Reconstruction parameter determination for synthetic magnetic resonance image reconstruction.

Abstract

Disclosed herein is a medical system 100, 300 having a memory 110 storing machine-executable instructions 120 and an anatomical detection module 122, and a computing system 104. Execution of the machine-executable instructions causes the computing system to perform steps 200 of receiving a set of magnetic resonance images 124 depicting a field of view 109 of a subject 318 acquired according to a composite magnetic resonance imaging protocol, 202 receiving an anomaly indicator 126 from the anomaly detection module in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module, 204 determining a set of reconstruction parameters 128 using the anomaly indicator, and 206 reconstructing a composite magnetic resonance image 134 from the set of magnetic resonance images and the set of reconstruction parameters.

Description

[Technical Field]

[0001] The present invention relates to magnetic resonance imaging, and in particular to compound or composite magnetic resonance imaging. [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 procedure to generate 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 spatially measured and imaged using MRI. A difficulty in performing magnetic resonance imaging is the time required to acquire the k-space data needed to reconstruct the magnetic resonance image. Summary of the Invention [Problem to be solved by the invention]

[0003] When k-space data is acquired, different imaging protocols can be used to weight the image differently. For example, magnetic resonance images can be weighted to indicate proton density, spatial variations in T1, or spatial variations in T2 or T2*. These different weightings are commonly referred to as "contrasts" or "contrast types," and physicians and other medical professionals are accustomed to seeing specific "contrasts." Other imaging techniques, such as magnetic resonance imaging fingerprinting (MRF) or synthetic magnetic resonance imaging (SyntAC or 3D-QALAS), have been developed in recent years. In these techniques, k-space data is used to acquire images that can be used to construct composite or map images that mimic or reproduce common or standard "contrasts."

[0004] In synthetic magnetic resonance imaging, a set of magnetic resonance images depicting a field of view describing an object is received. This series of magnetic resonance images represents an essentially standardized acquisition (for a particular synthetic MR reconstruction) that provides data that can be used to calculate spatially varying quantitative maps describing the object. These quantitative maps then provide sufficient information to simulate other magnetic resonance images using the MR signal equation. Two techniques that make this possible are magnetic resonance fingerprinting (MRF) and synthetic magnetic resonance imaging (SyntAc or 3D-QALAS).

[0005] U.S. Patent Application Publication No. 2021174937A1 discloses a diagnostic apparatus for medical diagnosis of raw medical imaging data generated by a medical imaging device, as opposed to medical diagnosis of conventional reconstructed medical images reconstructed from the raw medical imaging data. In operation, the raw diagnostic engine has a medical imaging diagnostic controller that implements a dimensionality reduction preprocessor for selecting or extracting one or more dimensionally reduced feature vectors from the raw medical imaging data, and further implements a raw diagnostic artificial intelligence engine for performing a diagnostic evaluation of the raw medical imaging data represented by the dimensionality reduced feature vectors. The medical imaging diagnostic controller can further control communication (e.g., display, printing, email, text conversion, etc.) of the diagnostic evaluation of the raw medical imaging data.

[0006] The paper Baur, et. al., "Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study," arXiv 2004.03271, https: / / doi.org / 10.48550 / arXiv.2004.03271, provides a detailed description of the use of variational autoencoders to segment anomalies in MRI brain images. [Means for solving the problem]

[0007] The present invention provides a medical system, a computer program and a method in the independent claims. Embodiments are set out in the dependent claims.

[0008] Various synthetic or composite magnetic resonance imaging techniques generally allow for the reconstruction of various types of synthetic magnetic resonance images that are modeled after the actual magnetic resonance imaging acquisition. This includes the ability to model the selection of various reconstruction parameters, such as the echo time (TR) or repetition time (TR) set when acquiring the k-space data, or the selection of the pulse sequence type used to acquire the k-space data. The selection of these parameters affects the image contrast in the image and ultimately affects what type of anatomical structures are visible in the synthetic magnetic resonance image.

[0009] Correctly setting the reconstruction parameters to ensure that abnormalities are visible or optimally visualized in the composite magnetic resonance image can involve trial and error. Abnormalities include anatomical abnormalities or abnormal tissue pathology, or abnormal tissue structures or characteristics, such as white matter hyperintensities. Embodiments can provide a means for automatically determining a set of reconstruction parameters for the composite magnetic resonance image. This can be achieved by using an anomaly detection module configured to receive a set of magnetic resonance images (or a subset of these images) and output an anomaly indicator. The anomaly indicator is then used to determine a set of reconstruction parameters that are optimized or selected to display the detected anomaly in the reconstructed composite magnetic resonance image.

[0010] The concept of interactively generating synthetic contrast relies on providing the radiologist with a set of parameters for a particular map and then reviewing several images for pathology assessment and identification, resulting in a time-consuming workflow.

[0011] For example, the workflow for reading synthetic MRI images can be accelerated by selecting predefined standard synthetic sequences or parameters specific to synthetic contrast based on anomaly detection in quantitative sequences, which allows optimal visualization of lesions and rapid visual assessment, improving the radiologist's workflow.

[0012] Embodiments may include one or more of the following subsequent work steps, which will be described in more detail below:

[0013] 1. Anomaly Detection: AI-based anomaly detection using quantitative SyntAc images can be performed using various approaches: (i) anatomical structure-based anomaly detection that analyzes symmetrized contrast between the left and right hemispheres, or other known approaches such as variational autoencoders. In the case of SyntAc in particular, voxel-wise anomalies can be further derived from deviations from the brain's normal tissue characteristics, as seen in the lower left portion of Figure 1. All approaches can ultimately generate maps showing voxel-wise anomalies, which can also be post-processed with filtering techniques to remove artifacts from the detected anomalies. In this optional step, standard image processing algorithms such as thresholding, smoothing, and filtering are applied. The generation of symmetrized contrast involves (a) mesh-based image warping of the segmented scan to a symmetric template; (b) L / R flipping the resulting anatomically symmetric image; (c) computing a difference image between the results of (a) and (b); and (d) using the (symmetric) difference image and the symmetric image of the brain as inputs to a convolutional neural network to indicate (1) areas where abnormal contrast changes remain and (2) the side on which the lesion occurs. Symmetrized contrast is the contrast distribution of the image that is symmetrized from the asymmetric original version.

