Automated determination of b-values ​​from diffusion-weighted magnetic resonance images.

Abstract

A mechanism is provided in a data processing system for automatically determining b-value differentials from diffusion weighted (DW) images. The mechanism receives a series of images, a first image having a first b-value and a second image having an unknown b-value. The mechanism applies a generative adversarial network (GAN) model to estimate differences between b-values ​​in the series of images. The mechanism determines a b-value for the second image based on the first b-values ​​and the differences between the estimated b-values.

Description

[Technical field]

[0001] The present application relates generally to improved data processing apparatus and methods, and more particularly to mechanisms for automatically determining b-values ​​from diffusion-weighted magnetic resonance images. [Background technology]

[0002] Diffusion weighted imaging (DWI) is the use of specific magnetic resonance imaging (MRI) sequences, and software that generates images from the acquired data, to generate contrast in magnetic resonance images using the diffusion of water molecules. DWI allows for noninvasive in vivo mapping of the diffusion process of molecules, primarily water, in biological tissues. The diffusion of molecules in tissues is not random but reflects interactions with many obstacles, such as macromolecules, fibers, and membranes. Thus, the diffusion pattern of water molecules can reveal microscopic details about tissue structure in normal or diseased states.

[0003] In diffusion-weighted imaging (DWI), the intensity of each image element (voxel) reflects the best estimate of water diffusivity at that location. Because water movement is driven by thermal motion and depends heavily on its cellular environment, the hypothesis behind DWI is that findings may indicate pathological changes. For example, DWI is more sensitive to early changes after a stroke than traditional MRI measurements such as T1 or T2 relaxation rates.

[0004] Diffusion weighted imaging is very useful in diagnosing cerebrovascular strokes. Diffusion weighted imaging is also increasingly used in staging non-small cell lung cancer. DWI is best suited when the tissue of interest is dominated by isotropic water motion, where the diffusivity appears to be the same no matter which axis is measured along, for example in the cerebral cortex and major brain nuclei, or in gray matter in the body. However, DWI still retains sensitivity to T1 and T2 relaxation. To intertwine the diffusion and relaxation effects on image contrast, quantitative images of the diffusion coefficient, or more precisely the apparent diffusion coefficient (ADC), can be acquired. The concept of ADC was introduced to take into account that diffusion processes in biological tissues are complex and reflect several different mechanisms.

[0005] Apparent diffusion coefficient (ADC) images, or ADC maps, are images that show diffusion more specifically than conventional DWI by eliminating the T2 weighting inherent in conventional DWI. ADC imaging does this by acquiring multiple conventional DWI images with different amounts of DWI weighting, with the change in signal proportional to the diffusivity. The b-value reflects the intensity and gradient used to generate the DW image. Generally, there is no optimal set of b-values ​​to be acquired, and therefore DW images are acquired at multiple b-values. ADC maps are often generated using DW images acquired at multiple b-values. Summary of the Invention

[0006] This Summary is provided to introduce a selection of concepts in a simplified form that are further described herein in the Detailed Description. This Summary is not intended to identify key elements or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

[0007] In an exemplary embodiment, a method for automatically determining b-value differences from diffusion weighted (DW) images is provided in a data processing system. The method includes receiving a series of images, where a first image has a first b-value and a second image has an unknown b-value. The method further includes applying a generative adversarial network (GAN) model to estimate differences between b-values ​​in the series of images. The method further includes determining a b-value for the second image based on the difference between the first b-value and the estimated b-value. An exemplary embodiment provides a computer-implemented technique for determining b-values ​​for images with missing b-values.

[0008] In another exemplary embodiment, a computer program product is provided that includes a computer usable medium or computer readable medium having a computer readable program that, when executed on a computing device, causes the computing device to perform various and combinations of the operations outlined above with respect to the exemplary embodiment of the method.

[0009] In an exemplary embodiment, a computer program product comprises a computer readable storage medium having a computer readable program stored thereon that, when executed on a computing device, causes the computing device to receive a series of DW images, where a first image has a first b-value and a second image has an unknown b-value, apply a generative adversarial network (GAN) model to estimate differences between b-values ​​in the series of DW images, and determine a b-value for the second image based on the first b-value and the difference between the estimated b-values.

[0010] In yet another exemplary embodiment, a system / apparatus is provided. The system / apparatus may include one or more processors and a memory coupled to the one or more processors. The memory may include instructions that, when executed by the one or more processors, cause the one or more processors to perform various and combinations of the operations outlined above with respect to the exemplary embodiment of the method.

[0011] In an exemplary embodiment, an apparatus includes a processor and a memory coupled to the processor, the memory including instructions that, when executed by the processor, cause the processor to receive a sequence of DW images, where a first image has a first b-value and a second image has an unknown b-value, apply a generative adversarial network (GAN) model to estimate differences between b-values ​​in the sequence of DW images, and determine a b-value for the second image based on the first b-value and the differences between the estimated b-values.

[0012] In an exemplary embodiment, applying the GAN model includes constructing a latent space with latent variables for learning to generate a synthetic apparent diffusion coefficient (ADC) map for identifying unknown b-values ​​in the sequence of DW images, and a loss function based on the relationship between the ADC map and the spatial relationship between images in the sequence of DW images. This embodiment provides information for applying the GAN model, thereby achieving higher accuracy.

[0013] In another exemplary embodiment, constructing the latent space includes applying an encoder to the images in the sequence of DW images. In another exemplary embodiment, the latent space includes latent variables and difference values ​​representing differences between b-values. In yet another exemplary embodiment, the GAN model includes a generator, a discriminator, and an estimator. These embodiments provide computer-implemented techniques for configuring the GAN model to specifically determine b-values, thereby improving effectiveness and accuracy.

[0014] In another exemplary embodiment, the GAN model performs identity-preserving loss (L identity ) function.

[0015]

number

[0016] Here, the α value is a parameter for normalization, and is given as follows:

[0017] α x= σ x -1 ||x-μ x ||

[0018] This embodiment specially configures the GAN model to determine the b value with higher accuracy.

[0019] In yet another exemplary embodiment, the GAN model calculates the pixel loss (L pixel ) function.

[0020]

number

[0021] This embodiment specially configures the GAN model to determine the b value with higher accuracy.

[0022] In another exemplary embodiment, the GAN model calculates a regression loss (L regression ) function.

[0023]

number

[0024] This embodiment specially configures the GAN model to determine the b value with higher accuracy.

[0025] In yet another exemplary embodiment, the GAN model is computed using a discriminator loss and a generator loss (L GAN-D ,L GAN-G ).

[0026]

number

[0027]

number

[0028] This embodiment specially configures the GAN model to determine the b value with higher accuracy.

[0029] In another exemplary embodiment, the GAN model has an objective function for the generator and discriminator as follows:

[0030] L G =γ i L identity +γ p L pixel +γ r L regression +γ g L GAN-G

[0031] L D =L GAN-D

[0032] The objective is to find the objective function L G and the objective function L D The aim of the present embodiment is to minimize both b and σ. This embodiment specially configures the GAN model to determine the b value with higher accuracy.

[0033] These and other features and advantages of the present invention will be described in, or will become apparent to those skilled in the art in view of, the following detailed description of exemplary embodiments of the invention.

[0034] The invention, its preferred mode of use, together with further objects and advantages thereof, will be best understood by reference to the following detailed description of illustrative embodiments when read in conjunction with the accompanying drawings. [Brief description of the drawings]

[0035] [Figure 1] 1 is an exemplary diagram of a distributed data processing system in which aspects of the illustrative embodiments may be implemented; [Diagram 2] FIG. 1 is an exemplary block diagram of a computing device in which aspects of the exemplary embodiments may be implemented. [Diagram 3] FIG. 1 is a block diagram illustrating a system for diffusion weighted imaging with b-value detection, in accordance with an exemplary embodiment. [Figure 4A] FIG. 1 illustrates a generative adversarial network model for automatically determining b-values ​​from diffusion weighted images, according to an exemplary embodiment. [Figure 4B] FIG. 1 illustrates a generative adversarial network model for automatically determining b-values ​​from diffusion weighted images, according to an exemplary embodiment. [Figure 4C] FIG. 1 illustrates a generative adversarial network model for automatically determining b-values ​​from diffusion weighted images, according to an exemplary embodiment. [Diagram 5] 1 is a flowchart illustrating the operation of a generative adversarial network model for automatically determining b-values ​​from diffusion weighted images, in accordance with an exemplary embodiment. [Figure 6] 1 is a flowchart illustrating operation of a system for diffusion weighted imaging with b-value detection in accordance with an exemplary embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0036] In magnetic resonance imaging, diffusion weighted (DW) images are acquired to measure and visualize the movement of water molecules within organs. DW images provide useful information about tissues. The b-value reflects the intensity and gradient used to generate the DW image. Digital Imaging and Communications in Medicine (DICOM) is a standard for the communication and management of medical imaging information and related data. DICOM is most commonly used for the storage and transmission of medical images, allowing the integration of medical imaging devices such as scanners, servers, workstations, printers, network hardware, and picture archiving and communication systems (PACS) from multiple manufacturers. DICOM has been widely adopted in hospitals and is increasingly being adopted in smaller applications such as dental and medical clinics. There is no mandatory (Type I) DICOM tag for storing the b-value. The b-value may be stored in private DICOM tags that may often be removed by anonymization. The b-value may be captured from tags such as SeriesDescription or SequenceName, but these are not Type I tags and are subject to change, making string matching difficult. In other cases, the b-values ​​may be missing entirely in the DICOM tags: if the difference between the b-values ​​(Δb=|b2-b1|) is not known, the ADC map cannot be generated accurately.

