CN116646061B - Distributed CT imaging and intelligent diagnosis and treatment system and method - Google Patents
Distributed CT imaging and intelligent diagnosis and treatment system and method Download PDFInfo
- Publication number
- CN116646061B CN116646061B CN202310506674.8A CN202310506674A CN116646061B CN 116646061 B CN116646061 B CN 116646061B CN 202310506674 A CN202310506674 A CN 202310506674A CN 116646061 B CN116646061 B CN 116646061B
- Authority
- CN
- China
- Prior art keywords
- imaging
- task
- data
- intelligent
- distributed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 55
- 238000013170 computed tomography imaging Methods 0.000 title claims abstract description 34
- 238000011282 treatment Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000003384 imaging method Methods 0.000 claims abstract description 75
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 230000005540 biological transmission Effects 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims description 21
- 238000012800 visualization Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 3
- 238000002405 diagnostic procedure Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010923 batch production Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012774 diagnostic algorithm Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/566—Grouping or aggregating service requests, e.g. for unified processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
Abstract
The invention discloses a distributed CT imaging and intelligent diagnosis and treatment system, which comprises a plurality of lightweight CT terminals respectively deployed in different hospitals, wherein each lightweight CT terminal comprises a basic hardware device and an intelligent transmission terminal, the intelligent transmission terminal uploads original data scanned by the basic hardware device to a cloud end, the cloud end deploys a Pretools middleware service for data standardization processing, and a scheduling platform based on Kubernetes and a message queue based on RabbitMQ are constructed for creating and executing calculation tasks; the invention also discloses a distributed CT imaging and intelligent diagnosis and treatment method, which mainly comprises the steps of scanning through a lightweight CT terminal and uploading original data to a cloud end, wherein the cloud end obtains imaging and diagnosis and treatment results through standardized processing of the data and execution of calculation tasks. The distributed CT imaging and intelligent diagnosis and treatment system has the advantages of low cost and high intelligent degree, and realizes complete closed loop of scanning, imaging and diagnosis.
Description
Technical Field
The invention belongs to the technical field of medical imaging, and particularly relates to a distributed CT imaging and intelligent diagnosis and treatment system and a distributed CT imaging and intelligent diagnosis and treatment method.
Background
With the advancement of hierarchical diagnosis and reformation in China, computed tomography (Computed Tomography, CT) plays an extremely important role as one of the most commonly used tools in medical diagnosis. However, the conventional CT apparatus has the following problems: (1) Due to the high integration of CT hardware equipment and the lack of the national capacity of part of core components, the conventional CT price is high, which is far beyond the bearing capacity of community hospitals and primary hospitals; (2) Because the traditional CT equipment is solidified by matched software and algorithms, the traditional CT equipment generally only bears the basic functions of scanning and imaging, and needs to rely on various third party auxiliary diagnosis products to realize intelligent diagnosis, and most of the products can promote CT diagnosis efficiency, but only stay in the post-processing of CT images and are respectively administrative, too scattered and difficult to maintain; (3) Because of differences among different CT brands, different machine types and different algorithms, the imaged images are difficult to realize cross-hospital standardization, so that the problem of mutual recognition of the existing images among hospitals is difficult to solve, and the construction of each level of medical conjuncted units is hindered. The above problems severely restrict the popularization and popularization of national grading diagnosis and treatment system, so it is needed to provide a CT imaging and intelligent diagnosis and treatment system based on a plurality of CT hardware devices, and realize complete closed loop of scanning, imaging and diagnosis while reducing the cost.
Disclosure of Invention
The invention aims to provide a distributed CT imaging and intelligent diagnosis and treatment system, which solves the problems that the traditional CT equipment in the prior art has high cost and low intelligent degree and cannot realize complete closed loop of scanning, imaging and diagnosis.
It is another object of the present invention to provide a distributed CT imaging and intelligent diagnostic method.