[0014] 2. Derivation of optimal sequence parameters for synthetic contrast generation. Based on the results of step 1, the parameters for generating synthetic contrast (TE, TR, and TI) are determined to maximize the range of gray values ​​in the region suspected to be abnormal, thereby making the abnormality prominently displayed.

[0015] 3. Optionally, these parameters can be optimized individually for each suspected pathology in the image, rather than for the complete volume, and the final composite image can be merged by interpolation to provide the best representation of each suspected pathology.

[0016] In one aspect, the present invention provides a medical system having a memory storing machine-executable instructions and an anatomical detection module. The medical system further includes a computing system. Upon execution of the machine-executable instructions, the computing system receives a set of magnetic resonance images depicting a field of view of a subject acquired according to a synthetic magnetic resonance imaging protocol. The synthetic magnetic resonance imaging protocol can specify acquisition parameters used to acquire the set of magnetic resonance images and / or reconstruction techniques used in reconstructing the set of magnetic resonance images.

[0017] Execution of the machine-executable instructions further causes the anomaly detection module to receive an anomaly indicator from the anomaly detection module in response to inputting at least one magnetic resonance image from the set of magnetic resonance images. The anomaly indicator may take different forms in different instances. In some cases, the anomaly indicator may simply indicate, as a label, that an anomaly exists in the set of magnetic resonance images. For example, the set of magnetic resonance images may indicate that a particular type of tumor or abnormal tissue structure is present.

[0018] In this case, the anomaly indicator may not provide an indication of where the anomaly is located within the field of view. In other examples, the anomaly indicator may provide a location box or bounding box within the field of view to indicate where the anomaly is located. In yet other examples, the anomaly indicator may provide an indicator or bounding box for the location of the anomaly as well as a label for the type or identification of the anomaly type.

[0019] Execution of the machine-executable instructions further causes the computing system to determine a set of reconstruction parameters using the anomaly indicator. As used herein, a set of reconstruction parameters refers to instructions or details used to reconstruct a composite magnetic resonance image from a set of magnetic resonance images. For example, in the well-known SyntAC or 3D-QALAS techniques, known T1, T2, and proton density values ​​are used to generate a composite contrast-enhanced image. The reconstruction parameters in this case may be, for example, TE and TR times. This may depend, for example, on the various models used to reconstruct the composite magnetic resonance image.

[0020] However, the set of reconstruction parameters can be selected so that the composite magnetic resonance image has the anomaly highlighted or displayed in an easily accessible manner. Determining the set of reconstruction parameters can be done in various ways. For example, if the anomaly indicator includes an indication of the type of anomaly, the set of reconstruction parameters can simply be recalled from a lookup table or database. In another example, if the anomaly indicator indicates a location, reconstruction of the composite magnetic resonance image can be performed in an iterative manner so that various image parameters, such as contrast distribution, within the identified region where the anomaly is located conform to a predetermined range or set of values. That is, determining the set of reconstruction parameters can be implemented, for example, by machine-executable instructions.

[0021] Execution of the machine-executable instructions further causes the computing system to reconstruct a composite magnetic resonance image from the set of magnetic resonance images and the set of reconstruction parameters. This embodiment is advantageous because the reconstruction of the composite magnetic resonance image can be controlled or guided so that anomalies detected by the anomaly detection module can be displayed in a manner that highlights or reveals the structure of the anomaly. For example, regions containing anomalies may have their contrast maximized, thus presenting the structure of the anomaly in detail on a particular display or graphic type.

[0022] In another embodiment, the field of view depicts the right and left hemispheres of the subject's brain. The abnormality indicator includes one or more anatomically anonymous locations within the field of view. The abnormality detection module is further configured to spatially locate one or more abnormalities within the subject's brain using symmetrical contrast between the right and left hemispheres of the subject's brain. It is expected that there may be similarities in the anatomical structures of the left and right hemispheres of the subject's brain. An abnormal structure, such as a tumor, may cause a large asymmetry between the right and left hemispheres of the subject's brain. The symmetrical contrast between the right and left hemispheres of the brain can be used to identify such types of abnormalities.

[0023] In another embodiment, the anomaly indicator comprises one or more anatomically abnormal locations within the field of view. The anomaly detection module comprises an autoencoder neural network configured to output an autoencoded image for each magnetic resonance image of at least one of a set of magnetic resonance images. Receiving the anomaly indicator in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module comprises receiving the autoencoded image in response to inputting the at least one set of magnetic resonance images to the autoencoder neural network. Receiving the anomaly indicator in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module further comprises determining the one or more anatomically abnormal locations by comparing the autoencoded image of the at least one magnetic resonance image of the set of magnetic resonance images with at least one of the set of magnetic resonance images.

[0024] In this embodiment, an autoencoder is used to generate an image in response to receiving at least one magnetic resonance image of a set of magnetic resonance images as input to the autoencoder network. The autoencoder is expected to generate an identical image after each image is taken. If the autoencoder is trained to use only anatomically correct images, the autoencoder can generate an error when it encounters an abnormality. Thus, comparison between the input image and the output image can provide a means to easily identify anatomically abnormal regions.

[0025] An autoencoder can be any autoencoder architecture that can take an image as input and output an autoencoder version of the same image as output. There can be multiple inputs and outputs for each image. Alternatively, a series of autoencoders can be used, one for each image in a set of images. The autoencoder can be, for example, a fully connected autoencoder, a sparse autoencoder, a deep (fully connected) autoencoder, a convolutional autoencoder, or a variational autoencoder.

