CN112669940A - Quality control film reading method and system based on AI (Artificial Intelligence) image - Google Patents
Quality control film reading method and system based on AI (Artificial Intelligence) image Download PDFInfo
- Publication number
- CN112669940A CN112669940A CN202011550751.2A CN202011550751A CN112669940A CN 112669940 A CN112669940 A CN 112669940A CN 202011550751 A CN202011550751 A CN 202011550751A CN 112669940 A CN112669940 A CN 112669940A
- Authority
- CN
- China
- Prior art keywords
- data
- quality control
- image
- image data
- medical
- 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.)
- Pending
Links
Images
Abstract
The invention discloses a quality control film reading method and a system based on AI images, wherein the method comprises the following steps: s1, collecting real-time image data and historical image data; s2, the collected data are sorted and standardized; s3, generating a standardized database from the processed data by a preset method; s4, performing data mining and classification on the quality control factor of each image data in the standardized database by using a preset rule; and S5, outputting quality control factor conclusion corresponding to each image data, and arranging into label and assets for storage. Has the advantages that: when the image quality of the medical image is specifically evaluated, the image is automatically matched with the corresponding inspection part of the image, so that effective preliminary quality control is output, and related quality control evaluation factor conclusions are output for experts to refer and correct, repeated content reading of the medical image and selection of the quality control evaluation factors are reduced, and the quality control efficiency is improved.
Description
Technical Field
The invention relates to the field of medical images, in particular to a quality control film reading method and system based on AI images.
Background
The medical image is a technique and a processing process for obtaining an internal tissue image of a human body or a certain part of the human body in a non-invasive way for medical treatment or medical research, the medical image is one of important techniques for auxiliary diagnosis of diseases, the medical image examination generally applied in clinic at present mainly comprises X-rays, CT, ultrasound, electrocardiogram and the like, and the medical image examination provides visual and scientific basis for medical diagnosis, can better match the symptoms, the assay indexes and the like of patients and plays an important role in accurately diagnosing diseases for clinicians.
When the image quality of the medical image is specifically reviewed, the medical image quality control expert is required to check and confirm, and in the aspect of quality control of the image, the construction of the current medical image quality control platform is basically to carry out quality control work by a technical expert group through film reading.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
The invention provides a quality control film reading method and system based on AI images, aiming at the problems in the prior art and overcoming the technical problems in the prior art.
Therefore, the invention adopts the following specific technical scheme:
according to one aspect of the present invention, there is provided an AI-based image quality control film reading method, comprising the steps of:
s1, collecting real-time image data and historical image data;
s2, the collected data are sorted and standardized;
s3, generating a standardized database from the processed data by a preset method;
s4, performing data mining and classification on the quality control factor of each image data in the standardized database by using a preset rule;
and S5, outputting quality control factor conclusion corresponding to each image data, and arranging into label and assets for storage.
Further, in the step S1, in the real-time image data and the historical image data, the real-time image data is real-time medical image data that is continuously pushed by each medical institution in the area, and the historical image data is a large amount of medical image examination data that is uploaded by the medical institutions before the quality control work is performed.
Further, the step of sorting and normalizing the collected data in S2 further includes the following steps:
s21, firstly, carrying out comprehensive data management in the medical image industry on multi-dimensional medical image data;
and S22, comparing the medical image part standard to perform part standardization processing on the inspection type, the part and the inspection method.
Further, the preset method in S3 includes: the medical big data management and the part standardization are realized by using an NLP algorithm in the AI technology and combining with the medical image quality control professional knowledge and quickly using a general data standard template.
Further, the data mining and classifying the quality control factor of each image data in the standardized database by using the preset rule in S4 further includes the following steps:
s41, establishing a quality control evaluation model of each part by using AI analysis, artificial intelligence and big data tools;
s42, optimizing the quality control evaluation model by using the image data uploaded in real time;
and S43, mining and classifying the quality control factor data of each image data by comparing the image data with the quality control evaluation model.
Further, the optimizing the quality control evaluation model by using the image data uploaded in real time in S42 includes: and aiming at the data uploaded in real time, carrying out data standardization meeting regional standard specifications to serve as a new real-time data set, and carrying out deep learning and optimization on the model based on a core AI algorithm and a big data tool so as to continuously output the optimized part quality control evaluation model.
Further, the quality control factors include, but are not limited to, contrast, white balance, and signal-to-noise ratio in the inspection image quality.