The technical scheme adopted by the invention is that the distributed CT imaging and intelligent diagnosis and treatment system comprises a plurality of lightweight CT terminals which are respectively deployed in different hospitals, wherein each lightweight CT terminal comprises a basic hardware device and an intelligent transmission terminal, the intelligent transmission terminal uploads original data scanned by the basic hardware device to a cloud end, the cloud end is deployed with a Pretools middleware service for data standardization processing, and a scheduling platform based on Kubernetes and a message queue based on RabbitMQ are constructed for creating and executing calculation tasks.
The present invention is also characterized in that,
the basic hardware equipment comprises an emitter, a detector, a scanning bed and a scanning frame.
The intelligent transmission terminal adopts a tailored openSUSE system and is used for monitoring whether the scanning data are updated in real time, if yes, connection is established with the cloud and the updated scanning data are uploaded to the cloud.
The Pretools middleware service converts raw data of different manufacturers and brands into standard imaging data files and imaging parameter files, and stores the imaging data files and imaging parameter files in a distributed parallel storage system.
The original data is in a ct format, the imaging data file is in a prep format, and the imaging parameter file is in a param format; the distributed parallel storage system includes a full SSD data cache field for storing unscheduled raw data, imaging data files, and imaging parameter files, and a high available data storage field for storing raw data and calculation result data.
The computing task comprises four subtasks, which are respectively: the method comprises the steps of task initialization, cloud imaging, intelligent diagnosis and task ending processing, wherein a message queue based on RabbitMQ correspondingly comprises a task queue to be initialized, a task queue to be imaged, a task queue to be diagnosed and a task queue to be ended processing, which are sequentially triggered and switched.
Services running in Kubernetes-based dispatch platform include four resident services and two batch services, the resident services including: an initialization service, an imaging dispatch service, a diagnostic dispatch service, an end process service, a batch process service comprising: the imaging calculation service and the diagnosis calculation service are respectively packaged into independent Docker images and stored in a Harbor algorithm image warehouse.
The scheduling platform based on the Kubernetes also encapsulates an algorithm container, comprising (1) for execution of the algorithm, a multilingual supporting environment and remote invocation of a native algorithm are provided in the algorithm container; (2) Aiming at the collection of the logs, a monitoring interface mode based on Linux file protocol specification is adopted in an algorithm container, the standard log output rule of the algorithm is defined, the task logs are automatically collected and redirected into the platform task log; (3) For error monitoring, all possible anomalies are captured in the algorithm container and generalized into an anomaly mapping table defining the unique code, anomaly cause and anomaly handling means for each anomaly.
The cloud end performs operation and maintenance management in a centralized configuration and automatic monitoring mode, wherein the centralized configuration adopts Nacos as a configuration center of a cluster and is used for managing and updating the configuration of all applications in the platform; the automatic monitoring comprises a task monitoring center and a resource monitoring center, and is used for summarizing detailed indexes of task and cluster operation, and realizing resource visualization, task visualization, real-time log monitoring, real-time imaging preview, host monitoring implementation and historical task statistics.
The invention adopts another technical scheme that the distributed CT imaging and intelligent diagnosis and treatment method is executed on the distributed CT imaging and intelligent diagnosis and treatment system, and is specifically implemented according to the following steps:
step S1: the lightweight CT terminal scans a patient;
step S2: the lightweight CT terminal caches the original data locally and waits for uploading the original data to the cloud through the intelligent transmission terminal;
step S3: the cloud call Pretools middleware service performs standardization processing on the received original data to obtain imaging data files and imaging parameter files, and the imaging data files and the imaging parameter files are stored in a distributed parallel storage system;
step S4: the cloud end builds a computing cluster based on a dispatching platform of Kubernetes, a plurality of high-performance GPU servers which can be expanded at any time are relied on at the bottom layer, and computing tasks are created for imaging data files obtained in the step S3 in the form of Nvidia Docker containers;
step S5: and (3) triggering and executing all sub-tasks in the calculation task of the step S4 in sequence according to the set RabbitMQ message queue until the execution is successful, and releasing the result.