[0026] The training data for these autoencoders can be sets of magnetic resonance images that do not contain anomalies. During training, images are input to the autoencoder and its output can be compared with the input images.

[0027] In another embodiment, execution of the machine-executable instructions further causes the computing system to iteratively vary the set of reconstruction parameters and reconstruct a composite magnetic resonance image to adjust the image contrast of one or more anatomical abnormality locations relative to their surroundings in the image to have a predetermined image contrast range. In this embodiment, determination of the set of reconstruction parameters occurs simultaneously with the reconstruction. Once the abnormality locations are determined, predetermined image contrast ranges for these locations can be defined. Reconstruction can begin with seed values ​​for the reconstruction parameters, which are varied until the predetermined image contrast range is achieved within these regions.

[0028] In another embodiment, the anomaly indicator indicates multiple locations of the anatomical anomaly. A composite magnetic resonance image is reconstructed for each of the multiple locations of the anatomical anomaly, resulting in a set of composite magnetic resonance images. In this embodiment, the anomaly indicator indicates or locates multiple regions of the field of view where an anomaly may exist within the field of view. Because there are multiple locations, there is a composite magnetic resonance image reconstructed for each of these locations. For example, an image can be generated for each of these locations having a predetermined image contrast range.

[0029] In another embodiment, execution of the machine-executable instructions further causes the computing system to construct a composite image from the set of composite magnetic resonance images by including anatomically abnormal locations from each of the set of composite magnetic resonance images and blending pixel values ​​of the anatomically abnormal locations from each of the set of composite magnetic resonance images. Displaying the set of composite magnetic resonance images may not be convenient. In this embodiment, the set of composite magnetic resonance images is used to generate a single composite image. The composite image is formed by including anatomically abnormal locations from each of these images, i.e., by taking abnormal images from the field of view and pasting them together to generate the composite image. Pixel values ​​are blended between these anatomically abnormal locations. This example can take different forms in different examples. Images providing multiple anatomically abnormal locations can have their values ​​averaged or blended to transition smoothly from one image contrast range to the next.

[0030] In another embodiment, execution of the machine-executable instructions further causes the computing system to display the composite image on a graphical user interface. Execution of the machine-executable instructions further causes the computing system to receive a selection of an anatomically abnormal location within the composite image from the graphical user interface, and then display a composite magnetic resonance image including the selected anatomically abnormal location. This embodiment provides a means for selecting one of a set of composite magnetic resonance images. However, the composite image displayed on the graphical user interface may be different or unusual for a physician or other healthcare provider. The physician or other healthcare provider can then select a particular anatomically abnormal location (referred to as selecting an anatomically abnormal location) and then use this to select a particular composite magnetic resonance image from the set of composite magnetic resonance images. In this manner, the physician or other healthcare provider can easily use the composite image to select an image to review.

[0031] In another embodiment, the anatomical detection module includes a convolutional neural network configured to output an anomaly classification as an anomaly indicator in response to receiving at least one of the sets of magnetic resonance images. In this embodiment, instead of assigning a location, a label is assigned to the set of magnetic resonance images. An example of this may indicate a specific anomaly type or a specific tumor type. Knowledge of this specific anomaly type can then be used to select a set of reconstruction parameters. For example, it may be known from previous experience or from previous reconstructions what type of reconstruction parameter set can be used for a specific anomaly classification.

[0032] The convolutional neural network may use a neural network architecture configured to receive one or more images as input and output labels. For example, a deep convolutional neural network (DCCN) architecture may be used. The convolutional neural network may be trained by inputting a set of neural networks labeled with anomalies.

[0033] In another embodiment, the anatomical detection module includes a variational autoencoder neural network having a latent space, and is configured to output an anomaly classification as an anomaly indicator. Receiving the anomaly indicator in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module includes inputting at least one magnetic resonance image of the set of magnetic resonance images to the variational autoencoder and determining an anomaly classification using an out-of-distribution detection method on the latent space of the variational autoencoder.

[0034] An autoencoder uses two neural network sections: the first, encoding section, encodes an input image into a vector in a so-called latent space. The vector in the latent space is then fed into the decoder section of the autoencoder, which, if properly trained, will turn it into the same or a very similar image. During training, a variational autoencoder uses additional constraints on the vectors in the latent space. Typically, vectors in the latent space are assigned a cost or penalty function that tends to push them toward the center. This has the effect of enforcing an order on the positions of vectors in the latent space. By monitoring the latent space while using a variational autoencoder, it is possible to detect when an input image deviates from the learned distribution.

[0035] A variational autoencoder configured to output an autoencoded image for each magnetic resonance image in the magnetic resonance image set, or a group of variational autoencoders, one variational autoencoder for each image in the magnetic resonance image set, can be used. The variational autoencoder or encoder can be trained to reproduce magnetic resonance images without anomalies. Out-of-distribution techniques in the latent space of the variational autoencoder can then be used to detect anomalies.

[0036] In another embodiment, the reconstruction parameters are determined by searching a reconstruction parameter lookup table or reconstruction parameter database using the anomaly classification. In such a case, the label or anomaly classification can be used to retrieve data from the reconstruction parameter lookup table or reconstruction parameter database. The reconstruction parameter lookup table or reconstruction parameter database can be filled by using previous experience in reconstructing images to properly display particular anomalies, such as tumors or other anatomical structures.

[0037] In another embodiment, reconstructing the composite magnetic resonance image includes determining a T1-dependent value (such as a T1 map), a T2-dependent value (such as a T2 map, a T2 star map, an R2 map, or an R2 star map), and a proton density for each voxel of the field of view (by performing voxel-by-voxel processing of the selected signal intensity formula on the set of magnetic resonance images). Reconstructing the composite magnetic resonance image further includes reconstructing the composite magnetic resonance image by calculating a signal intensity value for each voxel using a reconstructed signal intensity formula that has as input the voxel-by-voxel T1-dependent value, the voxel-by-voxel T2-dependent value, and the voxel-by-voxel proton density value, and the reconstruction parameters.

