CN117457134A - Medical data management method and system based on intelligent AI - Google Patents
Medical data management method and system based on intelligent AI Download PDFInfo
- Publication number
- CN117457134A CN117457134A CN202311461912.4A CN202311461912A CN117457134A CN 117457134 A CN117457134 A CN 117457134A CN 202311461912 A CN202311461912 A CN 202311461912A CN 117457134 A CN117457134 A CN 117457134A
- Authority
- CN
- China
- Prior art keywords
- medical image
- feature
- medical
- semantic
- topological
- 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
- 238000013523 data management Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims description 118
- 239000011159 matrix material Substances 0.000 claims description 80
- 230000004927 fusion Effects 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 16
- 238000003062 neural network model Methods 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 238000012098 association analyses Methods 0.000 claims description 10
- 230000000903 blocking effect Effects 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 238000009533 lab test Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000002591 computed tomography Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000002372 labelling Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000000547 structure data Methods 0.000 description 3
- 230000001934 delay Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010061818 Disease progression Diseases 0.000 description 1
- 208000026350 Inborn Genetic disease Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005750 disease progression Effects 0.000 description 1
- 238000009509 drug development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000016361 genetic disease Diseases 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000007614 genetic variation Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000004962 physiological condition Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 210000002700 urine Anatomy 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G16H40/63—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 local operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Library & Information Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a medical data management method and a system based on intelligent AI, which acquire medical images to be archived; performing image feature analysis on the medical image to be archived to obtain medical image semantic features; determining a type tag of the medical image to be archived based on the medical image semantic features; and archiving the medical image to be archived based on the type tag of the medical image to be archived. Thus, an organized image archiving system is facilitated to be established, doctors and researchers can conveniently search and access specific types of images, and the efficiency and quality of medical data management are improved.
Description
Technical Field
The invention relates to the technical field of intelligent data management, in particular to a medical data management method and system based on intelligent AI.
Background
With the continuous advancement of medical technology and the advancement of digital transformation, the scale and complexity of medical data have been increasing in an explosive manner, including various types of data such as electronic medical records of patients, medical images, laboratory test results, physiological parameters, genome data, and the like.
Management of medical data is critical to medical institutions, doctors, researchers, and decision makers. The effective medical data management can help doctors to better know the illness state and treatment history of patients, support decision making of medical research and clinical practice, improve medical quality and safety, improve medical efficiency and reduce medical cost.
Traditional medical data management schemes typically require a doctor or technician to manually perform classification and labeling of medical images. However, the conventional manual classification and labeling method requires a lot of manpower and time investment due to the huge amount of medical image data. This not only increases the workload, but may also lead to misclassification that delays diagnosis and treatment time. Furthermore, in conventional medical data management, medical images are typically stored in a decentralized fashion in different systems and devices, lacking a unified organization and indexing approach. This makes it difficult for doctors and researchers to find a particular type of image, wasting valuable time and resources.
Accordingly, an optimized smart AI-based medical data management scheme is desired.
Disclosure of Invention
The embodiment of the invention provides a medical data management method and a system based on intelligent AI, which acquire medical images to be archived; performing image feature analysis on the medical image to be archived to obtain medical image semantic features; determining a type tag of the medical image to be archived based on the medical image semantic features; and archiving the medical image to be archived based on the type tag of the medical image to be archived. Thus, an organized image archiving system is facilitated to be established, doctors and researchers can conveniently search and access specific types of images, and the efficiency and quality of medical data management are improved.
The embodiment of the invention also provides a medical data management method based on the intelligent AI, which comprises the following steps:
acquiring a medical image to be archived;
performing image feature analysis on the medical image to be archived to obtain medical image semantic features;
determining a type tag of the medical image to be archived based on the medical image semantic features; and
and archiving the medical image to be archived based on the type label of the medical image to be archived.
The embodiment of the invention also provides a medical data management system based on intelligent AI, which comprises:
the image acquisition module is used for acquiring medical images to be archived;
the image feature analysis module is used for carrying out image feature analysis on the medical image to be archived so as to obtain semantic features of the medical image;
the type label determining module is used for determining type labels of medical images to be archived based on the semantic features of the medical images; and
and the archiving module is used for archiving the medical image to be archived based on the type label of the medical image to be archived.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a flowchart of a medical data management method based on intelligent AI according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a system architecture of a medical data management method based on intelligent AI according to an embodiment of the present invention.
Fig. 3 is a flowchart of the sub-steps of step 120 in a medical data management method based on intelligent AI according to an embodiment of the present invention.
Fig. 4 is a block diagram of a medical data management system based on intelligent AI according to an embodiment of the present invention.
Fig. 5 is an application scenario diagram of a medical data management method based on intelligent AI provided in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Unless defined otherwise, all technical and scientific terms used in the examples of this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In the description of the embodiments of the present application, unless otherwise indicated and defined, the term "connected" should be construed broadly, and for example, may be an electrical connection, may be a communication between two elements, may be a direct connection, or may be an indirect connection via an intermediary, and it will be understood by those skilled in the art that the specific meaning of the term may be understood according to the specific circumstances.
It should be noted that, the term "first\second\third" in the embodiments of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
Medical data refers to various types of data related to healthcare including personal information of a patient, medical history, medical images, laboratory test results, physiological parameters, genomic data, and the like. Such data is collected, stored, managed, and shared among medical institutions, doctors, researchers, and decision makers to support the provision of healthcare and decision making.
The medical data types include:
1. electronic medical record (Electronic Health Records, EHR): an electronic medical record is an electronic version of a medical record of a patient. Including personal information of the patient, medical history, diagnostic results, treatment plans, medication records, etc. The use of the electronic medical record can improve the accessibility, sharing and security of medical information.
2. Medical image data: medical image data includes images generated by various imaging techniques such as X-ray, CT scan, MRI, ultrasound, etc., which can provide detailed information about the internal structure and lesions of the patient, helping doctors make diagnostic and therapeutic decisions.
3. Laboratory test data: laboratory test data includes test results for samples of blood, urine, tissue, etc. Such data may provide information about patient physiological conditions, disease markers, drug concentrations, etc., for diagnosing and monitoring the disease.
4. Physiological parameter data: the physiological parameter data includes vital sign data of the patient, such as blood pressure, heart rate, respiratory rate, body temperature, etc. These data can be used to monitor the physiological status and disease progression of a patient, supporting clinical decision making and treatment planning.
5. Genome data: genomic data includes genetic information of a patient, such as gene sequences, genetic variations, and the like. The data can be used in the fields of personalized medicine, diagnosis and treatment of genetic diseases, drug development and the like.
Management of medical data is critical to medical institutions, doctors, researchers, and decision makers. The effective medical data management can help doctors to better know the illness state and treatment history of patients, support decision making of medical research and clinical practice, improve medical quality and safety, improve medical efficiency and reduce medical cost.
Management of medical data is critical to medical institutions, doctors, researchers, and decision makers. The effective medical data management can help doctors to better know the illness state and treatment history of patients, and by accessing and analyzing the data such as the electronic medical record, the medical image, the laboratory test result and the like of the patients, the doctors can make more accurate diagnosis and treatment decisions, and the care and treatment results of the patients are improved.
Medical data management is important for decision making in medical research and clinical practice, and by analyzing large-scale medical data, researchers can discover new treatment methods, prevention strategies, and disease patterns. Medical data management may also support guidelines for clinical practice and the development of decision support systems to assist doctors in making better treatment options.
Good medical data management can improve medical quality and safety, and potential medical errors and adverse events can be identified and corrected by recording and tracking medical data. Medical data management can also help medical institutions to perform quality assessment and performance improvement, and improve quality and safety of medical services.
The effective medical data management can improve the working efficiency of medical institutions, reduce repeated labor and errors, save time and resources through the digitalized and automatic data management flow, and improve the working efficiency. In addition, medical data management may also aid medical institutions in cost control and resource allocation, optimizing the use and provision of medical services.
Medical data management has important needs in improving patient care, facilitating medical research, improving medical quality and safety, and improving efficiency and control costs. Effective medical data management may bring many benefits to various aspects of the healthcare system and support future medical innovations and developments.
Traditional medical data management schemes typically require a doctor or technician to manually perform classification and labeling of medical images. However, the conventional manual classification and labeling method requires a lot of manpower and time investment due to the huge amount of medical image data. This not only increases the workload, but may also lead to misclassification that delays diagnosis and treatment time. Accordingly, in the present application, an optimized smart AI-based medical data management scheme is provided.
In one embodiment of the present invention, fig. 1 is a flowchart of a medical data management method based on intelligent AI provided in the embodiment of the present invention. Fig. 2 is a schematic diagram of a system architecture of a medical data management method based on intelligent AI according to an embodiment of the present invention. As shown in fig. 1 and 2, a smart AI-based medical data management method 100 according to an embodiment of the invention includes: 110, acquiring medical images to be archived; 120, performing image feature analysis on the medical image to be archived to obtain medical image semantic features; 130, determining a type tag of the medical image to be archived based on the medical image semantic features; and, archiving 140 the medical image to be archived based on the type tag of the medical image to be archived.
In said step 110 it is ensured that the acquired medical image is accurate and complete, including the identity information of the patient and the image itself. By acquiring medical images, a basis for medical data can be established and a data source provided for subsequent image feature analysis and archiving.
In the step 120, key features of the medical image, such as shape, texture, color, etc., are extracted using advanced image processing and analysis techniques. Through image feature analysis, meaningful information can be extracted from medical images, helping understand and interpret image content, and providing a basis for subsequent type tag determination and archiving.
In the step 130, the semantic features of the medical image are associated with and classified by a predefined type tag using techniques such as machine learning, deep learning, etc. By determining the type label of the medical image, the medical image can be classified and organized, so that the medical image is easier to manage and retrieve, and the usability and accessibility of the data are improved.
In step 140, the medical image is archived in a corresponding storage location or database based on the type tag and the index and metadata are built for subsequent retrieval. By archiving the medical images, the medical data can be tidied and organized, and the manageability and discoverability of the data are improved. The archived medical images can be more conveniently accessed and utilized by doctors, researchers, and decision makers.
The medical data management method based on the intelligent AI can improve the processing efficiency and accuracy of medical data in an automatic and intelligent mode, lighten the burden of medical staff, and simultaneously provide more reliable and useful data to support the provision, research and decision making of medical care. The method can improve the effect of medical data management, promote medical progress and improve medical quality.
Specifically, in said step 110, a medical image to be archived is acquired. In view of the above technical problems, the technical idea of the present application is to perform image processing and analysis on medical images by machine vision technology, thereby automatically identifying and classifying different types of medical images, such as X-rays, CT scan, MRI, and the like. Thus, an organized image archiving system is facilitated to be established, doctors and researchers can conveniently search and access specific types of images, and the efficiency and quality of medical data management are improved.
Specifically, in the technical scheme of the application, first, a medical image to be archived is acquired. Acquiring an accurate medical image to be archived is the basis for ensuring the determination of a subsequent type of tag, which may lead to errors or deletions of the type of tag if the acquired image is inaccurate or incomplete.
By acquiring medical images, image feature analysis may be performed to extract key features of the images, which may be used for subsequent type tag determination to aid in identifying and classifying different types of medical images. Acquiring diversified medical images to be archived can increase the richness of data, different types of medical images have different characteristics and semantic information, and a wider medical scene can be covered by acquiring multiple types of images, so that the diversity and representativeness of the data are improved. The type labels of the medical images to be archived can be labeled and classified according to the acquired images, and the medical images can be organized and archived by associating the images with specific labels, so that the medical images are easier to manage and retrieve. After the type labels of the medical images to be archived are determined, the images can be used in different applications and fields, such as medical research, clinical decision support, medical education and the like, and the type labels can help to quickly locate and retrieve the images of the specific types, so that the utilization value and the efficiency of the data are improved.
The method has the advantages that the medical image to be archived is obtained, the important role is played in determining the type label of the medical image to be archived finally, accuracy, richness and classification of data are guaranteed, and a foundation is provided for subsequent medical data management and application.
Specifically, in the step 120, image feature analysis is performed on the medical image to be archived to obtain medical image semantic features. Fig. 3 is a flowchart of the sub-steps of step 120 in a medical data management method based on intelligent AI according to an embodiment of the present invention. As shown in fig. 3, performing image feature analysis on the medical image to be archived to obtain semantic features of the medical image, including: 121, performing image blocking processing on the medical image to be archived to obtain a sequence of medical image blocks; 122, passing the sequence of medical image blocks through a medical image feature extractor based on a convolutional neural network model to obtain a sequence of medical image block semantic feature vectors; 123, respectively carrying out similarity association analysis on any two semantic feature vectors of the medical image blocks in the sequence of the semantic feature vectors of the medical image blocks to obtain a topological feature matrix of semantic similarity among the image blocks; and 124, performing feature fusion on the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks to obtain a global semantic feature matrix of the topological medical image blocks as the semantic features of the medical image.
In the application, first, image blocking processing is performed on the medical image to be archived to obtain a sequence of medical image blocks. By dividing the medical image into blocks, local information in the image can be extracted. In this way, capturing details and features of specific areas in the medical image is facilitated, providing finer data for subsequent feature extraction and analysis.
The sequence of medical image blocks is then passed through a medical image feature extractor based on a convolutional neural network model to obtain a sequence of medical image block semantic feature vectors. By using a feature extractor based on a convolutional neural network model, advanced semantic features can be extracted from each medical image block, and the feature vectors can capture important information of the medical image block, so that the method has higher expressive power and discrimination.
And then, respectively carrying out similarity association analysis on any two semantic feature vectors of the medical image blocks in the sequence of the semantic feature vectors of the medical image blocks to obtain a topological feature matrix of semantic similarity among the image blocks. By performing association analysis on the similarity between the semantic feature vectors of the medical image blocks, a semantic similarity topological feature matrix between the image blocks can be constructed. The semantic similarity topological feature matrix can reflect similarity relations among different image blocks, and is helpful for capturing structure and semantic information among the image blocks.
And finally, carrying out feature fusion on the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks to obtain a global semantic feature matrix of the topological medical image blocks as the semantic features of the medical image. And carrying out feature fusion on the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks, so as to obtain the global semantic feature matrix of the topological medical image blocks. The global semantic feature matrix of the topological medical image block comprehensively considers the local features of the image block and the semantic similarity relation between the local features, and provides more global and richer semantic features of the medical image.
Through the steps, richer and more semantic features can be extracted from the medical image to be archived. These features may better represent the content and structure of the medical image, providing more accurate and useful information for subsequent type tag determination and medical data management.
Next, it is considered that, when the type detection and archiving of medical images to be archived are actually performed, since different local areas in the medical images to be archived may have different features and information, and detailed feature information of certain specific local areas between X-ray, CT scan and MRI images is different, while detailed features of certain specific local areas in the same kind of images are the same. Therefore, in the technical scheme of the application, the medical image to be archived is further subjected to image blocking processing to obtain a sequence of medical image blocks. By processing the medical image to be archived in blocks, independent feature analysis can be performed on each image block to more accurately understand the details and characteristics of a specific area. This facilitates a more accurate understanding and identification of detailed feature information of certain specific areas in the medical image for classification and archiving of the medical image.
Feature extraction of each medical image block in the sequence of medical image blocks is then performed using a convolutional neural network model that has excellent performance in implicit feature extraction of the image. Specifically, feature mining is carried out on the sequence of the medical image blocks in a medical image feature extractor based on a convolutional neural network model so as to extract local semantic feature information related to medical images in each medical image block of the sequence of the medical image blocks, thereby obtaining a sequence of semantic feature vectors of the medical image blocks.
In one embodiment of the present application, for the step 123, performing similarity association analysis on any two semantic feature vectors of the medical image blocks in the sequence of semantic feature vectors of the medical image blocks to obtain a topological feature matrix of semantic similarity between the image blocks, includes: respectively calculating cosine similarity between any two medical image block semantic feature vectors in the sequence of the medical image block semantic feature vectors to obtain an inter-image block semantic similarity topological matrix; and the semantic similarity topological matrix among the image blocks passes through a topological feature extractor based on a convolutional neural network model to obtain the semantic similarity topological feature matrix among the image blocks.
Further, considering that in the medical image to be archived, semantic features between the medical image blocks have an association relationship, in order to make full use of the association relationship, in the technical scheme of the application, cosine similarity between any two medical image block semantic feature vectors in the sequence of the medical image block semantic feature vectors is calculated respectively to obtain an inter-image block semantic similarity topology matrix. By calculating the cosine similarity between any two medical image block semantic feature vectors in the sequence of the medical image block semantic feature vectors, the semantic similarity between the medical image blocks can be quantified, and semantic similarity information of the medical image blocks can be obtained. And the semantic similarity calculation result among the medical image blocks is constructed into the semantic similarity topological matrix among the image blocks, so that a similarity relation network among the image blocks can be formed. By analyzing the semantic similarity topological matrix among the image blocks, the relevance among the medical image blocks can be better understood and analyzed, and the subsequent medical image classification and archiving tasks are facilitated.
And then, carrying out feature mining on the inter-image-block semantic similarity topological matrix through a topological feature extractor based on a convolutional neural network model so as to extract similarity topological association feature information among semantic features of each medical image block, thereby obtaining the inter-image-block semantic similarity topological feature matrix.
In one embodiment of the present application, for the step 124, feature fusion is performed on the sequence of semantic feature vectors of the medical image block and the topological feature matrix of semantic similarity between image blocks to obtain a global semantic feature matrix of the topological medical image block as the semantic feature of the medical image, including: and the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks are processed through a graph neural network model to obtain the global semantic feature matrix of the topological medical image blocks.
And taking each medical image block semantic feature vector in the sequence of the medical image block semantic feature vectors as a feature representation of a node, taking the inter-image block semantic similarity topological feature matrix as a feature representation of a node-to-node edge, and obtaining a topological medical image block global semantic feature matrix by using the medical image block semantic feature matrix and the inter-image block semantic similarity topological feature matrix obtained by two-dimensional arrangement of the plurality of medical image block semantic feature vectors through a graph neural network model. Specifically, the graph neural network model performs graph structure data coding on the medical image block semantic feature matrix and the inter-image block semantic similarity topological feature matrix through a learnable neural network parameter to obtain the topological medical image block global semantic feature matrix containing irregular image block semantic similarity topological association features and the image block semantic feature information.
The graph neural network (Graph Neural Network, GNN for short) is a machine learning model for processing graph structure data, can effectively capture the relationship and dependence between nodes in the graph, and is suitable for processing data with a complex topological structure, such as a semantic similarity topological feature matrix between medical image blocks. The core idea of the graph neural network model is that information transmission and aggregation are carried out on nodes, and local information of the nodes and information of neighbor nodes are aggregated by iteratively updating the representation vectors of the nodes, so that global characteristics of the nodes are deduced.
When the sequence of the semantic feature vectors of the medical image blocks and the semantic similarity topological feature matrix among the image blocks are input into the graph neural network model, the medical image blocks can be regarded as nodes in the graph, and the semantic similarity topological relation among the image blocks can be regarded as edges in the graph. The graph neural network model generates a topological medical image block global semantic feature matrix by learning interactions and dependency relationships between nodes.
Specifically, the graph neural network model is generally composed of a plurality of graph convolution layers and a full connection layer, and the graph convolution layers update the representation vector of the node by aggregating the neighbor information of the node, so that the local characteristics and the global context of the node can be captured. The full connection layer is used for combining and mapping the extracted features to generate a final topological medical image block global semantic feature matrix.
The training process of the graph neural network model generally adopts a supervised learning method, and model parameters are optimized by minimizing the gap between the prediction result and the real label. In medical image data, known labels or other relevant supervision information may be used to guide the training process of the neural network of the map to obtain a more accurate and interpretable global semantic feature matrix of the topological medical image block.
The graph neural network model can extract global semantic features of the topological medical image block from the sequence of semantic feature vectors of the medical image block and the topological feature matrix of semantic similarity among the image blocks by utilizing the relation and the dependence among nodes in the graph structure data. These features can better represent the overall semantic information of the medical image, providing a richer and more accurate representation of the features for subsequent medical data management and application.
Specifically, in the step 130, determining a type tag of the medical image to be archived based on the medical image semantic features includes: performing feature distribution optimization on the global semantic feature matrix of the topological medical image block to obtain an optimized global semantic feature matrix of the topological medical image block; and the global semantic feature matrix of the optimized topological medical image block passes through a classifier to obtain a classification result, wherein the classification result is used for representing the type label of the medical image to be archived.
In one embodiment of the present application, performing feature distribution optimization on the topological medical image block global semantic feature matrix to obtain an optimized topological medical image block global semantic feature matrix, including: cascading the sequence of the semantic feature vectors of the medical image block to obtain a first cascade feature vector; cascading each row of feature vectors of the topological medical image block global semantic feature matrix to obtain a second cascading feature vector; performing homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector to obtain an optimized second cascade feature vector; and carrying out dimension reconstruction on the optimized second cascade feature vector to obtain the optimized topological medical image block global semantic feature matrix.
Particularly, in the technical scheme of the application, when the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks are used for obtaining the global semantic feature matrix of the topological medical image blocks through a graph neural network model, each row of feature vectors of the global semantic feature matrix of the topological medical image blocks express the topological association expression of the image semantic features of the corresponding medical image blocks under the semantic similarity topology of each block, so that in order to keep the image semantic feature information of the semantic feature vectors of the medical image blocks as far as possible while carrying out topological association, the global semantic feature matrix of the topological medical image blocks can be optimized by fusing the sequence of the semantic feature vectors of the medical image blocks.
And, further, considering that the image neural network model performs topological association based on semantic similarity topology in vector units, each row vector of the topological medical image block global semantic feature matrix still has point-to-point homogeneous correspondence with the medical image block semantic feature vector, namely, feature values of each position are densely collected pattern image semantic feature expression of the corresponding medical image block under the two-dimensional local association scale based on the convolution kernel of the convolution neural network model, and therefore, a first cascade feature vector obtained after cascading the sequence of the medical image block semantic feature vectors is recorded as, for exampleAnd a second cascade feature vector obtained by cascade of respective line feature vectors of the topological medical image block global semantic feature matrix, e.g., denoted +.>Performing homogeneous Gilbert spatial metric dense point distribution sampling fusion to obtain optimized second cascade feature vector, such as +.>The method is specifically expressed as follows: carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector by using the following fusion optimization formula to obtain the optimized second cascade feature vector; wherein the fusion optimizationThe formula is:wherein (1)>Is the first cascade feature vector, +.>Is said second concatenated feature vector, +.>Is a transpose of the second concatenated feature vector,represent Min distance and +.>Is super-parameter (herba Cinchi Oleracei)>And->Global feature means of the current load time sequence feature vector and the ambient temperature time sequence feature vector, respectively, and feature vector +.>And->Are all row vectors, +.>For multiplying by position point +.>For the addition of position->Is the optimized second concatenated feature vector.
Here, by the first cascade feature vectorAnd said second cascade feature vector +.>Homogeneous gilbert spatial metric of the feature distribution center of (2) to +.>And said second cascade feature vector +.>Carrying out real (group-trunk) geometric center constraint of fusion feature manifold hyperplane in high-dimensional feature space, and taking point-by-point feature association of cross distance constraint as bias item to realize feature dense point sampling pattern distribution fusion in association constraint limit of feature distribution, thereby enhancing homogeneous sampling association fusion among vectors, thus, optimizing second cascade feature vector>Restoring to the global semantic feature matrix of the topological medical image block improves the expression of the global semantic feature matrix of the topological medical image block on the image semantic feature information of the semantic feature vector of the medical image block, thereby improving the accuracy of the classification result obtained by the classifier. Therefore, the medical images of different types can be automatically identified and classified, thereby being beneficial to establishing an organized image archiving system, facilitating doctors and researchers to search and access the images of specific types and improving the efficiency and quality of medical data management.