[0037] A similar issue can arise with computed tomography (CT) contrast imaging, where the acquisition time point is missing and cannot be extracted from the DICOM tag.

[0038] Exemplary embodiments provide a computer-implemented b-value determination engine for automatically determining b-value differences from diffusion weighted images. Given a diffusion weighted imaging series, the b-value determination engine determines the b-value difference (Δb) between each pair of DW images in the series. The series is made up of b1, b2, ..., b n The b-value decision engine is configured as a generative adversarial network (GAN) for regression. GANs are a class of machine learning frameworks in which two neural networks compete against each other in a game (a form of zero-sum game where the gain of one agent is the loss of the other). Given a training set, the technique learns to generate new data with the same statistics as the training set. The core concept of GANs is based on "indirect" training via a discriminator, which itself is also dynamically updated. This basically means that the generator is not trained to minimize the distance to a particular image, but rather to fool the discriminator. This allows the model to learn in an unsupervised fashion.

[0039] At least two DWI images acquired at two b-values ​​(b1 and b2) are required. The computer-implemented b-value determination engine uses an encoder to construct a latent space for learning the transformation from the original DWI series to the ADC map. To achieve this, the exemplary embodiment uses a latent variable (z). The exemplary embodiment incorporates the spatial relationship between the ADC map and the original DWI intensity into the loss function.

[0040] Thus, the exemplary embodiment uses an image-based artificial intelligence (AI) model to automatically estimate the difference between two b-values ​​from a pair of DW images. The exemplary embodiment enables accurate construction of ADC maps when b-values ​​are missing or unavailable. The exemplary embodiment uses an AI model to determine information that cannot be obtained using manual or mental processes. The results of the exemplary embodiment enable better and more reliable characterization of lesions in magnetic resonance imaging or computed tomography.

[0041] Before commencing with a discussion of various aspects of the exemplary embodiments and improved computer operations performed by the exemplary embodiments, it should first be understood that throughout this description, the term "mechanism" is used to refer to an element of the present invention that performs various operations, functions, and the like. The term "mechanism" as used herein may be an implementation of a function or aspect of the exemplary embodiments in the form of an apparatus, a procedure, or a computer program product. In the case of a procedure, the procedure is performed by one or more devices, apparatus, computers, data processing systems, and the like. In the case of a computer program product, the logic represented by the computer code or instructions embodied in or on the computer program product is executed by one or more hardware devices to implement a function or perform an operation associated with a particular "mechanism." Thus, the mechanisms described herein may be implemented as dedicated hardware, software that executes on the hardware to configure the hardware to implement special functions of the present invention that the hardware cannot inherently perform, software instructions stored on a medium to facilitate execution of the instructions by the hardware to specifically configure the hardware to perform the enumerated functions and specific computer operations described herein, a procedure or method for performing a function, or any combination of the above.

[0042] The description and claims may use the terms "a," "at least one of," and "one or more of" in reference to certain features and elements of exemplary embodiments. It should be understood that these terms and phrases are intended to indicate that there is at least one of a particular feature or element present in a particular exemplary embodiment, but that there may be more than one. That is, these terms / phrases are not intended to limit the description or claims to the presence of a single feature / element, nor to require the presence of a plurality of such features / elements. To the contrary, these terms / phrases require only at least a single feature / element, and there may be a plurality of such features / elements within the scope of the description and claims.

[0043] Furthermore, it should be understood that the use of the term "engine", when used herein with respect to describing embodiments and features of the present invention, is not intended to limit a particular implementation for realizing and / or performing actions, steps, processes, etc., that are attributed to and / or performed by an engine. An engine may be, but is not limited to, software running on computer hardware, dedicated computer hardware or firmware, or both, or any combination thereof, that performs the specified functions, including but not limited to the use of general purpose or special purpose processors or both in combination with appropriate software that is loaded or stored in a machine-readable memory and executed by the processor to specifically configure the processor to perform the specific functions of the exemplary embodiments. Furthermore, names associated with a particular engine are for convenience of reference, unless otherwise specified, and are not intended to limit a particular implementation. Furthermore, functionality attributed to an engine may be equally performed by multiple engines, or may be incorporated into or combined with the functionality of another engine of the same or different type, or both, or may be distributed across one or more engines in various configurations.

[0044] Furthermore, it should be understood that the following description uses multiple different examples of the various elements of the exemplary embodiments to further explain example implementations of the exemplary embodiments and to aid in understanding the mechanisms of the exemplary embodiments. These examples are non-limiting and do not exhaust the various possibilities for implementing the mechanisms of the exemplary embodiments. It will be apparent to one of ordinary skill in the art, upon consideration of this description, that there are many other alternative implementations of these various elements that may be utilized in addition to or instead of the examples provided herein without departing from the scope of the present invention.

[0045] The present invention may be a system, a method, and / or a computer program product, which may include a computer-readable storage medium (or media) having computer-readable program instructions for causing a processor to perform aspects of the present invention.

[0046] A computer readable storage medium may be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. A non-exhaustive list of more specific examples of computer readable storage media includes: portable computer diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically encoded devices such as punch cards or grooved structures having instructions recorded thereon, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be construed as a transitory signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or electrical signals transmitted over electrical wires.

[0047] The computer readable program instructions described herein may be downloaded from a computer readable storage medium into each computing / processing device or to an external computer or storage device via a network, such as the Internet, a local area network, a wide area network, or a wireless network, or a combination thereof. The network may include copper transmission cables, optical transmission fiber, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer readable program instructions from the network and forwards the computer readable program instructions to a computer readable storage medium in the respective computing / processing device for storage.

[0048] The computer readable program instructions for carrying out the operations of the present invention may be either source or object code written in any combination of one or more programming languages, including assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, or object code, including object oriented programming languages ​​such as Java®, Smalltalk®, C++, and traditional procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer as a standalone software package, partly on the user's computer and partly on a remote computer, or all on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or the connection may be to an external computer (e.g., via the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) can execute computer readable program instructions to individualize the electronic circuitry by utilizing state information of the computer readable program instructions to perform aspects of the invention.

[0049] Aspects of the present invention are described herein 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 of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0050] These computer readable program instructions may be provided to a processor of a computer or other programmable data processing apparatus to produce a machine, such that the instructions, executed by the processor of the computer or other programmable data processing apparatus, produce means for performing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer readable program instructions may also be stored on a computer readable storage medium, such that the computer readable storage medium on which the instructions are stored comprises an article of manufacture including instructions implementing aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams, and can direct a computer, programmable data processing apparatus, or other device, or combination thereof, to function in a particular manner.

[0051] The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause the computer, other programmable apparatus, or other device to perform a series of operable steps to create a computer-implemented process such that the instructions, which execute on the computer, other programmable apparatus, or other device, implement the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0052] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or part of an instruction, which includes one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions described in the blocks may occur out of the order described in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may be executed in reverse order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, may be implemented by a dedicated hardware-based system that performs the specified functions or actions or a combination of dedicated hardware and computer instructions.

[0053] The exemplary embodiment may be utilized in many different types of data processing environments. To provide a context for the description of certain elements and functions of the exemplary embodiment, Figures 1 and 2 are provided below as exemplary environments in which aspects of the exemplary embodiment may be implemented. It should be understood that Figures 1 and 2 are merely examples and are not intended to assert or imply any limitation with respect to the environments in which aspects or embodiments of the invention may be implemented. Many modifications to the illustrated environments may be made without departing from the scope of the present invention.

[0054] 1 depicts a diagrammatic representation of an exemplary distributed data processing system in which aspects of the exemplary embodiments may be implemented. Distributed data processing system 100 may include a network of computers in which aspects of the exemplary embodiments may be implemented. Distributed data processing system 100 includes at least one network 102, which is the medium used to provide communications links between various devices and computers connected together within distributed data processing system 100. Network 102 may include connections, such as wired communications links, wireless communications links, or fiber optic cables.

[0055] In the depicted example, server 104 and server 106 are connected to network 102 along with storage unit 108. Additionally, clients 110, 112, and 114 are also connected to network 102. Clients 110, 112, and 114 may be, for example, personal computers, network computers, etc. In the depicted example, server 104 provides data to clients 110, 112, and 114, such as boot files, operating system images, and applications. In the depicted example, clients 110, 112, and 114 are clients to server 104. Distributed data processing system 100 may include additional servers, clients, and other devices not shown.