[0038] In another embodiment, the reconstruction parameters include echo time, repetition time, and preferably inversion delay.

[0039] The above-described embodiments relating to constructing a synthetic magnetic resonance image from T1-dependent values, T2-dependent values, and proton density may relate to synthetic magnetic resonance imaging, or SyntAc. SyntAc provides a standardized quantitative MR sequence (SyntAc) to be applied to a magnetic resonance imaging system. One of its claims is the derivation of standard contrasts, such as T1-weighted or T2-weighted images, from SyntAc in a post-processing step. However, this is currently done interactively, and finding the best contrast for a particular pathology is time-consuming and not reproducible. The present disclosure proposes automatically finding the best derived contrast through AI-based evaluation of quantitative SyntAc images so that automatically suspected pathologies can be visually confirmed or rejected with a very high degree of confidence.

[0040] Automated detection of brain abnormalities is a top priority for medical representatives aiming for "speed" as their North Star ("personalized exams in under five minutes for every patient with fully automated workflow and decision support").

[0041] Synthetic MR provides a standardized quantitative MR sequence (SyntAc) to be applied. One of its advantages is that standard contrasts, such as T1-weighted or T2-weighted images, can be derived from SyntAc in post-processing steps by freely selecting acquisition-related parameters such as TE, TR, and TI.

[0042] In another embodiment, the set of magnetic resonance images forms a magnetic resonance fingerprint, and a composite magnetic resonance image is reconstructed from the series of magnetic resonance images according to a magnetic resonance fingerprinting protocol.

[0043] During the creation of the magnetic resonance fingerprint, a so-called dictionary or magnetic resonance fingerprint dictionary is used to compare the magnetic resonance fingerprint of each voxel. This allows the calculation of various spatially dependent values ​​such as T1 time, T2 time, and proton density. These values ​​can be used to simulate the magnetic resonance signal and thereby recalculate the synthetic magnetic resonance image.

[0044] In another embodiment, the medical system further comprises a magnetic resonance imaging system, and the memory further comprises pulse sequence commands configured to control the magnetic resonance imaging system to acquire k-space data according to a compound magnetic resonance imaging protocol, and execution of the machine-executable instructions causes the computing system to further acquire the k-space data by controlling the magnetic resonance imaging system with the pulse sequence commands and reconstruct a set of magnetic resonance images from the k-space data, preferably according to the compound magnetic resonance imaging protocol.

[0045] In another aspect, the present invention provides a method of operating a medical system, the method including receiving a set of magnetic resonance images depicting a field of view of a subject acquired according to a composite magnetic resonance imaging protocol. The method further includes receiving an anomaly indicator from an anomaly detection module in response to inputting at least one of the set of magnetic resonance images to the anomaly detection module. The method further includes determining a set of reconstruction parameters using the anomaly indicator. The method further includes reconstructing a composite magnetic resonance image from the set of magnetic resonance images and the set of reconstruction parameters.

[0046] In another aspect, the present invention provides a computer program having machine-executable instructions for execution by a computing system, the computer program further comprising an anatomical detection module for execution by the computing system.

[0047] Execution of the machine-executable instructions causes the computing system to receive a set of magnetic resonance images depicting a field of view of a subject acquired according to a composite magnetic resonance imaging protocol. Execution of the machine-executable instructions also causes the anomaly detection module to receive an anomaly indicator from the anomaly detection module in response to inputting at least one of the set of magnetic resonance images. Execution of the machine-executable instructions also causes the computing system to determine a set of reconstruction parameters using the anomaly indicator. Execution of the machine-executable instructions also causes the computing system to reconstruct a composite magnetic resonance image from the set of magnetic resonance images and the set of reconstruction parameters.

[0048] It should be understood that one or more of the above-described embodiments of the present invention may be combined, provided that the combined embodiments are not mutually exclusive. As will be appreciated by those 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 form, an entirely software form (including firmware, resident software, microcode, etc.), or a combination of software and hardware forms, all of which may be referred to 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 thereon.

[0049] Any combination of one or more computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. As used herein, "computer-readable storage medium" encompasses any tangible storage medium capable of storing instructions executable by a processor or computing system of a computing device. The computer-readable storage medium may also be referred to as a computer-readable non-transitory storage medium. The computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, the computer-readable storage medium may also store data accessible by the computing system of a computing device. Examples of computer-readable storage media include, but are not limited to, floppy disks, magnetic hard disk drives, solid-state hard disks, flash memory, USB thumb drives, random access memory, read-only memory (ROM), optical disks, magneto-optical disks, and computing system register files. Examples of optical disks include compact discs (CDs) and digital versatile discs (DVDs), such as CD-ROM, CD-RW, CD-R, DVD-ROM, DVD-RW, or DVD-R discs. The term computer-readable storage medium also refers to various types of storage media that can be accessed by a computer device over a network or communications link. For example, data can be retrieved via a modem, over the Internet, or over a local area network. Computer-executable code embodied on a computer-readable medium can be transmitted using any suitable medium, including, but not limited to, wireless, wired, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

[0050] A computer-readable signal medium may include a propagated data signal having computer-executable code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium, and such computer-readable medium is not a computer-readable storage medium, but is capable of communicating, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0051] "Computer memory" or "memory" is one example of a computer-readable storage medium. Computer memory is any memory directly accessible to a computing system. "Computer storage" or "storage" is another example of a computer-readable storage medium. Computer storage is any non-volatile computer-readable storage medium. In some embodiments, computer storage may be computer memory, or vice versa.

[0052] 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 possibly including two or more computing systems or processing cores. A computing system may be, for example, a multi-core processor. A computing system may also refer to a collection of computing systems within a single computer system or distributed among multiple computer systems. The term computing system should also be interpreted as referring to a collection or network of computing devices, each of which includes a processor or computing system. Machine-executable code or instructions may be executed by multiple computing systems or processors, which may be within the same computing device or 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 for aspects of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages, such as the "C" programming language or similar programming languages, compiled into machine-executable instructions. In some examples, the computer-executable code may be in the form of a high-level language or pre-compiled, or may be used in conjunction with an interpreter that generates machine-executable instructions on the fly. In other examples, the machine-executable instructions or computer-executable code may form a program for a programmable logic gate array.

[0054] 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 situation, 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 using an Internet Service Provider).

[0055] Aspects of the present invention will be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block or portion of a block in the flowcharts, diagrams, and / or block diagrams, where applicable, can be implemented by computer program instructions in the form of computer-executable code. It will also be understood that blocks in different flowcharts, diagrams, and / or block diagrams can be combined, if not mutually exclusive. These computer program instructions can be provided to a general-purpose computer, special-purpose computer, or other programmable data processing device computing system to generate a machine, such that the instructions, executed via the computer or other programmable data processing device computing system, create means for performing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0056] These machine-executable instructions or computer program instructions may be stored on a computer-readable medium that can cause a computer, other programmable data processing device, or other device to function in a particular manner, such that the instructions stored on the computer-readable medium produce an article of manufacture that includes instructions that implement the functions / acts specified in one or more of the flowcharts and / or blocks.

[0057] Furthermore, the machine-executable instructions or computer program instructions may be loaded into a computer, other programmable data processing device, or other device to cause the computer, other programmable device, or other device to perform a series of operational steps to create a computer-executed process, such that the instructions executing on the computer or other programmable device provide a process for performing the functions / operations specified in one or more blocks of the flowcharts and / or block diagrams.

[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" is also called a "human interface device," and a user interface can provide information or data to an operator and / or receive information or data from an operator. A user interface can allow a computer to receive input from an operator and provide output from the computer to a user. In other words, a user interface can allow an operator to control or manipulate a computer, and an interface can allow a computer to show the effects of the operator's control or manipulation. The display of data or information on a display or graphical user interface is an example of providing information to an operator. Receiving data via a keyboard, mouse, trackball, touchpad, pointing stick, graphics tablet, joystick, gamepad, webcam, headset, pedals, wired gloves, remote control, and accelerometer are all examples of user interface components that allow receiving information or data from an operator.

[0059] As used herein, a "hardware interface" includes an interface that allows a computing system of a computer system to interact with and / or control external computing devices and / or equipment. A hardware interface may allow a computing system to send control signals or instructions to external computing devices and / or equipment. A hardware interface may also allow a computing system to exchange data with external computing devices and / or equipment. Examples of hardware interfaces include, but are not limited to, a universal serial bus, an IEEE 1394 port, a parallel port, an IEEE 1284 port, a serial port, an RS-232 port, an IEEE-488 port, a Bluetooth connection, a wireless local area network connection, a TCP / IP connection, an Ethernet connection, a control voltage interface, a MIDI interface, an analog input interface, and a digital input interface.

[0060] As used herein, "display" or "display device" encompasses an output device or user interface adapted to display images or data. A display can output visual, auditory, 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.

[0061] K-space data is defined herein as the recorded measurements of radio frequency signals emitted by atomic spins using the antenna of a magnetic resonance apparatus during a magnetic resonance imaging scan. Magnetic resonance image data is an example of tomographic medical image data.

[0062] A magnetic resonance imaging (MRI) image or MR image is defined herein as a reconstructed two-dimensional or three-dimensional visualization of anatomical data contained within magnetic resonance imaging data, which visualization can be performed, for example, using a computer. [Brief explanation of the drawings]

[0063] [Figure 1] FIG. 1 is a diagram illustrating an example of a medical system. [Figure 2] 2 is a flow chart illustrating a method of using the medical system of FIG. 1 . [Figure 3] FIG. 10 is a diagram showing another example of a medical system. [Figure 4] 4 is a flow chart illustrating a method of operating the medical system of FIG. 3. [Figure 5] FIG. 10 is a diagram showing an example of an anomaly detection module. [Figure 6] FIG. 10 is a diagram showing an example of a graphical user interface. DETAILED DESCRIPTION OF THE INVENTION

[0064] Preferred embodiments of the present invention will now be described, by way of example only, with reference to the drawings in which:

[0065] Like numbered components in these figures are either equivalent components or perform the same function. An aforementioned component is not necessarily described in a subsequent figure if the functionality is equivalent.

[0066] 1 illustrates an example of a medical system 100. The medical system 100 is shown to include a computer 102. The computer 102 is intended to represent one or more computing devices at one or more locations. The computer also includes a computing system 104, which is intended to represent one or more computing systems or cores located within the one or more computer systems 102. The computing system 104 is shown in communication with an optional hardware interface 106, a user interface 108, and a memory 110. If other components are present, the hardware interface 106 allows the computing system 104 to exchange commands and data with these other components.

[0067] The hardware interface 106 thus allows the computing system 104 to control other components, such as a magnetic resonance imaging system. The user interface 108, if present, may be used to provide a means for interacting with an operator or user and displaying data. Similarly, the medical system 100 can receive control commands from the user interface 108. The memory 110 is intended to represent various types of memory accessible to the computing system 104, e.g., non-transitory storage media.

[0068] The memory is shown as including machine-executable instructions 120. The machine-executable instructions enable the computing system 104 to perform tasks such as controlling other components, performing numerical tasks, and performing basic image processing tasks. The memory 110 is further shown as having an anatomical detection module 122 capable of receiving at least one of the sets of magnetic resonance images 124 and outputting an anomaly indicator 126 in response. The anatomical detection module 122 may be implemented using, for example, either a machine learning module or an algorithm module, or a combination of the two. The memory 110 is further shown as having an anomaly indicator 126 output by the anatomical detection module 122 in response to receiving at least one of the sets of magnetic resonance images 124.