The invention has the advantages that,
(1) Compared with the traditional CT terminal, the distributed CT imaging and intelligent diagnosis and treatment system does not perform local imaging, can reduce the equipment cost, and is beneficial to popularization and application of the CT terminal in primary and community hospitals.
(2) The distributed CT imaging and intelligent diagnosis system of the invention uploads the original data scanned by the distributed CT terminal to the cloud for imaging and intelligent diagnosis, thereby realizing complete closed loop of scanning, imaging and diagnosis; and the algorithm, software and the running environment related to the CT imaging and intelligent diagnosis and treatment method are all arranged in the cloud, so that unified deployment, updating and maintenance are facilitated.
(3) The distributed CT imaging and intelligent diagnosis and treatment system provided by the invention is provided with the Pretools middleware service, and can be used for carrying out standardized processing on the original data scanned by CT terminals of different manufacturers and different brands, so that the problem of mutual identification of CT images among different hospitals is solved, and the construction of each level of medical conjunct units is promoted.
Drawings
FIG. 1 is a block diagram of a distributed CT imaging and intelligent diagnostic system of the present invention;
FIG. 2 is a flow chart of task state switching in the distributed CT imaging and intelligent diagnostic system of the present invention;
FIG. 3 is a schematic diagram of a Harbor algorithm mirror warehouse structure in the distributed CT imaging and intelligent diagnosis and treatment system of the present invention;
FIG. 4 is a schematic diagram of the imaging/diagnostic algorithm mirror image structure in the distributed CT imaging and intelligent diagnostic system of the present invention;
FIG. 5 is a schematic illustration of error handling within an imaging/diagnostic container in a distributed CT imaging and intelligent diagnostic system of the present invention;
fig. 6 is a business flow diagram of the distributed CT imaging and intelligent diagnostic method of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The structural block diagram of the distributed CT imaging and intelligent diagnosis and treatment system is shown in figure 1, and the distributed CT imaging and intelligent diagnosis and treatment system comprises a plurality of lightweight CT terminals which are respectively deployed in different hospitals, wherein each lightweight CT terminal comprises a basic hardware device and an intelligent transmission terminal, and the intelligent transmission terminal uploads original data scanned by the basic hardware device to a cloud end; the basic hardware equipment comprises a transmitter, a detector, a scanning bed, a scanning frame and the like, and is mainly used for scanning a patient, and the scanned data generate original data in the intelligent transmission terminal; the intelligent transmission terminal adopts a tailored openSUSE system and is used for monitoring whether the scanning data are updated in real time, if yes, connection is established with the cloud and the updated scanning data are uploaded to the cloud. Compared with the traditional CT terminal, the lightweight CT terminal does not perform local imaging, can reduce equipment cost, and is beneficial to popularization and application of the CT terminal in primary and community hospitals.
The cloud end of the distributed CT imaging and intelligent diagnosis and treatment system is provided with a Pretools middleware service for data standardization processing, and a scheduling platform based on Kubernetes and a message queue based on RabbitMQ are constructed for creating and executing calculation tasks.
Because of the difference of technical routes, imaging output standards of CT manufacturers are different, so that images among hospitals cannot be recognized mutually when patients cross-hospital to visit, and repeated scanning is required, the radiation risk is increased undoubtedly. The original data is the most original raw data file after the lightweight CT terminal scans, and is in a CT format, the imaging data file is a preprocessed file which is required to be read by an imaging algorithm, and is in a prep format, the imaging parameter file is a parameter file which is required to be read by the imaging algorithm, and information of a patient, a hospital and the like is recorded, and is in a param format; the distributed parallel storage system includes a full SSD data cache field for storing unscheduled raw data, imaging data files, and imaging parameter files, and a high available data storage field for storing raw data and calculation result data.
In order to further reduce the complexity of the platform and improve the concurrency capability, the cloud end builds a message queue based on RabbitMQ, simplifies the switching among a plurality of states of a single task in a message driving mode, and simultaneously weakens the pressure of the cloud end service peak period cluster. In addition, the calculation task created by the invention comprises four sub-tasks, namely: task initialization, cloud imaging, intelligent diagnosis and task ending processing, based on which, the message queues based on RabbitMQ correspondingly comprise four message queues which are sequentially triggered and switched, and the four message queues are respectively: the method comprises the steps of initializing a task queue, imaging the task queue, diagnosing the task queue and finishing the processing task queue, wherein a message of the task queue to be initialized is generated by a Pretools middleware, consumed by an initialization service, a new message is inserted into the task queue to be initialized after the Pretools middleware service finishes data standardization, the initialization service monitors that the message starts to operate, and a message is inserted into the task queue to be imaged after the initialization is successful; the method comprises the steps that a to-be-imaged task queue message is generated by an initialization service, consumed by an imaging scheduling service, when the imaging scheduling service monitors a new message, a host with residual resources in a cluster is acquired, the imaging task is distributed to a specific host to start execution, and a message is inserted into a to-be-diagnosed task queue after the imaging task is successful; the method comprises the steps that a to-be-diagnosed task queue message is generated by an imaging subtask, consumed by a diagnosis scheduling service, when the diagnosis scheduling service monitors a new message, a host with residual resources in a cluster is acquired, the diagnosis task is distributed to a specific host to start execution, and a message is inserted into a to-be-ended processing task queue after the diagnosis task is successful; the task queue information to be processed is generated by the diagnosis subtask, consumed by the task end processing service, and when the task end processing service monitors the new information, the task imaging and diagnosis results are finally processed, namely the results are issued, for example, the images are pushed to the pacs system, and the diagnosis report is pushed to the browsing software.
The task state switching flow is shown in fig. 2, and the specific process is as follows: after the image data file is preprocessed, the presools service sends a message to be initialized to the message queue, and the initialization service monitors the message to initialize the task, such as creating a task record, distributing cluster resources and the like; after the initialization is completed, the initialization service sends a message to be imaged to a message queue, and the imaging scheduling service monitors the message and distributes imaging tasks to a certain GPU node in the cluster for operation; after the imaging is finished, the imaging scheduling service sends a message to be diagnosed to a message queue, and the diagnosis scheduling service monitors the message and distributes a diagnosis task to a certain GPU node in the cluster for operation; after diagnosis is finished, the diagnosis scheduling service sends a task to be finished to a message queue, the finishing service monitors the message, and finishes the task, such as updating the task database state, uploading the image to the pacs system, and sending a diagnosis report to other terminal equipment.
The dispatching platform based on the Kubernetes is used for dispatching calculation in the platform in the form of a dock container for imaging and diagnosing tasks, and the services running in the platform comprise four resident services and two batch processing services for sequentially completing all sub-tasks of the calculation tasks, wherein the resident services comprise: initializing service, imaging scheduling service, diagnosing scheduling service and ending processing service; the batch service includes: an imaging computing service and a diagnostic computing service; and the algorithms corresponding to the services are packaged into independent Docker images and stored in a Harbor algorithm image warehouse for management, wherein the structure of the Harbor algorithm image warehouse is shown in figure 3, when the corresponding tasks are triggered only by being packaged and uploaded to the Harbor algorithm image warehouse during updating of the algorithm version, the platform automatically acquires the latest version or the specific historical version of the algorithm from the Harbor algorithm image warehouse and operates in the cluster. In addition, since the management of the Kubernetes on the algorithm container is limited to global and coarse granularity, the execution progress of the algorithm is required to be obtained, log printing and abnormal information need a large number of command line operations, and cannot be intuitively managed and monitored. Therefore, in order to ensure the stable operation of the algorithm, and simultaneously provide a plurality of necessary interfaces for docking with the platform side, so that the platform side can manage the operation of all tasks in real time, the platform performs finer encapsulation on the algorithm container on the basis of the original algorithm, and mainly comprises the following steps: (1) For the execution of the algorithm, a multi-language supporting environment such as Java, python, nvidia GPU or other languages and remote call of the original algorithm are provided in the algorithm container, so that the algorithm can be conveniently used by a platform no matter what language is used for development and what kind of input/output, and the imaging/diagnosis algorithm mirror structure is shown in figure 4. (2) Aiming at the collection of the logs, a monitoring interface mode based on Linux file protocol specifications is adopted in an algorithm container, standard log output criteria of the algorithm are defined, task logs are automatically collected, and the task logs are redirected into a platform task log. (3) For error monitoring, all possible anomalies, such as data anomalies, configuration file anomalies, resource anomalies, environmental anomalies, etc., are captured within the algorithm container and generalized into an anomaly mapping table defining unique codes, anomaly causes, and anomaly handling means for each anomaly, as shown in FIG. 5.
