CN113034489A - Artificial intelligence nasal sinus CT image processing system based on degree of depth learning - Google Patents
Artificial intelligence nasal sinus CT image processing system based on degree of depth learning Download PDFInfo
- Publication number
- CN113034489A CN113034489A CN202110411483.4A CN202110411483A CN113034489A CN 113034489 A CN113034489 A CN 113034489A CN 202110411483 A CN202110411483 A CN 202110411483A CN 113034489 A CN113034489 A CN 113034489A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- sinus
- data
- model
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
- G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
-
- 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
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- 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
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5862—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using texture
-
- 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
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides an artificial intelligence sinus CT image processing system based on deep learning, which comprises a data mechanism through platform, an image collecting module, an image processing module, a model building system, a big data technology module and a safety system, wherein the data mechanism through platform contains and integrates data information and image information of a medical institution and is connected to a cloud system; according to the invention, the image collection module is used for collecting the patient sinus CT image, the image element extraction module is used for extracting the characteristics and characteristic values of the sinus CT image, the depth learning modeling module is used for constructing the visual vector model, the diagnosis prediction module is used for comparing the patient sinus CT image with a plurality of main models, so that the corresponding focus can be determined, the focus is compared with a plurality of sub models in the focus main model, the time point of the degree of the patient can be determined, the diagnosis result is accurate to the time point of the course of the disease, and the diagnosis accuracy is high and detailed.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an artificial intelligence sinus CT image processing system based on deep learning.
Background
With the progress of the times and the development of scientific technology, medical research becomes more and more important, and in the field of medical research, the analysis and processing of some image data information are particularly important, and at present, mature products capable of being practically applied in the aspect are rarely reported and are mainly in the research level;
in the diagnosis of the paranasal sinuses, the paranasal sinuses are cavities containing air in the skull around the nasal cavity, so that the focus is difficult to determine through external observation and diagnosis, the paranasal sinuses need to be photographed and computed, and then doctors diagnose CT images, the diagnosis has the characteristic of strong subjectivity and is easy to generate errors, and therefore, the invention provides an artificial intelligent paranasal sinus CT image processing system for establishing database model comparison analysis based on deep learning to solve the problems in the prior art.
Disclosure of Invention
Aiming at the problems, the invention provides an artificial intelligent sinus CT image processing system based on deep learning, the diagnosis result of the system is accurate to the time point of the course of disease, and the diagnosis accuracy is high and detailed.
In order to realize the purpose of the invention, the invention is realized by the following technical scheme: the artificial intelligence sinus CT image processing system based on deep learning comprises a data mechanism through platform, an image collecting module, an image processing module, a model building system, a big data technology module and a safety system, wherein the data mechanism through platform contains and integrates data information and image information of a medical mechanism and is connected to a cloud system, and the image collecting module is built in a cloud system and collects CT images of the sinus of a patient;
the image processing module comprises a data image screening module, an image set constructing module and an image element extracting module, wherein the image screening module screens the CT images of the paranasal sinuses collected by the image collecting module, the weight of the CT images is removed firstly, then low-quality image data is removed, the image set constructing module analyzes and classifies the screened data to form a CT image data set of the paranasal sinuses, the image element extracting module extracts the color characteristics of the CT image data set of the paranasal sinuses firstly, extracts the texture characteristics of the images, then determines the texture fineness of the images, and finally determines the characteristic value of each image;
the model construction system comprises a deep learning modeling module and a diagnosis prediction module, wherein the deep learning modeling module firstly constructs a paranasal sinus focus knowledge base, then establishes a global shared image base to obtain a multi-element heterogeneous knowledge source, defines and constructs the concept, the attribute, the example and the characteristic element of the paranasal sinus according to the knowledge source on the basis, then perfects the concept, the attribute, the example and the characteristic element of the paranasal sinus again, carries out three-dimensional model 3D visualization on the image data after completion, constructs a plurality of main models according to focus classification, develops and constructs a plurality of sub models according to time processes in the plurality of main models, and finally carries out the numerical vectorization on the corresponding color feature, texture feature and time feature in the models to complete the visual vector model;
the diagnosis prediction module receives a patient sinus CT image collected by the big data technology module, sends the image to the image element extraction module, extracts the feature elements of the image, inputs the extracted feature elements into the visual vector model for comparison, and excavates the associated information to obtain the reliable state description of the patient degree time point;
big data technology module includes search engine and patient's module of seeing a doctor, search engine is the multi-user full text search engine of distributed, search engine inserts the direct platform of degree of depth study modeling module and data mechanism, realizes the inquiry search to the direct platform of degree of depth study modeling module and data mechanism, the patient module of seeing a doctor includes CT room access module, log generation module and diagnosis report module, CT room access module inserts medical structure CT room, receives the sinus CT image of patient to with sinus CT image transmission to diagnosis prediction module, simultaneously, log generation module automatic generation is these each item data of patient and is preserved, diagnosis report module receives the reliable state description of diagnosis prediction module to the patient and automatic generation diagnosis report.
The further improvement lies in that: the image collection module comprises a standard information conversion interface used for transmitting texts, PDFs and image files, combines the Big data technology and adopts the distributed rapid exchange technology for information transmission.
The further improvement lies in that: and the image set construction module analyzes and classifies the screened data, classifies the data according to the types of the focuses of the patients, classifies the focuses according to the development sequence of each type of the focuses along with the time process, stamps the timestamps, and forms a sinus CT image data set after the classification is finished.
The further improvement lies in that: the image element extraction module extracts color features of images in a CT image data set of the paranasal sinus, converts RGB images into HLS images directly by utilizing ENVI software, extracts the color features, performs filtering along the direction of the overall trend by the filtering function of the ENVI software, extracts image textures, places the texture results of filtering extraction in an ARCGIS for density analysis, determines the texture fineness of the images, then performs the calculation of second derivative of spectrum on the images, writes a second derivative operation algorithm in ENVI IDL, and determines the feature value of each image.
The further improvement lies in that: the deep learning modeling module acquires a CT image data set of the paranasal sinuses and a characteristic value of each image from the image processing module, constructs a paranasal sinus focus knowledge base, then establishes a global shared image base around the field knowledge characteristics, then obtains a multi-element heterogeneous knowledge source according to focus classification and focus development classification of the paranasal sinuses along with time process, defines and constructs the concept, the attribute, the example and the characteristic element of the paranasal sinuses according to the knowledge source on the basis, detects the concept, the attribute, the example and the characteristic element of the paranasal sinuses by taking a convolutional neural network as a basic frame on the basis of a TensorFlow and a PyTorch platform, migrates knowledge from the existing paranasal sinus model concept by utilizing a migration learning connection data mechanism through platform, performs cross verification, completes the concept, the attribute, the example and the characteristic element of the paranasal sinuses once again, and performs three-dimensional model 3D visualization on the image data after completion by adopting ContextCapture, and finally, carrying out numerical vectorization on the corresponding color characteristics, texture characteristics and time characteristics in the model by using the SVG to complete the visual vector model.
The further improvement lies in that: the diagnosis prediction module receives a patient sinus CT image collected by the big data technology module, sends the image to the image element extraction module, extracts color features, texture features and texture fineness of the image, inputs the extracted information into the visual vector model, compares the extracted information with a plurality of main models, excavates the associated information between the image and the main models, determines a corresponding focus main model according to the amount of the associated information, compares the focus main model with a sub model in the focus main model, excavates the associated information, filters the sub model by screening mutually contradictory concepts, determines the sub model with the highest similarity with the sinus CT image, and obtains the reliable state description of the patient degree time point.
The further improvement lies in that: in the visual vector model, a plurality of message packets are constructed corresponding to each submodel, a voice playing module is arranged in each silencing packet, and the voice playing module is used for describing patients for the submodels corresponding to the patients.
The further improvement lies in that: the search engine is deployed by adopting an ElasticSearch + Logstash + Kibana framework, a distributed multi-user full-text search engine is formed by utilizing an ElasticSearch search server, and the search engine realizes inquiry and search on a deep learning modeling module and a data mechanism direct platform by utilizing an ELK technology.
The further improvement lies in that: the security system adopts a LINUX operating system and is provided with a firewall, adopts access authorization, control authorization, variable/parameter uploading selected by a user independently and reverse control judgment, and adopts channel encryption, data packet encryption and a private protocol.
The invention has the beneficial effects that: the invention collects CT images of paranasal sinuses of patients through an image collecting module, extracts the characteristics and characteristic values of the CT images of paranasal sinuses through an image element extracting module, constructs a paranasal sinus focus knowledge base through a deep learning modeling module, establishes a global shared image base, obtains a plurality of heterogeneous knowledge sources, defines and constructs the concepts, attributes, examples and characteristic elements of the paranasal sinuses according to the knowledge sources on the basis of the knowledge base, completes a visual vector model, the model comprises a main model for focus classification and a sub model developed according to a time process, has perfect characteristic elements, compares the CT images of the paranasal sinuses of patients with a plurality of main models through a diagnosis predicting module, can determine corresponding focuses, compares the focuses with a plurality of sub models in the main model, can determine the time point of the degree of the patients, the diagnosis result is accurate to the time point of the disease process, has high and detailed diagnosis accuracy, meanwhile, through the arrangement of the big data technology module, the inquiry and search of the deep learning modeling module and the data mechanism direct platform can be realized, a doctor can conveniently retrieve a case, and convenience is brought to diagnosis.
Drawings
FIG. 1 is a schematic view of the present invention;
FIG. 2 is a diagnostic flow chart of the present invention.
Detailed Description
In order to further understand the present invention, the following detailed description will be made with reference to the following examples, which are only used for explaining the present invention and are not to be construed as limiting the scope of the present invention.
According to fig. 1 and 2, the embodiment provides an artificial intelligence sinus CT image processing system based on deep learning, which includes a data mechanism through platform, an image collection module, an image processing module, a model construction system, a big data technology module and a safety system, wherein the data mechanism through platform encloses and integrates data information and image information of a medical mechanism and is connected to a cloud system, and the image collection module is built in a cloud system and collects CT images of a sinus of a patient;
the image processing module comprises a data image screening module, an image set constructing module and an image element extracting module, wherein the image screening module screens the CT images of the paranasal sinuses collected by the image collecting module, the weight of the CT images is removed firstly, then low-quality image data is removed, the image set constructing module analyzes and classifies the screened data to form a CT image data set of the paranasal sinuses, the image element extracting module extracts the color characteristics of the CT image data set of the paranasal sinuses firstly, extracts the texture characteristics of the images, then determines the texture fineness of the images, and finally determines the characteristic value of each image;
the model construction system comprises a deep learning modeling module and a diagnosis prediction module, wherein the deep learning modeling module firstly constructs a paranasal sinus focus knowledge base, then establishes a global shared image base to obtain a multi-element heterogeneous knowledge source, defines and constructs the concept, the attribute, the example and the characteristic element of the paranasal sinus according to the knowledge source on the basis, then perfects the concept, the attribute, the example and the characteristic element of the paranasal sinus again, carries out three-dimensional model 3D visualization on the image data after completion, constructs a plurality of main models according to focus classification, develops and constructs a plurality of sub models according to time processes in the plurality of main models, and finally carries out the numerical vectorization on the corresponding color feature, texture feature and time feature in the models to complete the visual vector model;
the diagnosis prediction module receives a patient sinus CT image collected by the big data technology module, sends the image to the image element extraction module, extracts the feature elements of the image, inputs the extracted feature elements into the visual vector model for comparison, and excavates the associated information to obtain the reliable state description of the patient degree time point;
big data technology module includes search engine and patient's module of seeing a doctor, search engine is the multi-user full text search engine of distributed, search engine inserts the direct platform of degree of depth study modeling module and data mechanism, realizes the inquiry search to the direct platform of degree of depth study modeling module and data mechanism, the patient module of seeing a doctor includes CT room access module, log generation module and diagnosis report module, CT room access module inserts medical structure CT room, receives the sinus CT image of patient to with sinus CT image transmission to diagnosis prediction module, simultaneously, log generation module automatic generation is these each item data of patient and is preserved, diagnosis report module receives the reliable state description of diagnosis prediction module to the patient and automatic generation diagnosis report.
The image collection module comprises a standard information conversion interface used for transmitting texts, PDFs and image files, combines the Big data technology and adopts the distributed rapid exchange technology for information transmission.
And the image set construction module analyzes and classifies the screened data, classifies the data according to the types of the focuses of the patients, classifies the focuses according to the development sequence of each type of the focuses along with the time process, stamps the timestamps, and forms a sinus CT image data set after the classification is finished.
The image element extraction module extracts color features of images in a CT image data set of the paranasal sinus, converts RGB images into HLS images directly by utilizing ENVI software, extracts the color features, performs filtering along the direction of the overall trend by the filtering function of the ENVI software, extracts image textures, places the texture results of filtering extraction in an ARCGIS for density analysis, determines the texture fineness of the images, then performs the calculation of second derivative of spectrum on the images, writes a second derivative operation algorithm in ENVI IDL, and determines the feature value of each image.
The deep learning modeling module acquires a CT image data set of the paranasal sinuses and a characteristic value of each image from the image processing module, constructs a paranasal sinus focus knowledge base, then establishes a global shared image base around the field knowledge characteristics, then obtains a multi-element heterogeneous knowledge source according to focus classification and focus development classification of the paranasal sinuses along with time process, defines and constructs the concept, the attribute, the example and the characteristic element of the paranasal sinuses according to the knowledge source on the basis, detects the concept, the attribute, the example and the characteristic element of the paranasal sinuses by taking a convolutional neural network as a basic frame on the basis of a TensorFlow and a PyTorch platform, migrates knowledge from the existing paranasal sinus model concept by utilizing a migration learning connection data mechanism through platform, performs cross verification, completes the concept, the attribute, the example and the characteristic element of the paranasal sinuses once again, and performs three-dimensional model 3D visualization on the image data after completion by adopting ContextCapture, and finally, carrying out numerical vectorization on the corresponding color characteristics, texture characteristics and time characteristics in the model by using the SVG to complete the visual vector model.
The diagnosis prediction module receives a patient sinus CT image collected by the big data technology module, sends the image to the image element extraction module, extracts color features, texture features and texture fineness of the image, inputs the extracted information into the visual vector model, compares the extracted information with a plurality of main models, excavates the associated information between the image and the main models, determines a corresponding focus main model according to the amount of the associated information, compares the focus main model with a sub model in the focus main model, excavates the associated information, filters the sub model by screening mutually contradictory concepts, determines the sub model with the highest similarity with the sinus CT image, and obtains the reliable state description of the patient degree time point.
In the visual vector model, a plurality of message packets are constructed corresponding to each submodel, a voice playing module is arranged in each silencing packet, and the voice playing module is used for describing patients for the submodel corresponding to the patients;
the search engine is deployed by adopting an ElasticSearch + Logstash + Kibana framework, a distributed multi-user full-text search engine is formed by utilizing an ElasticSearch search server, and the search engine realizes inquiry and search on a deep learning modeling module and a data mechanism direct platform by utilizing an ELK technology.
The security system adopts a LINUX operating system and is provided with a firewall, adopts access authorization, control authorization, variable/parameter uploading selected by a user independently and reverse control judgment, and adopts channel encryption, data packet encryption and a private protocol.
The artificial intelligent sinus CT image processing system based on deep learning collects CT images of sinuses of a patient through an image collecting module, extracts the characteristics and characteristic values of the CT images of the sinuses through an image element extracting module, constructs a sinus focus knowledge base through a deep learning modeling module, establishes a global shared image base, obtains a plurality of heterogeneous knowledge sources, defines and constructs concepts, attributes, examples and characteristic elements of the sinuses according to the knowledge sources on the basis of the characteristics and the characteristic values to complete a visual vector model, comprises a focus classification main model and a sub model developing according to a time process, has perfect characteristic elements, compares the CT images of the sinuses of the patient with a plurality of main models through a diagnosis predicting module, can determine corresponding focuses, compares the focuses with a plurality of sub models in the focus main model, and can determine the time point of the degree of the patient, the diagnosis result is accurate to the time point of the disease course, the diagnosis accuracy is high and detailed, meanwhile, through the arrangement of the big data technology module, the inquiry and search of the deep learning modeling module and the data mechanism direct platform can be realized, a doctor can conveniently retrieve cases, and convenience is brought to diagnosis.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. Artificial intelligence sinus CT image processing system based on degree of depth study, its characterized in that: the system comprises a data mechanism through platform, an image collection module, an image processing module, a model construction system, a big data technology module and a safety system, wherein the data mechanism through platform contains and integrates data information and image information of a medical mechanism and is connected to a cloud system, and the image collection module is established in the cloud system and collects CT images of the paranasal sinuses of a patient;
the image processing module comprises a data image screening module, an image set constructing module and an image element extracting module, wherein the image screening module screens the CT images of the paranasal sinuses collected by the image collecting module, the weight of the CT images is removed firstly, then low-quality image data is removed, the image set constructing module analyzes and classifies the screened data to form a CT image data set of the paranasal sinuses, the image element extracting module extracts the color characteristics of the CT image data set of the paranasal sinuses firstly, extracts the texture characteristics of the images, then determines the texture fineness of the images, and finally determines the characteristic value of each image;
the model construction system comprises a deep learning modeling module and a diagnosis prediction module, wherein the deep learning modeling module firstly constructs a paranasal sinus focus knowledge base, then establishes a global shared image base to obtain a multi-element heterogeneous knowledge source, defines and constructs the concept, the attribute, the example and the characteristic element of the paranasal sinus according to the knowledge source on the basis, then perfects the concept, the attribute, the example and the characteristic element of the paranasal sinus again, carries out three-dimensional model 3D visualization on the image data after completion, constructs a plurality of main models according to focus classification, develops and constructs a plurality of sub models according to time processes in the plurality of main models, and finally carries out the numerical vectorization on the corresponding color feature, texture feature and time feature in the models to complete the visual vector model;
the diagnosis prediction module receives a patient sinus CT image collected by the big data technology module, sends the image to the image element extraction module, extracts the feature elements of the image, inputs the extracted feature elements into the visual vector model for comparison, and excavates the associated information to obtain the reliable state description of the patient degree time point;
big data technology module includes search engine and patient's module of seeing a doctor, search engine is the multi-user full text search engine of distributed, search engine inserts the direct platform of degree of depth study modeling module and data mechanism, realizes the inquiry search to the direct platform of degree of depth study modeling module and data mechanism, the patient module of seeing a doctor includes CT room access module, log generation module and diagnosis report module, CT room access module inserts medical structure CT room, receives the sinus CT image of patient to with sinus CT image transmission to diagnosis prediction module, simultaneously, log generation module automatic generation is these each item data of patient and is preserved, diagnosis report module receives the reliable state description of diagnosis prediction module to the patient and automatic generation diagnosis report.
2. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: the image collection module comprises a standard information conversion interface used for transmitting texts, PDFs and image files, combines the Big data technology and adopts the distributed rapid exchange technology for information transmission.
3. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: and the image set construction module analyzes and classifies the screened data, classifies the data according to the types of the focuses of the patients, classifies the focuses according to the development sequence of each type of the focuses along with the time process, stamps the timestamps, and forms a sinus CT image data set after the classification is finished.
4. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: the image element extraction module extracts color features of images in a CT image data set of the paranasal sinus, converts RGB images into HLS images directly by utilizing ENVI software, extracts the color features, performs filtering along the direction of the overall trend by the filtering function of the ENVI software, extracts image textures, places the texture results of filtering extraction in an ARCGIS for density analysis, determines the texture fineness of the images, then performs the calculation of second derivative of spectrum on the images, writes a second derivative operation algorithm in ENVI IDL, and determines the feature value of each image.
5. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: the deep learning modeling module acquires a CT image data set of the paranasal sinuses and a characteristic value of each image from the image processing module, constructs a paranasal sinus focus knowledge base, then establishes a global shared image base around the field knowledge characteristics, then obtains a multi-element heterogeneous knowledge source according to focus classification and focus development classification of the paranasal sinuses along with time process, defines and constructs the concept, the attribute, the example and the characteristic element of the paranasal sinuses according to the knowledge source on the basis, detects the concept, the attribute, the example and the characteristic element of the paranasal sinuses by taking a convolutional neural network as a basic frame on the basis of a TensorFlow and a PyTorch platform, migrates knowledge from the existing paranasal sinus model concept by utilizing a migration learning connection data mechanism through platform, performs cross verification, completes the concept, the attribute, the example and the characteristic element of the paranasal sinuses once again, and performs three-dimensional model 3D visualization on the image data after completion by adopting ContextCapture, and finally, carrying out numerical vectorization on the corresponding color characteristics, texture characteristics and time characteristics in the model by using the SVG to complete the visual vector model.
6. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: the diagnosis prediction module receives a patient sinus CT image collected by the big data technology module, sends the image to the image element extraction module, extracts color features, texture features and texture fineness of the image, inputs the extracted information into the visual vector model, compares the extracted information with a plurality of main models, excavates the associated information between the image and the main models, determines a corresponding focus main model according to the amount of the associated information, compares the focus main model with a sub model in the focus main model, excavates the associated information, filters the sub model by screening mutually contradictory concepts, determines the sub model with the highest similarity with the sinus CT image, and obtains the reliable state description of the patient degree time point.
7. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: in the visual vector model, a plurality of message packets are constructed corresponding to each submodel, a voice playing module is arranged in each silencing packet, and the voice playing module is used for describing patients for the submodels corresponding to the patients.
8. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: the search engine is deployed by adopting an ElasticSearch + Logstash + Kibana framework, a distributed multi-user full-text search engine is formed by utilizing an ElasticSearch search server, and the search engine realizes inquiry and search on a deep learning modeling module and a data mechanism direct platform by utilizing an ELK technology.
9. The artificial intelligence sinus CT image processing system based on deep learning of claim 1, characterized in that: the security system adopts a LINUX operating system and is provided with a firewall, adopts access authorization, control authorization, variable/parameter uploading selected by a user independently and reverse control judgment, and adopts channel encryption, data packet encryption and a private protocol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110411483.4A CN113034489B (en) | 2021-04-16 | 2021-04-16 | Artificial intelligence nasal sinus CT image processing system based on degree of deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110411483.4A CN113034489B (en) | 2021-04-16 | 2021-04-16 | Artificial intelligence nasal sinus CT image processing system based on degree of deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113034489A true CN113034489A (en) | 2021-06-25 |
| CN113034489B CN113034489B (en) | 2022-11-01 |
Family
ID=76457311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110411483.4A Active CN113034489B (en) | 2021-04-16 | 2021-04-16 | Artificial intelligence nasal sinus CT image processing system based on degree of deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034489B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610831A (en) * | 2021-08-19 | 2021-11-05 | 江西应用技术职业学院 | Wood defect detection method based on computer image technology and transfer learning |
| CN113820321A (en) * | 2021-09-23 | 2021-12-21 | 广州利科科技有限公司 | Road and bridge pavement crack detection system and detection method thereof |
| CN115131343A (en) * | 2022-08-03 | 2022-09-30 | 华中科技大学同济医学院附属同济医院 | Method, device and equipment for parting chronic nasosinusitis and readable storage medium |
| CN115502619A (en) * | 2022-09-27 | 2022-12-23 | 江苏省特种设备安全监督检验研究院 | Temperature monitoring system for longitudinal seam welding of pressure vessel cylinder |
| CN116013504A (en) * | 2022-12-29 | 2023-04-25 | 上海市中医医院 | Traditional Chinese medicine tongue diagnosis device based on image retrieval analysis |
| CN117788461A (en) * | 2024-02-23 | 2024-03-29 | 华中科技大学同济医学院附属同济医院 | Magnetic resonance image quality evaluation system based on image analysis |
| CN118039088A (en) * | 2024-04-15 | 2024-05-14 | 达州爱迦飞诗特科技有限公司 | Artificial intelligence auxiliary diagnosis data processing system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040122704A1 (en) * | 2002-12-18 | 2004-06-24 | Sabol John M. | Integrated medical knowledge base interface system and method |
| US20140330115A1 (en) * | 2011-07-21 | 2014-11-06 | Carrestream Health, Inc. | System for paranasal sinus and nasal cavity analysis |
| CN109389584A (en) * | 2018-09-17 | 2019-02-26 | 成都信息工程大学 | Multiple dimensioned rhinopharyngeal neoplasm dividing method based on CNN |
| US20190066303A1 (en) * | 2017-08-31 | 2019-02-28 | Council Of Scientific & Industrial Research | Method And System For Automatic Volumetric-Segmentation Of Human Upper Respiratory Tract |
| CN110008971A (en) * | 2018-08-23 | 2019-07-12 | 腾讯科技（深圳）有限公司 | Image processing method, device, computer readable storage medium and computer equipment |
| CN110123249A (en) * | 2019-04-09 | 2019-08-16 | 苏州西能捷科技发展有限公司 | A kind of nasosinusitis detection device and application method |
| CN110335665A (en) * | 2019-04-01 | 2019-10-15 | 佛山原子医疗设备有限公司 | It is a kind of applied to medical image auxiliary diagnosis analysis to scheme to search drawing method and system |
| CN111128328A (en) * | 2019-10-25 | 2020-05-08 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | Nasopharyngeal carcinoma structured image report and data processing system and method |
| CN111863237A (en) * | 2020-05-29 | 2020-10-30 | 东莞理工学院 | Intelligent auxiliary diagnosis system for mobile terminal diseases based on deep learning |
| CN112259220A (en) * | 2020-09-30 | 2021-01-22 | 吾征智能技术(北京)有限公司 | System, device and storage medium for predicting disease based on epistaxis accompanying symptoms |
-
2021
- 2021-04-16 CN CN202110411483.4A patent/CN113034489B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040122704A1 (en) * | 2002-12-18 | 2004-06-24 | Sabol John M. | Integrated medical knowledge base interface system and method |
| US20140330115A1 (en) * | 2011-07-21 | 2014-11-06 | Carrestream Health, Inc. | System for paranasal sinus and nasal cavity analysis |
| US20190066303A1 (en) * | 2017-08-31 | 2019-02-28 | Council Of Scientific & Industrial Research | Method And System For Automatic Volumetric-Segmentation Of Human Upper Respiratory Tract |
| CN110008971A (en) * | 2018-08-23 | 2019-07-12 | 腾讯科技（深圳）有限公司 | Image processing method, device, computer readable storage medium and computer equipment |
| CN109389584A (en) * | 2018-09-17 | 2019-02-26 | 成都信息工程大学 | Multiple dimensioned rhinopharyngeal neoplasm dividing method based on CNN |
| CN110335665A (en) * | 2019-04-01 | 2019-10-15 | 佛山原子医疗设备有限公司 | It is a kind of applied to medical image auxiliary diagnosis analysis to scheme to search drawing method and system |
| CN110123249A (en) * | 2019-04-09 | 2019-08-16 | 苏州西能捷科技发展有限公司 | A kind of nasosinusitis detection device and application method |
| CN111128328A (en) * | 2019-10-25 | 2020-05-08 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | Nasopharyngeal carcinoma structured image report and data processing system and method |
| CN111863237A (en) * | 2020-05-29 | 2020-10-30 | 东莞理工学院 | Intelligent auxiliary diagnosis system for mobile terminal diseases based on deep learning |
| CN112259220A (en) * | 2020-09-30 | 2021-01-22 | 吾征智能技术(北京)有限公司 | System, device and storage medium for predicting disease based on epistaxis accompanying symptoms |
Non-Patent Citations (1)
| Title |
|---|
| 袁欣等: "能谱CT鉴别鼻腔鼻窦良恶性肿物的研究", 《临床放射学杂志》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610831A (en) * | 2021-08-19 | 2021-11-05 | 江西应用技术职业学院 | Wood defect detection method based on computer image technology and transfer learning |
| CN113820321A (en) * | 2021-09-23 | 2021-12-21 | 广州利科科技有限公司 | Road and bridge pavement crack detection system and detection method thereof |
| CN115131343A (en) * | 2022-08-03 | 2022-09-30 | 华中科技大学同济医学院附属同济医院 | Method, device and equipment for parting chronic nasosinusitis and readable storage medium |
| CN115131343B (en) * | 2022-08-03 | 2023-12-26 | 华中科技大学同济医学院附属同济医院 | Method, device and equipment for typing chronic nasosinusitis and readable storage medium |
| CN115502619A (en) * | 2022-09-27 | 2022-12-23 | 江苏省特种设备安全监督检验研究院 | Temperature monitoring system for longitudinal seam welding of pressure vessel cylinder |
| CN116013504A (en) * | 2022-12-29 | 2023-04-25 | 上海市中医医院 | Traditional Chinese medicine tongue diagnosis device based on image retrieval analysis |
| CN117788461A (en) * | 2024-02-23 | 2024-03-29 | 华中科技大学同济医学院附属同济医院 | Magnetic resonance image quality evaluation system based on image analysis |
| CN117788461B (en) * | 2024-02-23 | 2024-05-07 | 华中科技大学同济医学院附属同济医院 | Magnetic resonance image quality evaluation system based on image analysis |
| CN118039088A (en) * | 2024-04-15 | 2024-05-14 | 达州爱迦飞诗特科技有限公司 | Artificial intelligence auxiliary diagnosis data processing system |
| CN118039088B (en) * | 2024-04-15 | 2024-06-07 | 达州爱迦飞诗特科技有限公司 | Artificial intelligence auxiliary diagnosis data processing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113034489B (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113034489B (en) | Artificial intelligence nasal sinus CT image processing system based on degree of deep learning | |
| WO2023077603A1 (en) | Prediction system, method and apparatus for abnormal brain connectivity, and readable storage medium | |
| KR102166010B1 (en) | System and method for determining cognitive impairment using face recognization | |
| CN109272048B (en) | Pattern recognition method based on deep convolutional neural network | |
| CN107247971B (en) | Intelligent analysis method and system for ultrasonic thyroid nodule risk index | |
| CN110491480A (en) | A kind of medical image processing method, device, electromedical equipment and storage medium | |
| CN108597605B (en) | personal health life big data acquisition and analysis system | |
| CN111582342B (en) | Image identification method, device, equipment and readable storage medium | |
| CN201788510U (en) | Dynamic EMR collaborative mining system with particle swarm and extension rough set/concept lattice theories integrated together | |
| CN110517253A (en) | The method of the good pernicious classification of Lung neoplasm based on 3D multiple target feature learning | |
| CN117237351B (en) | Ultrasonic image analysis method and related device | |
| CN113724185B (en) | Model processing method, device and storage medium for image classification | |
| Praveen et al. | Deep learning based intelligent and sustainable smart healthcare application in cloud-centric IoT | |
| CN117316409A (en) | Hospital information management method and system based on big data | |
| Elayaraja et al. | An efficient approach for detection and classification of cancer regions in cervical images using optimization based CNN classification approach | |
| Kuluozturk et al. | DKPNet41: Directed knight pattern network-based cough sound classification model for automatic disease diagnosis | |
| CN109192312B (en) | Intelligent management system and method for adverse events of heart failure patients | |
| CN116469542B (en) | Personalized medical image diagnosis path generation system and method | |
| Sakthivel et al. | Optimal Deep Learning‐Based Vocal Fold Disorder Detection and Classification Model on High‐Speed Video Endoscopy | |
| WO2022252107A1 (en) | Disease examination system and method based on eye image | |
| CN112967246A (en) | X-ray image auxiliary device and method for clinical decision support system | |
| CN113283465A (en) | Diffusion tensor imaging data analysis method and device | |
| Jumaa et al. | Internet of things mathematical approach for detecting brain tumor | |
| Mirarchi et al. | Data mining techniques for vestibular data classification | |
| He et al. | Intestinal polyp recognition based on salient codebook locality-constrained linear coding with annular spatial pyramid matching |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |