Medical image reconstruction

Abstract

Concepts are presented relating to assisting and / or improving the processing of medical images with a reconstruction algorithm. In particular, embodiments of the present invention may provide a method and / or system that provides a paintable reconstruction algorithm that may be restarted and completed at any time in a subsequent workflow, which may enable a flexible reconstruction scheduling framework.

Description

TECHNICAL FIELD

[0001] The present invention relates to the field of medical image processing, in particular to the field of processing medical images using reconstruction algorithms. BACKGROUND

[0002] Conventional medical imaging reconstruction algorithms require significant computation time, such as retrospective motion correction or compressed-sensing image reconstruction in magnetic resonance imaging (MRI). In some cases, it can be difficult to predict the computation time required to achieve sufficient diagnostic image quality at the end of data acquisition. For example, the computation time for retrospective motion correction can vary significantly (e.g., depending on the complexity of patient motion).

[0003] Excessive computation time can be problematic in a clinical routine, as it can tie up reconstruction hardware resources, hindering subsequent scans in a current subject examination. In some cases, a new scan can not be started when reconstruction hardware is busy with tasks from a previous scan (thus, keeping the entire workflow).

[0004] Furthermore, the reconstruction process is typically started during and immediately after data acquisition, thus requiring completion directly after the scan. Therefore, implementation of the reconstruction algorithm typically requires a trade-off between achievable image quality and available computation time during and between subsequent scans.

[0005] US 2023 / 110437 A1 describes an imaging system comprising at least one processor configured to apply a projection pre-computation algorithm and an x-ray tomography image reconstruction system.

[0006] CN 107221014 A describes a method for dispatching a medical image reconstruction task, which comprises performing a first reconstruction task and pausing the first reconstruction task when a second reconstruction task with higher priority joins. SUMMARY

[0007] The invention is defined by the claims.

[0008] According to an example of an aspect of the present invention, there is provided a medical image processing apparatus comprising: an image reconstruction unit configured to process acquired medical imaging data to generate a reconstructed image by performing a plurality of reconstruction tasks. The image reconstruction unit is further configured to: perform a first reconstruction task of the plurality of reconstruction tasks, wherein the first reconstruction task comprises execution of a suspendable reconstruction algorithm; suspend execution of the first reconstruction task; perform a second reconstruction task of the plurality of reconstruction tasks during suspension of the first reconstruction task; and resume execution of the first reconstruction task after completion of the second reconstruction task; and a control unit configured to control the image reconstruction unit to suspend execution of the first reconstruction task in dependence on a control signal provided from the control unit to the image reconstruction unit, and the control unit comprises: an input interface adapted to receive a control input signal describing at least one of: an execution schedule; and a scheduling limit for the first reconstruction task, and wherein the control unit is adapted to generate the control signal for the image reconstruction unit based on the received control input signal.

[0009] Thus, the proposed concept aims at providing schemes, solutions, concepts, designs, methods and systems related to assisting and / or improving medical image reconstruction. In particular, embodiments of the present invention propose to provide a suspendable / abortable reconstruction algorithm which can be restarted and completed at any time in a subsequent workflow. By starting execution of a second reconstruction task during suspension of a first reconstruction task, the proposed embodiments can support reconstruction job scheduling which facilitates optimal scheduling of required reconstruction tasks within an available time period.

[0010] By way of example only, the proposed embodiments can enable a flexible reconstruction scheduling framework by exploiting a suspendable reconstruction algorithm. At various points in time of a medical image reconstruction task (e.g. after data pre-processing or after a certain number of iterations), the entire state of the algorithm (e.g. parameter values and / or data arrays) can be captured and stored. This can allow resuming the reconstruction task at a later point in the clinical workflow (e.g. when sufficient computational resources are available).

[0011] In other words, the embodiments propose to support suspension of a first reconstruction algorithm to enable: (i) performing a second reconstruction task; and (ii) resuming the first reconstruction task after completion of the second reconstruction task. This can enable a flexible reconstruction scheduling framework to improve medical image reconstruction. For example, the embodiments can be used in relation to medical image processing in order to provide support to medical professionals when selecting a treatment for a subject. Such embodiments can also support clinical planning. Thus, the proposed concept can provide improved clinical decision support (CDS).

[0012] Some embodiments can further comprise a scheduling component configured to analyze usage of a medical imaging device for acquiring medical imaging data, determine, based on the analysis result, at least one of: an execution schedule, and a scheduling limit for the first reconstruction algorithm, and generate the control input signal for the control unit based on the determined execution schedule and / or scheduling limit. That is, embodiments can propose the concept of (i) analyzing usage to determine an execution schedule and / or a scheduling limit; and (ii) creating a control input signal based on the analysis result(s).

[0013] Some embodiments can further comprise a data storage unit. The image reconstruction unit can then be further configured to, in response to pausing execution of the first reconstruction task, store state information in the data storage unit, the state information describing an execution state of the first reconstruction task. In this way, embodiments can have the capability to capture and store necessary information for pausing (and subsequent resuming) the first reconstruction algorithm. This can alleviate the requirement of relying on one or more separate data storage systems.

[0014] For example, the state information comprises at least one of: a current version of a medical image; one or more algorithm parameter values; one or more algorithm setting values; an iteration identifier; a current version of a data array; and an algorithm state description. Thus, various types and / or forms of data can be captured and stored in order to enable pausing (and subsequent resuming) of the first reconstruction algorithm.

[0015] In some embodiments, the pauseable reconstruction algorithm can comprise an iterative algorithm. The image reconstruction unit can then be configured to pause execution of the first reconstruction task upon completion of an iteration of the pauseable reconstruction algorithm. Thus, embodiments can be configured to support pausing (and subsequent resuming) of an iterative reconstruction algorithm.

[0016] In some embodiments, the input interface can comprise a user interface for receiving the control input signal from a user. Thus, embodiments can support a user providing the control input signal for the control unit (e.g., resulting from a manual analysis of usage / schedule, etc.).

[0017] The medical imaging data may, for example, comprise CT or MRI data.

[0018] The apparatus can be remote from a user device for assessing the subject. In this way, a user, such as a medical professional, can have a suitably arranged system that can receive medical imaging data at a location remote from the subject. Embodiments can thus enable a user to perform a medical assessment of a subject using a local system, which can for example comprise a portable display device, such as a laptop computer, tablet computer, mobile phone, PDA, etc. As an example, embodiments can provide an application for a mobile computing device, and the application can be executed and / or controlled by a user of the mobile computing device.

[0019] The apparatus can further comprise a server device comprising the image reconstruction unit, and a client device comprising the user interface. A dedicated data processing apparatus can thus be used for the purpose of image reconstruction, thereby reducing the processing requirements or capabilities of other components or devices of the system.

[0020] The apparatus can further comprise a client device, wherein the client device comprises the image reconstruction unit and the display unit. In other words, a user, such as a doctor or medical professional, can have a suitably arranged client device, such as a laptop computer, tablet computer, mobile phone, PDA, etc., that processes received medical imaging data in order to generate a reconstructed image and to generate a display control signal. As an example only, embodiments can thus provide a medical image processing system that enables imaging of one or more subjects, e.g. patients, from a single location, wherein real-time communication between the subject and a user, e.g. a nurse or doctor, is provided, and its functionality can be extended or modified, e.g. in accordance with the presented concepts.

[0021] It will be appreciated that the processing capabilities can thus be distributed in different ways throughout the system / apparatus, in accordance with predetermined constraints and / or availability of processing resources.

[0022] According to another aspect of the present invention, a medical image acquisition system can be provided, comprising a medical imaging apparatus for acquiring medical imaging data, and a medical image processing apparatus according to the presented embodiments.

[0023] The presented embodiments can thus be used in conjunction with conventional / existing medical image acquisition and / or processing systems. In this way, embodiments can be integrated into legacy systems in order to improve and / or extend their functionality and capabilities. The presented embodiments can thus provide an improved medical image acquisition / processing system.

[0024] According to another aspect, there is provided a computer program product for processing acquired medical imaging data with a plurality of reconstruction algorithms to generate a reconstructed image, wherein the computer program product comprises a computer-readable storage medium containing computer-readable program code configured to perform all the steps of the proposed embodiments.

[0025] According to another aspect, there is provided a computer program product for processing acquired medical imaging data with a plurality of reconstruction algorithms to generate a reconstructed image, wherein the computer program product comprises a computer-readable storage medium containing computer-readable program code configured to perform all the steps of the proposed embodiments.

[0026] Accordingly, there can also be provided a computer system comprising: a computer program product according to the proposed embodiments; and one or more processors adapted to perform the method according to the proposed concepts by running the computer-readable program code of the computer program product.

[0027] As yet another exemplary embodiment of the invention, there is provided a medical image processing apparatus comprising: an image reconstruction unit configured to process acquired medical imaging data with a plurality of reconstruction algorithms to generate a reconstructed image. The image reconstruction unit is further configured to: perform a first reconstruction algorithm of the plurality of reconstruction algorithms; pause execution of the first reconstruction algorithm; perform a second reconstruction algorithm of the plurality of reconstruction algorithms during the pause of the first reconstruction algorithm; and resume execution of the first reconstruction algorithm after completion of the second reconstruction algorithm.

[0028] Accordingly, the proposed concept of a pausable reconstruction algorithm can be presented, which can be restarted and completed at any time in a subsequent workflow. At various points in time of the reconstruction task (e.g., after data pre-processing or after a certain number of iterations), the entire state of the reconstruction algorithm (e.g., key parameters and data arrays) can be saved. This can allow for resuming the task at a later point in the clinical workflow (e.g., when computational resources are available). By facilitating the use of pausable reconstruction algorithms, a flexible reconstruction scheduling framework can be achieved. Accordingly, the proposed concept(s) can enable improved (e.g., more flexible or optimized) medical image reconstruction.

[0029] These and other aspects of the application will become apparent from the following detailed description, taken in conjunction with the drawings, illustrating the principles of the application by way of example only. BRIEF DESCRIPTION OF DRAWINGS

[0030] For a better understanding of the present application, and to show how it can be put into effect, reference will now be made, purely by way of example, to the accompanying drawings in which: Figure 1 is a simplified block diagram of a medical image processing device according to an embodiment of the application; Figure 2 depicts an exemplary clinical workflow according to an embodiment employing a method for processing acquired medical imaging data with multiple reconstruction algorithms; Figure 3 is a simplified flowchart of a method for processing acquired medical imaging data with multiple reconstruction algorithms according to the proposed embodiments; and Figure 4 is a simplified block diagram of a computer in which one or more parts of an embodiment can be employed. DETAILED DESCRIPTION

[0031] The present application will be described with respect to the drawings in which:

[0032] It is to be understood that the detailed description and specific examples, while indicating exemplary embodiments of apparatuses, systems and methods, are intended for purposes of illustration only and are not intended to limit the scope of the present application. These and other features, aspects, and advantages of the apparatuses, systems and methods of the present application will become better understood from the following description, appended claims, and accompanying drawings. The fact that certain measures are recited in mutually different dependent clauses does not indicate that a combination of these measures cannot produce an advantage.

[0033] Variations of the disclosed embodiments can become apparent to those of ordinary skill in the art upon reading and understanding the present disclosure. In the claims, the word "comprising" does not exclude other elements or steps, and the words "a" or "an" do not exclude a plurality. The mere fact that certain measures are recited in mutually different dependent clauses does not indicate that a combination of these measures cannot be used to advantage.

[0034] It is to be understood that the drawings are solely for purposes of illustration and are not intended to limit the scope of the present application. It is to be understood that the same or equivalent parts are designated by the same reference characters.

[0035] The present application proposes the concept of utilizing reconstruction algorithms to assist and / or improve the processing of medical images. In particular, embodiments of the present application can provide a method and / or system that provides a pausable reconstruction algorithm that can be restarted and completed at any time in a subsequent workflow, which can enable a flexible reconstruction scheduling framework.

[0036] In particular, the proposed concept can provide a method of enabling execution of a second reconstruction task during a pause of a first reconstruction task. Thus, embodiments can support reconstruction job scheduling, which in turn enables optimal placement of required reconstruction tasks in available time periods.

[0037] For example, a flexible reconstruction scheduling framework can be implemented by utilizing a suspendable reconstruction algorithm: At various points in time of a reconstruction job (e.g., after data pre-processing or after a certain number of iterations), the entire state of the algorithm (key parameters and data arrays) can be saved locally to disk. This allows resuming the job at a later point in the clinical workflow when computational resources are available. As an example of the proposed concept(s) only, a suspendable (iterative) retrospective motion correction algorithm has been implemented by saving the current image and motion parameter estimates as well as certain optimizer settings (e.g., step size) to a data storage unit at the end of each iteration. If there is a problem with the reconstruction resources, e.g., when a new scan needs to be started, the current reconstruction can be stopped without losing the information computed so far. In case of such an interruption, the computation can be resumed later at the last completed iteration, i.e., the computational overhead is negligible.

[0038] Throughout the specification, a reconstruction task can be referred to as a reconstruction algorithm. For example, the first reconstruction task can be referred to as a first reconstruction algorithm, and the second reconstruction task can be referred to as a second reconstruction algorithm. This is because each reconstruction task comprises executing a reconstruction algorithm to be executed.

[0039] As an example, reference will now be made to Figure 1 The proposed embodiments are described.

[0040] Figure 1 is a simplified block diagram of a medical image processing apparatus 100 according to an embodiment of the present invention.

[0041] The medical image processing apparatus 100 comprises an image reconstruction unit 110 configured to process acquired medical imaging data with a plurality of reconstruction algorithms to generate reconstructed images. Here, the medical imaging data comprises CT or MRI data (i.e., image data captured using a CT or MRI scanner).

[0042] The image reconstruction unit 110 is configured to execute a first reconstruction algorithm 112. The image reconstruction unit 110 is further configured to pause execution of the first reconstruction algorithm 112, and, during the pause of the first reconstruction algorithm 112, to execute a different second reconstruction algorithm 114. In particular, in this example, the first reconstruction algorithm 112 comprises an iterative algorithm, and the image reconstruction unit 110 is configured to pause execution of the first reconstruction algorithm 112 upon completion of an iteration of the first reconstruction algorithm 112.

[0043] After the second reconstruction algorithm is completed, the image reconstruction unit 110 resumes execution of the first reconstruction algorithm 112. That is, the image reconstruction unit 110 is configured to facilitate a suspendability of the reconstruction algorithm, thereby enabling another reconstruction algorithm to be executed during a suspend period of the first reconstruction algorithm.

[0044] To support such suspendability functionality, the image processing apparatus 100 comprises a data storage unit 120. In response to suspending execution of the first reconstruction algorithm 112, the image reconstruction unit stores state information in the data storage unit 120. As an example, the state information describes an execution state of the first reconstruction algorithm 112, thereby providing information / data required to resume the first reconstruction algorithm 112 at a later time. For instance, the state information in this example embodiment comprises at least one of: a current version of the medical image; one or more algorithm parameter values; one or more algorithm setting values; an iteration identifier; a current version of a data array; and an algorithm state description.

[0045] In Figure 1 In an embodiment, the medical image processing apparatus 100 further comprises a control unit 130. The control unit 130 is configured to control the image reconstruction unit 110 to suspend execution of the first reconstruction algorithm 112 in accordance with a control signal 140 provided from the control unit 130 to the image reconstruction unit 110. Thus, the medical image processing apparatus 100 has a control functionality for controlling the suspend of the reconstruction algorithm.

[0046] Here, the control unit 130 comprises an input interface 150 configured to receive a control input signal 160 describing at least one of: an execution schedule; and a scheduling limit for the first reconstruction algorithm. The control unit 130 is adapted to generate the control signal 140 for the image reconstruction unit 110 based on the received control input signal. In other words, the control unit 130 is configured to receive control information (i.e. the control input signal 160) for determining the control signal 140 of the image reconstruction unit 110. In this way, a framework for controlling the suspend of the reconstruction algorithm can be provided, wherein such control is defined in accordance with information provided to the control unit. The information for defining the control can for instance be from an external system and / or a user, thus providing a broad range of factors and / or aspects that can be used to control the image reconstruction unit 110 to suspend the reconstruction algorithm.

[0047] By demonstrating potential control options, Figure 1 Additional features that can be comprised in the medical image processing apparatus 100 are also depicted (using dashed lines).

[0048] In particular, Figure 1Embodiments of the application can also comprise a scheduling component 170. The scheduling component 170 is configured to analyze usage of medical imaging devices for acquiring medical imaging data to determine, based on the analysis result, at least one of: an execution schedule; and a scheduling limit for the first reconstruction algorithm. Based on the determined execution schedule and / or scheduling limit, the scheduling component 170 generates a control input signal 160 for the control unit 130.

[0049] The scheduling component 170 can for example automatically analyze CT / MRI scanner usage at a clinical site (e.g. using log file parsing). In particular, idle times, i.e. prolonged periods of time in which no data acquisition is performed, can be monitored. A prediction of typical idle times, e.g. during the turnaround from one patient to the next, can then be implemented using a learnable algorithm (e.g. a neural network). The scheduling component takes this prediction into account as well as an estimated computation time for all reconstruction jobs to be completed.

[0050] Furthermore, for each clinical site, the scheduling component 170 can take into account specific requirements regarding the completion of reconstruction tasks. For example, the clinical workflow can require immediate availability of reconstructed images after an examination (e.g. in an emergency department). At other sites, radiologists can routinely analyze diagnostic images after the last examination of the day, leaving more time for image reconstruction. In addition to these general requirements, individual reconstruction tasks can be manually prioritized by an operator, e.g. if immediate diagnosis or quality control is required, e.g. when the patient is still on the table. Such prioritization can also be a default setting of the protocol.

[0051] The scheduling component 170 can take into account the predicted idle times and reconstruction task durations as well as the requirements of the reconstruction tasks. In particular, the reconstruction algorithm settings, e.g. the total number of iterations, can be automatically adjusted to optimize image quality for the available computation time. If required, intermediate (preview) images can be provided at an earlier point in time, while the final images with the best quality can be reconstructed at a suitable later point in time.

[0052] Furthermore, Figure 1 The input interface of the application can also comprise a user interface for receiving control input signals from a user. That is, the embodiment can facilitate providing control input signals 160 from a user, enabling to manually provide information that can be used to control the image reconstruction unit 110 (via the control unit).

[0053] To further explain the proposed concept, reference will now be made to Figure 2 An exemplary workflow utilizing the proposed flexible reconstruction framework is described.

[0054] Figure 2An exemplary clinical workflow according to an embodiment is depicted that employs a method for processing acquired medical imaging data with multiple reconstruction algorithms.

[0055] The data acquisition processes are illustrated in the upper / top timeline and the associated image reconstruction processes are illustrated in the lower / bottom timeline.

[0056] Here, it is assumed that the local guidelines require that all reconstruction processes / tasks for a particular exam (i.e., Patient A) be completed before a subsequent exam (i.e., Patient B). Furthermore, it is assumed that the operator manually prioritizes the reconstruction processes CD (Recon) 212 such that the motion correction process AB (MoCo) 208 is paused by the scheduling framework. The continuation proceeds during the idle time when patient turnover occurs (i.e., patient turnover period 205) and is completed before the next exam begins. That is, processing for the first subject (‘Patient A’) is performed, followed by the patient turnover period 205. Once the patient turnover period 205 is complete, processing for the second subject (‘Patient B’) is performed.

[0057] More specifically, for Patient A, the initial survey 202 is completed and the associated reconstruction process 204 is performed immediately upon completion of the initial survey 202 (using the results of the survey). Next, the first data acquisition process AB 206 is performed. The associated motion correction process AB (MoCo) 208 is performed immediately upon completion of the first data acquisition process AB 206.

[0058] Upon execution of the motion correction process AB (MoCo) 208, the second data acquisition process CD 210 is performed. The associated reconstruction process CD (Recon) 212 is performed immediately upon completion of the second data acquisition process CD 210. However, in order to perform the associated reconstruction process CD (Recon) 212 immediately upon completion of the second data acquisition process CD 210, the motion correction process AB (MoCo) 208 is paused (at time = Ts).

[0059] While the reconstruction process CD (Recon) 212 is executing, the third data acquisition process EF 214 is performed. Upon completion of the third data acquisition process EF 214 and the reconstruction process CD (Recon) 212, the associated reconstruction process EF (Recon) 216 is performed as soon as possible. Upon completion of the reconstruction process EF (Recon), the motion correction process AB (MoCo) 208 is resumed (at time = Ts).

[0060] That is, due to the (manual) prioritization of the operator on the reconstruction process CD(Recon) 212, the motion correction process AB(MoCo) 208 is automatically paused. Moreover, according to the requirements of the local guidelines, all reconstruction processes are completed at the start of the following data acquisition process of the second ('Patient B').

[0061] For simplicity, in the example Figure 2 parallel execution of reconstruction tasks is not considered, which can occur, for example, when only a single GPU is available but all reconstruction algorithms are required. However, it is simple to extend the framework to parallel execution. With a parallel reconstruction architecture, the reconstruction tasks can be more flexibly scheduled. However, in practice, the maximum amount of parallel processing can be limited (by the overall computing power) and the reconstruction tasks that can be paused will allow a better distribution of the computation over the available time slots. Thus, the proposed embodiments reduce the need for maximum computing power and thus can be used for cost savings.

[0062] Reference is now made to Figure 3 , depicting a simplified flowchart of a method for processing acquired medical imaging data with multiple reconstruction algorithms according to the proposed embodiments.

[0063] The method 300 starts with the execution 310 of a first reconstruction algorithm of the multiple reconstruction algorithms.

[0064] Next, the method comprises the step of pausing 320 the execution of the first reconstruction algorithm. Here, because the first reconstruction algorithm comprises an iterative algorithm, the pausing 320 of the execution of the first reconstruction algorithm depends on the completion of one iteration of the first reconstruction algorithm.

[0065] In response to the pausing 320 of the execution of the first reconstruction algorithm, the method then proceeds to the step of storing 330 state information in a data storage unit, wherein the state information describes the execution state of the first reconstruction algorithm.

[0066] Next, during the pausing of the first reconstruction algorithm, the method proceeds to the step of executing 340 a second reconstruction algorithm of the multiple reconstruction algorithms. It is then determined in step 350 whether the execution of the second reconstruction algorithm is completed. If it is determined that the execution of the second reconstruction algorithm is not completed, the method returns to step 350 for a subsequent check. If it is determined in step 350 that the execution of the second reconstruction algorithm is completed, the method proceeds to step 360. Thus, the method loops until the execution of the second reconstruction algorithm is completed.

[0067] In step 360 (i.e. after the completion of the second reconstruction algorithm), the stored state information is retrieved from the data storage unit. Using the retrieved state information, the execution of the first reconstruction algorithm is resumed in step 370.

[0068] The following additional embodiments can be considered in view of the design and application of the proposed concepts: If a camera-based workflow support system is available, the idle time of the scanner can be predicted more accurately by taking into account the status of the examination preparation (e.g., patient on examination table, coil placement completed, examination table movement, etc.).

[0069] By receiving information about planned follow-up examinations from a radiology information system (RIS), the scheduling of reconstruction tasks / processes can be further optimized. For example, if the current examination is the last examination planned for the day, the reconstruction algorithm settings can be selected to maximize image quality, regardless of the computation time.

[0070] In the case of a very costly reconstruction algorithm, the suspended reconstruction task can be continued on different hardware (like a dedicated hospital computing cluster), or the task can be outsourced to a cloud computing environment to avoid clogging the scanner’s reconstruction resources.

[0071] Figure 4 An example of a computer 600 in which one or more parts of an embodiment can be employed is shown. The various operations discussed above can utilize the capabilities of the computer 600. For example, one or more parts of the proposed medical image processing apparatus can be incorporated into any of the elements, modules, applications, and / or components discussed herein. In this regard, it should be appreciated that system functions blocks can run on a single computer or can be distributed across several computers and locations (e.g., via Internet connection).

[0072] The computer 600 includes, but is not limited to, PCs, workstations, laptops, PDAs, palm devices, servers, storages, and the like. In general, in terms of hardware architecture, the computer 600 can include one or more processors 610, memory 620, and one or more I / O devices 670 that are communicatively coupled via a local interface (not shown). The local interface can be, for example but not limited to, one or more buses or other wired or wireless connections, as is known in the art. The local interface can have additional elements, such as controllers, buffers (caches), drivers, repeaters, and receivers, to enable communications. Still, the local interface can include address, control, and / or data connections to enable appropriate communications among the aforementioned components.

[0073] The processor 610 is a hardware device for executing software that can be stored in memory 620. The processor 610 can be virtually any custom made or commercially available processor, a central processing unit (CPU), an auxiliary processor among several processors associated with the computer 600, and / or a semiconductor-based microprocessor (in the form of a microchip) that

[0074] The memory 620 can include any one or a combination of volatile memory elements (e.g., random access memory (RAM, such as dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and nonvolatile memory elements (e.g., ROM, erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), tape, compact disc read only memory (CD-ROM), disk, diskette, cartridge, cassette, etc.). Also, the memory 620 can include electronic, magnetic, optical, and / or other types of storage. It should be noted that the memory 620 can have a distributed architecture where various components are situated remote from one another, but can be accessed by the processor 610.

[0075] The software in the memory 620 can include one or more separate programs, each of which comprises an ordered listing of executable instructions for implementing logical functions. The software in the memory 620 includes a suitable operating system (O / S) 650, compiler 640, source code 630, and one or more application programs 660 in accordance with exemplary embodiments. As illustrated, the application programs 660 include a number of functional components for implementing features and operations of exemplary embodiments. The application programs 660 of the computer 600 can represent various applications, computational units, logic, functional units, processes, operations, virtual entities, and / or modules in accordance with exemplary embodiments, but the application programs 660 are not meant to be limiting.

[0076] The operating system 650 controls the execution of other computer programs, and provides scheduling, input-output control, file and data management, memory management, and communication control and related services. The inventors contemplate that the application programs 660 for implementing exemplary embodiments can be suitable for all commercially available operating systems.

[0077] The application programs 660 can be source programs, executable programs (object code), script, or any other entity including a set of instructions to be executed. When a source program, the program is usually translated via a compiler (such as the compiler 640), assembler, interpreter, or the like, which can or can not be included within the memory 620, so as to operate in conjunction with the O / S 650. Furthermore, the application programs 660 can be written as an object oriented programming language, which has classes of data and methods, or a procedure programming language, which has routines, subroutines, and / or functions, for example but not limited to, C, C++, C#, Pascal, BASIC, API calls, HTML, XHTML, XML, ASP scripts, JavaScript, FORTRAN, COBOL, Perl, Java, ADA,.NET, and the like.

[0078] I / O devices 670 can include input devices such as, but not limited to, a mouse, keyboard, scanner, microphone, camera, etc. Furthermore, I / O devices 670 can also include output devices such as, but not limited to, a printer, display, etc. Finally, I / O devices 670 can also include devices that function both as input and output devices, such as, but not limited to, a NIC or a modem (for accessing remote devices, other files, devices, systems, or networks), a radio frequency (RF) or other transceiver, a telephone, a facsimile, and the like. I / O devices 670 also include components for communicating over various networks, such as the Internet or intranet.

[0079] If computer 600 is a PC, workstation, intelligent device or the like, software in memory 620 can also include a basic input output system (BIOS) (omitted for simplicity). The BIOS is a set of basic software routines that initialize and test hardware, start the O / S 650, and support the transfer of data between hardware devices.

[0080] When computer 600 is in operation, processor 610 is configured to execute software stored within memory 620, to communicate data to and from memory 620, and to generally control operations of computer 600 pursuant to the software. Application 660 and O / S 650 are read, possibly buffered within processor 610, and then executed.

[0081] When the application 660 is implemented in software it should be noted that the application 660 can be stored on virtually any computer readable medium for use by or in connection with any computer related system or method. In this document, the terms "computer- readable medium" and "computer program product" can be used interchangeably. A computer readable medium can be, for example but not limited to, an electronic, magnetic, optical, or other physical apparatus or device.

[0082] Application 660 can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this document, a "computer-readable medium" can be any means that can store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0083] Figure 1 the apparatus of Figure 3 the method of may be implemented in hardware or software, or in a hybrid implementing both hardware and software (e.g., as firmware running on hardware devices). Where an embodiment or a portion thereof is implemented in software, the functions shown in the process flow diagrams can be performed by one or more physically-located computing devices, such as one or more central processing units (CPUs) or graphics processing units (GPUs), suitably programmed. Each process as shown in the flow diagrams, and the individual steps of each, can be performed by the same or different computing devices. According to an embodiment, a computer-readable storage medium stores a computer program comprising computer program code configured to cause one or more physically-located computing devices to perform an encoding or decoding method as described above when the program is run on the one or more physically-located computing devices.

[0084] The storage medium can include volatile and non-volatile computer memory such as RAM, PROM, EPROM, and EEPROM, optical discs (such as CD, DVD, BD), magnetic storage media (such as hard disks and magnetic tape). The various storage media can be fixed within a computing device or can be removable so that one or more programs stored thereon can be loaded into a processor.

[0085] Data describing the alertness value determined according to an embodiment can be stored on a storage medium. Task performance data according to an embodiment can be stored on the same storage medium or on a different storage medium. Such data can be transmitted as a signal modulated onto an electromagnetic carrier. The signal can be defined according to a standard for digital communication. The carrier can be an optical carrier, a radio frequency wave, a millimeter wave, or a near field communication wave. It can be wired or wireless.

[0086] In case an embodiment or a portion thereof is implemented in hardware, Figure 1 The blocks shown in the block diagram of may be individual physical components or logical subdivisions of a single physical component, or can all be implemented in an integrated manner in one physical component. The functionality of one block shown in the drawings can be divided among multiple components in implementation, or the functionality of multiple blocks shown in the drawings can be combined in a single component in implementation. Hardware components suitable for use in embodiments of the present invention include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs). One or more blocks can be implemented as a combination of dedicated hardware to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.

[0087] Variations of the disclosed embodiments can be understood and implemented by those skilled in the art by studying the drawings, disclosure and claims in practice of the claimed invention. In the claims, the word "comprising" 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 can implement the functionality of several items recited in the claims. The mere fact that measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. If a computer program is discussed above, it can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state storage 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 telecommunication systems. If the term "adapted to" is used in the claims or the specification, it should be noted that the term "adapted to" is intended to be equivalent to the term "configured to." Any reference signs in the claims should not be construed as limiting the scope.

[0088] The flow and block diagrams in the drawings show architectural, functional, and operational representations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow and block diagrams can represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession can in fact be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Claims

1. A medical image processing device (100), comprising: An image reconstruction unit (110) is configured to process acquired medical imaging data by performing multiple reconstruction tasks to generate reconstructed images. The image reconstruction unit (110) is further configured as follows: Execute the first reconstruction task of the plurality of reconstruction tasks (310), wherein the first reconstruction task includes the execution of a reconstruction algorithm that can be paused; Pause (320) the execution of the first reconstruction task; During the pause of the first reconstruction task, the second reconstruction task of the plurality of reconstruction tasks (340) is executed; and After the second reconstruction task is completed, resume (370) the execution of the first reconstruction task; and A control unit (130) is configured to control the image reconstruction unit to suspend the execution of the first reconstruction task according to a control signal (140) provided from the control unit to the image reconstruction unit, and the control unit includes: Input interface (150), adapted to receive control input signals (160) describing at least one of the following: execution schedule; and scheduling constraints for the first reconstruction task. Furthermore, the control unit (130) is adapted to generate the control signal for the image reconstruction unit (110) based on the received control input signal.

2. The medical image processing apparatus according to claim 1, further comprising: A scheduling component (170) is configured to analyze the usage of a medical imaging device used to acquire medical imaging data. Based on the analysis results, at least one of the following is determined: an execution schedule table and scheduling constraints for the first reconstruction algorithm; and the control input signal (160) for the control unit (130) is generated based on the determined execution schedule table and / or scheduling constraints.

3. The medical image processing apparatus according to claim 1 or 2 further includes a data storage unit (120). And among them, The image reconstruction unit (110) is also configured to store (330) status information in the data storage unit in response to pausing the execution of the first reconstruction task, the status information describing the execution status of the first reconstruction task.

4. The medical image processing apparatus according to claim 3, wherein, The status information includes at least one of the following: The current version of the medical images; One or more algorithm parameter values; One or more algorithm settings; Iteration identifier; The current version of the data array; and Algorithm state description.

5. The medical image processing apparatus according to any one of claims 1 to 4, wherein, The reconstruction algorithms that can be paused include iterative algorithms. Furthermore, the image reconstruction unit (110) is configured to pause the execution of the first reconstruction task when one iteration of the pauseable reconstruction algorithm is completed.

6. The medical image processing apparatus according to claim 1, wherein, The input interface (150) includes a user interface (180) for receiving the control input signal from the user (190).

7. The medical image processing apparatus according to any one of claims 1 to 6, wherein, The medical imaging data includes CT or MRI data.

8. A medical image acquisition system, comprising: Medical imaging devices used to acquire medical imaging data; as well as The medical image processing apparatus (100) according to any one of claims 1 to 7.

9. A method for processing acquired medical imaging data to generate reconstructed images by performing multiple reconstruction tasks, the method comprising: Execute the first reconstruction task of the plurality of reconstruction tasks (310), wherein the first reconstruction task includes the execution of a reconstruction algorithm that can be paused; The execution of the first reconstruction task is suspended (320) according to a control signal, wherein the control signal is based on at least one of an execution schedule table and / or scheduling constraints for the first reconstruction task; During the pause of the first reconstruction task, the second reconstruction task of the plurality of reconstruction tasks (340) is executed; and After the second reconstruction task is completed, the execution of the first reconstruction task is resumed (370).

10. The method of claim 9, further comprising: In response to pausing the execution of the first reconstruction task, state information is stored (330) in the data storage unit, the state information describing the execution state of the first reconstruction algorithm.

11. The method according to claim 10, wherein, The pauseable reconstruction algorithm includes an iterative algorithm, wherein pausing the execution of the first reconstruction task depends on the completion of one iteration of the pauseable reconstruction algorithm.

12. A computer program including computer program code modules, wherein when the computer program is run on a computer, the computer program code modules are adapted to implement the method according to any one of claims 9 to 11.

Images