WO2023165622A1

WO2023165622A1 - Image recontruction task scheduling method and device

Info

Publication number: WO2023165622A1
Application number: PCT/CN2023/079756
Authority: WO
Inventors: 从洪伟; 程茂上
Original assignee: 上海联影医疗科技股份有限公司
Priority date: 2022-03-04
Filing date: 2023-03-06
Publication date: 2023-09-07
Also published as: CN114610455A

Abstract

An image reconstruction task scheduling method, a scheduling apparatus, a computer device, a non-volatile computer-readable storage medium, and a computer program product. The method comprises: acquiring a dependency relationship between multiple first image reconstruction tasks of a target object (S11); determining, according to the dependency relationship, scheduling information of the multiple first image reconstruction tasks (S12); and scheduling, on the basis of the scheduling information, reconstruction data corresponding to the first image reconstruction task on which the target image reconstruction task depends (S13).

Description

Image reconstruction task scheduling method and device

Cross References to Related Applications

This application claims the priority of the Chinese patent application filed with the State Intellectual Property Office of China on March 4, 2022, with the application number 2022102123034, and the title of the invention is "Image Reconstruction Task Scheduling Method and Device", the entire content of which is incorporated herein by reference Applying.

technical field

The present application relates to the technical field of image processing, in particular to an image reconstruction task scheduling method and device.

Background technique

For images obtained by techniques such as computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET) or PET-CT, in the process of image reconstruction , there are more tasks to rebuild. However, when the current mainstream medical image reconstruction methods perform image reconstruction tasks, there is a waste of reconstruction resources.

Contents of the invention

The first aspect of the present application provides a method for scheduling image reconstruction tasks, the method comprising: acquiring the dependency relationship between multiple first image reconstruction tasks of a target object; determining the multiple first image reconstruction tasks according to the dependency relationship Scheduling information of an image reconstruction task; and based on the scheduling information, scheduling reconstruction data corresponding to the first image reconstruction task on which the target image reconstruction task depends.

In one of the embodiments, the method further includes: acquiring a splitting instruction for the second image reconstruction task; and splitting the second image reconstruction task into a plurality of subtasks in response to the splitting instruction.

In one of the embodiments, after the acquisition of the dependencies among the multiple first image reconstruction tasks of the target object includes: displaying the tasks of the multiple first image reconstruction tasks on the task management interface according to the dependencies information.

In one of the embodiments, the method further includes: acquiring a scheduling instruction for at least one first task among the plurality of first image reconstruction tasks; and responding to the scheduling instruction, based on the scheduling information The multiple first image reconstruction tasks execute the scheduling corresponding to the scheduling instruction at the same time.

In one of the embodiments, the acquiring the scheduling instruction for at least one of the plurality of first image reconstruction tasks includes: receiving a selection operation for at least one of the plurality of first image reconstruction tasks; responding In the selection operation, determine the at least one first task; receive a trigger on the task scheduling control of the task management interface operations; and in response to the triggering operation, obtaining the scheduling instruction of the at least one first task among the plurality of first image reconstruction tasks.

In one of the embodiments, the task scheduling control is any one of a pause control, a resume control, an up control, a down control and a highest priority control.

In one of the embodiments, the method further includes: receiving a closing operation on the task management platform; and in response to the closing operation, saving the information to be restored of at least one second task before the task management platform is closed, Wherein, the second task is an unfinished task among the plurality of first image reconstruction tasks.

In one of the embodiments, the method further includes: after the task management platform is started, acquiring the information to be restored of the second task; and when the information to be restored meets a preset condition, The second task is started based on the information to be restored.

In one of the embodiments, the preset condition includes: the raw data required by the second task exists in the information to be restored, and the data corresponding to the first image reconstruction task on which the second task depends reconstruction data, the raw data is the scan data required by the second task.

In one of the embodiments, displaying the task information of the plurality of first image reconstruction tasks on the task management interface according to the dependency relationship includes: generating the plurality of first image reconstruction tasks according to the dependency relationship corresponding to at least one key-value pair; and based on the at least one key-value pair, display task information of the plurality of first image reconstruction tasks on the task management interface, wherein the tasks contained in the key-value pair are all for unfinished tasks.

In one of the embodiments, the method further includes: after the third task of the plurality of first image reconstruction tasks is completed, acquiring a key-value pair including the third task; A key-value pair, the determination of the plurality of first image reconstruction tasks depends on the fourth task of the third task; if there is a key-value pair that does not contain the third task, there is other tasks that depend on, delete the key-value pair of the third task; if there are no other tasks that are dependent on the fourth task in the key-value pairs that do not contain the third task, then start the third task Four tasks.

A second aspect of the present invention provides an image reconstruction task scheduling device, the device comprising: an acquisition module configured to acquire dependencies among multiple first image reconstruction tasks of a target object; and a processing module configured to: The dependency relationship is to determine scheduling information of the plurality of first image reconstruction tasks; and based on the scheduling information, schedule reconstruction data corresponding to the first image reconstruction tasks that a target image reconstruction task depends on.

In one of the embodiments, the device further includes: a display module configured to display task information of the plurality of first image reconstruction tasks on a task management interface according to dependencies.

In one of the embodiments, the obtaining module is further configured to obtain a splitting instruction for the second image reconstruction task; and the processing module is also configured to respond to the splitting instruction, and the second image reconstruction task Split into multiple subtasks.

In one of the embodiments, the obtaining module is further configured to obtain a scheduling instruction for at least one first task in the plurality of first image reconstruction tasks; and the processing module is also configured to respond to the scheduling instruction and concurrently execute scheduling corresponding to the scheduling instruction for the multiple first image reconstruction tasks based on the scheduling information.

In one of the embodiments, the obtaining module is further configured to: receive a shutdown operation on the task management platform; and obtain the information to be restored of the second task after the task management platform is turned on; and The processing module is further configured to: in response to the shutdown operation, save the to-be-recovered information of at least one second task before the task management platform is closed; a completed task; and when the information to be restored satisfies a preset condition, start the second task based on the information to be restored.

In one of the embodiments, the presentation module is configured to: generate at least one key-value pair corresponding to the plurality of first image reconstruction tasks according to the dependency relationship; and based on the at least one key-value pair, in the The task management interface displays task information of the plurality of first image reconstruction tasks, wherein the tasks included in the key-value pairs are unfinished tasks.

In one of the embodiments, the processing module is further configured to: after the third task of the plurality of first image reconstruction tasks is completed, obtain a key-value pair including the third task; based on the third task The key-value pair of tasks, the determination of the plurality of first image reconstruction tasks depends on the fourth task of the third task; if there is a key-value pair that does not contain the third task, there is For other tasks that the fourth task depends on, delete the key-value pair of the third task; and if there are no other tasks that are dependent on the fourth task in the key-value pairs that do not contain the third task, start The fourth task.

A third aspect of the present application provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to the first aspect of the present application when executing the computer program.

A fourth aspect of the present application provides a non-volatile computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method according to the first aspect of the present application are implemented .

A fifth aspect of the present application provides a computer program product. The computer program product includes a computer program, which implements the steps of the method according to the first aspect of the present application when executed by a processor.

Description of drawings

FIG. 1 is an architecture diagram of an image reconstruction task scheduling system according to an embodiment of the present application;

FIG. 2 is a schematic flow diagram illustrating a first process of an image reconstruction task scheduling method according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a directed acyclic graph according to an embodiment of the present application;

FIG. 4 is a schematic diagram showing a task management interface according to an embodiment of the present application;

FIG. 5 is a schematic flow diagram illustrating a second process of an image reconstruction task scheduling method according to an embodiment of the present application;

FIG. 6 is another schematic diagram showing a task management interface according to an embodiment of the present application;

FIG. 7 is a schematic flow diagram illustrating a third process of an image reconstruction task scheduling method according to an embodiment of the present application;

FIG. 8 is a schematic flow diagram showing the fourth process of an image reconstruction task scheduling method according to an embodiment of the present application;

FIG. 9 is a schematic structural diagram of an image reconstruction task scheduling device according to an embodiment of the present application;

FIG. 10 is an internal structure diagram of a computer device according to an embodiment of the present application.

Detailed ways

The technical solutions in some embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present application, not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments provided in this application belong to the scope of protection of this application.

Throughout the specification and claims, unless the context requires otherwise, the term "comprise" and other forms such as the third person singular "comprises" and the present participle "comprising" are used Interpreted as the meaning of openness and inclusion, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "example", "specific examples" example)" or "some examples (some examples)" etc. are intended to indicate that specific features, structures, materials or characteristics related to the embodiment or example are included in at least one embodiment or example of the present application. Schematic representations of the above terms are not necessarily referring to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be included in any suitable manner in any one or more embodiments or examples.

Hereinafter, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, a feature defined as "first" and "second" may explicitly or implicitly include one or more of these features. In the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

In describing some embodiments, the expressions "coupled" and "connected" and their derivatives may be used. For example, the term "connected" may be used in describing some embodiments to indicate that two or more elements are in direct physical or electrical contact with each other. As another example, the term "coupled" may be used when describing some embodiments to indicate that two or more elements are in direct physical or electrical contact. However, the terms "coupled" or "communicatively coupled" may also mean that two or more elements are not in direct contact with each other, but yet still co-operate or interact with each other. The embodiments disclosed herein are not necessarily limited by the context herein.

"At least one of A, B and C" has the same meaning as "at least one of A, B or C" and both include the following combinations of A, B and C: A only, B only, C only, A and B A combination of A and C, a combination of B and C, and a combination of A, B and C.

As used herein, the term "if" is optionally interpreted to mean "when" or "at" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined that ..." or "if [the stated condition or event] is detected" are optionally construed to mean "when determining ..." or "in response to determining ..." depending on the context Or "upon detection of [stated condition or event]" or "in response to detection of [stated condition or event]".

The use of "suitable for" or "configured to" herein means open and inclusive language that does not exclude devices that are suitable for or configured to perform additional tasks or steps.

In addition, the use of "based on" or "according to" is meant to be open and inclusive, as a process, step, calculation or other action "based on" or "according to" one or more stated conditions or values may in practice be based on additional condition or exceed the stated value.

The current mainstream medical image reconstruction methods are all relatively independent task modes. One reconstruction parameter corresponds to one reconstruction task, and the reconstruction parameters of each reconstruction task are not related to each other, which leads to the inability to schedule reconstruction resources for some reconstruction tasks that can use each other, wasting a lot of reconstruction resources and wasting A lot of user time.

Aiming at the technical problem of waste of reconstruction resources in the traditional technology when performing image reconstruction tasks, in one embodiment of the present application, a method for scheduling image reconstruction tasks is provided. The principle of the method is: to establish dependencies between image reconstruction tasks relationship, using the dependency relationship to determine the scheduling information of multiple first image reconstruction tasks, so that when reconstructing the target image reconstruction tasks among the multiple first image reconstruction tasks, the scheduling information on which the target image reconstruction tasks depend can be scheduled based on the scheduling information The reconstruction data corresponding to the first image reconstruction task, and, according to the scheduling instructions of any one or more tasks in the multiple first image reconstruction tasks, based on the scheduling information, the multiple first image reconstruction tasks can be executed simultaneously with the scheduling instructions corresponding schedule.

Fig. 1 schematically shows the architecture of an image reconstruction task scheduling system 10 according to an embodiment of the present application. picture The image reconstruction task scheduling system 10 includes an image reconstruction task scheduling device 11 and an imaging device 12 . The imaging device 12 can photograph the ROI of the target object, and obtain an image of the ROI of the target object, so that the image reconstruction task scheduling device 11 performs a corresponding image reconstruction task on the image. In the embodiment of the present application, the image reconstruction task scheduling device 11 and the image device 12 may be configured in the same device, or may be configured in different devices.

In an exemplary solution, generally, the image reconstruction task scheduling apparatus 11 may be a terminal device; the terminal device may have a general-purpose or dedicated computing device environment or configuration. For example: personal computer, server computer, handheld or portable device, tablet type device, multiprocessor device, distributed computing environment including any of the above devices or devices, etc. The terminal equipment may have different names, such as user equipment (UE), access equipment, terminal unit, terminal station, mobile station, mobile station, remote station, remote terminal, mobile equipment, wireless communication equipment, terminal agent or terminal devices, etc. In the embodiment of the present application, the device for implementing the function of the image reconstruction task scheduling device 11 may be a terminal device, or a device capable of supporting the image reconstruction task scheduling device 11 to realize the function, such as a chip system. In this application, a system on a chip may consist of chips, or may include chips and other discrete devices.

The image reconstruction task scheduling method provided in this embodiment will be described in detail below with reference to FIG. 1 , and the method is applied to a task management platform. Referring to FIG. 2, the method includes steps S11 to S13.

In step S11, the dependency among multiple first image reconstruction tasks of the target object is acquired.

Optionally, the dependencies between multiple first image reconstruction tasks can be manually set by the operator, or based on the associations between various task types and the The association relationship of each image reconstruction task under the type is obtained. In this embodiment, this is not limited.

It should be noted that the dependency relationship is used to characterize the job order of multiple first image reconstruction tasks.

Exemplarily, it is assumed that there are two first image reconstruction tasks, task A and task B. When task B can use the reconstruction results of task A, the dependency between task A and task B can be expressed as task B depends on task A.

In step S12, the scheduling information of multiple first image reconstruction tasks is determined according to the dependencies.

Optionally, the scheduling information carries the task identifier of the first image reconstruction task that the target image reconstruction task depends on; the scheduling information is used to indicate that the target image reconstruction is scheduled according to the task identifier of the first image reconstruction task that the target image reconstruction task depends on The reconstruction data of the first image reconstruction task on which the task depends.

In a possible implementation manner, the directed acyclic graph of multiple first image reconstruction tasks may be generated according to the dependencies, and the directed acyclic graph is stored in the database of the task management platform.

For example, referring to the directed acyclic graph shown in Figure 3, assuming that there are 7 first image reconstruction tasks, for the convenience of expression, the 7 first image reconstruction tasks are represented by node 1, node 2, node 3, node 4, node 5. Node 6, Node 7. Among them, node 0 represents the start node of the image reconstruction task, and node -1 represents the end node of the image reconstruction task. Traverse the directed acyclic graph for each node, and get multiple arrays including three elements, which in turn include dependent data, this section Point data and post data, get [0, 1, 2], [0, 1, 3], [1, 2, 5], [1, 3, 4], [2, 5, 6], [3 , 4, 6], [5, 6, 7], [4, 6, 7] and [6, 7, -1]. If the post data of the first node is the same as the dependent data of the second node, it is determined that there is a dependency relationship between the first node and the second node. It could be that two jobs are dependent if the third element of one array is equal to the first element of the other. Referring to FIG. 3 , for node 5, the dependency information includes [2, 5, 6]; for node 7, the dependency information includes [6, 7, -1]. If the post data of node 5 is the same as the dependent data of the node, it can be determined that there is a dependency relationship between node 5 and node 7 . According to the dependency relationship, it can be known that there is a dependency relationship between node 5 and node 2, and between node 2 and node 1. Therefore, the directed acyclic graph can be determined according to the dependency relationship between multiple nodes with dependency relationship.

As described above, the directed acyclic graph of multiple first image reconstruction tasks is obtained from the database of the task management platform according to the dependency relationship, and the scheduling information of the multiple first image reconstruction tasks is determined according to the directed acyclic graph.

In step S13, based on the scheduling information, schedule reconstruction data corresponding to the first image reconstruction task on which the target image reconstruction task depends.

Wherein, the target image reconstruction task may be at least one of multiple first image reconstruction tasks.

Specifically, according to the scheduling information, among the plurality of first image reconstruction tasks, the reconstruction data of the task to be used by the target image reconstruction task is determined, so as to schedule the reconstruction data of the task.

In a possible implementation manner, after acquiring the dependencies among the multiple first image reconstruction tasks of the target object, the steps include: displaying the task information of the multiple first image reconstruction tasks on the task management interface according to the dependencies, In order to intuitively display the dependency information and other information in the task information of multiple first image reconstruction tasks.

Optionally, the task information of the first image reconstruction task may include the serial number, sequence, image description, target object identification, dependency information, reconstruction progress and used reconstruction machine of the first image reconstruction task.

Exemplarily, the task management platform includes four task management modules of the total task, the main reconstruction machine, the iterative reconstruction machine and the post-processing reconstruction machine. Among them, the task management interface corresponding to the total task can display the task information of all image reconstruction tasks such as the main reconstruction machine, iterative reconstruction machine and post-processing reconstruction machine, and the image reconstruction task can be displayed in the task management interface corresponding to the main reconstruction machine as The task information of the main reconstruction task, the task information of the image reconstruction task as an iterative reconstruction task can be displayed in the task management interface corresponding to the iterative reconstruction machine, and the post-processing reconstruction task can be displayed in the task management interface corresponding to the post-processing reconstruction machine Task information for the task. The user can display the task management interface corresponding to the total task, the main reconstruction machine, the iterative reconstruction machine and the post-processing reconstruction machine by triggering the corresponding controls of the total task, the main reconstruction machine, the iterative reconstruction machine and the post-processing reconstruction machine.

Referring to FIG. 4 , the task management interface 01 of the total task is shown in the task management platform, and the task information of 9 image reconstruction tasks is displayed in this interface. Task information includes sequence number, sequence, image description (referred to as description), target object identification (referred to as target object), dependency information (referred to as dependency), reconstruction progress (referred to as reconstruction) and the used The reconstruction machine used (referred to as the reconstruction machine). Among them, in Figure 4, in the dependent column, the corresponding serial number is 5, and the identification 4 is displayed in the display box, which represents that the image reconstruction task with the serial number 5 depends on the image reconstruction task with the serial number 4; in the dependent column in Figure 4 In the display frame corresponding to serial number 8, a mark 7 is displayed, which indicates that the image reconstruction task with serial number 8 depends on the image reconstruction task with serial number 7.

Specifically, displaying task information of the plurality of first image reconstruction tasks on the task management interface according to the dependency relationship includes: generating at least one key-value pair corresponding to the plurality of first image reconstruction tasks according to the dependency relationship. And based on at least one key-value pair, the task information of multiple first image reconstruction tasks is displayed on the task management interface; the tasks contained in the key-value pair are unfinished tasks.

Exemplarily, a base job (BaseJob) dependent job (DependJob) map (Map), ie, BaseJobDependJobMap, of the dependency relationship is constructed as a basis for restarting the second job. details as follows:

Assume that the task to be rebuilt first is BaseJob (its ID is expressed as BaseJobID), and the task that depends on BaseJob is DependJob (its ID is expressed as DependJobID). When the BaseJob is rebuilt, DependJob needs to be started, and the <BaseJobID, DependJobID> key is generated according to this rule Value pair, stored in BaseJobDependJobMap. For example, task 2 is started after task 1 is rebuilt, then BaseJob is task 1, DependJob is task 2, and the key-value pairs of task 1 and task 2 are <1, 2>.

For example, the multiple first image reconstruction tasks are 5 reconstruction tasks (task 1, task 2, task 3, task 4, task 5), it is necessary to start task 2 after task 1 is reconstructed, and start task 3 after task 2 is reconstructed And 4, start task 5 after rebuilding tasks 3 and 4, the whole process must be rebuilt in a certain order. Then the BaseJobDependJobMap constructed based on the above dependencies can be [<1,2>,<2,3>,<2,4>,<3,5>,<4,5>].

After the third task of the plurality of first image reconstruction tasks is completed, a key-value pair including the third task is acquired. Based on the key-value pairs of the third task, the determination of the plurality of first image reconstruction tasks depends on the fourth task of the third task. If there are other tasks that are dependent on the fourth task among the key-value pairs that do not include the third task, delete the key-value pair of the third task. If there is no other task dependent on the fourth task among the key-value pairs not including the third task, the fourth task is started.

Exemplarily, after receiving the reconstruction completion message of the third task, the next reconstruction task is scheduled according to the mapping relationship and scheduling rules in the BaseJobDependJobMap. The scheduling rules are as follows:

Rule 1. Assuming that the currently rebuilt task is BaseJob1, search for the key-value pair whose BaseJobID is BaseJob1 from BaseJobDependJobMap; if found, record the key-value pair as map1 and its DependJobID as DependJob1, and delete map1 from BaseJobDependJobMap; if not found to, it ends.

Rule 2. Find the key-value pair whose DependJobID is DependJob1 from the BaseJobDependJobMap; if found, it indicates that DependJob1 also depends on other tasks, and end; if not found, it indicates that all dependent tasks of DependJob1 have been rebuilt, and start the DependJob1 task.

The image reconstruction task scheduling method described above determines the scheduling information of the multiple first image reconstruction tasks through the acquired dependencies between the multiple first image reconstruction tasks of the target object, so that the multiple first image reconstruction tasks in the When the target image reconstruction task performs reconstruction, reconstruction data corresponding to the first image reconstruction task on which the target image reconstruction task depends can be scheduled based on the scheduling information. Not only can the speed of image reconstruction be improved, but the time for image reconstruction can be saved; at the same time, computing resources for image reconstruction can be effectively saved, thereby avoiding the waste of reconstruction resources and improving the utilization rate of reconstruction resources.

In one embodiment, considering the excessive calculation in an image reconstruction task, in order to shorten the image reconstruction time, an image reconstruction task may be split into multiple subtasks. Therefore, referring to FIG. 5 , the image reconstruction task scheduling method provided in this embodiment further includes steps S21 and S22.

In step S21, a split instruction for the second image reconstruction task is acquired.

In this embodiment, the split instruction of the second image reconstruction task may be generated according to a preset operation of the operator. For example, the preset operation may be to trigger the split control after the second image reconstruction task is selected; it may also be to double-click the left mouse button after the second image reconstruction task is selected. The embodiment of the present application does not impose any limitation on the manner of the preset operation.

In step S22, in response to the split instruction, split the second image reconstruction task into multiple subtasks.

In this embodiment, there are multiple ways to split the second image reconstruction task into multiple subtasks, specifically, including but not limited to at least one of the following ways:

Way 1: The second image reconstruction task is equally divided into N parts by using an average division method, so that the second image reconstruction task is divided into N subtasks.

Method 2: Determine the resource size that can be allocated according to the resource utilization rate of the current image reconstruction task, and determine the number of subtasks that can be divided into the second image reconstruction task according to the allocated resource size.

Further, task information corresponding to multiple subtasks is displayed in the task management interface. Wherein, the operator controls whether the task information of the multiple subtasks is hidden or displayed by triggering the folding and unfolding controls corresponding to the multiple subtasks.

Exemplarily, it can be determined which image reconstruction tasks corresponding to serial numbers are subtasks obtained by splitting the same image reconstruction task through the sequences displayed in the task management interface 01, specifically, subtasks belonging to the same sequence are split tasks of the same image reconstruction task Got it. The sequences corresponding to serial number 1, serial number 2, and serial number 3 shown in Figure 4 are all 101, which can be determined as three subtasks obtained by splitting the same image reconstruction task, by triggering the folding and unfolding control 011 at the area where serial number 1 is located. Control the task information corresponding to serial number 2 and serial number 3 to hide or display. Refer to Figure 6 for the folded rendering.

In this embodiment, the image reconstruction task is split to obtain multiple subtasks through the split instruction for the image reconstruction task, which shortens the image reconstruction time of the image reconstruction task, thereby improving the reconstruction efficiency of the image reconstruction task. Rate.

In one embodiment, referring to FIG. 7 , in order to implement control operations on multiple first image reconstruction tasks at the same time, the image reconstruction task scheduling method provided in this embodiment further includes steps S31 and S32.

In step S31, a scheduling instruction for at least one first task among the plurality of first image reconstruction tasks is acquired.

It should be noted that, if it is necessary to perform operations corresponding to related scheduling instructions for multiple first image reconstruction tasks, it is preferable to trigger one of the first tasks to obtain the scheduling instruction, and realize multiple first image reconstruction tasks according to the scheduling instruction. Co-scheduling of reconstruction tasks. It can be understood that acquiring a scheduling instruction for at least one first task among the multiple first image reconstruction tasks may also be acquiring a scheduling instruction for multiple first image reconstruction tasks.

Specifically, an operation of selecting at least one task among the plurality of first image reconstruction tasks is received. In response to the selection operation, at least one first task is determined. Receive a trigger operation on the task scheduling control of the task management interface. In response to the triggering operation, a scheduling instruction of at least one first task among the plurality of first image reconstruction tasks is obtained.

Optionally, the task scheduling control is any one of a pause control, a resume control, an up control, a down control, and a highest priority control. The corresponding scheduling instruction may include any one of a pause instruction, a continue instruction, an up instruction, a down instruction, and a highest priority instruction. Wherein, the upward instruction refers to adjusting the priority upward, and the downward instruction refers to adjusting the priority downward.

For example, referring to Fig. 4, when it is necessary to stop the tasks of sequence number 7 and sequence number 8, by selecting the area 701 where the task information of sequence number 7 is located, or the selection operation of the area 801 where the task information of sequence number 8 is located, or At least one first task can be determined by simultaneously selecting the area 701 where the task information of sequence number 7 is located and the area 801 where the task information of sequence number 8 is located. Afterwards, dispatch instructions can be generated by triggering the pause control.

In step S32, in response to the scheduling instruction, based on the scheduling information, the scheduling corresponding to the scheduling instruction is executed simultaneously for a plurality of first image reconstruction tasks.

Optionally, after obtaining the scheduling instruction, the task management platform determines other image reconstruction tasks that have a dependency relationship with the first task by scheduling the new area, and at the same time execute the pairing of the first task and other image reconstruction tasks that have a dependency relationship with the first task. The dispatch corresponding to the dispatch instruction.

Based on the above example, assuming that it is the selection operation of the area 701 where the task information of No. 7 is located, after the pause control is triggered, a pause command is generated; according to the scheduling information, it can be determined that the image reconstruction task of No. 8 and the image reconstruction task of No. 7 exist dependency relationship, the image reconstruction task with sequence number 7 and the image reconstruction task with sequence number 8 are suspended at the same time.

In this embodiment, multiple first image reconstruction tasks can be determined according to the scheduling information related to the first task through the scheduling instruction of at least one first task among the multiple first image reconstruction tasks, so that multiple first image reconstruction tasks can be implemented. An image reconstruction task executes the scheduling corresponding to the scheduling instruction at the same time, thereby saving user operations.

In one embodiment, during the operation of the task management platform, due to various reasons, it needs to be shut down, powered off, restarted, etc. Operation, some image reconstruction tasks can only be forced to be interrupted, and simple reconstruction tasks (such as axial, helical, etc.) can be restored through reconstruction persistence. However, as business needs increase, an image reconstruction task (such as automatic optimal heartbeat reconstruction , automatic post-processing of pulmonary nodules, etc.) may require multiple image reconstruction tasks to be completed collaboratively, and the existing restoration methods for image reconstruction tasks are no longer applicable to the restoration of complex image reconstruction tasks. It is inconvenient to perform offline reconstruction after the completed image reconstruction task. Therefore, referring to FIG. 8 , the image reconstruction task scheduling method provided by this embodiment further includes steps S41 and S42.

In step S41, an operation of closing the task management platform is received.

It can be understood that operations such as shutting down, powering off, and restarting the task management platform include shutting down the task management platform.

In step S42, in response to the shutdown operation, the to-be-restored information of at least one second task before the task management platform is closed is saved; the second task is an unfinished task among the plurality of first image reconstruction tasks.

Optionally, when the task management platform is closed, at least one reconstruction task set of the second task is constructed; the information to be restored of the unfinished task (ie, the second task) is saved in the reconstruction task set in the form of a database, a file, or the like. The content of the information to be restored includes, but is not limited to: raw data required by the second task and reconstruction data corresponding to the first image reconstruction task on which the second task depends. Of course, the identification information and scheduling information of the second task also need to be saved in the reconstruction task set, where the identification information may be a sequence number and/or a sequence number.

Among them, unfinished tasks include image reconstruction tasks not yet reconstructed and image reconstruction tasks under reconstruction.

In an implementation manner, for an image reconstruction task that does not have a dependency relationship, when the task management platform is closed, the information to be restored that needs to be saved may only include raw data required by the image reconstruction task.

Further, after the task management platform is closed, there is an opening operation corresponding to this closing. Therefore, after the task management platform is started, the to-be-recovered information of the second task is acquired. In the case that the information to be restored satisfies the preset condition, the second task is started based on the information to be restored.

Wherein, the information to be restored satisfying the preset conditions includes: the raw data required by the second task exists in the information to be restored, and the reconstruction data corresponding to the first image reconstruction task that the second task depends on; the raw data is required by the second task scan data.

In this embodiment, for image reconstruction tasks without dependencies, the information to be restored only needs to include the required raw data; then when judging whether the information to be restored meets the preset conditions, it is only necessary to judge whether there is a second The raw data required for the task is enough.

It should be noted that, for image reconstruction tasks without dependencies, when the preset conditions are not met, the image reconstruction tasks are directly removed from the reconstruction task set; for image creation tasks with dependencies, when the preset conditions are not met When the condition is set, the image reconstruction task and tasks that have dependencies with it are removed from the reconstruction task set.

Specifically, according to the dependency relationship, at least one key-value pair corresponding to multiple first image reconstruction tasks is generated, and based on at least one key-value pair, the first image reconstruction on which the second task depends is determined among the multiple first image reconstruction tasks Task.

In this embodiment, in response to the closing operation of the task management platform, the unfinished tasks of the multiple first image reconstruction tasks before the task management platform is closed are saved to be restored, so that after the task management platform is restarted later, for Facilitate the unfinished task of rebuilding.

It should be understood that although the steps in the flow charts of FIG. 2 , FIG. 5 , FIG. 7 , and FIG. 8 are sequentially displayed as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in Fig. 2, Fig. 5, Fig. 7, and Fig. 8 may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be executed at different moments The execution order of these steps or stages is not necessarily performed sequentially, but may be executed in turn or alternately with other steps or at least a part of steps or stages in other steps.

In one embodiment, referring to FIG. 9 , an image reconstruction task scheduling device 11 is provided, which is applied to a task management platform. The device 11 includes an acquisition module 111 , a processing module 112 and a presentation module 113 .

The acquiring module 111 is configured to acquire dependencies among multiple first image reconstruction tasks of the target object. The processing module 112 is configured to: determine scheduling information of multiple first image reconstruction tasks according to dependencies; and schedule reconstruction data corresponding to the first image reconstruction tasks on which the target image reconstruction tasks depend based on the scheduling information. The presentation module 113 is configured to display the task information of multiple first image reconstruction tasks on the task management interface according to the dependencies.

In one of the embodiments, the acquiring module 111 is further configured to acquire split instructions for the second image reconstruction task. The processing module 112 is further configured to split the second image reconstruction task into a plurality of subtasks in response to the split instruction.

In one of the embodiments, the obtaining module 111 is further configured to obtain a scheduling instruction for at least one first task among the plurality of first image reconstruction tasks. The processing module 112 is further configured to, in response to the scheduling instruction, simultaneously execute the scheduling corresponding to the scheduling instruction for the plurality of first image reconstruction tasks based on the scheduling information.

In one of the embodiments, the acquisition module 111 is further configured to receive a selection operation of at least one of the plurality of first image reconstruction tasks; and receive a trigger operation of a task scheduling control on the task management interface. The processing module 112 is further configured to: determine at least one first task in response to the selection operation; obtain a scheduling instruction of at least one first task in the plurality of first image reconstruction tasks in response to the trigger operation.

In one embodiment, the task scheduling control is any one of a pause control, a resume control, an up control, a down control, and a highest priority control.

In one of the embodiments, the acquisition module 111 is further configured to receive a shutdown operation on the task management platform. The processing module 112 is further configured to, in response to the shutdown operation, save the to-be-recovered data of at least one second task before the shutdown of the task management platform. reply information. The second task is an unfinished task among the multiple first image reconstruction tasks.

In one of the embodiments, the acquiring module 111 is further configured to acquire the to-be-recovered information of the second task after the task management platform is started. The processing module 112 is further configured to start a second task based on the information to be restored when the information to be restored satisfies a preset condition.

In one embodiment, the information to be restored that meets the preset conditions includes: the raw data required by the second task exists in the information to be restored, and the reconstruction data corresponding to the first image reconstruction task that the second task depends on; the raw data is The scan data needed for the second task.

In one of the embodiments, the display module 113 is configured to: generate at least one key-value pair corresponding to a plurality of first image reconstruction tasks according to the dependency relationship; based on at least one key-value pair, display a plurality of first images on the task management interface Task information for rebuild tasks. The tasks contained in the key-value pair are unfinished tasks.

In one of the embodiments, the processing module 112 is further configured to: after the third task of the plurality of first image reconstruction tasks is completed, obtain the key-value pair containing the third task; based on the key-value pair of the third task, in The determination of multiple first image reconstruction tasks depends on the fourth task of the third task; if there are other tasks that are dependent on the fourth task in the key-value pairs that do not include the third task, delete the key-value pair of the third task ; If there is no other task that is dependent on the fourth task in the key-value pair that does not include the third task, start the fourth task.

For the specific limitations of the image reconstruction task scheduling device, refer to the above-mentioned limitations of the image reconstruction task scheduling method, which will not be repeated here. Each module in the above-mentioned image reconstruction task scheduling device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure may be as shown in FIG. 10 . The computer device includes a processor, memory and a network interface connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used to store initial data, and the network interface of the computer equipment is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, an image reconstruction task scheduling method is realized. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touch pad provided on the casing of the computer device , and can also be an external keyboard, touchpad, or mouse.

Those skilled in the art can understand that the structure shown in Figure 10 is only a partial structure related to the solution of this application The block diagram does not constitute a limitation to the computer equipment on which the application scheme is applied. The specific computer equipment may include more or less components than those shown in the figure, or combine certain components, or have different components. layout.

In one embodiment, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: Obtaining the dependency between multiple first image reconstruction tasks of the target object ; According to the dependency relationship, determine scheduling information of the plurality of first image reconstruction tasks; based on the scheduling information, schedule reconstruction data corresponding to the first image reconstruction tasks on which the target image reconstruction tasks depend.

In one embodiment, a non-volatile computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: acquiring one of multiple first image reconstruction tasks of a target object Dependencies between; according to the dependencies, determine the scheduling information of the multiple first image reconstruction tasks; based on the scheduling information, schedule the reconstruction data corresponding to the first image reconstruction tasks that the target image reconstruction tasks depend on .

In one embodiment, a computer program product is provided, which includes a computer program, and when the computer program is executed by a processor, the following steps are implemented: obtaining the dependency among multiple first image reconstruction tasks of the target object; according to the The dependency relationship is to determine scheduling information of the plurality of first image reconstruction tasks; based on the scheduling information, schedule reconstruction data corresponding to the first image reconstruction tasks that the target image reconstruction tasks depend on.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be completed by instructing related hardware through computer programs, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile and volatile storage. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive variable memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided by this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

The technical features of the above embodiments can be combined arbitrarily, and for the sake of concise description, the All possible combinations of various technical features are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered as within the scope of this specification.

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be determined by the appended claims.

Claims

A method for scheduling an image reconstruction task, characterized in that the method comprises:

Obtaining dependencies among multiple first image reconstruction tasks of the target object;

determining scheduling information of the plurality of first image reconstruction tasks according to the dependencies; and

Based on the scheduling information, schedule reconstruction data corresponding to the first image reconstruction task that the target image reconstruction task depends on.
The image reconstruction task scheduling method according to claim 1, wherein the method further comprises:

obtaining split instructions for the second image reconstruction task; and

In response to the split instruction, split the second image reconstruction task into multiple subtasks.
The image reconstruction task scheduling method according to claim 1, wherein after said obtaining the dependencies between a plurality of first image reconstruction tasks of the target object comprises:

According to the dependency relationship, task information of the plurality of first image reconstruction tasks is displayed on a task management interface.
The image reconstruction task scheduling method according to claim 1, wherein the method further comprises:

obtaining a scheduling instruction for at least one first task of the plurality of first image reconstruction tasks; and

In response to the scheduling instruction, based on the scheduling information, the scheduling corresponding to the scheduling instruction is executed on the plurality of first image reconstruction tasks simultaneously.
The image reconstruction task scheduling method according to claim 4, wherein said acquiring a scheduling instruction for at least one task in said plurality of first image reconstruction tasks comprises:

receiving a selection operation of at least one of the plurality of first image reconstruction tasks;

determining the at least one first task in response to the selecting operation;

receiving a trigger operation on the task scheduling control of the task management interface; and

In response to the triggering operation, the scheduling instruction of the at least one first task among the plurality of first image reconstruction tasks is obtained.
The image reconstruction task scheduling method according to claim 1, wherein the method further comprises:

receiving a shutdown operation on said task management platform; and

In response to the shutdown operation, the to-be-recovered information of at least one second task before the shutdown of the task management platform is saved, wherein the second task is an unfinished task among the plurality of first image reconstruction tasks.
The image reconstruction task scheduling method according to claim 6, wherein the method further comprises:

After the task management platform is started, acquiring the information to be resumed of the second task; and

If the information to be restored satisfies a preset condition, the second task is started based on the information to be restored.
The image reconstruction task scheduling method according to claim 7, wherein the preset conditions include:

The raw data required by the second task and the reconstruction data corresponding to the first image reconstruction task that the second task depends on exist in the information to be restored, and the raw data is required by the second task scan data required.
The image reconstruction task scheduling method according to claim 3, wherein, according to the dependency relationship, displaying the task information of the plurality of first image reconstruction tasks on the task management interface includes:

Generate at least one key-value pair corresponding to the plurality of first image reconstruction tasks according to the dependency relationship; and

Based on the at least one key-value pair, task information of the plurality of first image reconstruction tasks is displayed on the task management interface, wherein all tasks included in the key-value pair are unfinished tasks.
The image reconstruction task scheduling method according to claim 9, wherein the method further comprises:

After the third task of the plurality of first image reconstruction tasks is completed, obtain a key-value pair including the third task;

Based on the key-value pair of the third task, the determination of the plurality of first image reconstruction tasks depends on a fourth task of the third task;

If there are other tasks that the fourth task depends on in the key-value pairs that do not include the third task, then delete the key-value pair of the third task; and

If there is no other task dependent on the fourth task among the key-value pairs not including the third task, start the fourth task.
An image reconstruction task scheduling device, characterized in that the device comprises:

An acquisition module configured to acquire dependencies among multiple first image reconstruction tasks of the target object; and

The processing module is configured to: determine the scheduling information of the plurality of first image reconstruction tasks according to the dependency relationship; and based on the scheduling information, schedule the tasks corresponding to the first image reconstruction tasks on which the target image reconstruction task depends. Rebuild data.
The image reconstruction task scheduling device according to claim 11, said device further comprising:

The display module is configured to display the task information of the plurality of first image reconstruction tasks on the task management interface according to the dependency relationship.
The image reconstruction task scheduling device according to claim 11, characterized in that:

The obtaining module is also configured to obtain splitting instructions for the second image reconstruction task; and

The processing module is further configured to split the second image reconstruction task into a plurality of subtasks in response to the split instruction.
The image reconstruction task scheduling device according to claim 11, characterized in that:

The obtaining module is further configured to obtain a scheduling instruction for at least one first task in the plurality of first image reconstruction tasks; and

The processing module is further configured to, in response to the scheduling instruction, simultaneously execute the scheduling corresponding to the scheduling instruction for the plurality of first image reconstruction tasks based on the scheduling information.
The image reconstruction task scheduling device according to claim 11, characterized in that:

The obtaining module is further configured to: receive a shutdown operation on the task management platform; and obtain the to-be-recovered information of the second task after the task management platform is turned on; and

The processing module is further configured to: in response to the shutdown operation, save the to-be-recovered information of at least one second task before the task management platform is closed; a completed task; and when the information to be restored satisfies a preset condition, start the second task based on the information to be restored.
The image reconstruction task scheduling device according to claim 15, wherein the preset conditions include:

The raw data required by the second task and the reconstruction data corresponding to the first image reconstruction task that the second task depends on exist in the information to be restored, and the raw data is required by the second task scan data required.
The image reconstruction task scheduling device according to claim 12, wherein the display module is configured as:

Generate at least one key-value pair corresponding to the plurality of first image reconstruction tasks according to the dependency relationship; and

Based on the at least one key-value pair, task information of the plurality of first image reconstruction tasks is displayed on the task management interface, wherein all tasks included in the key-value pair are unfinished tasks.
The image reconstruction task scheduling device according to claim 17, wherein the processing module is further configured to:

After the third task of the plurality of first image reconstruction tasks is completed, obtain a key-value pair including the third task;

Based on the key-value pair of the third task, the determination of the plurality of first image reconstruction tasks depends on a fourth task of the third task;

If there are other tasks that the fourth task depends on in the key-value pairs that do not include the third task, then delete the key-value pair of the third task; and

If there is no other task dependent on the fourth task among the key-value pairs not including the third task, start the fourth task.
A computer device comprising a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 10 when executing the computer program.
A non-volatile computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is realized.