[0069] The memory 110 is shown as optionally including a lookup table 130 or database 130. For example, a particular anomaly indicator 126 can be used as a query to the lookup table or database 130, which can then output a set of reconstruction parameters 128. The memory 110 is further shown as including a reconstruction algorithm 132 used to reconstruct a composite magnetic resonance image 134, which is also stored in the memory. In some cases, the reconstruction algorithm 132 can be iterative and used to generate the set of reconstruction parameters 128 while reconstructing the composite magnetic resonance image 134. For example, the anomaly indicator 126 can represent a region within the field of view of the set of magnetic resonance images 124 that should have a predetermined contrast range. The reconstruction algorithm 132 can then iteratively modify the reconstruction parameters 128 so that the composite magnetic resonance image 134 has the predetermined image contrast range within this region.

[0070] 2 shows a flowchart illustrating a method of operation of the medical system 100 of FIG. 1. First, in step 200, a set of magnetic resonance images 124 is received. These images 124 depict a field of view of a subject acquired according to a composite magnetic resonance imaging protocol. This can mean that the images that make up the set of magnetic resonance images all relate to the same field of view but have different contrasts. Contrast, in relation to magnetic resonance images, refers to a particular set of acquisition and / or reconstruction parameters.

[0071] Next, in step 202, an anomaly indicator 126 is received from the anatomical detection module 122 in response to inputting at least one of the magnetic resonance image sets 124. Next, in step 204, a set of reconstruction parameters 128 is determined using the anomaly indicator 126, which may be, for example, using the iterative reconstruction algorithm 132 described above, as well as using a lookup table or database 130.

[0072] Figure 3 shows another example of a medical system 300. The medical system 300 shown in Figure 3 is similar to the medical system 100 of Figure 1, except that it further includes a magnetic resonance imaging system 302 controlled by the computer system 104.

[0073] The magnetic resonance imaging system 302 includes a magnet 304. The magnet 304 is a cylindrical superconducting magnet with a bore 306 extending therethrough. Different types of magnets can be used; for example, both split-cylinder magnets and so-called open magnets can be used. Split-cylinder magnets are similar to standard cylindrical magnets, except that the cryostat is divided into two sections to allow access to the magnet's isosurface. Such magnets can be used, for example, in conjunction with charged particle beam therapy. Open magnets have two magnet sections, one above the other, with a space between them large enough to accommodate a subject. The arrangement of the two magnet sections resembles a Helmholtz coil. Open magnets are popular because the subject is not enclosed. Inside the cryostat of a cylindrical magnet is a collection of superconducting coils.

[0074] Within the bore 306 of the cylindrical magnet 304 is an imaging zone 308 where the magnetic field is strong and uniform enough to perform magnetic resonance imaging. A field of view 309 is shown within the imaging zone 308. K-space data is typically acquired for the field of view 309. A region of interest may be identical to the field of view 309 or may be a subvolume of the field of view 309. A subject 318 is shown supported by a subject support 320 such that at least a portion of the subject 318 is within the imaging zone 308 and the field of view 309.

[0075] Also within the magnet bore 306 are a set of magnetic field gradient coils 310 used for preliminary k-space data acquisition to spatially encode magnetic spins within the imaging zone 308 of the magnet 304. The magnetic field gradient coils 310 are connected to a magnetic field gradient coil power supply 312. The magnetic field gradient coils 310 are intended to be exemplary. Typically, the magnetic field gradient coils 310 have three separate coil sets for spatial encoding in three orthogonal spatial directions. The magnetic field gradient power supply supplies current to the magnetic field gradient coils 310. The current supplied to the magnetic field gradient coils 310 is controlled as a function of time and may be ramped or pulsed.

[0076] Adjacent to the imaging zone 308 is a radio frequency coil 314 for manipulating the orientation of magnetic spins within the imaging zone 308 and also for receiving radio transmissions from the spins within the imaging zone 308. The radio frequency antenna can have multiple coil elements. The radio frequency antenna can also be referred to as a channel or antenna. The radio frequency coil 314 is connected to a radio frequency transceiver 316. The radio frequency coil 314 and the radio frequency transceiver 316 can be replaced with separate transmit and receive coils and separate transmitters and receivers. It is understood that the radio frequency coil 314 and the radio frequency transceiver 316 are exemplary. The radio frequency coil 314 is also intended to represent a dedicated transmit antenna and a dedicated receive antenna. Similarly, the transceiver 316 can also represent a separate transmitter and receiver. The radio frequency coil 314 can also have multiple receive / transmit elements, and the radio frequency transceiver 316 can have multiple receive / transmit channels. The transceiver 316 and the gradient controller 312 are shown connected to the hardware interface 106 of the computer system 102 .

[0077] The memory 110 is further shown as having pulse sequence commands 330 that enable the computing system 104 to control the magnetic resonance imaging system 302 to acquire k-space data 332 in accordance with a composite magnetic resonance imaging protocol. The pulse sequence commands 330 are commands or data that can be converted into commands that control the timing and function of various components of the magnetic resonance imaging system 302. The memory 110 is further shown as having k-space data 332 acquired by controlling the magnetic resonance imaging system 302 using the pulse sequence commands 330. In this example, a set of reconstruction parameters 128 and a composite magnetic resonance image 134 are iteratively determined.

[0078] The memory 110 is further shown as having a preliminary set of reconstruction parameters 334 used during the reconstruction of a trial magnetic resonance image 336. Within the trial magnetic resonance image 336, an anomaly location 338 is identified. Also within the memory 110 is a calculated image contrast range 340 within the anatomical anomaly location 338 of the trial magnetic resonance image 336. This is compared to a predetermined image contrast range 342. If the calculated image contrast range 340 differs from the predetermined image contrast range 342, the preliminary set of reconstruction parameters 334 can be modified and the trial magnetic resonance image 336 can be recalculated.

[0079] FIG. 4 shows a flowchart illustrating a method of operating the medical system 300 of FIG. 3. First, in step 400, k-space data 332 is acquired by controlling the magnetic resonance imaging system 302 with a pulse sequence command 330. Next, in step 402, a set of magnetic resonance images 124 is reconstructed from the acquired k-space data 332. The method then performs steps 200 and 202 as shown in FIG. 2. Steps 404, 406, 408, 410, and 412 can be used in place of step 204 in FIG. 2. In this example, after step 202 is completed, the process proceeds to step 404. In this case, a preliminary set of reconstruction parameters 334 is set or determined. Next, in step 406, a trial magnetic resonance image 336 is reconstructed from the set of magnetic resonance images 124 and the preliminary set of reconstruction parameters 334.

[0080] The method then proceeds to step 408, which is a question box asking, "Is the calculated image contrast range 340 the same as the predetermined image contrast range 342?" If the answer is yes, the method proceeds to step 410, where a trial magnetic resonance image 336 is provided as the synthetic magnetic resonance image 134. If the answer is no, the method proceeds to step 412, where the preliminary set of reconstruction parameters 334 is modified, and the method returns to step 406, where the trial magnetic resonance image 336 is recalculated. This loop is then repeated until the calculated image contrast range 340 matches the predetermined image contrast range 342.

[0081] 5 illustrates an example of an anatomical detection module 122. The anatomical detection module 122 receives as input a set of magnetic resonance images 124 and outputs an anomaly indicator 126. As discussed above, the anatomical detection module 122 can be implemented as an algorithm, as a trained machine learning module, or as a combination of the two.

[0082] 6 shows an example of a graphical user interface 600 displaying a composite image 602. In this example, the composite image 602 is formed from a set of composite magnetic resonance images, each with its own abnormality location 338. The abnormality locations 338 from each image are displayed within the composite image 602, and the spaces between these abnormality locations in the composite image 602 are formed by blending the individual composite magnetic resonance images. In this user interface, when a user selects one of the anatomical abnormality locations 338, the image in which the anatomical abnormality location 338 was captured is displayed. Thus, this graphical user interface 600 can be used to quickly display various anatomical abnormality locations 338 and to select more clinically relevant images for a physician or medical professional to review.

[0083] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive. The invention is not limited to the disclosed embodiments.

[0084] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprise" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain means are recited in mutually different dependent claims does not indicate that a combination of these means cannot be used to advantage. A computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. Any reference signs in the claims should not be construed as limiting the scope. [Explanation of symbols]

[0085] 100: Medical Systems 102: Computer 104: Computing Systems 106: Hardware Interface 108: User Interface 110: Memory 120: Machine executable instructions 122: Anatomical Detection Module 124: Magnetic Resonance Image Set 126: Abnormal indicator 128: Set of reconstruction parameters 130: Lookup table or database 132: Reconstruction Algorithm 134: Synthetic Magnetic Resonance Imaging 200: Receive a set of magnetic resonance images depicting a field of view of a subject acquired according to a synthetic magnetic resonance imaging protocol. 202. Receive an anomaly indicator from the anomaly detection module in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module. 204: Determine the reconfiguration parameter set using the anomaly indicator 206: Reconstruct a synthetic magnetic resonance image from a set of magnetic resonance images and a set of reconstruction parameters 300: Medical Systems 302: Magnetic resonance imaging system 304: Magnet 306: Magnet bore 308: Imaging zone 309: Field of view 310: magnetic field gradient coil 312: Magnetic field gradient coil power supply 314: High frequency coil 316: Transceiver 318: Target 320: Target support 330: Pulse sequence command 332: k-space data 334: Preliminary set of reconstruction parameters 336: Prototype magnetic resonance imaging 338: Abnormal position 340: Calculated image contrast range 342: Predefined image contrast range 400: Acquire k-space data by controlling the magnetic resonance imaging system using pulse sequence commands. 402: Reconstruct a set of magnetic resonance images from k-space data 404: Set initial reconstruction parameters 406: Reconstruction of trial magnetic resonance images using preliminary reconstruction parameters 408: Is the image contrast within the anomaly location within a predetermined image contrast range? 410: Providing a trial magnetic resonance image as a composite magnetic resonance image 412: Modify preliminary reconstruction parameters 600: Graphical User Interface 602: Composite image

Claims

1. It is a medical system, A memory that stores machine-executable instructions and anomaly detection modules, Computation system and, It has, Upon execution of the aforementioned machine-executable instructions, the computing system will The steps include receiving a set of magnetic resonance images depicting the field of view of an object, acquired according to a composite magnetic resonance imaging protocol, The step of receiving an anomaly indicator from the anomaly detection module in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module, wherein the anomaly indicator includes one or more anomaly locations in the field of view, and the anomaly detection module has an autoencoder neural network configured to output an autoencoded image for each of the at least one set of magnetic resonance images, and the step of receiving the anomaly indicator in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module is, The steps include receiving an autoencoded image in response to inputting at least one magnetic resonance image from the set of magnetic resonance images into the autoencoder neural network, The step of determining the one or more abnormal locations by comparing the auto-encoded image of each of the at least one magnetic resonance images in the set of magnetic resonance images with the at least one magnetic resonance image in the set of magnetic resonance images, The receiving step has, The steps include determining a set of reconstruction parameters using the aforementioned abnormality indicator, The steps include: reconstructing a composite magnetic resonance image from the set of magnetic resonance images and the set of reconstruction parameters; A medical system that performs [this action].

2. The medical system according to claim 1, wherein the field of view depicts the right and left hemispheres of the subject brain, the anomaly indicator includes one or more anomaly locations within the field of view, and the algorithmic anomaly detection module is further configured to spatially locate one or more anomalies within the subject brain using the symmetrical contrast between the right and left hemispheres of the subject brain.

3. The anatomical detection module has a variational autoencoder neural network having a latent space, The anomaly detection module is configured to output the anomaly classification as the anomaly indicator. The step of receiving the anomaly indicator in response to inputting at least one magnetic resonance image from the set of magnetic resonance images to the anomaly detection module is: Inputting at least one magnetic resonance image from the set of magnetic resonance images into the variational autoencoder neural network, The anomaly classification is determined using an out-of-distribution detection method on the latent space of the variational autoencoder neural network, A medical system according to claim 1, having the following:

4. The medical system according to claim 2 or 3, wherein, upon execution of the machine-executable instructions, the computing system further performs the steps of iteratively changing the set of reconstruction parameters and reconstructing the composite magnetic resonance image to adjust the image contrast of the one or more abnormal locations relative to the periphery of the image to have a predetermined image contrast range.

5. The medical system according to claim 2 or 3, wherein the abnormality indicator indicates a plurality of abnormal locations, and the composite magnetic resonance image is reconstructed for each of the plurality of abnormal locations, thereby obtaining a set of composite magnetic resonance images.

6. By executing the aforementioned machine-executable instructions, the computing system further: The abnormal location is included from each composite magnetic resonance image in the set of composite magnetic resonance images. Using the aforementioned set of composite magnetic resonance images, the pixel values ​​are blended between the abnormal locations from each composite magnetic resonance image in the set of composite magnetic resonance images. The medical system according to claim 5, wherein the step of constructing a composite image from the set of composite magnetic resonance images is performed by doing so.

7. By executing the aforementioned machine-executable instructions, the computing system further: The steps include: displaying the composite image on a graphical user interface; The steps include receiving the selection of an abnormal location in the composite image from the graphical user interface, The steps include displaying a composite magnetic resonance image including the selected abnormal location, A medical system according to claim 6, which performs the following:

8. The medical system according to claim 1, wherein the anatomical detection module comprises a convolutional neural network configured to output an anomaly classification as the anomaly indicator in response to receiving at least one of the magnetic resonance image sets.

9. The medical system according to claim 1 or 8, wherein the reconstruction parameters are determined by searching a reconstruction parameter lookup table or a reconstruction parameter database using the anomaly classification.

10. The step of reconstructing the composite magnetic resonance image is, The T1-dependent value, T2-dependent value, and proton density for each voxel in the field of view are determined by fitting the selected signal intensity formula to the set of magnetic resonance images voxels. The composite magnetic resonance image is reconstructed by calculating the signal intensity value of each voxel using a reconstruction signal intensity formula that takes the T1-dependent value, T2-dependent value, proton density value, and reconstruction parameters of each voxel as inputs. A medical system according to any one of claims 1 to 3, comprising:

11. The medical system according to any one of claims 1 to 3, wherein the set of magnetic resonance images forms a magnetic resonance fingerprint, and the composite magnetic resonance image is reconstructed from the set of magnetic resonance images according to a magnetic resonance fingerprint protocol.

12. The medical system further comprises a magnetic resonance imaging system, the memory further comprises pulse sequence commands configured to control the magnetic resonance imaging system to acquire k-space data according to the composite magnetic resonance imaging protocol, and the computing system further comprises, by execution of the machine-executable instructions The steps include: acquiring k-space data by controlling the magnetic resonance imaging system using the pulse sequence command; The steps include: reconstructing the set of magnetic resonance images from the k-space data; A medical system according to any one of claims 1 to 3, which performs the following:

13. A method for operating a medical system, The steps include receiving a set of magnetic resonance images depicting the field of view of an object, acquired according to a composite magnetic resonance imaging protocol, The step of receiving an anomaly indicator from an anomaly detection module in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module, wherein the anomaly indicator includes one or more anomaly locations in the field of view, and the anomaly detection module has an autoencoder neural network configured to output an autoencoded image for each of the at least one set of magnetic resonance images, and the step of receiving the anomaly indicator in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module is, The steps include receiving an autoencoded image in response to inputting at least one magnetic resonance image from the set of magnetic resonance images into the autoencoder neural network, The step of determining the one or more abnormal locations by comparing the auto-encoded image of each of the at least one magnetic resonance images in the set of magnetic resonance images with the at least one magnetic resonance image in the set of magnetic resonance images, The receiving step has, The steps include determining a set of reconstruction parameters using the aforementioned abnormality indicator, The steps include: reconstructing a composite magnetic resonance image from the set of magnetic resonance images and the set of reconstruction parameters; A method of having.

14. A computer program having machine-executable instructions executed by a computing system, the computer program further having an anatomical detection module executed by the computing system, wherein by the execution of the machine-executable instructions, the computing system The steps include receiving a set of magnetic resonance images depicting the field of view of an object, acquired according to a composite magnetic resonance imaging protocol, The step of receiving an anomaly indicator from an anomaly detection module in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module, wherein the anomaly indicator includes one or more anomaly locations in the field of view, and the anomaly detection module has an autoencoder neural network configured to output an autoencoded image for each of the at least one set of magnetic resonance images, and the step of receiving the anomaly indicator in response to inputting at least one magnetic resonance image of the set of magnetic resonance images to the anomaly detection module is, The steps include receiving an autoencoded image in response to inputting at least one magnetic resonance image from the set of magnetic resonance images into the autoencoder neural network, The step of determining the one or more abnormal locations by comparing the auto-encoded image of each of the at least one magnetic resonance images in the set of magnetic resonance images with the at least one magnetic resonance image in the set of magnetic resonance images, The receiving step has, The steps include determining a set of reconstruction parameters using the aforementioned anomaly indicator, The steps include: reconstructing a composite magnetic resonance image from the set of magnetic resonance images and the set of reconstruction parameters; Execute Computer program.

Images