In one embodiment of the present application, the global semantic feature matrix of the optimized topological medical image block is passed through a classifier to obtain a classification result, where the classification result is used to represent a type tag of a medical image to be archived, and the method includes: expanding the global semantic feature matrix of the optimized topological medical image block into classification feature vectors according to row vectors or column vectors; performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
And then, the global semantic feature matrix of the topological medical image block passes through a classifier to obtain a classification result, wherein the classification result is used for representing the type label of the medical image to be archived. That is, the classification tag of the classifier is a type tag of a medical image to be archived, and thus, after the classification result is obtained, the medical image to be archived can be archived based on the classification result.
In summary, the intelligent AI-based medical data management method 100 in accordance with an embodiment of the present invention is illustrated for automatically identifying and classifying different types of medical images, such as X-rays, CT scans, MRI, etc., by performing image processing and analysis on the medical images via machine vision techniques. Thus, an organized image archiving system is facilitated to be established, doctors and researchers can conveniently search and access specific types of images, and the efficiency and quality of medical data management are improved.
Fig. 4 is a block diagram of a medical data management system based on intelligent AI according to an embodiment of the present invention, as shown in fig. 4, where the medical data management system based on intelligent AI includes: an image acquisition module 210 for acquiring medical images to be archived; the image feature analysis module 220 is configured to perform image feature analysis on the medical image to be archived to obtain semantic features of the medical image; a type tag determination module 230, configured to determine a type tag of a medical image to be archived based on the semantic features of the medical image; and an archiving module 240, configured to archive the medical image to be archived based on the type tag of the medical image to be archived.
In the intelligent AI-based medical data management system, the image feature analysis module includes: the image blocking processing unit is used for carrying out image blocking processing on the medical image to be archived so as to obtain a sequence of medical image blocks; the feature extraction unit is used for enabling the sequence of the medical image blocks to pass through a medical image feature extractor based on a convolutional neural network model to obtain a sequence of semantic feature vectors of the medical image blocks; the association analysis unit is used for carrying out similarity association analysis on any two semantic feature vectors of the medical image blocks in the sequence of the semantic feature vectors of the medical image blocks so as to obtain a topological feature matrix of semantic similarity among the image blocks; and the feature fusion unit is used for carrying out feature fusion on the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks to obtain a global semantic feature matrix of the topological medical image blocks as the semantic features of the medical image.
It will be appreciated by those skilled in the art that the specific operation of the respective steps in the above-described smart AI-based medical data management system has been described in detail in the above description of the smart AI-based medical data management method with reference to fig. 1 to 3, and thus, repeated descriptions thereof will be omitted.
As described above, the smart AI-based medical data management system 100 according to an embodiment of the present invention may be implemented in various terminal devices, such as a server or the like for smart AI-based medical data management. In one example, the smart AI-based medical data management system 100 may be integrated into a terminal device as a software module and/or hardware module in accordance with an embodiment of the invention. For example, the smart AI-based medical data management system 100 may be a software module in the operating system of the terminal device or may be an application developed for the terminal device; of course, the intelligent AI-based medical data management system 100 can likewise be one of a number of hardware modules of the terminal device.
Alternatively, in another example, the smart AI-based medical data management system 100 and the terminal device may be separate devices, and the smart AI-based medical data management system 100 may be connected to the terminal device via a wired and/or wireless network and transmit the interaction information in accordance with the agreed data format.
Fig. 5 is an application scenario diagram of a medical data management method based on intelligent AI provided in an embodiment of the present invention. As shown in fig. 5, in the application scenario, first, a medical image to be archived (e.g., C as illustrated in fig. 5) is acquired; then, inputting the acquired medical image to be archived into a server (e.g., S as illustrated in fig. 5) deployed with a smart AI-based medical data management algorithm, wherein the server is capable of processing the medical image to be archived based on the smart AI' S medical data management algorithm to determine a type tag of the medical image to be archived; and archiving the medical image to be archived based on the type tag of the medical image to be archived.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A medical data management method based on intelligent AI, comprising:
acquiring a medical image to be archived;
performing image feature analysis on the medical image to be archived to obtain medical image semantic features;
determining a type tag of the medical image to be archived based on the medical image semantic features; and
and archiving the medical image to be archived based on the type label of the medical image to be archived.
2. The intelligent AI-based medical data management method of claim 1, wherein performing image feature analysis on the medical image to be archived to obtain medical image semantic features comprises:
performing image blocking processing on the medical image to be archived to obtain a sequence of medical image blocks;
passing the sequence of medical image blocks through a medical image feature extractor based on a convolutional neural network model to obtain a sequence of medical image block semantic feature vectors;
respectively carrying out similarity association analysis on any two medical image block semantic feature vectors in the sequence of the medical image block semantic feature vectors to obtain an inter-image block semantic similarity topological feature matrix; and
and carrying out feature fusion on the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks to obtain a global semantic feature matrix of the topological medical image blocks as the semantic features of the medical image.