According to another aspect of the present invention, there is provided an AI-based image quality control film reading system, comprising: the system comprises a data acquisition module, a data sorting module, a database generation module, a data mining and classifying module and a data storage module;
the data acquisition module is used for acquiring real-time image data and historical image data;
the data sorting module is used for sorting and standardizing the collected data;
the database generation module is used for generating a standardized database from the processed data by using a preset method;
the data mining and classifying module is used for mining and classifying the quality control factors of each image data in the standardized database by using a preset rule;
and the data storage module is used for outputting quality control factor conclusions corresponding to each image data, and arranging the quality control factor conclusions into labels and assets for storage.
Further, the data sorting module further sorts and standardizes the acquired data, and the data sorting module further comprises the following steps:
s21, firstly, carrying out comprehensive data management in the medical image industry on multi-dimensional medical image data;
and S22, comparing the medical image part standard to perform part standardization processing on the inspection type, the part and the inspection method.
Further, the data mining and classifying module for performing data mining and classifying on the quality control factor of each image data in the standardized database by using a preset rule further comprises the following steps:
s41, establishing a quality control evaluation model of each part by using AI analysis, artificial intelligence and big data tools;
s42, optimizing the quality control evaluation model by using the image data uploaded in real time;
and S43, mining and classifying the quality control factor data of each image data by comparing the image data with the quality control evaluation model.
The invention has the beneficial effects that:
(1) according to the invention, the primary quality control of the image is realized through AI analysis, artificial intelligence and a big data tool, and an expert group checks and proofreads mechanism, so that the working efficiency of quality control is improved.
(2) The image quality control aspect of the medical image examination is developed for the quality control center, the workload of a technical expert group is greatly reduced, and the development of quality control work is promoted.
(3) The image of the medical image data is subjected to quality control evaluation factor analysis through AI, artificial intelligence and big data tools, in the medical image inspection, quality control evaluation factors corresponding to inspection types, inspection parts and inspection methods are different, finally effective preliminary quality control of the image is completed in a one-to-one matching mode, medical image quality control experts check and confirm, repetitive content reading and quality control evaluation factor checking of the medical image are reduced, and quality control working efficiency is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of an AI-based image quality control film reading method according to an embodiment of the invention;
FIG. 2 is a functional block diagram of an NLP algorithm;
FIG. 3 is a schematic flow chart of the establishment of a quality control evaluation model for each part;
FIG. 4 is a schematic flow chart of optimization of the quality control evaluation model of each part;
FIG. 5 is a schematic flow chart of medical image data standardization in accordance with the present invention;
FIG. 6 is a schematic view of a medical image pan/tilt head architecture upon which the present invention is based;
fig. 7 is a schematic block diagram of an AI-based image quality control film reading system according to an embodiment of the invention.
In the figure:
1. a data acquisition module; 2. a data sorting module; 3. a database generation module; 4. a data mining classification module; 5. and a data storage module.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to an embodiment of the invention, a quality control film reading method based on AI images is provided.
Referring to fig. 1 to 6, the present invention will be further described, in which an AI-based image quality control film reading method according to an embodiment of the present invention includes the following steps:
s1, collecting real-time image data and historical image data;
the step is a data base for data management and part standardization work development;
s2, the collected data are sorted and standardized;
this step is a necessary task for quality control application to standardize database generation.
S3, generating a standardized database from the processed data by a preset method;
specifically, the universal data standard template is rapidly applied to medical big data management and position standardization by using big data management professional experience, applying an NLP (natural language processing) algorithm in an AI technology and combining medical image quality control professional knowledge. The method is a data base for the quality control work to develop image data retrieval (data center station) and is also source data for data mining/classification;
in addition, the NLP algorithm is specifically applied as follows:
for various description data generated in the medical diagnosis and treatment process, basic algorithms such as lexical analysis, syntactic analysis, semantic analysis and the like in the NLP algorithm are used and combined with a structured data standard definition template and professional contents of medical image quality control, so that the application management and standardization under a medical scene are carried out on various types of data, and finally, output normative data are converged into a quality control application standardized database. (detailed process: basic algorithms in NLP algorithm such as lexical analysis, syntactic analysis, semantic analysis, etc. when applied, it is necessary to know what governance is performed on data, i.e. what results are output, and then professional experience of big data governance is required, a structured data standardized definition template (standardized template formed in accordance with medical image quality control) is formed, basic algorithm application such as lexical analysis, syntactic analysis, semantic analysis, etc. is performed on text in combination with attribute definition content of the template, specific content of attribute definition is output, finally a quality control application standardized database is formed), then a simplest example is taken, for example, an age field, and the final standardized database age field is a standardized format of 25Y in all ages 25Y, 25year, 25 weeks, etc. transmitted by hospitals by applying;
s4, performing data mining and classification on the quality control factor of each image data in the standardized database by using a preset rule;
the step is necessary work for forming quality control labeling and asset data;
specifically, firstly, on the basis of a large amount of medical image data, a quality control evaluation model of each part is established through AI analysis and a big data tool (quality control factors such as image shooting quality like white balance and signal-to-noise ratio are judged and are common conclusions obtained by calculating the data of the image), and the image data uploaded in real time is used for optimizing the quality control evaluation model. Then, detecting the data of the extracted image per se by each image data through the model to calculate the data with similar white balance more than a certain value-excellent and the like, and then classifying the data (all data of the patient in the examination);
and S5, outputting quality control factor conclusion corresponding to each image data, and arranging into label and assets for storage.
In one embodiment, in the step S1, the real-time image data is real-time medical image data continuously pushed by each medical institution in the area, and the historical image data is a large amount of medical image examination data uploaded by the medical institutions before the quality control work is performed.
In one embodiment, the step of collating and normalizing the collected data in S2 further includes the steps of:
s21, firstly, carrying out comprehensive data management in the medical image industry on multi-dimensional medical image data;
and S22, comparing the medical image part standard to perform part standardization processing on the inspection type, the part and the inspection method.
In one embodiment, the preset method in S3 includes: the medical big data management and the part standardization are realized by using an NLP algorithm in the AI technology and combining with the medical image quality control professional knowledge and quickly using a general data standard template.
In one embodiment, the data mining and classifying the quality control factor of each image data in the standardized database by using the preset rule in S4 further includes the following steps:
s41, establishing a quality control evaluation model of each part by using AI analysis, artificial intelligence and big data tools;
specifically, the quality control of medical images is carried out, and due to the data difference of multiple medical institutions, the quality control data must be a standardized data set so as to carry out effective quality control work. Firstly, carrying out part standardization on multi-dimensional medical image data according to specific contents such as examination types, parts, examination methods and the like by matching medical image part standards, finally forming a standardized data set conforming to the development of medical image quality control, matching quality control evaluation factors of all parts of the medical image, and realizing the establishment of a quality control evaluation part model of each part in a big data + AI analysis + artificial intelligence mode. Similar to the signal-to-noise ratio, which is a quality control factor, a standard calculation formula SNR is (sum of gray values of pixels in a clean picture)/abs (sum of gray values of a noise picture-sum of gray values in the clean picture), and the quality control evaluation part model is finally formed according to the judgment result that the quality control evaluation part model meets or does not meet the evaluation standard. Because the quality control factor is 200+, the establishment of each part evaluation model suitable for medical image quality control is finally completed through an open source AI algorithm, big data and an artificial intelligence tool.
S42, optimizing the quality control evaluation model by using the image data uploaded in real time;
and S43, mining and classifying the quality control factor data of each image data by comparing the image data with the quality control evaluation model.
In an embodiment, the optimizing the quality control evaluation model using the image data uploaded in real time in S42 includes: aiming at the data uploaded in real time, carrying out data standardization meeting regional standard specifications to serve as a new real-time data set, and carrying out deep learning and optimization on the model based on a core AI algorithm and a big data tool so as to continuously output an optimized part quality control evaluation model;
specifically, after the quality control evaluation model of each part in the medical image quality control is established, in order to form continuously usable, reliable and credible gradual quality control on increasingly complex medical industry image data, the core evaluation model needs to be periodically updated. And aiming at the data uploaded in real time, data standardization meeting regional standard specifications is normally carried out to serve as a new real-time data set, and then deep learning and optimization are carried out on the model based on a core AI algorithm and a big data tool, so that a new version part quality control evaluation model is continuously output.
In one embodiment, the quality control factors include, but are not limited to, contrast, white balance, and signal-to-noise ratio in the inspection image quality.
In addition, the middle station service: the method is divided into a data center station and a service center station, wherein the service center station is an application program service end server, the data center station is a medical image data retrieval end server, and image data of a quality control application standardized database and corresponding quality control labeling and asset data are retrieved and used for front-end application interaction.
Front-end application interaction: when the front end needs to acquire medical image data and business data, the front end interacts with the middle platform service to finish the acquisition, and finally pushes the image data in the quality control application standardized database, and quality control factor labeling and asset data formed by the image to the front platform.
And (3) displaying the final quality control data of the front end: and automatically filling each image data interacted by the application and the corresponding content label of each quality control factor into a quality control review interface.
According to another embodiment of the present invention, as shown in fig. 7, there is provided an AI-based image quality control film reading system, including: the system comprises a data acquisition module 1, a data sorting module 2, a database generation module 3, a data mining classification module 4 and a data storage module 5;
the data acquisition module 1 is used for acquiring real-time image data and historical image data;
the data sorting module 2 is used for sorting and standardizing the collected data;
the database generation module 3 is used for generating a standardized database from the processed data by using a preset method;
the data mining and classifying module 4 is used for mining and classifying the quality control factors of each image data in the standardized database by using preset rules;
and the data storage module 5 is used for outputting quality control factor conclusions corresponding to each image data, and arranging the quality control factor conclusions into labels and assets for storage.
In one embodiment, the data sorting module 2 further comprises the following steps:
s21, firstly, carrying out comprehensive data management in the medical image industry on multi-dimensional medical image data;
and S22, comparing the medical image part standard to perform part standardization processing on the inspection type, the part and the inspection method.
In one embodiment, the data mining and classifying module 4 further performs data mining and classifying on the quality control factor of each image data in the standardized database by using a preset rule, and includes the following steps:
s41, establishing a quality control evaluation model of each part by using AI analysis, artificial intelligence and big data tools;
s42, optimizing the quality control evaluation model by using the image data uploaded in real time;
and S43, mining and classifying the quality control factor data of each image data by comparing the image data with the quality control evaluation model.
The following explains the english words and proper nouns appearing above:
AI technology: artificial Intelligence (Artificial Intelligence), abbreviated in english as AI. The method is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.
NLP algorithm: natural Language Processing (NLP) is a field of computer science, artificial intelligence, linguistics that focuses on the interaction between computers and human (natural) language.
Data set: refers to a sorted list of data that can be used to train a model or evaluate the effectiveness of a model;
data mining: translating into data exploration and data mining. It is a step in database Knowledge Discovery (English: Knowledge-Discovery in Databases, abbreviated as KDD). Data mining generally refers to the process of algorithmically searching a large amount of data for information hidden therein. Data mining is generally related to computer science, and achieves the aims through various methods such as statistics, online analysis and processing, information retrieval, machine learning, expert systems (depending on past experience rules), pattern recognition and the like;
model: according to the specific purpose of research, the material form or thinking form of the essential characteristics of the structure, function, attribute, relationship, process and the like of an prototype (isotope) object is reproduced under certain assumed conditions;
big data: is a very large and complex data set, one is the Volume of data (Volume), which is continuously increasing rapidly; second, high speed (Velocity) data I/O; third is the diversity (Variety) data type and source;
and (3) data management: is the set of activities (planning, monitoring, and execution) that exercise power and control over data asset management;
medical imaging: refers to a technique and a process for obtaining an image of an internal tissue of a human body or a part of the human body in a non-invasive manner for medical treatment or medical research;
OLTP is also called transaction-oriented processing process, and is basically characterized in that user data received by a foreground can be immediately transmitted to a computing center for processing, and a processing result is given in a short time, so that the OLTP is one of modes for quickly responding to user operation;
OLAP: the method is a software technology which enables an analyst, a manager or an executor to quickly, consistently and interactively access information which is converted from original data, can be really understood by a user and truly reflects enterprise dimensional characteristics from multiple angles, so that the analyst, the manager or the executor can obtain deeper understanding of the data;
distributed storage: the data storage technology is characterized in that disk space on each machine in an enterprise is used through a network, and the dispersed storage resources form a virtual storage device, and data are dispersedly stored in each corner of the enterprise;
DaaS (Data-as-a-Service, DaaS): through centralized management of resources, the direction is pointed out for improving IT efficiency and system performance.
In summary, by means of the technical scheme of the invention, the invention realizes the preliminary quality control of the image through AI analysis, artificial intelligence and big data tools, and the expert group checks and proofreads the mechanism, thereby improving the working efficiency of quality control; the image quality control aspect of medical image examination is carried out on the quality control center, the workload of a technical expert group is greatly reduced, and the development of quality control work is promoted; the image of the medical image data is subjected to quality control evaluation factor analysis through AI, artificial intelligence and big data tools, in the medical image inspection, the quality control evaluation factors corresponding to each inspection type, each part and each inspection method are different, finally, the effective preliminary quality control of the image is finished one by one and automatically, the medical image quality control experts check and confirm, the repetitive content reading and the quality control evaluation factor checking of the medical image are reduced, and the quality control working efficiency is greatly improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A quality control film reading method based on AI images is characterized by comprising the following steps:
s1, collecting real-time image data and historical image data;
s2, the collected data are sorted and standardized;
s3, generating a standardized database from the processed data by a preset method;
s4, performing data mining and classification on the quality control factor of each image data in the standardized database by using a preset rule;
and S5, outputting quality control factor conclusion corresponding to each image data, and arranging into label and assets for storage.
2. The AI-based image quality control film reading method according to claim 1, wherein the step S1 includes collecting real-time image data and historical image data, the real-time image data is real-time medical image data that is continuously pushed by medical institutions in an area, and the historical image data is a large amount of medical image inspection data uploaded by the medical institutions before quality control work is performed.
3. The AI-based image quality control reading method according to claim 1, wherein the step of collating and standardizing the collected data in S2 further comprises the steps of:
s21, firstly, carrying out comprehensive data management in the medical image industry on multi-dimensional medical image data;
and S22, comparing the medical image part standard to perform part standardization processing on the inspection type, the part and the inspection method.
4. The AI-based image quality control reading method according to claim 1, wherein the preset method in S3 comprises: the medical big data management and the part standardization are realized by using an NLP algorithm in the AI technology and combining with the medical image quality control professional knowledge and quickly using a general data standard template.
5. The AI-based image quality control film reading method according to claim 1, wherein the data mining and classifying the quality control factors of each image data in the standardized database by using the preset rules in S4 further comprises the following steps:
s41, establishing a quality control evaluation model of each part by using AI analysis, artificial intelligence and big data tools;
s42, optimizing the quality control evaluation model by using the image data uploaded in real time;
and S43, mining and classifying the quality control factor data of each image data by comparing the image data with the quality control evaluation model.
6. The AI-based image quality control film reading method according to claim 5, wherein the optimizing the quality control evaluation model using the real-time uploaded image data in S42 includes: and aiming at the data uploaded in real time, carrying out data standardization meeting regional standard specifications to serve as a new real-time data set, and carrying out deep learning and optimization on the model based on a core AI algorithm and a big data tool so as to continuously output the optimized part quality control evaluation model.
7. The AI-based image quality control chip reading method of claim 5, wherein the quality control factors include but are not limited to contrast, white balance and signal-to-noise ratio in the quality of the inspected image.
8. An AI-based image quality control reading system for implementing the steps of the AI-based image quality control reading method according to any one of claims 1 to 7, wherein the system comprises: the system comprises a data acquisition module, a data sorting module, a database generation module, a data mining and classifying module and a data storage module;
the data acquisition module is used for acquiring real-time image data and historical image data;
the data sorting module is used for sorting and standardizing the collected data;
the database generation module is used for generating a standardized database from the processed data by using a preset method;
the data mining and classifying module is used for mining and classifying the quality control factors of each image data in the standardized database by using a preset rule;
and the data storage module is used for outputting quality control factor conclusions corresponding to each image data, and arranging the quality control factor conclusions into labels and assets for storage.
9. The AI-based image quality control chip reading system of claim 8, wherein the data collating module collates and standardizes the collected data further comprises the following steps:
s21, firstly, carrying out comprehensive data management in the medical image industry on multi-dimensional medical image data;
and S22, comparing the medical image part standard to perform part standardization processing on the inspection type, the part and the inspection method.
10. The AI-based image quality control chip reading system of claim 8, wherein the data mining and classifying module further performs data mining and classifying on the quality control factors of each image data in the standardized database by using the preset rules, and further comprises the following steps:
s41, establishing a quality control evaluation model of each part by using AI analysis, artificial intelligence and big data tools;
s42, optimizing the quality control evaluation model by using the image data uploaded in real time;
and S43, mining and classifying the quality control factor data of each image data by comparing the image data with the quality control evaluation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011550751.2A CN112669940A (en) | 2020-12-24 | 2020-12-24 | Quality control film reading method and system based on AI (Artificial Intelligence) image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011550751.2A CN112669940A (en) | 2020-12-24 | 2020-12-24 | Quality control film reading method and system based on AI (Artificial Intelligence) image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112669940A true CN112669940A (en) | 2021-04-16 |
Family
ID=75408332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011550751.2A Pending CN112669940A (en) | 2020-12-24 | 2020-12-24 | Quality control film reading method and system based on AI (Artificial Intelligence) image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112669940A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050256743A1 (en) * | 2004-05-11 | 2005-11-17 | Dale Richard B | Medical imaging-quality assessment and improvement system (QAISys) |
| CN108171272A (en) * | 2018-01-12 | 2018-06-15 | 上海东软医疗科技有限公司 | A kind of evaluation method and device of Medical Imaging Technology |
| CN108257132A (en) * | 2018-03-05 | 2018-07-06 | 南方医科大学 | A kind of method of the CT image quality measures based on machine learning |
| CN109564779A (en) * | 2016-07-15 | 2019-04-02 | 皇家飞利浦有限公司 | For evaluating the device of medical supply quality |
| CN110140178A (en) * | 2016-11-23 | 2019-08-16 | 皇家飞利浦有限公司 | The closed-loop system collected and fed back for knowing the picture quality of context |
| CN111798439A (en) * | 2020-07-11 | 2020-10-20 | 大连东软教育科技集团有限公司 | Medical image quality interpretation method and system for online and offline fusion and storage medium |
-
2020
- 2020-12-24 CN CN202011550751.2A patent/CN112669940A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050256743A1 (en) * | 2004-05-11 | 2005-11-17 | Dale Richard B | Medical imaging-quality assessment and improvement system (QAISys) |
| CN109564779A (en) * | 2016-07-15 | 2019-04-02 | 皇家飞利浦有限公司 | For evaluating the device of medical supply quality |
| CN110140178A (en) * | 2016-11-23 | 2019-08-16 | 皇家飞利浦有限公司 | The closed-loop system collected and fed back for knowing the picture quality of context |
| CN108171272A (en) * | 2018-01-12 | 2018-06-15 | 上海东软医疗科技有限公司 | A kind of evaluation method and device of Medical Imaging Technology |
| CN108257132A (en) * | 2018-03-05 | 2018-07-06 | 南方医科大学 | A kind of method of the CT image quality measures based on machine learning |
| CN111798439A (en) * | 2020-07-11 | 2020-10-20 | 大连东软教育科技集团有限公司 | Medical image quality interpretation method and system for online and offline fusion and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 姚侃敏等: "影像云在放射诊断质控工作中的应用价值", 《中国医学计算机成像杂志》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11500818B2 (en) | Method and system for large scale data curation | |
| US11423538B2 (en) | Computer-implemented machine learning for detection and statistical analysis of errors by healthcare providers | |
| Shvaiko et al. | Ten challenges for ontology matching | |
| US5671333A (en) | Training apparatus and method | |
| US20200303072A1 (en) | Method and system for supporting medical decision making | |
| KR20220064395A (en) | A system for collecting and identifying skin conditions from images and expertise | |
| Khadilkar et al. | An experimental evaluation of design information reuse during conceptual design | |
| Jiménez-Ruiz et al. | Introducing the HOBBIT platform into the ontology alignment evaluation campaign | |
| Maitra | Clustering massive datasets with application in software metrics and tomography | |
| Calikli et al. | An algorithmic approach to missing data problem in modeling human aspects in software development | |
| CN108549672A (en) | A kind of intelligent data analysis method and system | |
| CN112669940A (en) | Quality control film reading method and system based on AI (Artificial Intelligence) image | |
| CN111063433A (en) | Medical data processing method and device, electronic equipment and storage medium | |
| CN114741459A (en) | Data query method and device based on artificial intelligence, electronic equipment and medium | |
| CN114840522A (en) | Data query method and device based on artificial intelligence, electronic equipment and medium | |
| CN113972009A (en) | Medical examination consultation system based on clinical examination medical big data | |
| CN117149868B (en) | Cross-hospital area data distribution processing method | |
| CN110289065A (en) | A kind of auxiliary generates the control method and device of medical electronic report | |
| US11526548B1 (en) | Image-based query language system for performing database operations on images and videos | |
| Hu et al. | Characterizing the Progression of Pulmonary Edema Severity: Can Pairwise Comparisons in Radiology Reports Help? | |
| Kvesko et al. | Expert systems as the basis of decisions in the knowledge society | |
| CN115132314B (en) | Examination impression generation model training method, examination impression generation model training device and examination impression generation model generation method | |
| Li et al. | Rule evaluations, attributes, and rough sets: Extension and a case study | |
| Cychnerski et al. | Segmentation Quality Refinement in Large-Scale Medical Image Dataset with Crowd-Sourced Annotations | |
| Corazza et al. | A new dataset for source code comment coherence |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210416 |