CN112862342A - Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence - Google Patents
Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence Download PDFInfo
- Publication number
- CN112862342A CN112862342A CN202110215428.8A CN202110215428A CN112862342A CN 112862342 A CN112862342 A CN 112862342A CN 202110215428 A CN202110215428 A CN 202110215428A CN 112862342 A CN112862342 A CN 112862342A
- Authority
- CN
- China
- Prior art keywords
- pet
- information
- key elements
- image quality
- key element
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Nuclear Medicine (AREA)
Abstract
The invention relates to an intelligent judgment method for evaluating PET/CT image quality key elements based on artificial intelligence, belonging to the technical field of medical images. According to international and national regulations of nuclear medicine and molecular images, combined with clinical application practice, the invention induces and classifies the quality key elements of the whole process of the PET/CT examination process, designs a quality control key element quantification comparison library on the basis of the quality control key elements, adopts an artificial intelligent deep learning model and a key element identification technology, takes the PET/CT examination process as a time line, and utilizes AI technology to carry out integrated quality control evaluation on associated information at each stage of the PET/CT examination, thereby avoiding the PET/CT image quality problem caused by artificial energy deficiency or negligence, warning the problem in time in the examination process, correcting and modifying in time, avoiding the increase of the time cost of a patient and the addition of random radiation, improving the accuracy of image diagnosis, and being beneficial to the standardized application and popularization of the PET/CT technology.
Description
Technical Field
The invention relates to an intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence, belonging to the technical field of medical images.
Background
Positron Emission Tomography (PET) was a modality of medical imaging introduced in the early 70 s of the 20 th century. From PET to PET/CT (positron emission tomography), it has been developed as a routine and important clinical imaging modality for noninvasive evaluation of metabolic and functional imaging of the human body at the molecular level. The advantage of PET/CT is that it is a very sensitive imaging modality that can provide quantitative analysis information with anatomical context information. Since 2001, 6000 PET/CT systems have been installed worldwide, and the number of PET/CT systems installed in China as an advanced medical device has increased year by year in recent years due to localization of PET/CT systems. PET/CT examination is generally accepted and widely used in clinical medicine, and the bimodal quantitative analysis advanced precise medical molecular imaging technology is widely applied to the fields of oncology, cardiology, neurology, metabolic diseases and the like. Since such techniques include medical imaging technology equipment of at least two modalities, multiple examination sequences involve whole-body imaging; the whole process is complex, key factors influencing images are numerous, the requirement on the professional ability of a user is high, and in order to ensure the accuracy of medical diagnosis and assist medical personnel to quickly master the advanced technology on the premise of ensuring high-standard medical quality, an intelligent judgment method for quality control management and supervision of PET/CT quality key factors is urgently needed.
In the prior art, PET/CT is used for clinical and scientific research application and relates to control of a plurality of image quality key elements, and individual key elements have an individual factor warning function but lack relevance evaluation with other elements. In the clinical practice at present, the method basically depends on the active conscious execution of clinical operation specifications by users, and has no specific supervision method. Sometimes, retrospective integral image browsing after examination is finished and then image quality control is carried out, at this time, if the quality problem of patient image acquisition is found, repeated acquisition is usually only carried out, the time cost and the radiation dose of a patient are increased, and if quality evaluation standards are reduced for evaluation, the diagnosis accuracy is necessarily reduced. Meanwhile, the main problems faced by the prior art are: first, key quality control key elements of the overall PET/CT examination process are not classified. Secondly, no professional key element comparison and judgment method is provided for quality control supervision, evaluation and warning of each link of the inspection.
Disclosure of Invention
The invention aims to solve the technical problem of intelligent judgment on quality control management and supervision of PET/CT quality key elements.
In order to solve the problem, the technical scheme adopted by the invention is to provide an intelligent judgment method for evaluating key elements of PET/CT image quality based on artificial intelligence; the method comprises the following steps:
step 1: obtaining information related to key elements of PET/CT image quality;
step 2: extracting and classifying the acquired information into elements, wherein the classified categories comprise standardized index digital information, professional term information of natural language identification and medical image information;
and step 3: inputting the classified information into an AI key element recognition and decision-making system of the deep learning model;
and 4, step 4: and obtaining PET/CT quality control key element warning and protocol optimization recommendation.
Preferably, the information related to the key elements of PET/CT image quality in step 1 includes patient medical history information, nuclide drug information, clinical requirement information, equipment operation information, and PET acquisition and image post-processing information.
Preferably, the AI key element recognition and decision system of the deep learning model in step 3 includes a key element classification information unit, a quality control key element quantitative comparison information base used as a training set, an AI intelligent discrimination unit based on deep learning, and a result recognition output unit, which are connected in sequence.
Compared with the prior art, the invention has the following beneficial effects:
1. in view of the defects of the prior art, the invention sums up the key quality factors of the whole process flow of the classified PET/CT inspection process according to the international and national specifications of nuclear medicine and molecular images and by combining clinical application practice, designs a quality control key element quantization comparison library according to the key quality control factors, and adopts an artificial intelligent deep learning model and a key factor identification technology.
2. The invention takes the PET/CT inspection flow as a time line, and utilizes AI identification to judge the quality of the imported information in each technical link, so that the system can automatically and timely warn and optimize suggestion recommendation, and automatically warn the factors of parameter setting, technical operation, equipment failure and the like which influence the quality of PET/CT images.
3. The invention carries out grouping and quantitative classification on key elements influencing the quality of the PET/CT image, utilizes AI technology to carry out integrated quality control evaluation on associated information at each stage of PET/CT examination, avoids the problem of PET/CT quality image caused by human energy deficiency or negligence, simultaneously warns the problem in time in the examination process, reminds the patient to correct and modify in time, avoids increasing the time cost of the patient and adding extra random radiation, improves the accuracy of image diagnosis, and is beneficial to the standardized application and popularization of the PET/CT technology.
Drawings
FIG. 1 is a process block diagram of the PET/CT whole body imaging quality key element intelligent discrimination method of the invention;
FIG. 2 is a block diagram of the AI key element identification and decision system construction process of the deep learning model of the present invention;
Detailed Description
In order to make the invention more comprehensible, preferred embodiments are described in detail below with reference to the accompanying drawings:
as shown in FIGS. 1 and 2, the invention provides an intelligent judgment method for evaluating key elements of PET/CT image quality based on artificial intelligence; the method comprises the following steps:
step 1: obtaining information related to key elements of PET/CT image quality;
step 2: extracting and classifying the acquired information into elements, wherein the classified categories comprise standardized index digital information, professional term information of natural language identification and medical image information;
and step 3: inputting the classified information into an AI key element recognition and decision-making system of the deep learning model;
and 4, step 4: and obtaining PET/CT quality control key element warning and protocol optimization recommendation.
The information related to the key elements of the PET/CT image quality in the step 1 comprises patient medical history information, nuclide drug information, clinical requirement information, equipment operation information and PET acquisition and image post-processing information.
The AI key element identification and decision system of the deep learning model in the step 3 comprises a key element classification information unit, a quality control key element quantitative comparison information base used as a training set, an AI intelligent judgment unit based on deep learning and a result identification output unit which are connected in sequence. The result recognition output unit prompts passing of the information meeting the requirements and makes element warning information and protocol optimization suggestions of the information not meeting the requirements.
The invention takes the PET/CT inspection flow as a time line, and utilizes AI identification to judge the quality of the imported information in each technical link, so that the system can automatically and timely warn and optimize suggestion recommendation, and automatically warn the factors of parameter setting, technical operation, equipment failure and the like which influence the quality of PET/CT images.
The invention carries out grouping quantitative classification on key elements influencing the quality of the PET/CT image, utilizes AI technology to carry out integrated quality control evaluation on associated information at each stage of PET/CT examination, avoids the problem of PET/CT quality image caused by artificial energy deficiency or negligence, simultaneously warns the problem in time during the examination process, reminds the patient to correct and modify in time, avoids increasing the time cost of the patient and adding extra random radiation, improves the accuracy of image diagnosis, and is beneficial to the standardized application and popularization of the PET/CT technology
While the invention has been described with respect to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention. Those skilled in the art can make various changes, modifications and equivalent arrangements, which are equivalent to the embodiments of the present invention, without departing from the spirit and scope of the present invention, and which may be made by utilizing the techniques disclosed above; meanwhile, any changes, modifications and variations of the above-described embodiments, which are equivalent to those of the technical spirit of the present invention, are within the scope of the technical solution of the present invention.
Claims (3)
1. An intelligent discrimination method for evaluating PET/CT image quality key elements based on artificial intelligence; the method is characterized in that: the method comprises the following steps:
step 1: obtaining information related to key elements of PET/CT image quality;
step 2: extracting and classifying the acquired information into elements, wherein the classified categories comprise standardized index digital information, professional term information of natural language identification and medical image information;
and step 3: inputting the classified information into an AI key element recognition and decision-making system of the deep learning model;
and 4, step 4: and obtaining PET/CT quality control key element warning and protocol optimization recommendation.
2. The method for intelligently discriminating the evaluation of the key elements of the PET/CT image quality based on the artificial intelligence as claimed in claim 1, wherein: the information related to the key elements of the PET/CT image quality in the step 1 comprises patient medical history information, nuclide drug information, clinical requirement information, equipment operation information and PET acquisition and image post-processing information.
3. The method for intelligently discriminating the evaluation of the key elements of the PET/CT image quality based on the artificial intelligence as claimed in claim 2, wherein: the AI key element recognition and decision system of the deep learning model in the step 3 comprises a key element classification information unit, a quality control key element quantitative comparison information base used as a training set, an AI intelligent discrimination unit based on deep learning and a result recognition output unit which are connected in sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110215428.8A CN112862342A (en) | 2021-02-26 | 2021-02-26 | Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110215428.8A CN112862342A (en) | 2021-02-26 | 2021-02-26 | Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112862342A true CN112862342A (en) | 2021-05-28 |
Family
ID=75990145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110215428.8A Pending CN112862342A (en) | 2021-02-26 | 2021-02-26 | Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862342A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114559177A (en) * | 2022-03-07 | 2022-05-31 | 北京洞微科技发展有限公司 | Welding evaluation method and device based on image data analysis and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424385A (en) * | 2013-08-22 | 2015-03-18 | 上海联影医疗科技有限公司 | Method and device for evaluating medical images |
| 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 |
| CN109741317A (en) * | 2018-12-29 | 2019-05-10 | 成都金盘电子科大多媒体技术有限公司 | Medical image intelligent Evaluation method |
| CN111192682A (en) * | 2019-12-25 | 2020-05-22 | 上海联影智能医疗科技有限公司 | Image exercise data processing method, system and storage medium |
| 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 |
-
2021
- 2021-02-26 CN CN202110215428.8A patent/CN112862342A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424385A (en) * | 2013-08-22 | 2015-03-18 | 上海联影医疗科技有限公司 | Method and device for evaluating medical images |
| 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 |
| CN109741317A (en) * | 2018-12-29 | 2019-05-10 | 成都金盘电子科大多媒体技术有限公司 | Medical image intelligent Evaluation method |
| CN111192682A (en) * | 2019-12-25 | 2020-05-22 | 上海联影智能医疗科技有限公司 | Image exercise data processing method, system and storage medium |
| 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 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114559177A (en) * | 2022-03-07 | 2022-05-31 | 北京洞微科技发展有限公司 | Welding evaluation method and device based on image data analysis and storage medium |
| CN114559177B (en) * | 2022-03-07 | 2023-12-05 | 北京洞微科技发展有限公司 | Welding evaluation method, device and storage medium based on image data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3916674A1 (en) | Brain image segmentation method, apparatus, network device and storage medium | |
| Ieracitano et al. | A fuzzy-enhanced deep learning approach for early detection of Covid-19 pneumonia from portable chest X-ray images | |
| Liu et al. | Weakly supervised deep learning for brain disease prognosis using MRI and incomplete clinical scores | |
| Berkaya et al. | Classification models for SPECT myocardial perfusion imaging | |
| CN108961215A (en) | Parkinson's disease assistant diagnosis system and method based on Multimodal medical image | |
| CN108511056A (en) | Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system | |
| CN110141220A (en) | Myocardial infarction automatic testing method based on multi-modal fusion neural network | |
| Yang et al. | Large-scale brain functional network integration for discrimination of autism using a 3-D deep learning model | |
| CN111462916B (en) | Method and device for predicting dose volume histogram of organ at risk of radiotherapy plan | |
| CN1977273A (en) | System and method to quantify patients clinical trends and monitoring their status progression | |
| WO2020154562A1 (en) | Method and system for automatic multiple lesion annotation of medical images | |
| CN110246109A (en) | Merge analysis system, method, apparatus and the medium of CT images and customized information | |
| US20210304896A1 (en) | Systems and methods for medical diagnosis | |
| CN109685671A (en) | Medical data exception recognition methods, equipment and storage medium based on machine learning | |
| Qiao et al. | Early Alzheimer’s disease diagnosis with the contrastive loss using paired structural MRIs | |
| Han et al. | A novel convolutional variation of broad learning system for Alzheimer’s disease diagnosis by using MRI images | |
| Ruthven et al. | Deep-learning-based segmentation of the vocal tract and articulators in real-time magnetic resonance images of speech | |
| CN108597615A (en) | A kind of screening reference method of Patients with Mild Cognitive Impairment dementia conversion | |
| Yadav et al. | Automated cardiac disease diagnosis using support vector machine | |
| CN108520283A (en) | A kind of classification method of medical image based on brain area indirect relation network struction | |
| Walger et al. | Artificial intelligence for the detection of focal cortical dysplasia: Challenges in translating algorithms into clinical practice | |
| CN112862342A (en) | Intelligent discrimination method for evaluating key elements of image quality based on artificial intelligence | |
| CN108648183B (en) | Method for analyzing SPECT brain three-dimensional image | |
| CN116844733B (en) | Medical data integrity analysis method based on artificial intelligence | |
| CN110473636A (en) | Intelligent doctor's advice recommended method and system based on deep learning |
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 |