In addition, the cloud end of the invention adopts a centralized configuration and automatic monitoring mode to carry out operation and maintenance management, thereby realizing complete closed loop of scanning, imaging and diagnosis. The centralized configuration adopts Nacos as a configuration center of the cluster and is used for managing and updating the configuration of all applications in the platform; the automatic monitoring comprises a task monitoring center and a resource monitoring center, and is used for summarizing detailed indexes of task and cluster operation, and realizing resource visualization, task visualization, real-time log monitoring, real-time imaging preview, host monitoring implementation and historical task statistics.
Based on the distributed CT imaging and intelligent diagnosis and treatment system, the business flow of the distributed CT imaging and intelligent diagnosis and treatment method is shown in figure 6, and is implemented specifically according to the following steps:
step S1: the lightweight CT terminal scans a patient;
step S2: the lightweight CT terminal caches original scanning data locally and waits for uploading the original scanning data to the cloud end through the intelligent transmission terminal;
step S3: the cloud call Pretools middleware service performs standardization processing on the received original data to obtain imaging data files and imaging parameter files, and the imaging data files and the imaging parameter files are stored in a distributed parallel storage system;
step S4: the cloud end builds a computing cluster based on a dispatching platform of Kubernetes, a plurality of high-performance GPU servers which can be expanded at any time are relied on at the bottom layer, and computing tasks are created for imaging data files obtained in the step S3 in the form of Nvidia Docker containers;
step S5: and (3) triggering and executing all sub-tasks in the calculation task of the step S4 in sequence according to the set RabbitMQ message queue until the execution is successful, and releasing the result.
Claims (5)
1. The distributed CT imaging and intelligent diagnosis and treatment system is characterized by comprising a plurality of lightweight CT terminals which are respectively deployed in different hospitals, wherein each lightweight CT terminal comprises a basic hardware device and an intelligent transmission terminal, the intelligent transmission terminal uploads original data scanned by the basic hardware device to a cloud end, the cloud end is provided with a pre middleware service for data standardization processing, and a scheduling platform based on Kubernetes and a message queue based on RabbitMQ are constructed for creating and executing calculation tasks;
the basic hardware equipment comprises an emitter, a detector, a scanning bed and a scanning frame;
the intelligent transmission terminal adopts a tailored openSUSE system and is used for monitoring whether the scanning data are updated in real time, if yes, connection is established with a cloud end, and the updated scanning data are uploaded to the cloud end;
the pre tools middleware service converts the original data of different manufacturers and different brands into standard imaging data files and imaging parameter files, and stores the standard imaging data files and the imaging parameter files in a distributed parallel storage system;
the computing task comprises four sub-tasks, namely: the method comprises the steps of task initialization, cloud imaging, intelligent diagnosis and task ending processing, wherein the RabbitMQ-based message queue correspondingly comprises a task queue to be initialized, a task queue to be imaged, a task queue to be diagnosed and a task queue to be ended, which are triggered and switched in sequence;
the services running in the Kubernetes-based scheduling platform comprise four resident services and two batch services, wherein the resident services comprise: an initialization service, an imaging dispatch service, a diagnostic dispatch service, an end process service, the batch process service comprising: the imaging calculation service and the diagnosis calculation service are respectively packaged into independent Docker images and stored in a Harbor algorithm image warehouse.
2. The distributed CT imaging and intelligent diagnostic system of claim 1, wherein the raw data is in a.ct format, the imaging data file is in a.prep format, the imaging parameter file is in a param format; the distributed parallel storage system includes a full SSD data cache domain for storing unscheduled raw data, imaging data files, and imaging parameter files, and a high available data storage domain for storing raw data and calculation result data.
3. The distributed CT imaging and intelligent diagnostic system of claim 1 wherein the Kubernetes-based dispatch platform further encapsulates an algorithm container comprising (1) for execution of an algorithm, a multilingual support environment is provided within the algorithm container and remote invocation of a native algorithm; (2) Aiming at the collection of the logs, a monitoring interface mode based on Linux file protocol specification is adopted in an algorithm container, the standard log output rule of the algorithm is defined, the task logs are automatically collected and redirected into the platform task log; (3) For error monitoring, all possible anomalies are captured in the algorithm container and generalized into an anomaly mapping table defining the unique code, anomaly cause and anomaly handling means for each anomaly.
4. The distributed CT imaging and intelligent diagnosis and treatment system according to claim 3, wherein the cloud uses centralized configuration and automatic monitoring to perform operation and maintenance management, wherein the centralized configuration uses Nacos as a configuration center of a cluster for managing and updating configuration of all applications in the platform; the automatic monitoring comprises a task monitoring center and a resource monitoring center, and is used for summarizing detailed indexes of task and cluster operation, and realizing resource visualization, task visualization, real-time log monitoring, real-time imaging preview, host monitoring implementation and historical task statistics.
5. A distributed CT imaging and intelligent diagnostic method, characterized in that it is executed on a distributed CT imaging and intelligent diagnostic system according to claim 4, in particular according to the following steps:
step S1: the lightweight CT terminal scans a patient;
step S2: the lightweight CT terminal caches the original data locally and waits for uploading the original data to the cloud through the intelligent transmission terminal;
step S3: the cloud call Pretools middleware service performs standardization processing on the received original data to obtain imaging data files and imaging parameter files, and the imaging data files and the imaging parameter files are stored in a distributed parallel storage system;
step S4: the cloud end builds a computing cluster based on a dispatching platform of Kubernetes, a plurality of high-performance GPU servers which can be expanded at any time are relied on at the bottom layer, and computing tasks are created for imaging data files obtained in the step S3 in the form of Nvidia Docker containers;
step S5: and (3) triggering and executing all sub-tasks in the calculation task of the step S4 in sequence according to the set RabbitMQ message queue until the execution is successful, and releasing the result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506674.8A CN116646061B (en) | 2023-04-28 | 2023-04-28 | Distributed CT imaging and intelligent diagnosis and treatment system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506674.8A CN116646061B (en) | 2023-04-28 | 2023-04-28 | Distributed CT imaging and intelligent diagnosis and treatment system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116646061A CN116646061A (en) | 2023-08-25 |
| CN116646061B true CN116646061B (en) | 2024-01-26 |
Family
ID=87614521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310506674.8A Active CN116646061B (en) | 2023-04-28 | 2023-04-28 | Distributed CT imaging and intelligent diagnosis and treatment system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116646061B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016153790A1 (en) * | 2015-03-23 | 2016-09-29 | Oracle International Corporation | Knowledge-intensive data processing system |
| CN106963409A (en) * | 2017-04-28 | 2017-07-21 | 东北大学 | A kind of CT system and its application method |
| CN108492862A (en) * | 2018-02-01 | 2018-09-04 | 西安大数据与人工智能研究院 | Medical image cloud imaging based on Distributed C T terminating machines and interpretation method and system |
| CN109191541A (en) * | 2018-08-06 | 2019-01-11 | 沈阳晟诺科技有限公司 | A kind of CT remote image method for reconstructing |
| CN109979606A (en) * | 2019-01-07 | 2019-07-05 | 北京云度互联科技有限公司 | A method of micro services medical imaging cloud and cloud film are constructed based on containerization |
| CN110704164A (en) * | 2019-09-30 | 2020-01-17 | 珠海市新德汇信息技术有限公司 | Cloud native application platform construction method based on Kubernetes technology |
| EP3620112A1 (en) * | 2018-09-07 | 2020-03-11 | Canon Medical Systems Corporation | X-ray ct apparatus, medical image processing apparatus, and x-ray ct system |
| CN111831269A (en) * | 2020-07-21 | 2020-10-27 | 腾讯科技（深圳）有限公司 | Application development system, operation method, equipment and storage medium |
| CN112181592A (en) * | 2020-09-25 | 2021-01-05 | 上海聪充网络科技有限公司 | Method for lightweight deployment of distributed system in private cloud environment |
| CN113986830A (en) * | 2021-11-11 | 2022-01-28 | 西安交通大学 | Distributed CT-oriented cloud data management and task scheduling method and system |
| CN114429210A (en) * | 2022-01-27 | 2022-05-03 | 西安交通大学 | Cloud-protogenesis-based reinforcement learning pipeline method, system, equipment and storage medium |
| WO2022120806A1 (en) * | 2020-12-11 | 2022-06-16 | 深圳晶泰科技有限公司 | Multi-cloud distributed messaging method and system for high performance computing |
| CN115620897A (en) * | 2022-11-02 | 2023-01-17 | 明峰医疗系统股份有限公司 | Auxiliary method and system for automatic diagnosis of CT (computed tomography) equipment, CT equipment and storage medium |
| CA3178214A1 (en) * | 2021-09-29 | 2023-03-29 | Dr. Dadjou Dentistry Professional Corporation | System and method for intelligent diagnosis |
| CN116010518A (en) * | 2022-12-30 | 2023-04-25 | 江苏世通环宇电力科技有限公司 | Automatic cloud processing system for power line point cloud data based on container deployment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160092632A1 (en) * | 2014-09-25 | 2016-03-31 | Siemens Product Lifecycle Management Software Inc. | Cloud-Based Processing of Medical Imaging Data |
-
2023
- 2023-04-28 CN CN202310506674.8A patent/CN116646061B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016153790A1 (en) * | 2015-03-23 | 2016-09-29 | Oracle International Corporation | Knowledge-intensive data processing system |
| CN106963409A (en) * | 2017-04-28 | 2017-07-21 | 东北大学 | A kind of CT system and its application method |
| CN108492862A (en) * | 2018-02-01 | 2018-09-04 | 西安大数据与人工智能研究院 | Medical image cloud imaging based on Distributed C T terminating machines and interpretation method and system |
| CN109191541A (en) * | 2018-08-06 | 2019-01-11 | 沈阳晟诺科技有限公司 | A kind of CT remote image method for reconstructing |
| EP3620112A1 (en) * | 2018-09-07 | 2020-03-11 | Canon Medical Systems Corporation | X-ray ct apparatus, medical image processing apparatus, and x-ray ct system |
| CN109979606A (en) * | 2019-01-07 | 2019-07-05 | 北京云度互联科技有限公司 | A method of micro services medical imaging cloud and cloud film are constructed based on containerization |
| CN110704164A (en) * | 2019-09-30 | 2020-01-17 | 珠海市新德汇信息技术有限公司 | Cloud native application platform construction method based on Kubernetes technology |
| CN111831269A (en) * | 2020-07-21 | 2020-10-27 | 腾讯科技（深圳）有限公司 | Application development system, operation method, equipment and storage medium |
| CN112181592A (en) * | 2020-09-25 | 2021-01-05 | 上海聪充网络科技有限公司 | Method for lightweight deployment of distributed system in private cloud environment |
| WO2022120806A1 (en) * | 2020-12-11 | 2022-06-16 | 深圳晶泰科技有限公司 | Multi-cloud distributed messaging method and system for high performance computing |
| CA3178214A1 (en) * | 2021-09-29 | 2023-03-29 | Dr. Dadjou Dentistry Professional Corporation | System and method for intelligent diagnosis |
| CN113986830A (en) * | 2021-11-11 | 2022-01-28 | 西安交通大学 | Distributed CT-oriented cloud data management and task scheduling method and system |
| CN114429210A (en) * | 2022-01-27 | 2022-05-03 | 西安交通大学 | Cloud-protogenesis-based reinforcement learning pipeline method, system, equipment and storage medium |
| CN115620897A (en) * | 2022-11-02 | 2023-01-17 | 明峰医疗系统股份有限公司 | Auxiliary method and system for automatic diagnosis of CT (computed tomography) equipment, CT equipment and storage medium |
| CN116010518A (en) * | 2022-12-30 | 2023-04-25 | 江苏世通环宇电力科技有限公司 | Automatic cloud processing system for power line point cloud data based on container deployment |
Non-Patent Citations (3)
| Title |
|---|
| 医学影像系统的互联网应用;蒋君;庞树茂;冯前进;;中国数字医学(第01期);17-19+51 * |
| 基于微服务与容器技术的表达力测评系统的设计与实现;李龙飞;中国优秀硕士学位论文全文数据库信息科技辑(第6期);I138-173 * |
| 陕西科研团队国际首创云CT 中心技术;张梅;陕西日报;1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116646061A (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101605056B (en) | J2EE server monitoring device and monitoring method employing same | |
| US20090138318A1 (en) | Systems and methods for adaptive workflow and resource prioritization | |
| US9704207B2 (en) | Administering medical digital images in a distributed medical digital image computing environment with medical image caching | |
| US20070286466A1 (en) | DICOM adapter service for CAD system | |
| CN108243012B (en) | Charging application processing system, method and device in OCS (online charging System) | |
| US20120221346A1 (en) | Administering Medical Digital Images In A Distributed Medical Digital Image Computing Environment | |
| CN1755720A (en) | Methods and systems for caching and synchronizing project data | |
| US20030101291A1 (en) | Application programming interface for provision of DICOM services | |
| WO2019011765A1 (en) | Predictive maintenance for large medical imaging systems | |
| CN112615746B (en) | Edge calculation method, device and system | |
| US20130018694A1 (en) | Dynamically Allocating Business Workflows | |
| US20080133271A1 (en) | Job dispatcher for medical intelligent server architecture | |
| CN116646061B (en) | Distributed CT imaging and intelligent diagnosis and treatment system and method | |
| CN102508673B (en) | The system and method for fast Development and configuration platform class software | |
| CN112835713B (en) | Workload combination unified deployment method and system based on multi-container cluster | |
| CN109977173B (en) | Distributed and plug-in data monitoring system and method based on cloud data center | |
| US20230048473A1 (en) | Data labeling system and method, and data labeling manager | |
| CN1257463C (en) | System for automatic monitoring image management and communication | |
| Guojun et al. | An Application Research on the Workflow-based Large-scale Hospital Information System Integration | |
| KR100974621B1 (en) | Radio frequency identification business-aware framework | |
| CN106529153A (en) | Character set matching method and device for digital imaging and communications in medicine (DICOM) file | |
| WO2001028211A1 (en) | System and method for interfacing a radiology information system to a central dictation system | |
| CN113570347A (en) | RPA operation and maintenance method for micro-service architecture system | |
| CN114531479A (en) | General data acquisition system based on MQTT | |
| CN115081679A (en) | CDC-based industrial data dynamic change automatic perception processing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |