing system of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, so that the instruction executed by the computing system of a computer or other programmable data processing device creates a module for implementing the function / action specified in one or more frames of a flow chart and / or block diagram.

[0042] These machine-executable instructions or computer program instructions may also be stored in a computer-readable medium, which may direct a computer, other programmable data processing apparatus, or other device to work in a specific manner so that the instructions stored in the computer-readable medium produce an article of manufacture including instructions for implementing the novels / actions specified in one or more blocks of the flowchart and / or block diagram.

[0043] Machine executable instructions or computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to perform a series of operational steps on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0044] 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' may also be referred to as a 'human-machine interface device.' A user interface may provide information or data to an operator and / or receive information or data from an operator. A user interface may enable input from an operator to be received by a computer, and may provide output from a computer to a user. In other words, a user interface may allow an operator to control or manipulate a computer, and an interface may allow a computer to indicate the effects of the operator's control or manipulation. Displaying 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, graphic tablet, joystick, game controller, webcam, headset, pedal, wired gloves, remote controller, and accelerometer are all examples of user interface components that are capable of receiving information or data from an operator.

[0045] As used herein, "hardware interface" encompasses an interface that enables a computing system of a computer system to interact with and / or control an external computing device and / or apparatus. A hardware interface may allow a computing system to send control signals or instructions to an external computing device and / or apparatus. A hardware interface may also enable a computing system to exchange data with an external computing device and / or apparatus. 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 LAN connection, a TCP / IP connection, an Ethernet connection, a control voltage interface, a MIDI interface, an analog input interface, and a digital input interface.

[0046] As used herein, a "display" or "display device" encompasses an output device or user interface suitable for displaying images or data. A display may output visual, audio, and / or tactile data. Examples of displays include, but are not limited to, computer monitors, television screens, touch screens, tactile electronic displays, Braille screens, cathode ray tubes (CRTs), memory tubes, bi-stable displays, electronic paper, vectorscopes, flat panel displays, vacuum fluorescent displays (VFs), light emitting diode (LED) displays, electroluminescent displays (ELDs), plasma display panels (PDPs), liquid crystal displays (LCDs), organic light emitting diode displays (OLEDs), projectors, and head mounted displays.

[0047] K-space data is defined herein as recorded measurements of radio frequency signals emitted by atomic spins using an antenna of a magnetic resonance apparatus during a magnetic resonance imaging scan. Magnetic resonance data is an example of tomographic medical image data.

[0048] A Magnetic Resonance Imaging (MRI) image or MR image is defined herein as a reconstructed two-dimensional or three-dimensional visualization of anatomical data contained within the magnetic resonance imaging data. The visualization may be performed using a computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Preferred embodiments of the present invention will now be described by way of example only and with reference to the accompanying drawings, in which:

[0050] Figure 1 An example of a medical system is shown;

[0051] Figure 2 Shows instructions for use Figure 1 A flowchart of a method of a medical system;

[0052] Figure 3 Another example of a medical system is shown;

[0053] Figure 4Shows instructions for use Figure 3 A flowchart of a method of a medical system; and

[0054] Figure 5 Another example of a medical system is shown.

[0055] Reference numerals list

[0056] 100 Medical Systems

[0057] 102 Computer

[0058] 104 Computing System

[0059] 104' Controller

[0060] 106 Network Interfaces

[0061] 108 User Interface

[0062] 110 Memory

[0063] 110' Local Storage

[0064] 112 machine executable instructions

[0065] 114 Baseline Anatomical Measurements

[0066] 116 Scan metadata

[0067] 118 Scan parameter configuration module

[0068] 120 Scan parameters

[0069] 122 Subsequent k-space data

[0070] 124 Follow-up MRI

[0071] 126 segmentation module

[0072] 128 Follow-up anatomical measurements

[0073] 130 reservations

[0074] 132 Warning Signs

[0075] 200 Receive baseline anatomical measurements describing the subject's clinical MRI

[0076] 202 receiving scan metadata describing a clinical magnetic resonance image of a subject

[0077] 204 Sending scanning parameters to the low field magnetic resonance imaging system via the network connection

[0078] 206 Responsive to sending the scan parameters, receiving subsequent k-space data from the low-field magnetic resonance imaging system via the network connection

[0079] 208 Reconstructing subsequent magnetic resonance images based on subsequent k-space data

[0080] 210 Determine subsequent anatomical measurements in response to inputting the subsequent magnetic resonance image into the segmentation module

[0081] 212 Provides a warning signal when a subsequent anatomical measurement differs from a baseline anatomical measurement by more than a predetermined amount

[0082] 300 Medical Systems

[0083] 301 Low Field Magnetic Resonance Imaging System

[0084] 302 Clinical Magnetic Resonance Imaging System

[0085] 303 Hardware Interface

[0086] 304 Main magnet

[0087] 306 magnet hole

[0088] 308 Imaging Area

[0089] 309 Field of View

[0090] 310 magnetic field gradient coil

[0091] 312 Magnetic Field Gradient Coil Power Supply

[0092] 314 RF Coil

[0093] 316 transceiver

[0094] 318 subjects

[0095] 320 Subject Support

[0096] 330 Controller Commands

[0097] 332 Survey Scan Pulse Sequence Command

[0098] 334 Survey Scan K-space Data

[0099] 336 Survey Scan Image

[0100] 338 Predetermined location of anatomical landmarks

[0101] 340 Measurement pulse sequence command

[0102] 342 Modified measurement pulse sequence command

[0103] 400 Receive scan parameters via network connection

[0104] 402 Acquiring reconnaissance scan k-space data by controlling a low-resolution magnetic resonance imaging system using a reconnaissance scan pulse sequence command

[0105] 404 Reconstructing a survey scan image based on the survey scan k-space data

[0106] 406 Detecting the location of a predetermined anatomical landmark of the subject in the survey scan image

[0107] 408 adjusts the acquisition pulse sequence command using the position of the predetermined anatomical landmark of the subject in the survey scan image, the second resolution, and the scan coordinates of the predetermined anatomical landmark of the reference subject.

[0108] 410 Using acquisition pulse sequence commands to control low-resolution magnetic resonance imaging systems to acquire subsequent K-space data

[0109] 412 Sending subsequent k-space data to the computing system via the network connection

[0110] 350 network connections

[0111] 500 Medical Systems DETAILED DESCRIPTION

[0112] Elements with the same number in these figures are equivalent elements or perform the same function. Elements that have been discussed previously will not necessarily be discussed in subsequent figures if the function is equivalent.

[0113] Figure 1 An example of a medical system 100 is shown. The medical system 100 can be, for example, a cloud-based or virtual-based system. It can also be incorporated into a magnetic resonance imaging system. The medical system 100 is shown to include a computer 102. Computer 102 is intended to represent one or more computers located at one or more locations. Computer 102 is shown to include a computing system 104. Computing system 104 is intended to represent one or more computing systems or processing cores that can be located in one or more computer systems. Computing system 104 is shown in communication with a network interface 106 and an optional user interface 108 and a memory 110. Memory 110 is intended to represent various types of memory that can be accessed by computing system 104.

[0114] The memory 110 is shown as containing machine executable instructions 112. The memory 110 is also shown as containing baseline anatomical measurements 114 and scan metadata 116 describing the clinical magnetic resonance image. The memory 110 is further shown as containing an optional scan parameter configuration module 118. This can, for example, receive the scan metadata 116 and / or the baseline anatomical measurements 114 as input and then output scan parameters 120. The memory 110 is further shown as containing the scan parameters 120. The memory 110 is further shown as containing subsequent k-space data 122 obtained from the low-field magnetic resonance imaging system. The memory 110 is further shown as containing a subsequent magnetic resonance image 124 reconstructed from the subsequent k-space data 122.

[0115] The memory 110 is also shown as containing a segmentation module 126, which is configured to receive the subsequent magnetic resonance image 124 as input and output a subsequent anatomical measurement 128 in response. The memory 110 is shown as containing the subsequent anatomical measurement 128 that has been obtained by inputting the subsequent magnetic resonance image 124 into the segmentation module 126. The memory 110 is further shown as containing a predetermined amount 130, which is used as a threshold when comparing the subsequent anatomical measurement 128 with the baseline anatomical measurement 114. The memory 110 is further shown as containing a warning signal 132, which can be provided when the difference between the subsequent anatomical measurement 128 and the baseline anatomical measurement 114 exceeds the predetermined amount 130. The warning signal 132 can be, for example, a warning or data presented to an operator. In another example, the warning signal 132 can be a command, which is then executed by a remote server or computer or even a low-field magnetic resonance imaging system.

[0116] Figure 2 Shows the instructions for operation Figure 1 Flowchart of a method of a medical system 100 of the present invention. First, in step 200, a baseline anatomical measurement 114 is received. The baseline anatomical measurement 114 describes a clinical magnetic resonance image of a subject. Next, in step 202, scan metadata 116 describing the clinical magnetic resonance image is received. Next, in step 204, scan parameters 120 are sent to a low-field magnetic resonance imaging system via a network connection. Next, in step 206, in response to sending the scan parameters 120 to the low-field magnetic resonance imaging system, subsequent k-space data 122 is received from the low-field magnetic resonance imaging system via a network connection. Next, in step 208, a subsequent magnetic resonance image 124 is reconstructed based on the subsequent k-space data 122. Then, in step 210, in response to inputting the subsequent magnetic resonance image 124 into a segmentation module 126, a subsequent anatomical measurement is determined. Finally, in step 212, a warning signal 132 is provided when the subsequent anatomical measurement 128 differs from the baseline anatomical measurement 114 by more than a predetermined amount 130.

[0117] Figure 3 Another example of a medical system 300 is shown. The medical system 300 is similar to Figure 1 The medical system is shown except that it also includes a low-field magnetic resonance imaging system 301 and an optional clinical magnetic resonance imaging system 302 .

[0118] The low field magnetic resonance imaging system 301 comprises a main magnet 304. The main magnet 304 is a superconducting cylindrical magnet having a hole 306 passing through it. Different types of magnets may also be used; for example, split cylindrical magnets and so-called open magnets may also be used. A split cylindrical magnet is similar to a standard cylindrical magnet, except that the cryostat has been divided into two parts to allow access to the isoplane of the magnet, such a magnet may be used, for example, in conjunction with charged particle beam therapy. An open magnet has two magnet sections, one above the other with a space in between that is large enough to accommodate a subject: the arrangement of the two section areas is similar to that of a Helmholtz coil. Open magnets are popular because there are fewer restrictions on the subject. Inside the cryostat of the cylindrical magnet there is a collection of superconducting coils.

[0119] Within the bore 306 of the cylindrical magnet 304 is an imaging zone 308 in which the magnetic field is sufficiently strong and uniform to perform magnetic resonance imaging. A field of view 309 is shown within the imaging zone 308. The acquired k-space data is typically acquired for the field of view 309. The region of interest may be the same as the field of view 309, or it may be a sub-volume of the field of view 309. A subject 318 is shown supported by a subject support 320 such that at least a portion of the subject 318 is within the imaging zone 308 and the field of view 309.

[0120] Also within the bore 306 of the main magnet 304 is a set of magnetic field gradient coils 310 for acquiring preliminary k-space data to spatially encode magnetic spins within the imaging zone 308 of the magnet 304. The magnetic field gradient coils 310 are connected to a magnetic field gradient coil power supply 312. The magnetic field gradient coils 310 are intended to be representative. Typically, the magnetic field gradient coils 310 include three separate sets of coils for spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply supplies current to the magnetic field gradient coils. The current supplied to the magnetic field gradient coils 310 is controlled according to time and can be ramped or pulsed.

[0121] Adjacent to the imaging zone 308 is a radio frequency coil 314, which is used to manipulate the orientation of magnetic spins within the imaging zone 308 and to receive radio transmissions of spins also within the imaging zone 308. 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 314 is connected to a radio frequency transceiver 316. The radio frequency coil 314 and the radio frequency transceiver 316 may be replaced by separate transmit and receive coils and separate transmitters and receivers. It should be understood that the radio frequency coil 314 and the radio frequency transceiver 316 are representative. The radio frequency coil 314 is also intended to represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 316 may also represent a separate transmitter and receiver. The radio frequency coil 314 may also have multiple receive / transmit elements, and the radio frequency transceiver 316 may have multiple receive / transmit channels.

[0122] The low field magnetic resonance imaging system 301 includes a computer 102' having a controller 104' connected to a hardware interface 303. The hardware interface 303 enables the controller 104' to send commands to the low field magnetic resonance imaging system 300 and receive data in response. The controller 104' is shown as being further connected to a network interface 106' and a local memory 110'. The local memory 110' is intended to represent various types of memory accessible to the controller 104'.

[0123] The local memory 110' is shown as containing a copy of the scan parameters 120 and the subsequent k-space data 122. The memory 110 is also shown as storing controller commands 330. The controller commands 330 are commands that enable the controller 104' to perform various tasks, such as controlling the low-field magnetic resonance imaging system 300 and performing data and image analysis. The local memory 110' is also shown as storing survey scan pulse sequence commands 332. The pulse sequence commands are commands that enable the controller 104' to control the low-field magnetic resonance imaging system 300 to acquire k-space data. Therefore, the survey scan pulse sequence commands 332 are commands that enable the low-field magnetic resonance imaging system 300 to perform a survey scan.

[0124] The local memory 110' is also shown as containing survey scan k-space data 334 acquired by controlling the magnetic resonance imaging system 300 with the survey scan pulse sequence commands 332. The memory 110' is also shown as containing a survey scan image 336, which is a magnetic resonance image reconstructed from the survey scan k-space data 334. The memory 110' is also shown as containing a location 338 of a predetermined anatomical landmark in the survey scan image 336. Various segmentation and landmark recognition techniques can be used to identify the location 338 in the survey scan image 336. For example, a template image and various segmentation algorithms can be used. The memory 110' is also shown as containing acquisition pulse sequence commands 340. The acquisition pulse sequence commands 340 can be used to control the low-field magnetic resonance imaging system 300 to acquire subsequent k-space data 122. The memory 110' is also shown as containing a modified acquisition pulse sequence command 342 that has been modified with the scan parameters 120. This can be used, for example, to accurately position the field of view 309 during the acquisition of k-space data.

[0125] The low field magnetic resonance imaging system 300, the computer 102 and the optional clinical magnetic resonance imaging system 302 are shown connected via a network connection 350. The baseline anatomical measurements 114 and the scan metadata 116 may have been received from the clinical magnetic resonance imaging system 302 via the network connection 350.

[0126] Figure 4 Shows the instructions for operation Figure 3 Flow chart of a method of a medical system 300 . Figure 4 The method shown is similar to Figure 2 The method shown in FIG. 1 is similar to that shown in FIG. 1 , but with additional steps. First, Figure 2 As shown, steps 200, 202 and 204 are performed. After step 204, the method proceeds to step 400. In step 400, the scan parameters 120 are received by the low-field magnetic resonance imaging system via the network connection 350. Then, in step 402, the survey scan k-space data 334 is acquired by controlling the low-resolution magnetic resonance imaging system 300 with the survey scan pulse sequence commands 332. Next, in step 404, the survey scan image 336 is reconstructed based on the survey scan k-space data 334. Next, in step 406, the position 338 of the predetermined anatomical landmark is detected in the survey scan image 336. Then, in step 408, the acquisition pulse sequence commands 340 are adjusted using the position 338 of the predetermined anatomical landmark and / or the scan parameters 120.

[0127] This may include scanning coordinates of predetermined anatomical landmarks of the subject at the second resolution and with reference to the subject. Next, in step 410, subsequent k-space data 122 is acquired by controlling the low-resolution magnetic resonance imaging system with the modified acquisition pulse sequence command 342. Next, in step 412, the subsequent k-space data 122 is sent from the low-field magnetic resonance imaging system 300 to the computing system 104 via the network connection 350. After executing step 412, as shown in FIG. Figure 2 As shown, steps 206, 208, 210 and 212 are performed.

[0128] Figure 5 Another example of a medical system 500 is shown, where the computer 102 is used as a cloud based system connected to a clinical magnetic resonance imaging system 302 and a plurality of low field magnetic resonance imaging systems 300. Each low field magnetic resonance imaging system 300 has a controller 104' connected to the computer 102 via a network connection 350. Figure 5 The system shown may have the advantage that no clinical magnetic resonance imaging system 302 is required to repeatedly acquire the baseline anatomical measurements 114. A subject may enter any of the low-field magnetic resonance imaging systems 300 and have subsequent anatomical measurements 128 measured.

[0129] 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; the invention is not limited to the disclosed embodiments.

[0130] By studying the drawings, the disclosure and the claims, those skilled in the art can understand and implement other variations of the disclosed embodiments. In the claims, the word "comprising" does not exclude other elements or steps, and the attributive "one" or "an" does not exclude multiple. A single processor or other unit can implement the functions of several items recorded in the claims. The fact that certain measures are recorded in mutually different dependent claims does not indicate that the combination of these measures cannot be used advantageously. The computer program may be stored / distributed on a suitable medium, such as an optical storage medium or solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. Any reference numerals in the claims should not be interpreted as limiting the scope.

Claims

1. A medical system (100, 300, 500), comprising: a memory (110) storing machine-executable instructions (112); A computing system (104), wherein execution of the machine executable instructions causes the computing system to: receiving (200) baseline anatomical measurements (114) describing a clinical magnetic resonance image of a subject (318); receiving (202) scan metadata (116) describing the clinical magnetic resonance image of the subject, wherein the scan metadata includes scan coordinates referenced to predetermined anatomical landmarks of the subject, wherein the scan metadata describes the clinical magnetic resonance image having a first resolution and a first signal-to-noise ratio; Sending (204) scanning parameters to a low-field magnetic resonance imaging system (301) via a network connection (350), wherein the scanning parameters are associated with a second resolution and a second signal-to-noise ratio, wherein the first resolution is higher than the second resolution and / or the first signal-to-noise ratio is higher than the second signal-to-noise ratio; In response to sending the scan parameters, receiving (206) subsequent k-space data (122) of the subject from the low-field magnetic resonance imaging system via the network connection; reconstructing (208) a subsequent magnetic resonance image (124) based on the subsequent k-space data; In response to inputting the subsequent magnetic resonance image into the segmentation module, determining (210) subsequent anatomical measurements (128); and A warning signal (132) is provided (212) when the subsequent anatomical measurement differs from the baseline anatomical measurement by more than a predetermined amount.

2. The medical system according to claim 1, wherein: The medical system further comprises the low-field magnetic resonance imaging system, wherein the low-field magnetic resonance imaging system comprises a local memory (110') and a controller (104'); wherein the local memory stores a survey scan pulse sequence command (332) and a measurement pulse sequence command (340), wherein the local memory further stores a controller command (330), wherein execution of the controller command causes the controller to: receiving (400) the scanning parameters via the network connection; Acquiring (402) reconnaissance scan k-space data by controlling the low resolution magnetic resonance imaging system with the reconnaissance scan pulse sequence commands; reconstructing (404) a survey scan image (336) based on the survey scan k-space data; detecting (406) a location (338) of the predetermined anatomical landmark of the subject in the survey scan image; adjusting (408) acquisition pulse sequence commands using the location of the predetermined anatomical landmark of the subject in the survey scan image, the second resolution, and the scan coordinates referenced to the predetermined anatomical landmark of the subject; acquiring (410) the subsequent k-space data by controlling the low-resolution magnetic resonance imaging system with a modified acquisition pulse sequence command; The subsequent k-space data is sent (412) to the computing system via the network connection.

3. The medical system according to claim 2, wherein: The low resolution magnetic resonance imaging system comprises a main magnet (304) configured to generate a main magnetic field, wherein the main magnetic field has a strength of 0.6 Tesla or less, and wherein the main magnetic field preferably has a strength of 0.2 Tesla or less.

4. The medical system according to claim 2 or 3, wherein: The controller is configured to perform the acquisition of the subsequent k-space data and automatically send the subsequent k-space data to the computing system.

5. A medical system according to any one of the preceding claims, wherein: The memory also stores a scan parameter configuration module (118); wherein the scan parameter configuration module is configured to output the scan parameters in response to receiving the second resolution, the scan coordinates, and the baseline anatomical measurements; wherein execution of the machine-executable instructions further causes the computing system to receive the scan parameters in response to inputting the second resolution, the scan coordinates, and the baseline anatomical measurements into the scan parameter configuration module.

6. The medical system according to claim 5, wherein: The scanning parameter configuration module is at least partially implemented as a lookup table, a neural network or an expert system.

7. The medical system according to claim 5 or 6, wherein: The scanning parameters include the selection of the pulse sequence type.

8. A medical system according to any one of the preceding claims, wherein: The computing system is implemented as a cloud computing system.

9. A medical system according to any one of the preceding claims, wherein: The segmentation module is implemented as a neural network.

10. The medical system according to claim 9, wherein: The neural network is trained by repeating the following operations: receiving a training clinical magnetic resonance image or training clinical k-space data, wherein the training clinical magnetic resonance image has the first resolution; receiving training anatomical measurements describing the baseline anatomical measurements with respect to the training clinical magnetic resonance images; calculating a simulated subsequent magnetic resonance image having the second resolution based on the training clinical magnetic resonance image or the training clinical k-space data; constructing training data from alignments of said simulated subsequent magnetic resonance images and said training anatomical measurements; The neural network is trained using the training data.

11. A medical system according to any one of the preceding claims, wherein: The medical system also includes a clinical magnetic resonance imaging system, wherein the clinical magnetic resonance imaging system is configured to acquire the clinical magnetic resonance images of the subject and determine the baseline anatomical measurements based on the clinical magnetic resonance images, wherein the clinical magnetic resonance images are configured to provide the baseline anatomical measurements to the computing system.

12. A method of medical imaging, wherein: The method comprises: receiving (200) baseline anatomical measurements (114) describing a clinical magnetic resonance image of a subject (318); receiving (202) scan metadata (116) describing the clinical magnetic resonance image of the subject, wherein the scan metadata includes scan coordinates referenced to predetermined anatomical landmarks of the subject, wherein the scan metadata describes the clinical magnetic resonance image having a first resolution; sending (204) scanning parameters to a low-field magnetic resonance imaging system (301) via a network connection (350), wherein the scanning parameters are associated with a second resolution and the scanning coordinates are referenced to predetermined anatomical landmarks of the subject, wherein the first resolution is higher than the second resolution; In response to sending the scan parameters, receiving (206) subsequent k-space data (122) of the subject from the low-field magnetic resonance imaging system via the network connection; reconstructing (208) a subsequent magnetic resonance image (124) based on the subsequent k-space data; In response to inputting the subsequent magnetic resonance image into the segmentation module, determining (210) subsequent anatomical measurements (128); and A warning signal (132) is provided (212) when the subsequent anatomical measurement differs from the baseline anatomical measurement by more than a predetermined amount.

13. The method according to claim 12, wherein: The medical system further comprises the low-field magnetic resonance imaging system, wherein the method further comprises: receiving (400) the scanning parameters via the network connection; Acquiring (402) survey scan k-space data by controlling the low-field magnetic resonance imaging system with survey scan pulse sequence commands; reconstructing (404) a survey scan image (336) based on the survey scan k-space data; detecting (406) a location (338) of the predetermined anatomical landmark of the subject in the survey scan image; adjusting (408) acquisition pulse sequence commands using the location of the predetermined anatomical landmark of the subject in the survey scan image, the second resolution, and the scan coordinates referenced to the predetermined anatomical landmark of the subject; acquiring (410) subsequent k-space data by controlling the low-resolution magnetic resonance imaging system with the acquisition pulse sequence commands; and The subsequent k-space data is sent (412) to the computing system via the network connection.

14. A computer program product comprising machine executable instructions for execution by a computing system for controlling a medical system (100, 300, 500), wherein: Execution of the machine-executable instructions causes the computing system to: receiving (200) baseline anatomical measurements (114) describing a clinical magnetic resonance image of a subject (318); receiving (202) scan metadata (116) describing the clinical magnetic resonance image of the subject, wherein the scan metadata includes scan coordinates referenced to the predetermined anatomical landmarks of the subject, wherein the scan metadata describes the clinical magnetic resonance image having a first resolution; sending (204) scanning parameters to a low-field magnetic resonance imaging system (301) via a network connection (350), wherein the scanning parameters are associated with a second resolution and the scanning coordinates are referenced to predetermined anatomical landmarks of the subject, wherein the first resolution is higher than the second resolution; In response to sending the scan parameters, receiving (206) subsequent k-space data (122) of the subject from the low-field magnetic resonance imaging system via the network connection; reconstructing (208) a subsequent magnetic resonance image (124) based on the subsequent k-space data; In response to inputting the subsequent magnetic resonance image into the segmentation module, determining (210) subsequent anatomical measurements (128); and A warning signal (132) is provided (212) when the subsequent anatomical measurement differs from the baseline anatomical measurement by more than a predetermined amount.

Images