3. The intelligent AI-based medical data management method of claim 2, wherein performing similarity association analysis between any two medical image block semantic feature vectors in the sequence of medical image block semantic feature vectors to obtain an inter-image block semantic similarity topological feature matrix, respectively, comprises:
respectively calculating cosine similarity between any two medical image block semantic feature vectors in the sequence of the medical image block semantic feature vectors to obtain an inter-image block semantic similarity topological matrix; and
and the semantic similarity topological feature matrix among the image blocks is obtained through a topological feature extractor based on a convolutional neural network model.
4. The intelligent AI-based medical data management method of claim 3, wherein feature fusion of the sequence of medical image block semantic feature vectors and the inter-image block semantic similarity topological feature matrix to obtain a topological medical image block global semantic feature matrix as the medical image semantic features comprises: and the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks are processed through a graph neural network model to obtain the global semantic feature matrix of the topological medical image blocks.
5. The intelligent AI-based medical data management method of claim 4, wherein determining a type tag for a medical image to be archived based on the medical image semantic features comprises:
performing feature distribution optimization on the global semantic feature matrix of the topological medical image block to obtain an optimized global semantic feature matrix of the topological medical image block; and
and the global semantic feature matrix of the optimized topological medical image block passes through a classifier to obtain a classification result, wherein the classification result is used for representing the type label of the medical image to be archived.
6. The intelligent AI-based medical data management method of claim 5, wherein performing feature distribution optimization on the topological medical image block global semantic feature matrix to obtain an optimized topological medical image block global semantic feature matrix comprises:
cascading the sequence of the semantic feature vectors of the medical image block to obtain a first cascade feature vector;
cascading each row of feature vectors of the topological medical image block global semantic feature matrix to obtain a second cascading feature vector;
performing homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector to obtain an optimized second cascade feature vector; and
and carrying out dimension reconstruction on the optimized second cascade feature vector to obtain the optimized topological medical image block global semantic feature matrix.
7. The intelligent AI-based medical data management method of claim 6, wherein performing homogeneous gilbert spatial metric dense point distribution sampling fusion on the first cascading feature vector and the second cascading feature vector to obtain an optimized second cascading feature vector comprises:
carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector by using the following fusion optimization formula to obtain the optimized second cascade feature vector;
the fusion optimization formula is as follows:wherein (1)>Is the first cascade feature vector, +.>Is said second concatenated feature vector, +.>Is a transpose of the second concatenated feature vector,represent Min distance and +.>Is super-parameter (herba Cinchi Oleracei)>And->Global feature means of the current load time sequence feature vector and the ambient temperature time sequence feature vector, respectively, and feature vector +.>And->Are all row vectors, +.>For multiplying by position point +.>For the addition of position->Is the optimized second concatenated feature vector.
8. The intelligent AI-based medical data management method of claim 7, wherein passing the optimized topological medical image block global semantic feature matrix through a classifier to obtain a classification result, the classification result being used to represent a type tag of a medical image to be archived, comprising:
expanding the global semantic feature matrix of the optimized topological medical image block into classification feature vectors according to row vectors or column vectors;
performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and
and the coding classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
9. A medical data management system based on intelligent AI, comprising:
the image acquisition module is used for acquiring medical images to be archived;
the image feature analysis module is used for carrying out image feature analysis on the medical image to be archived so as to obtain semantic features of the medical image;
the type label determining module is used for determining type labels of medical images to be archived based on the semantic features of the medical images; and
and the archiving module is used for archiving the medical image to be archived based on the type label of the medical image to be archived.
10. The intelligent AI-based medical data management system of claim 9, wherein the image feature analysis module comprises:
the image blocking processing unit is used for carrying out image blocking processing on the medical image to be archived so as to obtain a sequence of medical image blocks;
the feature extraction unit is used for enabling the sequence of the medical image blocks to pass through a medical image feature extractor based on a convolutional neural network model to obtain a sequence of semantic feature vectors of the medical image blocks;
the association analysis unit is used for carrying out similarity association analysis on any two semantic feature vectors of the medical image blocks in the sequence of the semantic feature vectors of the medical image blocks so as to obtain a topological feature matrix of semantic similarity among the image blocks; and
the feature fusion unit is used for carrying out feature fusion on the sequence of the semantic feature vectors of the medical image blocks and the topological feature matrix of the semantic similarity among the image blocks to obtain a global semantic feature matrix of the topological medical image blocks as the semantic features of the medical image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311461912.4A CN117457134A (en) | 2023-11-06 | 2023-11-06 | Medical data management method and system based on intelligent AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311461912.4A CN117457134A (en) | 2023-11-06 | 2023-11-06 | Medical data management method and system based on intelligent AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117457134A true CN117457134A (en) | 2024-01-26 |
Family
ID=89594520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311461912.4A Pending CN117457134A (en) | 2023-11-06 | 2023-11-06 | Medical data management method and system based on intelligent AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117457134A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130179192A1 (en) * | 2012-01-05 | 2013-07-11 | GNAX Holdings, LLC | Systems and Methods for Managing, Storing, and Exchanging Healthcare Information and Medical Images |
| CN116452577A (en) * | 2023-05-09 | 2023-07-18 | 河南中医药大学第一附属医院 | Clinical detection device of ultrasonic department |
| CN116776872A (en) * | 2023-03-29 | 2023-09-19 | 浙江大学 | Medical data structured archiving system |
| CN116796045A (en) * | 2023-08-23 | 2023-09-22 | 北京人天书店集团股份有限公司 | Multi-dimensional book grading method, system and readable medium |
| CN116849683A (en) * | 2023-08-14 | 2023-10-10 | 河南中医药大学第一附属医院 | Intelligent auxiliary device for exercise rehabilitation |
| CN116864836A (en) * | 2023-08-18 | 2023-10-10 | 中恩电气有限公司 | Double-station heavy main switch for storage battery |
-
2023
- 2023-11-06 CN CN202311461912.4A patent/CN117457134A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130179192A1 (en) * | 2012-01-05 | 2013-07-11 | GNAX Holdings, LLC | Systems and Methods for Managing, Storing, and Exchanging Healthcare Information and Medical Images |
| CN116776872A (en) * | 2023-03-29 | 2023-09-19 | 浙江大学 | Medical data structured archiving system |
| CN116452577A (en) * | 2023-05-09 | 2023-07-18 | 河南中医药大学第一附属医院 | Clinical detection device of ultrasonic department |
| CN116849683A (en) * | 2023-08-14 | 2023-10-10 | 河南中医药大学第一附属医院 | Intelligent auxiliary device for exercise rehabilitation |
| CN116864836A (en) * | 2023-08-18 | 2023-10-10 | 中恩电气有限公司 | Double-station heavy main switch for storage battery |
| CN116796045A (en) * | 2023-08-23 | 2023-09-22 | 北京人天书店集团股份有限公司 | Multi-dimensional book grading method, system and readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chang et al. | Pima Indians diabetes mellitus classification based on machine learning (ML) algorithms | |
| Nichols et al. | Machine learning: applications of artificial intelligence to imaging and diagnosis | |
| RU2543563C2 (en) | Systems and methods for clinical decision support | |
| Mehmood et al. | Video summarization based tele-endoscopy: a service to efficiently manage visual data generated during wireless capsule endoscopy procedure | |
| Mahesh et al. | Early predictive model for breast cancer classification using blended ensemble learning | |
| CN113707264A (en) | Medicine recommendation method, device, equipment and medium based on machine learning | |
| CN110598722A (en) | Multi-modal neuroimaging data automatic information fusion system | |
| CN114399634B (en) | Three-dimensional image classification method, system, equipment and medium based on weak supervision learning | |
| Tripathi et al. | Fairness and ethics in artificial intelligence-based medical imaging | |
| Gezimati et al. | Internet of things enabled framework for terahertz and infrared cancer imaging | |
| Tong et al. | Locating abnormal heartbeats in ECG segments based on deep weakly supervised learning | |
| Refaee et al. | A computing system that integrates deep learning and the internet of things for effective disease diagnosis in smart health care systems | |
| AlZu’Bi et al. | transfer learning enabled CAD system for monkey pox classification | |
| Elhanashi et al. | Classification and Localization of Multi-type Abnormalities on Chest X-rays Images | |
| Jatmiko et al. | A review of big data analytics in the biomedical field | |
| Wang et al. | Segment medical image using U-Net combining recurrent residuals and attention | |
| CN117457134A (en) | Medical data management method and system based on intelligent AI | |
| Megalooikonomou et al. | Medical data fusion for telemedicine | |
| CN114678126A (en) | Disease tracking and predicting system | |
| Xiao et al. | Intracerebral haemorrhage growth prediction based on displacement vector field and clinical metadata | |
| Liu et al. | Development of an Expert-Level Right Ventricular Abnormality Detection Algorithm Based on Deep Learning | |
| Jin et al. | Content and semantic context based image retrieval for medical image grid | |
| Pivithuru et al. | E-patient Card: An Integrated Electronic Health Recording System for Patient | |
| Rayan | Machine Learning for Smart Health Care | |
| Tutuko et al. | A Deep Learning Approach to Integrate Medical Big Data for Improving Health Services in Indonesia. |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Hu Weifan Inventor after: Yang Jinji Inventor after: Chen Junyang Inventor after: Du Xiaoxue Inventor before: Du Xiaoxue |