Identification of consultation areas in breast magnetic resonance imaging

Abstract

A medical imaging method is disclosed. The method comprises receiving (200) an echo planar diffusion weighted magnetic resonance image (122) describing a region of interest (309) of breast tissue; receiving (202) a fat suppressed T2 weighted magnetic resonance image (124) describing the region of interest; segmenting (204) the echo planar diffusion weighted magnetic resonance image to identify a high diffusion rate region (128); segmenting (206) the fat suppressed T2 weighted magnetic resonance image to identify a tissue region (130); identifying (208) a portion of the tissue region as a consultation region (134) by inputting the high diffusion rate region and the tissue region into an image processing module; and providing (210) the consultation region as a segmentation of the fat suppressed T2 weighted magnetic resonance image.

Description

Technical Field

[0001] This invention relates to magnetic resonance imaging, and more particularly to breast screening using magnetic resonance imaging. Background Technology

[0002] As part of the process of generating images within a patient's body, a large static magnetic field is used by a magnetic resonance imaging (MRI) scanner to align the nuclear spins of atoms. This large static magnetic field is called the B0 field or main magnetic field. MRI can be used to spatially measure various quantities or properties of an object.

[0003] International patent application WO2012070951A1 discloses a process for distinguishing benign and malignant tumors in tissues (e.g., soft tissue, and particularly breast tissue) in vitro by registering and comparing measurement data from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and dynamic susceptibility contrast-enhanced magnetic resonance imaging (DSC) of tumors. The process is configured to initially execute two dynamic MRI pulse sequences in an interleaved pattern during parenteral administration of MR contrast material, wherein one pulse sequence is optimized for high spatial resolution while the other is adjusted for high temporal resolution. The high temporal resolution (dissolved) sequence also includes dual-echo collection sensitive to both DCE and DSC to generate multiple distinct biomarker data, such as pharmacokinetic biomarker data, descriptive DCE biomarkers, and descriptive DSC biomarkers. These data are then normalized and compared, respectively, with corresponding data from the corresponding benign and malignant tumors. Preferably, from each tumor volume, 95% of the collected biomarkers are present, identifying most anomalous kinetic properties (belonging to relevant biomarkers). Summary of the Invention

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

[0005] X-ray-based mammography is typically used to screen breast tissue for abnormalities. Examples can provide an improved means of locating counseling areas within breast tissue using magnetic resonance imaging (MRI). To achieve this, two types of images are used. Echo-plane diffusion-weighted MRI is used to locate high-diffusion-rate areas. High-diffusion-rate areas can be, for example, labeled regions with a diffusion rate above a predetermined diffusion rate threshold. This technique is very effective in identifying areas of abnormal tissue. However, echo-plane diffusion-weighted MRI may contain spatial distortions. Abnormal tissue may be identified, but its true location may then be uncertain.

[0006] For example, a region with high diffusivity can be alternatively referred to as an identified diffusivity region.

[0007] To provide accurate localization, fat-suppressed T2-weighted MRI images were used. These images were segmented to identify tissue regions. Due to the use of fat or lipid suppression, these segments could be considered as areas without fat tissue or fatty tissue. The resulting tissue regions were then segmented to include normal tissue structures within the breast, as well as any abnormal structures.

[0008] The imaging processing module is then used to identify portions of the tissue region as consultation areas. The imaging processing module can be configured to identify the spatial location of the tissue region responsible for the high-diffusion area using spatial, volumetric, or shape-based relationships between the high-diffusion region and the tissue region.

[0009] In one aspect, the present invention provides a medical system including a memory storing machine-executable instructions. The medical system also includes a computing system configured to control the medical system. In different examples, the medical system can take different forms. In one example, the medical system may be a workstation. In another example, the medical system may be a remote server, etc., providing image processing and reconstruction services for magnetic resonance imaging. In yet another example, the medical system is a system that includes a medical imaging system such as a magnetic resonance imaging system.

[0010] The execution of machine-executable instructions enables the computing system to receive echo-plane diffusion-weighted magnetic resonance images describing regions of interest in breast tissue.

[0011] The execution of machine-executable instructions also enables the computing system to receive fat-suppressed T2-weighted magnetic resonance images describing the region of interest. Registration may exist between the echo-plane diffusion-weighted magnetic resonance images and the fat-suppressed T2-weighted magnetic resonance images, making the regions of interest identical or equivalent. The execution of machine-executable instructions also enables the computing system to segment the echo-plane diffusion-weighted magnetic resonance images to identify regions with high diffusion rates.

[0012] There are different ways to identify high-diffusion-rate regions; however, one approach is to threshold echo-plane diffusion-weighted MRI images. Identification of high-diffusion-rate regions can help identify tissues with pathologies such as malignant tumors. Echo-plane diffusion-weighted MRI is adept at detecting such pathologies or tissue types; however, it is often distorted. Therefore, while it may be possible to identify such tissue types, the exact location may be uncertain.

[0013] The execution of machine-executable instructions also enables the computational system to segment fat-suppressed T2-weighted magnetic resonance images to identify tissue regions. These tissue regions can be, for example, non-fatty or non-adipose tissue. Because the image is fat-suppressed, the identified tissue regions may exclude fatty or adipose tissue. The execution of machine-executable instructions also enables the computational system to identify portions of the tissue regions as consultation areas by inputting high-diffusion regions and tissue regions into the image processing module.

[0014] The terminology consultation area can be used to provide or highlight areas for further review or examination by a doctor or other healthcare provider. Image processing modules can, for example, be used to correlate tissue areas with areas of high diffusion. In fat-suppressed T2-weighted MRI images, many parts of the tissue can be identified. For example, glandular tissue, as well as fibrous tissue, supporting tissue, or connective tissue, may be present in the breast. Additional ligaments and scar tissue may also be present. This is in addition to any cancers or tumors that may be present.

[0015] In magnetic resonance imaging (MRI), distinguishing these tissue types is often impractical. On the other hand, echo-planar diffusion-weighted MRI provides information about areas of the breast with high diffusion rates. That is, diffusion rate areas have diffusion above a predetermined threshold. Associating high diffusion rate areas with tissue regions allows for the identification of consultation areas and assists physicians. The execution of machine-executable instructions also enables the computational system to provide consultation areas as segments in fat-suppressed T2-weighted MRI images. Therefore, T2-weighted MRI images can be displayed alongside labeled or highlighted consultation areas. For example, this can help doctors plan further medical investigations or procedures.

[0016] It is worth mentioning that the above can be performed in both two-dimensional and three-dimensional imaging. Fat-suppressed T2-weighted MRI images and echo-plane diffusion-weighted MRI images can be two-dimensional images, collections of two-dimensional slices, or complete three-dimensional datasets.

[0017] In another embodiment, the echo-plane diffusion-weighted magnetic resonance image is a high b-value echo-plane diffusion-weighted magnetic resonance image. Using high b-value echo-plane diffusion-weighted magnetic resonance images can be advantageous because they may be useful for identifying high-diffusion areas that may contain tumors or cancerous tissue. However, using high b-value echo-plane diffusion-weighted magnetic resonance images can lead to greater image distortion. Identifying the consultation area using tissue regions from fat-suppressed T2-weighted magnetic resonance images allows for the identification of both the location and the high-diffusion area. The use of the label "high b-value" is a label that can be interpreted as indicating that the image was acquired using a b-value that may cause geometric distortion of the image.

[0018] In another embodiment, the execution of machine-executable instructions further causes the computing system to receive a conductivity map describing the region of interest. The execution of the machine-executable instructions also causes the computing system to use the conductivity map to calculate a conductivity measure for each element in the consultation region. The conductivity measure can be a statistical value or measure calculated for voxels identified as consultation regions. This can include various statistics, such as average conductivity, as well as minimum and maximum values ​​and the mean of conductivity.

[0019] In another embodiment, the consultation area is used to define boundaries during the calculation of the conductivity map.

[0020] The execution of machine-executable instructions also enables the computing system to assign a type to each consultation area based on a conductivity metric. Conductivity metrics can be highly dependent on various ion types, such as sodium. If a consultation area has a high diffusivity value above a certain high diffusivity value and an average conductivity or other conductivity metric above a predetermined threshold, it can indicate that the specific consultation area is cancerous or should be further investigated by a physician.

[0021] In another embodiment, the execution of machine-executable instructions also causes the computing system to plot the consultation area as a superposition on a fat-suppressed T2-weighted magnetic resonance image.

[0022] In another embodiment, the execution of machine-executable instructions also enables the computing system to map the type of each in the consultation area based on or using conductivity measurements.

[0023] For example, consultation areas with conductivity measurements above a predetermined conductivity measurement threshold can be highlighted on a display or drawing. In another example, the drawing can sort or assign the order in which consultation areas are suggested for investigation. The user interface can display a hierarchy on the drawing, or the user interface can have controls for the operator to highlight consultation areas sequentially according to their hierarchy.

[0024] In another embodiment, the medical system further includes a magnetic resonance imaging system configured to acquire k-space data from an imaging region. The memory also contains a first pulse sequence command and a second pulse sequence command. The first pulse sequence command is configured to acquire first k-space data according to an echo-plane diffusion-weighted magnetic resonance imaging protocol. The second pulse sequence command is configured to acquire second k-space data according to a T2-weighted magnetic resonance imaging protocol. The second pulse sequence command is for fat or lipid suppression.

[0025] The execution of the machine-executable instructions also enables the computing system to control the magnetic resonance imaging system using a first pulse sequence command to acquire first k-space data from a region of interest containing breast tissue. The execution of the machine-executable instructions further enables the computing system to control the magnetic resonance imaging system using a second pulse sequence command to acquire second k-space data from the region of interest containing breast tissue. The first and second pulse sequence commands can be configured such that the two acquired regions of interest originate from the same spatial volume. The execution of the machine-executable instructions further enables the computing system to reconstruct an echo-plane diffusion-weighted magnetic resonance image from the first k-space data. The execution of the machine-executable instructions further enables the computing system to reconstruct a fat-suppressed T2-weighted magnetic resonance image from the second k-space data.

[0026] In another embodiment, the first pulse sequence command is configured to acquire b values ​​at 0 s / mm. 2 and 3000s / mm 2 The first k-space data between.

[0027] In another embodiment, the first pulse sequence command is configured to acquire b values ​​at 800 s / mm. 2 and 1600s / mm 2 The first k-space data between. In some examples within this range, the b-value can be considered a high b-value. This embodiment can be beneficial because DWI detection of tissue types such as tumors works well when using these b-values, but there is significant geometric distortion.

[0028] In another embodiment, the first pulse sequence command is configured to acquire b values ​​at 1200 s / mm. 2 and 1400s / mm 2 The first k-space data between. In some examples within this range, the b-value can be considered a high b-value. This embodiment can be beneficial because DWI detection of tissue types such as tumors works very efficiently when using these b-values, but significant geometric distortion exists.

[0029] In another embodiment, the second pulse sequence command is based on an electrical tomography magnetic resonance imaging (EMI) protocol. An EMI protocol could be, for example, an EMI protocol used to measure distortions in the B1 magnetic field.

[0030] Multiple fat suppression pulses are compatible with electrical transduction tomography (EPT). Various methods exist, but several key approaches are mentioned. First, fat suppression using RF pulses, which selectively saturate fat protons via a fat-suppressing RF pulse frequency, is possible. Another method uses a Dixon-type technique similar to chemical shift imaging. Two images with different echo times are acquired and processed to obtain fat-only and water-only images. The water-only image in this paradigm can be used for fat-suppressed T2-weighted MRI. Another method is the inversion recovery method, which utilizes fat with a T1 value typically shorter than that of water. All three methods described above, used in conjunction with spin-echo pulse sequences, produce phase measurements that can be used for EPT calculations.

[0031] In another embodiment, the second pulse sequence command is a spin echo pulse sequence command.

[0032] In another embodiment, the second pulse sequence command is an ultrashort echo time pulse sequence command.

[0033] In another embodiment, the second pulse sequence command is a zero-echo-time pulse sequence command.

[0034] In another embodiment, the second pulse sequence command is a multi-echo gradient echo pulse sequence command.

[0035] In another embodiment, the second pulse sequence command is a balanced gradient echo pulse sequence command.

[0036] In another embodiment, the second pulse sequence command is a steady-state precession pulse sequence command. All of the above types of pulse sequence commands are compatible with measuring the phase that can be used for electrical tomography and performing fat suppression as described above.

[0037] In another embodiment, the execution of machine-executable instructions also enables the computational system to reconstruct a conductivity map describing the region of interest from second k-space data. This embodiment can be advantageous because spatially correlated conductivity often depends on various ion concentrations. This, combined with identifying regions as high-diffusion-rate areas or regions with a diffusion rate above predetermined criteria, can be used for tissue classification. For example, the type can be used to rank regions in order of priority for investigation or recommendation for investigation by a primary care physician or other healthcare professional.

[0038] In another embodiment, high diffusion rate regions are identified by thresholding the echo plane diffusion-weighted magnetic resonance image. In this example, high diffusion rate regions are defined by providing a threshold or predetermined diffusion rate that defines the region as having high diffusion rate.

[0039] In another embodiment, the image processing module is configured to algorithmically identify counseling regions. In one example, if one of the tissue regions has a superposition higher than any of the predetermined superposition of high-diffusion regions, the counseling region is algorithmically identified by recognizing one of the two tissue regions as one of the counseling regions.

[0040] In another example, if one of the tissue regions has a center distance less than a predetermined distance from any of the other high-diffusion regions, the image processing module identifies one of the tissue regions as one of the consultation regions. There may be no overlap, but if the centers are close enough, they may be classified as the same region. For example, the center could be the centroid. In another example, if one of the tissue regions has a volume that matches any of the high-diffusion regions within a predetermined volume difference, the image processing module identifies one of the tissue regions as one of the consultation regions. Echo-plane diffusion-weighted magnetic resonance imaging can cause distortion in the shape and location of high-diffusion regions. Comparing volumes may be one way to assign high-diffusion regions to appropriate tissue regions.

[0041] If one of the tissue regions has a shape that matches any of the high diffusion regions within a predetermined distortion, then in another example, the image processing module can identify one of the tissue regions as one of the consultation regions.

[0042] In another embodiment, the image processing module is a trained neural network configured to label portions of tissue regions as consultation regions in response to input tissue regions and high-diffusion regions. For example, the neural network can be trained by first having multiple tissue regions and high-diffusion regions classified by humans. This can be used to create training data. For example, the neural network can then be trained using deep learning algorithms.

[0043] In another embodiment, the tissue region is a non-adipose tissue region or a non-adipose tissue region.

[0044] In another aspect, the present invention provides a computer program comprising machine-executable instructions for execution by a computing system controlling a medical system. For example, the computer program may be a computer program product stored on a non-transient storage medium. The execution of the machine-executable instructions causes the computing system to receive echo-plane diffusion-weighted magnetic resonance images describing regions of interest in breast tissue. The execution of the machine-executable instructions also causes the computing system to receive fat-suppressed T2-weighted magnetic resonance images describing the regions of interest.

[0045] The execution of machine-executable instructions also enables the computing system to segment echo-plane diffusion-weighted magnetic resonance images to identify high-diffusion regions. The execution of machine-executable instructions also enables the computing system to segment fat-suppressed T2-weighted magnetic resonance images to identify tissue regions. The execution of machine-executable instructions also enables the computing system to identify portions of the tissue regions as consultation regions by inputting the high-diffusion regions and tissue regions into the image processing module. The execution of machine-executable instructions also enables the computing system to provide consultation regions as segments of fat-suppressed T2-weighted magnetic resonance images. The fat-suppressed T2-weighted magnetic resonance images can be displayed as an overlay, for example, along with the segmentation.

[0046] In another aspect, the method provides a medical or magnetic resonance imaging approach. The method includes receiving an echo-plane diffusion-weighted magnetic resonance image describing a region of interest (ROI) of breast tissue. The method also includes receiving a fat-suppressed T2-weighted magnetic resonance image describing the ROI. The method further includes segmenting the echo-plane diffusion-weighted magnetic resonance image to identify high-diffusion-rate regions. The method also includes segmenting the fat-suppressed T2-weighted magnetic resonance image to identify tissue regions. The method further includes identifying a portion of the tissue region as a consultation region by inputting the high-diffusion-rate regions and the tissue regions into an image processing module. The method also includes providing the consultation region as a segment of the fat-suppressed T2-weighted magnetic resonance image.

[0047] It should be understood that one or more of the foregoing embodiments of the present invention can be combined, as long as the combined embodiments are not mutually exclusive.

[0048] As those skilled in the art will recognize, various aspects of the present invention can be implemented as apparatus, method, or computer program product. Accordingly, various aspects of the present invention can take the form of a completely hardware embodiment, a completely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects (all of which may be referred to herein as "circuit," "module," or "system" in general). Furthermore, various aspects of the present invention can take the form of a computer program product implemented in one or more computer-readable media having computer-executable code implemented thereon.

[0049] Any combination of one or more computer-readable media can be used. The computer-readable media can be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" encompasses any tangible storage medium capable of storing instructions executable by a processor or computing system of a computing device. A computer-readable storage medium may be referred to as a computer-readable non-transitory storage medium. A computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, a computer-readable storage medium may also be capable of storing data accessible 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 drives, flash memory, USB thumb drives, random access memory (RAM), read-only memory (ROM), optical discs, magneto-optical discs, and register files of computing systems. Examples of optical discs include compact discs (CDs) and digital universal discs (DVDs), such as CD-ROMs, CD-RWs, CD-Rs, DVD-ROMs, DVD-RWs, or DVD-R discs. The term computer-readable storage medium also refers to various types of recording media accessible by a computer device via a network or communication link. For example, data can be retrieved on a modem, the Internet, or a local area network. Computer-executable code implemented on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, or any suitable combination thereof.

[0050] Computer-readable signal media may include propagated data signals having computer-executable code implemented therein, for example, in baseband or as a carrier wave. Such propagated signals may take any 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 is capable of conveying, propagating, or transmitting a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0051] "Computer memory" or "memory" is an example of a computer-readable storage medium. Computer memory is any memory that can be directly accessed by a computing system. "Computer storage device" or "storage device" is another example of a computer-readable storage medium. A computer storage device is any non-volatile computer-readable storage medium. In some embodiments, a computer storage device may also be computer memory, or vice versa.

[0052] As used herein, "computing system" encompasses electronic components capable of executing programs or machine-executable instructions or computer-executable code. References to computing systems that include the term "computing system" should be interpreted as potentially encompassing more than one computing system or processing core. A computing system can, for example, be a multi-core processor. A computing system can also refer to a collection of computing systems within a single computer system or distributed across multiple computer systems. The term computing system should also be interpreted as potentially referring to a collection or network of computing devices, each including a processor or computing system. Machine-executable code or instructions can be run by multiple computing systems or processors, which can be within the same computing device or even distributed across multiple computing devices.

[0053] Machine-executable instructions or computer-executable code may include instructions or programs that cause a processor or other computing system 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 ​​and compiled into machine-executable instructions, including object-oriented programming languages ​​such as Java, Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. In some instances, the computer-executable code may be in the form of a high-level language or in a pre-compiled form and used in conjunction with an interpreter that generates machine-executable instructions at runtime. In other instances, the machine-executable instructions or computer-executable code may be in the form of a programmable gate array.

[0054] The computer-executable code may be executed entirely on the user's computer, partially on the user's computer (as a standalone software package), partially on the user's computer 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 via 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., via the Internet provided by an Internet service provider).

[0055] Aspects of the invention are described with reference to flowchart illustrations, diagrams, and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that, when applicable, each block or portion of a flowchart illustration, diagram, and / or block diagram can be implemented by computer program instructions in the form of computer-executable code. It should also be understood that combinations of blocks from different flowchart illustrations, diagrams, and / or block diagrams can be combined when not mutually exclusive. 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 apparatus that produces the machine, such that the instructions, executable via the computer or other programmable data processing apparatus, create units for implementing the functions / actions specified in the flowchart illustrations and / or one or more block diagram blocks.

[0056] These machine-executable instructions or computer program instructions may also be stored in a computer-readable medium that can instruct a computer, other programmable data processing apparatus or other device to operate in a particular manner, such that the instructions stored in the computer-readable medium produce an article of writing including instructions that implement the functions / actions specified in flowcharts and / or one or more block diagrams.

[0057] Machine-executable instructions or computer program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device, thereby producing a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide for the process of the function / action specified in the flowchart and / or one or more block diagram boxes.

[0058] 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" can also be referred to as a "human-machine interface device." A user interface can provide or receive information or data from an operator. A user interface enables input from an operator to be received by the computer and output from the computer to the user. In other words, the user interface allows an operator to control or manipulate the computer, and the interface allows the computer to indicate the effects of the operator's control or manipulation. The display of data or information on a monitor or graphical user interface is an example of providing information to an operator. The reception of data via a keyboard, mouse, trackball, touchpad, pointing stick, graphics tablet, joystick, game controller, webcam, headset, pedal, wired gloves, remote control, and accelerometer are all examples of user interface components that implement the reception of information or data from an operator.

[0059] As used herein, "hardware interface" encompasses the interfaces that enable a computer system to interact with and / or control external computing devices and / or devices. A hardware interface allows the computing system to send control signals or instructions to external computing devices and / or devices. It also enables the computing system to exchange data with external computing devices and / or devices. Examples of hardware interfaces include, but are not limited to: Universal Serial Bus (USB), IEEE 1394 port, parallel port, IEEE 1284 port, serial port, RS-232 port, IEEE-488 port, Bluetooth connectivity, wireless LAN connectivity, TCP / IP connectivity, Ethernet connectivity, control voltage interfaces, MIDI interfaces, analog input interfaces, and digital input interfaces.

[0060] As used herein, “display” or “display device” encompasses an output device or user interface suitable for displaying images or data. Displays can output visual, audio, and / or tactile data. Examples of displays include, but are not limited to: computer monitors, television screens, touchscreens, tactile electronic displays, Braille screens, cathode ray tubes (CRTs), memory tubes, bistable 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 (OLED) displays, projectors, and head-mounted displays.

[0061] K-space data are defined in this paper as measurements of radio frequency signals emitted by atomic spins, recorded by the antenna of a magnetic resonance imaging (MRI) device during a magnetic resonance imaging (MRI) scan. MRI data is an example of tomographic medical image data.

[0062] Magnetic resonance imaging (MRI) images, or MR images, are defined in this paper as reconstructed two-dimensional or three-dimensional visualizations of anatomical data contained within magnetic resonance imaging data. This visualization can be performed using a computer. Attached Figure Description

[0063] Preferred embodiments of the invention will be described below by way of example only and with reference to the accompanying drawings, wherein:

[0064] Figure 1 The illustration shows an example of a medical system;

[0065] Figure 2 The illustrated operation is shown. Figure 1 A flowchart of the methods used in medical systems;

[0066] Figure 3 The illustration shows another example of a medical system; and

[0067] Figure 4 The diagram illustrates how to select a consultation area.

[0068] List of reference numerals

[0069] 100 Medical Systems

[0070] 102 Computer

[0071] 104 Hardware Interfaces

[0072] 106 Computing System

[0073] 108 User Interface

[0074] 110 Memory

[0075] 120 Machine-executable instructions

[0076] 122 echo plane diffusion-weighted magnetic resonance images

[0077] 124 fat-suppressed T2-weighted magnetic resonance images

[0078] 126 Optional Registration

[0079] 128 High Diffusion Region

[0080] 130 Organizational Area

[0081] 132 Image Processing Module

[0082] 134 Consultation Area

[0083] 136 Enhanced T2-weighted magnetic resonance images

[0084] 200 receive echo-planar diffusion-weighted magnetic resonance images describing regions of interest in breast tissue.

[0085] 202 Receive fat-suppressed T2-weighted magnetic resonance images describing the region of interest

[0086] 204 segmented echo plane diffusion-weighted magnetic resonance images to identify high diffusivity regions

[0087] 206 segmented fat-suppressed T2-weighted magnetic resonance images to identify tissue regions

[0088] 208 By inputting high-diffusion-rate regions and tissue regions into the image processing module, a portion of the tissue region is identified as the consultation region.

[0089] 210. Provide the consultation area for segmentation of fat-suppressed T2-weighted magnetic resonance images.

[0090] 300 Medical System

[0091] 302 Magnetic Resonance Imaging System

[0092] 304 magnet

[0093] 306 Magnet Chamber

[0094] 308 Imaging Area

[0095] 309 Areas of Interest

[0096] 310 Magnetic Gradient Coil

[0097] 312 Magnetic Gradient Coil Power Supply

[0098] 314 RF coil

[0099] 316 transceiver

[0100] 318 Objects

[0101] 320 Object Support

[0102] 330 First Pulse Sequence Command

[0103] 332 First k-space data

[0104] 334 Second Pulse Sequence Command

[0105] 336 Second k-space data

[0106] 338 Conductivity Diagram

[0107] 400 Overlay Area Detailed Implementation

[0108] In these figures, elements with similar numbers are either equivalent elements or perform the same function. If the functions are equivalent, elements already discussed will not need to be discussed in later figures.

[0109] Figure 1An example of a medical system 100 is illustrated. In this example, the medical system 100 includes a computer having a computing system 106. Computer 102 may represent one or more computer systems networked together. Computing system 106 may, for example, represent one or more processors, microcontrollers, or field-programmable gate arrays. Computing system 106 is shown as being connected to optional hardware interface 104, optional user interface 108, and memory 110. Hardware interface 104 may be used by computing system 106, for example, to control other components of medical system 100 (if such components are present). User interface 108 may, for example, provide an operator with a means to control medical system 100 and display magnetic resonance images or other data. Memory 110 represents any type of memory that can be accessed by computing system 106. For example, the contents of memory 110 may be partitioned among multiple storage devices or memory units.

[0110] Memory 110 is shown to contain machine-executable instructions 120. The machine-executable instructions 120 contain instructions that enable the computing system 106 to control the operation and functions of the medical system 100, as well as to control any other additional components. The machine-executable instructions 120 also enable the computing system 106 to perform various mathematical operations, data processing tasks, and image processing tasks. Memory 110 is also shown to contain echo-plane diffusion-weighted magnetic resonance images 122. Memory 110 is also shown to contain fat-suppressed T2-weighted magnetic resonance images 124.

[0111] Memory 110 is shown as containing an optional registration 126 between echo-plane diffusion-weighted magnetic resonance image 122 and fat-suppressed T2-weighted magnetic resonance image 124. In some instances, the two magnetic resonance images 122 and 124 can be acquired such that there is a one-to-one relationship between their voxels. In other instances, the object may have been moved and registration 126 may contain an image so that the data between the two can be used. It should also be noted that the echo-plane diffusion-weighted magnetic resonance image 122 may be distorted, in which case a slight deviation from the registration will not adversely affect the operation of medical system 100. This may also make the registration unnecessary.

[0112] The memory 110 is also shown to contain a plurality of high diffusivity regions 128 already identified in the echo-plane diffusion-weighted magnetic resonance image 122. This can be performed, for example, by thresholding the diffusivity according to a predetermined threshold for diffusion. The memory 110 is also shown to contain tissue regions 130 identified in the fat-suppressed T2-weighted magnetic resonance image 124. The tissue regions 130 may be, for example, non-fatty or non-adipose tissue regions of the tissue location of the identified object. The memory 110 is also shown to contain an image processing module 132. The image processing module 132 outputs a plurality of consultation regions 134 selected from the tissue regions 130. They are selected by associating or matching the high diffusivity regions 128 with the tissue regions 130. The memory 110 is also shown to contain an optional enhanced T2-weighted magnetic resonance image 136, which shows the consultation regions 134 superimposed or emphasized on the fat-suppressed T2-weighted magnetic resonance image 124.

[0113] Figure 2 The illustrated operation is shown. Figure 1 The flowchart describes a method for a medical system 100. First, in step 200, an echo-plane diffusion-weighted magnetic resonance (ECL) image 122 is received. Next, in step 202, a fat-suppressed T2-weighted ECL image 124 is received. Then, in step 204, the ECL image 122 is segmented to identify high-diffusion regions 128. Next, in step 206, the fat-suppressed T2-weighted ECL image 124 is segmented to identify tissue regions 130. In step 208, the high-diffusion regions 128 and tissue regions 130 are input to an image processing module 132 to provide or identify a portion of the tissue region 130 as a consultation region 134. Finally, in step 210, the consultation region 134 is provided as a segment of the fat-suppressed T2-weighted ECL image.

[0114] Figure 3 The illustration shows another example of a medical system 300. Figure 3 The medical system in 300 is similar to Figure 1 The medical system 100 includes, in addition to, a magnetic resonance imaging system 302 that can be controlled by a computing system 106.

[0115] The magnetic resonance imaging system 302 includes a magnet 304. Magnet 304 is a superconducting cylindrical magnet with a bore 306 passing through it. It is also possible to use different types of magnets; for example, both split cylindrical magnets and so-called open magnets may be used. A split cylindrical magnet is similar to a standard cylindrical magnet, except that the cryostat has been split into two segments to allow for approach to the equiplanar plane of the magnet. This type of magnet can be used, for example, in conjunction with charged particle beam therapy. An open magnet has two magnet segments, one on top of the other, with a sufficiently large space between them to receive the object: the arrangement of the two segments is similar to the arrangement of Helmholtz coils. Open magnets are common because the object is less constrained. A series of superconducting coils are present inside the cryostat of the cylindrical magnet.

[0116] An imaging region 308 is located within the bore 306 of a cylindrical magnet 304, wherein the magnetic field is sufficiently strong and uniform to perform magnetic resonance imaging. A region of interest 309 is shown within the imaging region 308. Magnetic resonance data is acquired from the region of interest. An object 318 is shown supported by an object support 320 such that at least a portion of the object 318 is within the imaging region 308 and the region of interest 309. Within the region of interest 309, breast tissue of the object 318 can be observed.

[0117] Within the bore 306 of the magnet, there is also an assembly of magnetic field gradient coils 310, which are used to acquire preliminary magnetic resonance data for spatial encoding of the magnetic spins within the imaging region 308 of the magnet 304. The magnetic field gradient coils are connected to a magnetic field gradient coil power supply 312. The magnetic field gradient coils 310 are intended to be representative. Typically, a magnetic field gradient coil comprises three separate coil assemblies for spatial encoding in three orthogonal spatial directions. The magnetic field gradient coil power supply 312 supplies current to the magnetic field gradient coils. The current supplied to the magnetic field gradient coils 310 is controlled according to time, and this current can be either slanted or pulsed.

[0118] Adjacent to the imaging region 308 is an RF coil 314, which is used to manipulate the orientation of magnetic spins within the imaging region 308 and to receive radio transmissions from spins also within the imaging region. The RF antenna may comprise multiple coil elements. The RF antenna may also be referred to as a channel or antenna. The RF coil 314 is connected to an RF transceiver 316. The RF coil 314 and RF transceiver 316 may be replaced by separate transmit and receive coils, and separate transmitters and receivers. It should be understood that the RF coil 314 and RF transceiver 316 are representative. The RF 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 RF coil 314 may also have multiple receive / transmit elements, and the RF transceiver 316 may have multiple receive / transmit channels. For example, if a parallel imaging technique such as SENSE is performed, the RF coil 314 will have multiple coil elements.

[0119] Transceiver 316 and gradient controller 312 are shown as hardware interface 106 connected to computer system 102.

[0120] The memory 110 is also shown to contain a first pulse sequence command 330, configured to acquire first k-space data according to an echo-plane diffusion-weighted magnetic resonance imaging (ECMA) protocol. The memory 110 is also shown to contain first k-space data 332 acquired by controlling the magnetic resonance imaging system 302 using the first pulse sequence command 330. An echo-plane diffusion-weighted magnetic resonance image 122 is reconstructed from the first k-space data 332. The memory 110 is also shown to contain a second pulse sequence command 334. The second pulse sequence command 334 is configured to acquire second k-space data according to a T2-weighted magnetic resonance imaging (T2) protocol.

[0121] exist Figure 3 In the illustrated example, the second pulse sequence command 334 is configured to acquire phase measurements suitable for electrical tomography. Memory 110 is shown to contain second k-space data 336 acquired by controlling the magnetic resonance imaging system 302 using the second pulse sequence command 334. The second k-space data 336 is used to reconstruct a fat-suppressed T2-weighted magnetic resonance image 124 and a conductivity map 338. The conductivity map 338 is shown to be stored in memory 110.

[0122] Magnetic resonance (MR) methods used in breast cancer research are typically based on the administration of contrast agents (e.g., for dynamic contrast-enhanced (DCE) imaging), which is considered a major drawback of MR-based general breast cancer screening.

[0123] Electrical conductivity computed tomography (EPT) may generally have the same potential for characterizing breast lesions as direct cerebral chemoradiography (DCE). However, in the prior art, the determination of conductivity requires the support of contrast agents for reliable tumor boundary detection; therefore, a contrast agent-free version of EPT for breast cancer remains lacking.

[0124] Examples may include (a) performing a first high-sensitivity MR sequence A 330 (e.g., high b-value EPI-DWI) that shows only tumor tissue but with geometric distortion (echo plane diffusion-weighted MRI image 122), (b) performing a second MR sequence B 334 (e.g., fat-suppressed T2-weighted imaging) suitable for EPT that shows many potential lesions but without geometric distortion (fat-suppressed T2-weighted MRI image), (c) identifying the correct tumor lesion of sequence B by searching for the maximum geometric superposition between the distorted lesion of sequence A and the potential lesion of sequence B (identifying consultation area 134), and optionally (d) characterizing the type of tissue by its conductivity reconstructed from sequence B.

[0125] The primary potential of EPT is not tumor identification (localization), but rather the potential characterization of suspicious consultation areas or tumors. Tumor identification / localization is typically performed by DCE. An example suggests replacing DCE with a first sequence (Sequence A). Sequence A has similar sensitivity to DCE, as given, for example, by EPI-based diffusion-weighted imaging (DWI) with high b-values. In the second step, potential lesions identified by EPI-DWI are characterized by EPT. Since EPT cannot be performed by post-processing EPI-DWI, a second dedicated EPT scan is required (Sequence B, e.g., fat-suppressed T2-weighted (T2w) imaging). To enable EPT, Sequence B has a phase that (i) is fully correlated with B1 and (ii) has sufficient intrinsic contrast between tumor versus fat and tumor versus glandular tissue.

[0126] (i) A fully B1-related phase can be given by a spin-echo-based sequence, a sequence with a balanced gradient (steady-state free precession), or an ultrashort / zero TE sequence. Multi-echo gradient echo sequences, in principle, allow voxel-by-voxel extrapolation of phase evolution to a TE = 0 equivalent to the B1-related phase; however, this requires potentially unstable and therefore error-prone extrapolation algorithms.

[0127] (ii) Sufficient intrinsic contrast between tumor and fat versus tumor and glandular tissue can be beneficial because the numerical differentiation of the phase requires an ensemble of neighboring voxels around the target voxel (the so-called “core”), which preferably contains only voxels with similar conductivity. Therefore, prior knowledge of the tumor boundaries is needed to locally shape the core to remain within the tumor volume. These tumor boundaries can be obtained from different scans. However, obtaining tumor boundaries and phase from individual scans is always problematic due to the risk of imperfect image registration. Especially for small tumors, incorrectly including only a few misregistered non-tumor voxels can significantly distort conductivity results.

[0128] Figure 4 The illustration shows one way to identify consultation area 134. Figure 4 A sketch representing fat-suppressed T2-weighted magnetic resonance image 124 is shown. Regions labeled 130 and 134 represent tissue region 130. Region 128 represents a high-diffusion region identified in echo-plane diffusion-weighted magnetic resonance image 122. Echo-plane diffusion-weighted magnetic resonance image 122 contains distortion and cannot definitively identify the location of consultation region 134. Examining this reveals an overlapping region 400 between curves 128 and 134. Region 134 is then identified as the consultation region. A comparison of the two clearly shows that region 134 is a region with high diffusion and therefore should be further investigated by a physician.

[0129] The superimposed region 400 can be compared to the area of ​​curve 134. If this exceeds a certain fraction, then this can be a pre-defined superimposed region, which can be used to trigger the identification of consultation region 134. Similarly, the centers or centroids of regions 128 and 134 can be identified, and the distances between them can be compared. (Similar checks...) Figure 4 It can be seen that the volume of region 128 is most similar to that of region 134. This could also be an alternative method for identifying consultation region 134. It can also be seen that, when compared with other tissue regions 130, the shape of region 128 is most similar to that of region 134. Therefore, the shape or deformation required to match region 128 to 134 could also be used to identify consultation region 134.

[0130] Although the invention has been described and illustrated in detail in the accompanying drawings and the foregoing description, such description and illustration are to be regarded as illustrative or exemplary rather than restrictive; the invention is not limited to the disclosed embodiments.

[0131] Those skilled in the art, through studying the accompanying drawings, description, and claims, will be able to understand and implement other variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the words "a" or "an" do not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. Although specific elements are recited in dissimilar dependent claims, this does not indicate that combinations of these elements cannot be advantageously used. Computer programs may be stored and / or distributed on suitable media, such as optical storage media or solid-state media provided with or as part of other hardware, but computer programs may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. No reference numerals in the claims shall be construed as limiting the scope.

Claims

1. A medical system (100, 300), comprising: Memory (110) storing machine-executable instructions (120). A computing system (106) configured to control the medical system, wherein the execution of machine-executable instructions enables the computing system to: Receive (200) echo-plane diffusion-weighted magnetic resonance images (122) describing the region of interest (309) of breast tissue; Receive (202) a fat-suppressed T2-weighted magnetic resonance image (124) describing the region of interest; The echo plane diffusion-weighted magnetic resonance image is segmented (204) to identify high diffusion rate regions (128), wherein the high diffusion rate region is a region with a diffusion rate higher than a predetermined diffusion rate threshold; Segment (206) the fat-suppressed T2-weighted magnetic resonance images to identify tissue regions (130); By inputting the high diffusion rate region and the tissue region into the image processing module, a portion of the tissue region is identified (208) as the consultation region (134). Receive a conductivity map (338) describing the region of interest. The conductivity map is used to calculate the conductivity measure of each consultation area within the consultation area; The type of each consultation area in the consultation area is assigned according to the conductivity measure; and The consultation area is provided (210) as a segmentation of the fat-suppressed T2-weighted magnetic resonance image.

2. The medical system according to claim 1, wherein, The echo plane diffusion-weighted magnetic resonance image is a high b-value echo plane diffusion-weighted magnetic resonance image.

3. The medical system according to claim 1 or 2, wherein, The medical system further includes a magnetic resonance imaging system configured to acquire k-space data from an imaging region, wherein the memory further contains a first pulse sequence command (330) and a second pulse sequence command (334), wherein the first pulse sequence command is configured to acquire first k-space data (332) according to an echo-plane diffusion-weighted magnetic resonance imaging protocol, wherein the second pulse sequence command is configured to acquire second k-space data (336) according to a T2-weighted magnetic resonance imaging protocol, wherein the second pulse sequence command is based on an electrical properties computed tomography (EMC) magnetic resonance imaging protocol, wherein the second pulse sequence command is fat-suppressed, wherein the execution of the machine-executable instructions further enables the computing system to: The magnetic resonance imaging system is controlled to acquire the first k-space data from the region of interest containing the breast tissue by using the first pulse sequence command; The magnetic resonance imaging system is controlled to acquire the second k-space data from the region of interest containing the breast tissue by using the second pulse sequence command; The echo plane diffusion-weighted magnetic resonance image is reconstructed based on the first k-space data; The fat-suppressed T2-weighted magnetic resonance image is reconstructed based on the second k-space data; and The conductivity map describing the region of interest is reconstructed based on the second k-space data (338).

4. The medical system according to claim 3, wherein, The first pulse sequence command is configured to acquire pulses with a frequency of 0 s / mm. 2 With 3000s / mm 2 The first k-space data between the b values.

5. The medical system according to claim 4, wherein, The first pulse sequence command is configured to acquire pulses with a speed of 800 s / mm. 2 With 1600s / mm 2 The first k-space data between the b values.

6. The medical system according to claim 5, wherein, The first pulse sequence command is configured to acquire pulses with a speed of 1200 s / mm. 2 With 1400s / mm 2 The first k-space data between the b values.

7. The medical system according to claim 3, wherein, The second pulse sequence command is any one of the following: Spin echo pulse sequence command; Ultrashort echo time pulse sequence command; Zero-echo time pulse sequence command; Multi-echo gradient echo pulse sequence command; Balanced gradient echo pulse sequence command; as well as Steady-state free precession pulse sequence command.

8. The medical system according to claim 3, wherein, The consultation area is used to define boundaries during the calculation of the conductivity map.

9. The medical system according to claim 1 or 2, wherein, The execution of the machine-executable instructions also causes the computing system to plot the consultation area as a superposition on the fat-suppressed T2-weighted magnetic resonance image.

10. The medical system according to claim 9, wherein, The execution of the machine-executable instructions also enables the computing system to sort the drawing of the consultation area using the conductivity measure.

11. The medical system according to claim 1 or 2, wherein, The high diffusion rate region is identified by thresholding the echo plane diffusion-weighted magnetic resonance image.

12. The medical system according to claim 1 or 2, wherein, The image processing module is configured to identify the consultation area algorithmically by performing any of the following: If an organization region in the organization region has a superposition (400) with any high diffusion rate region in the high diffusion rate region that is higher than the predetermined superposition, then the organization region in the organization region is identified as a consultation region in the consultation region; If a center distance between an organization region and any high diffusion rate region in the high diffusion rate region is less than a predetermined distance, then the organization region in the organization region is identified as a consultation region in the consultation region. If one of the tissue regions has a volume that matches any high diffusivity region within a predetermined volume difference, then that one tissue region in the tissue region is identified as a consultation region in the consultation region. If one of the tissue regions has a shape that matches any high-diffusion-rate region within a predetermined deformation, then that one tissue region in the tissue region is identified as a consultation region in the consultation region. as well as Their combination.

13. The medical system according to claim 1 or 2, wherein, The image processing module is a trained neural network configured to mark a portion of the tissue region as a consultation region in response to input of the tissue region and the high diffusion rate region.

14. The medical system according to claim 1 or 2, wherein, The tissue region in question is a non-adipose tissue region.

15. A computer program product comprising machine-executable instructions (120) for execution by a computing system (106), wherein, The execution of the machine-executable instructions enables the computing system to: Receive (200) echo-plane diffusion-weighted magnetic resonance images (122) describing the region of interest (309) of breast tissue; Receive (202) a fat-suppressed T2-weighted magnetic resonance image (124) describing the region of interest; The echo plane diffusion-weighted magnetic resonance image is segmented (204) to identify high diffusion rate regions (128), wherein the high diffusion rate region is a region with a diffusion rate higher than a predetermined diffusion rate threshold; Segment (206) the fat-suppressed T2-weighted magnetic resonance images to identify tissue regions (130); By inputting the high-diffusion-rate region and the tissue region into the image processing module, a portion of the tissue region is identified (208) as the consultation region (134); and Receive a conductivity map (338) describing the region of interest. The conductivity map is used to calculate the conductivity measure of each consultation area within the consultation area; The type of each consultation area in the consultation area is assigned according to the conductivity measure; and The consultation area is provided (210) as a segmentation of the fat-suppressed T2-weighted magnetic resonance image.

16. A medical imaging method, wherein, The method includes: Receive (200) echo-plane diffusion-weighted magnetic resonance images (122) describing the region of interest (309) of breast tissue; Receive (202) a fat-suppressed T2-weighted magnetic resonance image (124) describing the region of interest; The echo plane diffusion-weighted magnetic resonance image is segmented (204) to identify high diffusion rate regions (128), wherein the high diffusion rate region is a region with a diffusion rate higher than a predetermined diffusion rate threshold; Segment (206) the fat-suppressed T2-weighted magnetic resonance images to identify tissue regions (130); By inputting the high diffusion rate region and the tissue region into the image processing module, a portion of the tissue region is identified (208) as the consultation region (134). Receive a conductivity map (338) describing the region of interest. The conductivity map is used to calculate the conductivity measure of each consultation area within the consultation area; The type of each consultation area in the consultation area is assigned according to the conductivity measure; and The consultation area is provided (210) as a segmentation of the fat-suppressed T2-weighted magnetic resonance image.

Images