[0056] In the depicted example, distributed data processing system 100 is the Internet with network 102 representing a worldwide collection of networks and gateways that communicate with one another using the Transmission Control Protocol / Internet Protocol (TCP / IP) protocol suite. At the heart of the Internet is a backbone of high-speed data communication lines between major nodes or host computers comprised of thousands of commercial, governmental, educational, and other computer systems that route data and messages. Of course, distributed data processing system 100 may be implemented to include a number of different types of networks, such as, for example, an intranet, a local area network (LAN), a wide area network (WAN), etc. As noted above, FIG. 1 is intended as an example, and not as an architectural limitation for various embodiments of the present invention, and thus the specific elements illustrated in FIG. 1 should not be considered limiting with regard to the environments in which an illustrative embodiment of the present invention may be implemented.

[0057] As shown in FIG. 1, one or more of the computing devices, e.g., server 104, may be specially configured to implement a b-value determination engine for automatically determining b-value differentials from diffusion weighted images. Configuring a computing device may include providing special purpose hardware, firmware, etc., to facilitate performing the operations and generating output as described herein with respect to the exemplary embodiments. Configuring a computing device may also, or alternatively, include providing software applications stored in one or more storage devices and loaded into memory of a computing device, such as server 104, for causing one or more hardware processors of the computing device to execute software applications that configure the processors to perform the operations and generate output as described herein with respect to the exemplary embodiments. Moreover, any combination of special purpose hardware, firmware, software applications executing on the hardware, etc. may be used without departing from the scope of the exemplary embodiments.

[0058] It should be understood that once a computing device is configured in one of these ways, the computing device becomes a dedicated computing device specifically configured to implement the mechanisms of the exemplary embodiments, and not a general-purpose computing device. Moreover, as described below, implementation of the mechanisms of the exemplary embodiments provides useful and tangible results that improve the functionality of the computing device and facilitate automated determination of b-values ​​and b-value differentials.

[0059] As described above, the mechanisms of the exemplary embodiments utilize specially configured computing devices or data processing systems to perform the operations for determining b-values ​​from diffusion weighted images. These computing devices or data processing systems may comprise various hardware elements that are specially configured to implement one or more of the systems / subsystems described herein, either by hardware configuration, software configuration, or a combination of hardware and software configuration. FIG. 2 is a block diagram of merely one example of a data processing system in which aspects of the exemplary embodiments may be implemented. Data processing system 200 is an example of a computer, such as server 104 of FIG. 1, in which computer usable code or instructions implementing the processes and aspects of the exemplary embodiments of the present invention may be arranged and / or executed to achieve the operations, outputs, and external effects of the exemplary embodiments described herein.

[0060] In the illustrated example, data processing system 200 employs a hub architecture including a north bridge and memory controller hub (NB / MCH) 202 and a south bridge and input / output (I / O) controller hub (SB / ICH) 204. A processing unit 206, a main memory 208, and a graphics processor 210 are connected to the NB / MCH 202. The graphics processor 210 may be connected to the NB / MCH 202 via an accelerated graphics port (AGP).

[0061] In the illustrated example, a local area network (LAN) adapter 212 connects to the SB / ICH 204. An audio adapter 216, a keyboard and mouse adapter 220, a modem 222, a read-only memory (ROM) 224, a hard disk drive (HDD) 226, a CD-ROM drive 230, a universal serial bus (USB) port and other communication ports 232, and a PCI / PCIe device 234 connect to the SB / ICH 204 via a bus 238 and a bus 240. PCI / PCIe devices may include, for example, Ethernet adapters, add-in cards, and PC cards for notebook computers. PCI uses a card bus controller, whereas PCIe does not. The ROM 224 may be, for example, a flash basic input / output system (BIOS).

[0062] The HDD 226 and CD-ROM drive 230 connect to the SB / ICH 204 via a bus 240. The HDD 226 and CD-ROM drive 230 may use, for example, an Integrated Drive Electronics (IDE) or a Serial Advanced Technology Attachment (SATA) interface. A Super I / O (SIO) device 236 may be connected to the SB / ICH 204.

[0063] An operating system runs on the processing unit 206. The operating system coordinates and provides control of various components within data processing system 200 of FIG. 2. In a client device, the operating system may be a commercially available operating system, such as Microsoft® Windows® 10®. An object-oriented programming system, such as a Java®™ programming system, may run in conjunction with the operating system and provide calls to the operating system from Java®™ programs or applications running on data processing system 200.

[0064] As a server, data processing system 200 may be, for example, an IBM eServer™ System p™ computer system, a Power™ processor-based computer system, etc., running the Advanced Interactive Executive (AIX™) operating system or the LINUX™ operating system. Data processing system 200 may be a symmetric multiprocessor (SMP) system that includes multiple processors within processing unit 206. Alternatively, a single processor system may be employed.

[0065] Instructions for the operating system, object oriented programming system, and applications or programs may be located on a storage device, such as HDD 226, and loaded into main memory 208 for execution by processing unit 206. The processes of the exemplary embodiments of the present invention may be executed by processing unit 206 using computer usable program code, which may be located in a memory, such as, for example, main memory 208, ROM 224, or in, for example, one or more peripheral devices 226 and 230.

[0066] A bus system, such as bus 238 or bus 240 as shown in FIG. 2, may be comprised of one or more buses. Of course, a bus system may be implemented using any type of communications fabric or architecture that provides for a transfer of data between different components or devices attached to the fabric or architecture. A communications unit, such as modem 222 or network adapter 212 of FIG. 2, may include one or more devices used to transmit and receive data. A memory may be, for example, main memory 208, ROM 224, or a cache such as found in NB / MCH 202 of FIG. 2.

[0067] As noted above, in some exemplary embodiments, the mechanisms of the exemplary embodiments may be implemented as application specific hardware, firmware, or the like, stored in a storage device, such as HDD 226, and loaded into a memory, such as main memory 208, for execution by one or more hardware processors, such as processing unit 206. Thus, the computing device illustrated in FIG. 2 will be specially configured to implement the mechanisms of the exemplary embodiments and will be specially configured to perform the operations and generate output described below with respect to the b-value determination engine.

[0068] Those skilled in the art will appreciate that the hardware in Figures 1 and 2 may vary depending on the implementation. Other internal hardware or peripheral devices, such as flash memory, equivalent non-volatile memory, or optical disk drives, may be used in addition to or in place of the hardware depicted in Figures 1 and 2. Additionally, the processes of the illustrative embodiments may be applied to multiprocessor data processing systems other than the SMP systems described above without departing from the scope of the present invention.

[0069] Further, data processing system 200 may take the form of any of a number of different data processing systems, including a client computing device, a server computing device, a tablet computer, a laptop computer, a telephone or other communications device, a personal digital assistant (PDA), etc. In some illustrative examples, data processing system 200 may be a portable computing device configured with, for example, a flash memory that provides non-volatile memory for storing operating system files and / or user-generated data. In essence, data processing system 200 may be any known or later developed data processing system without architectural limitations.

[0070] 3 is a block diagram illustrating a system for diffusion weighted imaging with b-value detection, according to an exemplary embodiment. A diffusion weighted imaging (DWI) system 310 generates a series of images based on multiple b-values ​​(b1, b2).

number

number

[0071] In the embodiment shown in FIG. 3, the b-value determination engine 330 receives images 311, 312 from the storage 320 and determines the b-values ​​(b'1, b'2) of the images, or the difference between the b-values ​​(Δb). For example,

number

number

[0072] 4A-4C illustrate a generative adversarial network model for automatically determining b-values ​​from diffusion weighted images, according to an example embodiment. With reference to FIG. 4A, an encoder (E) 410 encodes an image series into a latent feature space (z, Δb) 420. In the illustrated example, the encoder 413 encodes the image series into a latent feature space (z, Δb) 420.

number

number

number

number

[0073] The generative adversarial network (GAN) 430 includes a generator (G) 440, a discriminator (D) 450, and a Δb estimator (R) 460. The generator 440 receives the latent space (z, Δb) 420 and calculates an ADC map

number

[0074] In the illustrated example, the discrimination network 451 is

number

[0075] The known data set serves as initial training data for the discriminator 450. Training the discriminator 450 involves presenting samples from the training data set to the discriminator 450 until an acceptable accuracy is reached. The generator network 441 trains based on whether it is successful in fooling the discriminator. In the illustrated example, the generator network 441 is seeded with randomized inputs sampled from the latent space 420. The candidates synthesized by the generator network 441 are then evaluated by the discriminator network 451 against the ADC series 452 generated by the MRI machine. The discriminator network 451 determines how close the estimated ADC map 445 is to the original ADC map 452. Independent back-propagation procedures are applied to both networks so that the generator produces better samples and the discriminator becomes more skilled in flagging the synthetic samples.

[0076] The Δb estimator (R) 460 uses a convolutional encoder 465 to generate the ADC map

number

[0077] Turning to FIG. 4B, the latent feature space 420 is defined as follows:

[0078]

number

[0079] Referring now to FIG. 4C, an encoder 451 outputs the generated ADC map

number

number

[0080] Training GAN430 relies on the following losses:

[0081] 1. Identity preservation loss (L identity )

[0082] 2. Pixel loss (L pixel )

[0083] 3. Regression loss (L regression )

[0084] 4.GAN loss (L GAN-D ,L GAN-G )

[0085] Identity preservation loss (L i ) are as follows:

[0086]

number

[0087] Here, the α value is a parameter for normalization, and is given as follows:

[0088] α x = σ x -1 ||x-μ x ||

[0089] Here, the data x is normalized by subtracting the mean μ and dividing by the standard deviation σ.

[0090] Pixel loss (L pixel ) are as follows:

[0091]

number

[0092]

number

[0093] Regression loss (L regression ) are as follows:

[0094]

number

[0095] GAN loss (L GAN-D ,L GAN-G ) are as follows:

[0096]

number

[0097]

number

[0098] Here, p represents the probability distribution function.

[0099] The objective functions for G and D are:

[0100] L G =γ i L identity +γ p L pixel +γ r L regression +γ g L GAN-G

[0101] L D =L GAN-D

[0102] The goal is to find the objective function L G and the objective function L D The aim of the present invention is to minimize both

[0103] FIG. 5 is a flowchart illustrating the operation of a generative adversarial network model for automatically determining b-values ​​from diffusion weighted images, according to an exemplary embodiment. The operation begins (block 500), and the generative adversarial network (GAN) model uses an encoder to build a latent space for learning a transformation from a DW image to an ADC map (block 501). The GAN model uses a generator to generate an ADC map from the latent space (block 502). The GAN model then uses a discriminator to determine a relationship between the specific difference between the ADC map and the DW image (block 503). The GAN model then uses an estimator to estimate the difference in b-values ​​(block 504), and the operation ends (block 505).

[0104] 6 is a flow chart illustrating the operation of a system for diffusion weighted imaging with b-value detection, according to an exemplary embodiment. The operation begins (block 600), and the system receives a DW image having at least one unknown b-value (block 601). The system applies a GAN to generate an ADC map to estimate the b-value difference between the DW images (block 602). The system then applies the ADC map to estimate the unknown b-value (block 603), and the operation ends (block 604).

[0105] As noted above, it should be understood that the exemplary embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment containing both hardware and software elements. In one exemplary embodiment, the mechanisms of the exemplary embodiments are implemented in software or program code, including but not limited to firmware, resident software, microcode, etc.

[0106] A data processing system suitable for storing and / or executing program code includes at least one processor coupled directly or indirectly via a communication bus, such as a system bus, to memory elements. The memory elements may include local memory employed during the actual execution of the program code, bulk storage, and cache memory that provides temporary storage of at least some of the program code to reduce the number of times the code must be retrieved from the bulk storage during execution. The memory may be of various types, including but not limited to ROM, PROM, EPROM, EEPROM, DRAM, SRAM, flash memory, solid state memory, etc.

[0107] Input / output or I / O devices (including but not limited to keyboards, displays, pointing devices, etc.) may be coupled to the system directly or through intervening wired or wireless I / O interfaces and / or I / O controllers, etc. I / O devices may take many different forms other than traditional keyboards, displays, pointing devices, etc., such as, for example, communication devices coupled through wired or wireless connections, including but not limited to smart phones, tablet computers, touch screen devices, voice recognition devices, etc. Any known or later developed I / O devices are intended to be within the scope of the exemplary embodiments.

[0108] Network adapters may also be coupled to the system to enable the data processing system to be coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modems, and Ethernet cards are just a few of the currently available types of network adapters for wired communications. Wireless communication based network adapters may also be utilized, including, but not limited to, 802.11a / b / g / n wireless communication adapters, Bluetooth wireless adapters, and the like. Any network adapter now known or later developed is intended to be within the scope of the present invention.

[0109] The description of the present invention has been presented for purposes of illustration and explanation and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The embodiments have been selected and described in order to best explain the principles, practical applications of the invention, and to enable those skilled in the art to understand the invention in various embodiments with various modifications as suited to the particular use contemplated. The terms used in this specification have been selected in order to best explain the principles, practical applications, or technical improvements over the art found in the marketplace of the embodiments, or to enable those skilled in the art to understand the embodiments disclosed herein.

Claims

1. 1. A method for automatically determining b-value difference from diffusion weighted (DW) images in a data processing system, comprising: receiving a series of DW images, a first image having a first b-value and a second image having an unknown b-value; applying a generative adversarial network (GAN) model to estimate differences between b-values ​​in the set of DW images; determining a b-value for the second image based on the first b-value and a difference between the estimated b-values; A method comprising:

2. 2. The method of claim 1, wherein applying the GAN model comprises constructing a latent space with latent variables for learning to generate a synthetic apparent diffusion coefficient (ADC) map for identifying unknown b-values ​​in the set of DW images, and a loss function based on a relationship between the ADC map and a spatial relationship between images in the set of DW images.

3. The method of claim 2 , wherein constructing the latent space comprises applying an encoder to the images in the sequence of DW images.

4. The method of claim 2 , wherein the latent space includes latent variables and difference values ​​that represent differences between b-values.

5. The method of claim 1 , wherein the GAN model includes a generator, a discriminator, and an estimator.

6. The GAN model has the following identity preservation loss (L ｉｄｅｎｔｉｔｙ ) function, [0010] 6. The method of claim 5, wherein the α value is a parameter for normalization and is as follows: a ｘ =s ｘ －１ ||k-μ ｘ ||

7. The GAN model has pixel losses (L ｐｉｘｅｌ 6. The method of claim 5, further comprising the step of: [0025]

8. The GAN model has a regression loss (L ｒｅｇｒｅｓｓｉｏｎ 6. The method of claim 5, further comprising the step of: [0030]

9. The GAN model has the following discriminator loss and generator loss (L ＧＡＮ－Ｄ , L ＧＡＮ－Ｇ 6. The method of claim 5, further comprising: [0045]

10. The GAN model has an objective function for the generator and the discriminator as follows: L Ｇ =c ｉ L ｉｄｅｎｔｉｔｙ +c ｐ L ｐｉｘｅｌ +c ｒ L ｒｅｇｒｅｓｓｉｏｎ +c ｇ L ＧＡＮ－Ｇ L Ｄ =L ＧＡＮ－Ｄ The objective is to calculate the objective function L Ｇ and the objective function L Ｄ 6. The method of claim 5, wherein the objective is to minimize both

11. A computer program product comprising a computer readable storage medium having a computer readable program stored thereon, the computer readable program, when executed on a computing device, causing the computing device to: receiving a series of DW images, a first image having a first b-value and a second image having an unknown b-value; applying a generative adversarial network (GAN) model to estimate differences between b-values ​​in the set of DW images; determining a b-value for the second image based on the first b-value and a difference between the estimated b-values; A computer program product that causes

12. 12. The computer program product of claim 11, wherein applying the GAN model comprises constructing a latent space with latent variables for learning to generate a synthetic apparent diffusion coefficient (ADC) map for identifying unknown b-values ​​in the set of DW images and a loss function based on a relationship between the ADC map and a spatial relationship between images in the set of DW images.

13. 13. The computer program product of claim 12, wherein constructing the latent space comprises applying an encoder to the images in the series of DW images, the latent space comprising latent variables and difference values ​​representing differences between b-values.

14. The computer program product of claim 11 , wherein the GAN model includes a generator, a discriminator, and an estimator.

15. The GAN model has the following identity preservation loss (L ｉｄｅｎｔｉｔｙ ) function, [0050] 15. The computer program product of claim 14, wherein the α value is a parameter for normalization and is as follows: a ｘ =s ｘ －１ ||k-μ ｘ ||

16. The GAN model has pixel losses (L ｐｉｘｅｌ 15. The computer program product of claim 14, further comprising a function: [006]

17. The GAN model has a regression loss (L ｒｅｇｒｅｓｓｉｏｎ 15. The computer program product of claim 14, further comprising a function: [0070]

18. The GAN model has the following discriminator loss and generator loss (L ＧＡＮ－Ｄ , L ＧＡＮ－Ｇ 15. The computer program product of claim 14, comprising: [0080]

19. The GAN model has an objective function for the generator and the discriminator as follows: L Ｇ =c ｉ L ｉｄｅｎｔｉｔｙ +c ｐ L ｐｉｘｅｌ +c ｒ L ｒｅｇｒｅｓｓｉｏｎ +c ｇ L ＧＡＮ－Ｇ L Ｄ =L ＧＡＮ－Ｄ The objective is to calculate the objective function L Ｇ and the objective function L Ｄ 15. The computer program product of claim 14, wherein the objective is to minimize both

20. An apparatus comprising: A processor; a memory coupled to the processor; wherein the memory, when executed by the processor, causes the processor to: receiving a series of DW images, a first image having a first b-value and a second image having an unknown b-value; applying a generative adversarial network (GAN) model to estimate differences between b-values ​​in the set of DW images; determining a b-value for the second image based on the first b-value and a difference between the estimated b-values; An apparatus comprising instructions for performing

Images