Magnetic resonance imaging of breast microcalcifications

Abstract

A method of medical imaging is disclosed herein. The method includes receiving 202 gradient-echo magnetic resonance imaging data 123 representing a chest region 318 of a subject 319. The method further includes receiving 202 DIXON magnetic resonance imaging data representing the chest region. The DIXON magnetic resonance imaging data and the gradient-echo magnetic resonance imaging data are spatially matched. The method further includes generating 204 a breast microcalcification magnetic resonance image 128 by inputting the gradient-echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data into a breast microcalcification image reconstruction module 122. The breast microcalcification image reconstruction module is configured to output a breast microcalcification magnetic resonance image in response to inputting the gradient-echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data. The breast microcalcification magnetic resonance image represents the locations of breast microcalcifications, and the gradient-echo magnetic resonance imaging data is a phase image.

Description

[Technical field]

[0001] The present invention relates to magnetic resonance imaging, and in particular to magnetic resonance imaging of breast tissue. [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 the process to produce images inside a patient's body. This large static magnetic field is called the B0 field or main magnetic field. Various quantities or properties of a subject can be measured spatially using MRI.

[0003] US Patent Application Publication No. 1,0401,459(B2) discloses a method for acquiring magnetic resonance images accurately depicting sites of vascular calcification or other objects composed of material with shifted magnetic susceptibility in a subject. The images are generally acquired using pulse sequences designed to reduce physiological motion-induced artifacts and to mitigate chemical shift artifacts from water-fat boundaries. Advantageously, the MRI techniques described herein suppress chemical shift artifacts without significantly reducing signal intensity from adipose tissue, thereby allowing more reliable visualization of sites of vascular calcification. Summary of the Invention

[0004] The invention provides a medical system, a computer program and a method in the independent claims. Embodiments are given in the dependent claims.

[0005] Breast microcalcifications are typically detected using mammograms. However, this exposes the subject to x-rays. The embodiments provide a means of imaging breast microcalcifications without the use of ionizing radiation. To accomplish this, two types of magnetic resonance image data are used. The first is gradient echo magnetic resonance imaging data, and the second is DIXON magnetic resonance image data. In DIXON magnetic resonance imaging, measurements are acquired at multiple phases and image components can be separated into fat images that image the fat or lipid content of the voxels, and water images that image non-fatty tissue. The DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data are input to a breast microcalcification image reconstruction module that outputs a breast microcalcification magnetic resonance image showing the breast microcalcifications. The breast microcalcification magnetic resonance image can be further filtered using a high pass spatial filter and used to generate a projection image. The resulting projection image is equivalent to a conventional mammogram for detecting breast microcalcifications.

[0006] In one aspect, the present invention provides a medical system comprising a memory having machine executable instructions stored thereon and a breast microcalcification image reconstruction module. The breast microcalcification image reconstruction module is configured to output a breast microcalcification magnetic resonance image in response to inputting gradient echo magnetic resonance imaging data and DIXON magnetic resonance imaging data. The DIXON magnetic resonance imaging data includes both fat and water images. The breast microcalcification phase magnetic resonance image is indicative of locations of breast microcalcifications. The gradient echo magnetic resonance imaging data is a phase image. The medical system further comprises a computing system configured to control the medical system.

[0007] Execution of the machine executable instructions causes the computing system to receive gradient echo magnetic resonance imaging data representative of a chest region of a subject. The chest region of the subject is, for example, within the region of interest. Execution of the machine executable instructions further causes the processor to receive DIXON magnetic resonance imaging data representative of the chest region. The DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data are spatially matched. Spatial matching means that there is a one-to-one correspondence between voxels of the gradient echo magnetic resonance imaging data and the Dixon magnetic resonance image, or there is a registration that provides a mapping between the two voxels.

[0008] In some examples, registration is used to transform one of the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data so that the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data match or are spatially matched to each other. In many cases, however, the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data are acquired so that the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data are spatially matched by the acquisition. In some examples, the acquisition of the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data is combined so that the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data are automatically spatially matched.

[0009] Execution of the machine-executable instructions further causes the computing system to generate a breast microcalcification magnetic resonance image by inputting the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data into a breast microcalcification image reconstruction module. This embodiment is beneficial because it provides a means of identifying breast microcalcifications without the use of an x-ray machine.

[0010] The gradient echo magnetic resonance imaging data may be acquired by a number of different techniques. In some instances, it is one echo length TE gradient echo magnetic resonance imaging data. In other instances, it is acquired using a multi-echo gradient echo magnetic resonance imaging protocol, in which case it is spread over several echo times. In the multi-echo gradient case, the DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data are acquired simultaneously.

[0011] In another embodiment, the gradient echo magnetic resonance imaging data is so-called long TE or echo time gradient echo magnetic resonance imaging data. The TE or echo time value is used to control how small a calcification site can be detected. The term long TE is further for DIXON magnetic resonance imaging acquisitions that use a relatively short TE or echo time. One criterion for defining long TE is to make it equal to or less than the T2* of adipose tissue for a particular magnetic resonance imaging protocol. T2* depends on the magnetic field strength and therefore on the particular magnetic resonance imaging system.

[0012] The phase of the gradient echo magnetic resonance imaging data is virtually freely chosen. However, there are some practical choices that make the operation or image reconstruction easier. For example, the gradient echo magnetic resonance imaging data can be chosen to be in phase with the fat signal, or out of phase. Being in phase with fat is beneficial because the image is more uniform and numerically image processing is easier. However, knowledge of the DIXON magnetic resonance imaging data allows the mapping to be performed efficiently.

[0013] In another embodiment, the breast microcalcification magnetic resonance images are phase images.

[0014] In another embodiment, the DIXON magnetic resonance imaging data is a water image.

[0015] In another embodiment, execution of the machine-executable instructions further causes the computing system to calculate a filtered breast microcalcification magnetic resonance image by applying a high-pass spatial filter to the breast microcalcification magnetic resonance image. This embodiment is beneficial because larger structures in the breast microcalcification magnetic resonance image are removed. One means of achieving a high-pass spatial filter is to first calculate a low-pass filtered image, which effectively blends out features with high spatial frequencies and then removes the high spatial frequency features from the original image.

[0016] In another embodiment, execution of the machine-executable instructions further causes the computing system to generate a breast microcalcification projection image by calculating a projection image of the filtered breast microcalcification image. This embodiment is beneficial because the breast microcalcification image is, for example, a three-dimensional data set or a stack of two-dimensional slices. The generation of the projection image makes the data easier to interpret for physicians accustomed to looking at x-rays. The projection image is, for example, calculated by different techniques. The projection image is calculated for the projection of a minimum or maximum value at a particular voxel.

[0017] In another embodiment, the breast microcalcification image reconstruction module is implemented as an algorithm that includes computing a fibroglandular tissue segmentation result of the DIXON magnetic resonance imaging data that identifies the location of fibroglandular tissue by inputting the DIXON magnetic resonance imaging data into a fibroglandular tissue identification module. The DIXON magnetic resonance imaging data includes a water image and a fat image. Since the breast is primarily fat or adipose tissue, the water image primarily shows fibroglandular tissue.

[0018] The water image is therefore easily segmented using the algorithm. The algorithm further comprises the step of calculating the fibroglandular tissue phase image of the fibroglandular tissue by inputting the fibroglandular tissue segmentation result into a phase image calculation module. The phase image calculation module takes the tissue position as input and then, knowing the strength of the B0 field, the possible disturbance of the field by the tissue can be calculated. Several different approaches are known how to achieve this. So-called kernel calculations can be used as well as trained neural networks.

[0019] The algorithm further comprises the step of calculating a modified phase image by subtracting the fibroglandular tissue phase image from the gradient echo magnetic resonance imaging data. Performing this step substantially removes the influence of fibroglandular tissue from the gradient echo magnetic resonance imaging data. Finally, the algorithm comprises the step of providing a breast microcalcification magnetic resonance image by performing phase unwrapping of the modified phase image. The phase in a normal phase image varies, for example, between -π and +π. When the phase transitions between one of these boundaries, there is an abrupt transition in the image. However, it is relatively easy to perform phase unwrapping automatically and to avoid this.

[0020] In another embodiment, the fibroglandular tissue identification module is configured to provide a fibroglandular tissue segmentation result by first thresholding the image and then performing region growing through the following steps, not limited to the order listed, namely, erosion, dilation or smoothing steps to provide a smoothed shape of the segmentation result.

[0021] In another embodiment, the fibroglandular tissue identification module is configured to provide fibroglandular tissue segmentation results by inputting DIXON magnetic resonance imaging data into a trained fibroglandular tissue identification neural network, for example, inputting DIXON magnetic resonance imaging data including water images, and even fat images in some examples, into a trained fibroglandular tissue identification neural network that then outputs results, which may be trained, for example, by generating a specialized magnetic resonance imaging phantom that includes calcium particles located within known locations of the magnetic resonance imaging breast phantom.

[0022] In another embodiment, the phase image calculation module is implemented using a dipole kernel calculation module, which is performed using known methods for calculating dipole kernels.

[0023] In another embodiment, the phase image computation module is implemented as a trained phase image generating neural network. In this example, the segmentation results are input to the trained phase image generating neural network, and as an output there is a modified phase image output. Training data for the trained phase image generating neural network can be generated in several different ways. In one example, known tissue constituents can be measured to compute or provide the training data. In another example, a dipole kernel is used to train the neural network.

[0024] In another embodiment, the breast microcalcification image reconstruction module is implemented as a trained breast microcalcification image reconstruction neural network. In this example, all steps of reconstructing a breast microcalcification magnetic resonance image are performed by one neural network. The neural network is trained by providing training data sets. Each set of training data includes gradient echo magnetic resonance imaging data, DIXON magnetic resonance imaging data, and control breast microcalcification magnetic resonance image data. The breast microcalcification magnetic resonance images may be generated, for example, by performing measurements on a phantom. In another example, the breast microcalcification magnetic resonance images are generated by an algorithm by analyzing the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data.

[0025] In another embodiment, execution of the machine executable instructions further causes the computing system to receive k-space data acquired according to a DIXON magnetic resonance imaging data protocol and a gradient echo magnetic resonance imaging protocol using a gradient echo or multiple gradient echoes. The k-space data may be combined in some instances, i.e., DIXON magnetic resonance imaging data and gradient echo magnetic resonance imaging data are combined. Thus, the data may be acquired in one acquisition, which ensures that the DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data are spatially matched. In another example, the k-space data may include two parts, one of which is DIXON magnetic resonance imaging data and the other of which is according to a gradient echo magnetic resonance imaging protocol.

[0026] Execution of the machine-executable instructions further causes the computing system to reconstruct gradient echo magnetic resonance imaging data in accordance with a gradient echo magnetic resonance imaging protocol. Execution of the machine-executable instructions further causes the processor to reconstruct DIXON magnetic resonance imaging data in accordance with a DIXON magnetic resonance imaging protocol.

[0027] In another embodiment, the DIXON magnetic resonance imaging protocol is a compressive sensing protocol.

[0028] In another embodiment, the gradient echo magnetic resonance imaging protocol is a compressive sensing protocol.

[0029] In another embodiment, the DIXON magnetic resonance imaging protocol is a multi-point DIXON magnetic resonance imaging protocol. Use of a multi-point DIXON magnetic resonance imaging protocol is beneficial because the resulting water and fat image(s) are more accurate, which results in more accurate identification of breast microcalcification site locations.

[0030] In another embodiment, the medical system further comprises a magnetic resonance imaging system configured to acquire k-space data from the imaging zone. The memory further stores pulse sequence commands configured to acquire k-space data measured according to a DIXON magnetic resonance imaging protocol and a gradient echo magnetic resonance imaging protocol. Execution of the machine executable instructions further causes the computing system to acquire the k-space data by controlling the magnetic resonance imaging system using the pulse sequence commands. As previously explained, when the DIXON magnetic resonance imaging protocol and the gradient echo magnetic resonance imaging protocol are combined, this is a single acquisition of k-space data. In another example, when the protocols are performed independently, it is two independent acquisitions of k-space data.

[0031] In another embodiment, the pulse sequence commands are configured to acquire k-space data for the region of interest. The pulse sequence commands are further configured to suppress vasculature by implementing at least one saturation band outside the region of interest. The use of a saturation band is useful because it can reduce or eliminate MR signals coming from blood diffusing within the breast. Since blood is primarily water, this reduces the difficulty in correctly segmenting fibroglandular tissue. Removal of blood from the magnetic resonance image also makes it easier for the neural network to generate breast microcalcification magnetic resonance images.

[0032] In another embodiment, the gradient echo magnetic resonance imaging involves an echo time, the echo time being a long echo time.

[0033] In another embodiment, the gradient echo magnetic resonance imaging data is accompanied by an echo time. In this embodiment, the echo time is between 100% and 90% of the T2* time point for adipose tissue. In some instances, this echo time provides the definition of a long echo time. This embodiment is beneficial because it provides a means to identify small breast microcalcification sites.

[0034] In another aspect, the present invention provides a computer program product including machine executable instructions for execution by a computing system configured to control a medical system, where execution of the machine executable instructions causes the computing system to receive gradient echo magnetic resonance imaging data representative of a chest region of a subject, where execution of the machine executable instructions further causes the computing system to receive DIXON magnetic resonance imaging data representative of the chest region, where the DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data are spatially matched.

[0035] Execution of the machine-executable instructions further causes the computing system to generate a breast microcalcification magnetic resonance image by inputting the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data into a breast microcalcification image reconstruction module. The breast microcalcification image reconstruction module is configured to output a breast microcalcification magnetic resonance image in response to inputting the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data. The breast microcalcification phase magnetic resonance image is indicative of the locations of the breast microcalcifications. The gradient echo magnetic resonance imaging data is a phase image.

[0036] In another aspect, the present invention provides a method of medical imaging. The method includes receiving gradient echo magnetic resonance imaging data representative of a chest region of a subject. The method further includes receiving DIXON magnetic resonance imaging data representative of the chest region. The DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data are spatially matched. The method further includes generating a breast microcalcification magnetic resonance image by inputting the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data to a breast microcalcification image reconstruction module. The breast microcalcification image reconstruction module is configured to output a breast microcalcification magnetic resonance image in response to inputting the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data. The breast microcalcification phase magnetic resonance image represents locations of breast microcalcifications. The gradient echo magnetic resonance imaging data is a phase image.

[0037] It should be understood that one or more of the above-described embodiments of the present invention may be combined, unless the combined embodiments are mutually exclusive.

[0038] As will be appreciated by one skilled 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." Furthermore, 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 on the computer readable medium(s).

[0039] 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, a "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, semiconductor hard disks, flash memory, USB thumb drives, random access memory (RAM), read only memory (ROM), optical disks, magneto-optical disks, and register files of a computing system. Examples of optical disks include compact disks (CDs) and digital versatile disks (DVDs), e.g., CD-ROM, CD-RW, CD-R, DVD-ROM, DVD-RW, or DVD-R disks. The term computer-readable storage medium also refers to various types of recording media that can be accessed by a computer device over a network or communication link. For example, data may be read by a modem, by the Internet, or by 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, wired, fiber optic cable, RF, etc., or any suitable combination of the above.

[0040] 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 is not a computer-readable storage medium and 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.

[0041] "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 computer-readable storage medium. In some embodiments, computer storage may be computer memory, and vice versa.

[0042] As used herein, a "computing system" encompasses electronic components capable of executing programs or machine-executable instructions or computer-executable code. References to a computing system, including examples of a "computing system," should be interpreted as potentially including more than one computing system or processing core. A computing system is, for example, a multi-core processor. A computing system may represent a collection of computing systems within a single computer system or distributed among multiple computer systems. The term computing system should further be interpreted as possibly representing a collection or network of computing devices, each comprising a processor or computing system. Machine-executable code or instructions are executed by multiple computing systems or processors that are present within the same computing device or even distributed across multiple computing devices.

[0043] Machine executable instructions or computer executable code include instructions or programs that cause a processor or other computing system to perform aspects of the present invention. Computer executable code may include machine executable instructions or programs that cause a processor to perform aspects of the present invention. Computer executable code for performing operations related to 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, or C++, and traditional procedural programming languages ​​such as the "C" programming language or similar programming languages, and may be 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 with an interpreter that generates machine executable instructions on the fly. In other examples, the machine executable instructions or computer executable code are in the form of a program for a programmable logic gate array.

[0044] 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 and partially 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 kind 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., through the Internet using an Internet Service Provider).

[0045] Aspects of the present invention are described with reference to flowcharts, figures and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block or part of multiple blocks of the flowcharts, figures and / or block diagrams, where applicable, may be implemented by computer program instructions in the form of computer executable code. It will be further understood that combinations of blocks in different flowcharts, figures and / or block diagrams may be combined, if not mutually exclusive. These computer program instructions are provided to a computing system of a processor of a general purpose computer, special purpose computer or other programmable data processing device to provide a machine, such that the instructions operating through the computing system of the computer or other programmable data processing device generate means for implementing the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams.

[0046] These machine-executable instructions or computer program instructions, which may instruct a computer, other programmable data processing apparatus, or other device to function in a particular manner, may then be stored on a computer-readable medium, resulting in an article of manufacture including instructions that implement the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams, the instructions stored on the computer-readable medium.

[0047] The machine executable instructions or computer program instructions may further be loaded into a computer, other programmable data processing apparatus, or other device such that a series of operational steps are performed in the computer, other programmable apparatus, or other device to effect computer-implemented processing such that the instructions executed on the computer or other programmable apparatus provide processing for implementing the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams.

[0048] A "user interface" as used herein 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 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 allow input from an operator to be received by the computer and may provide output from the computer to a user. That is, a user interface may allow an operator to control or manipulate a computer, and an interface may allow a computer to show the results 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, wand, graphic tablet, joystick, gamepad, webcom, headset, pedals, wired gloves, remote control, and accelerometer are all examples of user interface elements that allow receiving information or data from an operator.

[0049] As used herein, a "hardware interface" encompasses an interface that allows a computing system of a computer system to interact with and / or control external computing devices and / or devices. A hardware interface may allow a computing system to send control signals or commands to external computing devices and / or devices. A hardware interface may also allow a computing system to exchange data with external computing devices and / or devices. 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.

[0050] As used herein, a "display" or "display device" encompasses an output device or user interface configured to display 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), storage tubes, bi-stable displays, electronic paper, vector displays, 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.

[0051] K-space data is defined herein as the recorded measurements of radio frequency signals emitted by atomic spins by the antenna of a magnetic resonance apparatus during a magnetic resonance imaging scan. Magnetic resonance data is an example of medical tomography data.

[0052] A magnetic resonance imaging (MRI) image, MR image, or magnetic resonance imaging data is defined herein as a reconstructed two-dimensional or three-dimensional visualization result of anatomical data contained in magnetic resonance imaging data, which visualization may be performed using a computer.

[0053] In the following, preferred embodiments of the invention will be described, by way of example only, with reference to the following drawings, in which: [Brief description of the drawings]

[0054] [Figure 1] FIG. 1 illustrates an example of a medical system. [Diagram 2] 2 is a flow chart illustrating a method of operating the medical system of FIG. 1. [Diagram 3] FIG. 1 illustrates a further example of a medical system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0055] Like numbered elements in the figures are either equivalent elements or perform the same function. An element that is discussed earlier is not necessarily discussed in a later figure if the functionality is equivalent.

[0056] FIG. 1 illustrates an example of a medical system 100. The medical system 100 is shown as including a computing system 106 that is part of a computer 102 in this example. However, the computing system 106 may be embedded or incorporated in other devices or systems. The computer 102 is intended to represent one or more computers that are networked or connected to one another. The medical system 100 may take different forms in different examples. In one example, the medical system 100 may be a workstation or terminal that controls a magnetic resonance imaging system. In another example, the medical system 100 may be a computer or workstation used for review of medical images. In another example, the medical system 100 may be a remote computer that provides cloud computing or other image processing services.

[0057] The computer 102 is further shown to include a hardware interface 104 connected to the computing system 106. The hardware interface 104 allows the computing system 106 to communicate with other computer and computing systems. In some examples, the medical system 100 includes additional components, such as a magnetic resonance imaging system, and the hardware interface 104 allows the computing system 106 to control the operation and functionality of the magnetic resonance imaging system. The computer 102 is further shown to include a user interface 108 and a memory 110 further connected to the computing system 106. The user interface 108 is an optional component that allows an operator to use and control the medical system 100. The memory 110 is intended to represent any combination of memory accessible by the computing system 106. The memory 110 is a non-transitory storage medium in some examples.

[0058] The memory 110 is shown as including machine-executable instructions 120. The machine-executable instructions 120 enable the computing system 106 to control the operation and functionality of the medical system 100. The machine-executable instructions 120 further enable the computing system 106 to perform various computational, data processing, and image processing tasks. For example, the machine-executable instructions 120 enable the computing system 106 to perform magnetic resonance imaging reconstruction.

[0059] Memory 110 is further shown as including a breast microcalcification image reconstruction module 122. Breast microcalcification image reconstruction module 122 is configured to output a breast microcalcification magnetic resonance image 128 in response to receiving gradient echo magnetic resonance imaging data 124 and DIXON magnetic resonance imaging data 126. In various examples, DIXON magnetic resonance imaging data 126 is purely water images. In other examples, DIXON magnetic resonance imaging data 126 includes both water images and fat images. Gradient echo magnetic resonance imaging data 124, DIXON magnetic resonance imaging data 126, and breast microcalcification magnetic resonance image 128 are shown as stored in memory 110.

[0060] Breast microcalcification image reconstruction module 122 may take different forms in different examples: breast microcalcification image reconstruction module 122 may be a purely algorithmic module, breast microcalcification image reconstruction module 122 may be a hybrid module that combines several algorithms with various AI components such as neural networks, or breast microcalcification image reconstruction module 122 may be implemented purely as a neural network.

[0061] Memory 110 is further shown as including an optional high-pass spatial filter. The high-pass spatial filter is configured to allow objects that contain small spatial features relative to the size of the image to remain in the image from which larger features have been removed. The high-pass spatial filter reduces the low spatial frequency content of the image. One way to achieve this is to use a kernel of a particular dimension.

[0062] The memory 110 is further shown to include a filtered breast microcalcification image 132 received in response to inputting the breast microcalcification magnetic resonance image 128 through a high pass spatial filter 130. This embodiment is beneficial because it minimizes or removes objects that are not microcalcifications in some cases. Furthermore, the use of a high pass spatial filter aids in simulating a mammogram. The memory 110 is further shown to include a projection image 134. The projection image 134 is a projection of the filtered breast microcalcification image 132 onto a two dimensional plane. The filtered breast microcalcification image 132 may be, for example, a three dimensional magnetic resonance image, or the filtered breast microcalcification image 132 may be a collection of two dimensional slices that may be considered a three dimensional data set. The projection image 134 is useful to radiologists who are familiar with and trained to interpret mammograms. The combination of the high pass spatial filter and the generation of the projection image 134 produces a magnetic resonance image suitable to replace a mammogram.

[0063] 2 shows a flow chart illustrating a method of operating the medical system 100 of FIG. 1. First, in step 200, gradient echo magnetic resonance imaging data 124 is received. Next, in step 202, DIXON magnetic resonance imaging data 126 is received. The DIXON magnetic resonance imaging data 126 further represents a breast region. The breast region is, for example, a region of interest in a magnetic resonance image. The DIXON magnetic resonance imaging data 126 and the gradient echo magnetic resonance imaging data 124 are spatially matched. Finally, in step 204, a breast microcalcification magnetic resonance image 128 is generated by inputting the gradient echo magnetic resonance imaging data 124 and the DIXON magnetic resonance imaging data 126 to a breast microcalcification image reconstruction module 122.

[0064] Figure 3 illustrates a further example of a medical system 300. The medical system 300 illustrated in Figure 3 is similar to the medical system 100 in Figure 1, except that the medical system further comprises a magnetic resonance imaging system 302.

[0065] The magnetic resonance imaging system 302 comprises a magnet 304. The magnet 304 is a superconducting cylindrical magnet, which includes a bore 306 through the superconducting cylindrical magnet. Different types of magnets can be used, for example both segmented cylindrical magnets and so-called open magnets. A segmented cylindrical magnet is similar to a standard cylindrical magnet except that the cryostat is divided into two sections to allow access to the iso-face of the magnet, and such magnets may be used in combination with charged particle beam therapy, for example. An open magnet includes two magnet sections, one above the other with a space between them large enough to accommodate the subject, and the arrangement of the two section areas is similar to that of a Helmholtz coil. Open magnets are common because the subject is relatively unconfined. Inside the cryostat of the cylindrical magnet there is a collection of superconducting coils.

[0066] Within the bore 306 of the cylindrical magnet 304 is an imaging zone 308 where the magnetic field is sufficiently strong and uniform to perform magnetic resonance imaging. A region of interest 309 is shown within the imaging zone 308. Acquired magnetic resonance data is typically acquired for the region of interest. 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 region of interest 309. The region of interest 309 is shown to include a breast region or breast tissue 319 therein.

[0067] Within the magnet bore 306 there is also a set of magnetic field gradient coils 310 used for preliminary magnetic resonance data acquisition to spatially encode magnetic spins within an 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 and ramped or pulsed as a function of time.

[0068] Adjacent to the imaging zone 308 is a radio frequency coil 314 for manipulating the orientation of magnetic spins in the imaging zone 308 and for receiving radio transmissions from spins also in the imaging zone 308. A radio frequency antenna includes multiple coil elements. A radio frequency antenna is also referred to as a channel or an 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 with 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 also represents a separate transmitter and receiver. The radio frequency coil 314 may include multiple receive / transmit elements, and the radio frequency transceiver 316 may include multiple receive / transmit channels. When a parallel imaging technique, such as SENSE, is implemented, the radio frequency coil 314 includes multiple coil elements.

[0069] The transceiver 316 and the gradient controller 312 are shown as being connected to the hardware interface 106 of the computer system 102 .

[0070] Memory 110 is further shown as including pulse sequence commands 330. The pulse sequence commands include data or instructions used to control magnetic resonance imaging system 302 to acquire k-space data 332 according to a DIXON magnetic resonance imaging protocol and a gradient echo magnetic resonance imaging protocol. Memory 110 is further shown as including k-space data 332 acquired by controlling magnetic resonance imaging system 302 using pulse sequence commands 330.

[0071] Breast microcalcifications are one of the early signs of breast cancer. Mammography is the current preferred diagnostic mode for microcalcification detection, but mammography uses ionizing X-ray radiation. Reliable detection of breast microcalcifications using MR provides a safer alternative for breast cancer screening. Calcifications observed in vivo are associated with different magnetic susceptibility compared to the surrounding tissue. MRI signal phase may be sensitive to such susceptibility changes. Furthermore, the presence of fat, which affects the MRI signal phase, introduces a confounding factor. In the proposed method, the fat signal contribution is removed using prior information from mDIXON or other types of DIXONS scans to generate a relatively clean phase image that is primarily sensitive to the presence of breast calcifications. This method is a powerful enabler for MRI-based breast cancer screening, as it solves one of the key pitfalls of MR - the inability to image microcalcifications.

[0072] Breast cancer is the second most common form of cancer worldwide and the leading cause of cancer in women. Mammography is the standard first-line diagnostic imaging for breast cancer screening. The European Society for Medical Oncology, the American Cancer Society, and the Indian Council of Medical Research recommend annual breast screening using mammography for women over 45 years of age and / or at higher familial risk of breast cancer. Approximately 31% of patients undergoing screening mammograms have breast microcalcifications, which are associated with ductal carcinoma in situ (DCIS), a potential precursor to invasive breast cancer. As not all patients with DCIS progress to the invasive cancer stage, the detection of microcalcifications on an initial screening mammogram typically prompts a follow-up mammogram or a magnetic resonance imaging (MRI)-based evaluation. The mammography process uses ionizing radiation for imaging purposes, which is itself a significant carcinogenic risk factor. Annual screening mammography examinations further increase exposure to ionizing radiation. On the other hand, MRI offers a non-ionizing radiation-based imaging alternative for breast cancer evaluation. On the other hand, MRI offers a non-ionizing radiation-based imaging alternative for breast cancer evaluation. Nevertheless, one of the significant drawbacks in the use of MRI for general breast cancer screening is its inability to conclusively detect microcalcification sites, which are one of the early imaging markers of breast cancer.

[0073] Currently proposed MRI methods use phase-based pattern matching or quantitative susceptibility mapping-based methods to detect breast calcifications. Most of these methods have not been used in vivo due to long scan times and have not been used to detect near-micro or microcalcifications. They have been used to visualize large breast calcifications. Quantitative susceptibility mapping (QSM)-based methods have previously been used to detect large breast calcifications. QSM is an elegant tool that takes into account the phase effects of fibroglandular tissue and fat and can be useful in visualizing calcified nodules. However, QSM has not proven useful in detecting microcalcifications.

[0074] In this study, we propose an optimized MRI protocol for the detection of breast calcification sites and a post-processing algorithm that uses direct MRI.

[0075] Breast calcifications are nodular and are typically partial volume relative to the imaging voxel size due to relative size differences (microcalcifications have diameters of about 0.1-0.4 mm, with typical imaging voxel sizes having slice thicknesses of about 2 mm). Because vascular and fibroglandular tissues are continuous structures, partial volume phase is detectable in gradient echo MRI phase images and can be identified as nodules using projection images. Fibroglandular tissue also suffers from significant phase effects due to its difference in sensitivity between itself and the surrounding breast fat. This phase effect can be mitigated if the shape of the fibroglandular tissue is known a priori. This information can be obtained from mDIXON or other DIXON techniques, the implementation of which is specific to Philips. Phase from the fibroglandular tissue can then be estimated using a general dipole kernel. Using this simulated phase information, a clean breast phase image sensitive only to calcified nodules can then be obtained.

[0076] Visualization of breast calcification sites in phase images has been done before. Similarly, in the case of the brain, the use of tissue geometry to predict phase information has been done before, where the tissue geometry was extracted by a different acquisition. A novel aspect of this invention / innovation is the unique combination of gradient echo acquisition with mDIXON or other DIXON acquisition for breast calcification detection applications.

[0077] A method for detecting breast calcification sites includes one or more of the following steps. 1) Acquisition of long echo time (TE) gradient echo data and mDIXON or other DIXON data with matching resolution and bandwidth in only one sequence or as independent acquisitions. The long echo time (TE) gradient echo data may be gradient echo magnetic resonance imaging data 124 and may also be simply referred to as echo time (TE) gradient echo data without the "long TE" designation. The mDIXON or other DIXON data may be DIXON magnetic resonance imaging data 126. 2) Compressed SENSE is used in some examples for faster acquisition of high resolution data, but is not required. In some examples, the voxel size is approximately 0.1×0.1 mm, depending on the voxel aspect ratio of approximately 1:1:3 to 1:1:5. 2 From 0.4×0.4mm 2 It is. 3) Long TE gradient echo data is acquired using a TE that is in phase with fat. As mentioned above there are advantages to being in phase with fat, but the phase can be chosen freely. 4) Obtaining fibroglandular tissue shape (fibroglandular tissue segmentation result) from the mDIXON image using image processing methods including but not limited to thresholding, region growing, erosion, and dilation for smooth shape extraction. This is the fibroglandular tissue segmentation result of the DIXON magnetic resonance imaging data 126. 5) Removal of vascular structures in mDIXON images is performed where necessary using a saturation band during data acquisition or through vessel tracking measures in data acquired without saturation. 6) Simulate the phase effects of fibroglandular tissue using one of the dipole kernels or using a machine learning approach. 7) Removal of the phase effects of fibroglandular tissue from long TE phase images through phase subtraction. 8) Phase unwrapping. 9) Filtering the phase image (using a high-pass spatial filter) to remove low frequency background field information. 10) Generating projection images 134 (maximum or minimum intensity projections depending on the handiness of the phase image) for visualization of nodular breast calcifications. 11) An alternative implementation uses a machine learning framework (e.g., neural network) that uses phase and shape information as input, and the output is a projection image showing only calcified nodules.

[0078] 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, i.e., the invention is not limited to the disclosed embodiments.

[0079] Other variations of the disclosed embodiments can be understood and realized 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 "comprises" does not exclude other elements or steps, and the singular does not exclude a plurality. A single processor or other unit fulfills the functions of several items recited in the claims. The mere fact that certain means are recited in mutually different dependent claims does not indicate that a combination of these means cannot be used to advantage. The computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, provided 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 telecommunication systems. Any reference signs in the claims should not be interpreted as limiting the scope of the invention. [Explanation of symbols]

[0080] 100 Medical Systems 102 Computer 104 Hardware Interface 106 Computing System 108 User Interface 110 Memory 120 Machine Executable Instructions 122 Breast Microcalcification Image Reconstruction Module 124 Gradient Echo Magnetic Resonance Imaging Data 126 DIXON magnetic resonance imaging data 128 Magnetic Resonance Imaging of Microcalcifications in the Breast 130 High-pass spatial filter 132 Filtered Images of Breast Microcalcifications 134 Projected Images 200. Receive gradient echo magnetic resonance imaging data representative of a thoracic region of a subject. 202 Receive DIXON magnetic resonance imaging data representing the thoracic region 204 Breast Microcalcification Magnetic Resonance Images are Generated by Inputting Gradient Echo Magnetic Resonance Imaging Data and DIXON Magnetic Resonance Imaging Data to the Breast Microcalcification Image Reconstruction Module 300 Medical Systems 302 Magnetic Resonance Imaging System 304 Magnet 306 Magnet Bore 308 Imaging Zone 309 Areas of Interest 310 Magnetic field gradient coil 312 Magnetic field gradient coil power supply 314 Radio Frequency Coil 316 Transceiver 318 Target 319 Thoracic region 320 Subject Support 330 Pulse Sequence Commands 332 k-space data

Claims

1. a memory storing machine executable instructions and a breast microcalcification image reconstruction module, the breast microcalcification image reconstruction module responsive to receiving gradient echo magnetic resonance imaging data and DIXON magnetic resonance imaging data to output a breast microcalcification magnetic resonance image, the breast microcalcification magnetic resonance image representing locations of breast microcalcifications, and the gradient echo magnetic resonance imaging data being a phase image; a computing system for controlling the medical system, wherein execution of the machine-executable instructions causes the computing system to: receiving the gradient echo magnetic resonance imaging data representative of a chest region of a subject; receiving the DIXON magnetic resonance imaging data representative of the chest region, the DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data being spatially matched; generating the breast microcalcification magnetic resonance image by inputting the gradient echo magnetic resonance imaging data and the DIXON magnetic resonance imaging data into the breast microcalcification image reconstruction module, the breast microcalcification image reconstruction module being implemented as a trained breast microcalcification image reconstruction neural network; The medical system that makes this possible.

2. Execution of the machine-executable instructions further causes the computing system to calculate a filtered breast microcalcification image by applying a high pass spatial filter to the breast microcalcification magnetic resonance image. The medical system of claim 1 .

3. Execution of the machine-executable instructions further causes the computing system to generate a breast microcalcification projection image by calculating a projection of the filtered breast microcalcification image. The medical system of claim 2 .

4. said breast microcalcification image reconstruction module further comprising: calculating a fibroglandular tissue segmentation result of the DIXON magnetic resonance imaging data by inputting the DIXON magnetic resonance imaging data into a fibroglandular tissue identification module, the fibroglandular tissue segmentation result identifying the location of fibroglandular tissue; calculating a fibroglandular tissue phase image of the fibroglandular tissue by inputting the fibroglandular tissue segmentation result into a phase image calculation module; calculating a modified phase image by subtracting the fibroglandular tissue phase image from the gradient echo magnetic resonance imaging data; providing said breast microcalcification magnetic resonance image performing phase unwrapping of said altered phase image; The algorithm is implemented as The medical system of claim 1, 2 or 3.

5. said fibroglandular tissue identification module comprising: Thresholding, region growing, erosion, and dilation for smooth shape extraction; inputting the DIXON magnetic resonance imaging data into a trained fibroglandular tissue discrimination neural network; The combination of these, providing the fibroglandular tissue segmentation result by any one of The medical system of claim 4.

6. The phase image calculation module comprises: using a dipole kernel computation module; a trained phase image generating neural network; The present invention is realized as one of the following: The medical system according to claim 4 or 5.

7. Execution of the machine-executable instructions further comprises: receiving k-space data acquired according to a DIXON magnetic resonance imaging protocol and a gradient echo magnetic resonance imaging protocol using a gradient echo or multiple gradient echoes; reconstructing the gradient echo magnetic resonance imaging data according to the gradient echo magnetic resonance imaging protocol; reconstructing the DIXON magnetic resonance imaging data according to the DIXON magnetic resonance imaging protocol; To make A medical system according to any one of claims 1 to 6.

8. the DIXON magnetic resonance imaging protocol is a compressed sensing protocol and / or the gradient echo magnetic resonance imaging protocol is a compressed sensing protocol; The medical system of claim 7.

9. The DIXON magnetic resonance imaging protocol is a multi-point DIXON magnetic resonance imaging protocol; The medical system according to claim 7 or 8.

10. the medical system further comprises a magnetic resonance imaging system that acquires k-space data from an imaging zone, the memory further storing pulse sequence commands for acquiring the measured k-space data acquired according to the DIXON magnetic resonance imaging protocol and the gradient echo magnetic resonance imaging protocol, and executing the machine executable instructions further causes the computing system to control the magnetic resonance imaging system using the pulse sequence commands to acquire the k-space data.

10. The medical system of claim 7, 8 or 9.

11. the pulse sequence commands are for acquiring the k-space data for a region of interest, the pulse sequence commands further suppressing vasculature structures by achieving at least one saturation band outside the region of interest. The medical system of claim 10.

12. the gradient echo magnetic resonance imaging data includes an echo time, the echo time being between 100% and 90% of the T2* time for adipose tissue; A medical system according to any one of claims 7 to 11.

13. 1. A computer program product comprising machine executable instructions for execution by a computing system for controlling a medical system, the execution of said machine executable instructions causing said computing system to: Receiving gradient echo magnetic resonance imaging data representative of a thoracic region of a subject; receiving DIXON magnetic resonance imaging data representative of the chest region, the DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data being spatially matched; generating a breast microcalcification MRI image by inputting the gradient echo MRI data and the DIXON MRI data into a breast microcalcification image reconstruction module, the breast microcalcification image reconstruction module being implemented as a trained breast microcalcification image reconstruction neural network and outputting a breast microcalcification MRI image in response to inputting the gradient echo MRI data and the DIXON MRI data, the breast microcalcification MRI image representing locations of breast microcalcifications, the gradient echo MRI data being a phase image; To make Computer program.

14. 1. A method of medical imaging, said method comprising: receiving gradient echo magnetic resonance imaging data representative of a chest region of a subject; receiving DIXON magnetic resonance imaging data representative of the chest region, the DIXON magnetic resonance imaging data and the gradient echo magnetic resonance imaging data being spatially matched; generating a breast microcalcification MRI image by inputting the gradient echo MRI data and the DIXON MRI data into a breast microcalcification image reconstruction module, the breast microcalcification image reconstruction module being implemented as a trained breast microcalcification image reconstruction neural network and outputting a breast microcalcification MRI image in response to inputting the gradient echo MRI data and the DIXON MRI data, the breast microcalcification MRI image representing locations of breast microcalcifications, and the gradient echo MRI data being a phase image; The method comprising:

Images