CN114822823A - Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data - Google Patents

Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data Download PDF

Info

Publication number
CN114822823A
CN114822823A CN202210506871.5A CN202210506871A CN114822823A CN 114822823 A CN114822823 A CN 114822823A CN 202210506871 A CN202210506871 A CN 202210506871A CN 114822823 A CN114822823 A CN 114822823A
Authority
CN
China
Prior art keywords
firefly
medical
medical data
tumor
data
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
Application number
CN202210506871.5A
Other languages
Chinese (zh)
Other versions
CN114822823B (en
Inventor
李婷
李益非
罗学敏
樊心敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yunnan Shengyue Information Technology Co ltd
Original Assignee
Yunnan Shengyue Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yunnan Shengyue Information Technology Co ltd filed Critical Yunnan Shengyue Information Technology Co ltd
Priority to CN202211657024.5A priority Critical patent/CN115810130A/en
Priority to CN202210506871.5A priority patent/CN114822823B/en
Publication of CN114822823A publication Critical patent/CN114822823A/en
Application granted granted Critical
Publication of CN114822823B publication Critical patent/CN114822823B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Epidemiology (AREA)
  • Software Systems (AREA)
  • Primary Health Care (AREA)
  • Pathology (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The tumor fine classification system based on cloud computing and artificial intelligence and fusing multi-dimensional medical data comprises a medical data collection module, a medical data management module, a tumor diagnosis model updating module and an intelligent tumor classification module, wherein a tumor diagnosis model corresponding to each tumor disease type is constructed through medical data with tumor disease diagnosis labels collected by the medical data collection module, so that efficient and accurate diagnosis of each tumor disease type is realized, and the system has great significance for diagnosis and early screening of tumor diseases.

Description

Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data
Technical Field
The invention relates to the field of medical big data, in particular to a tumor fine classification system fusing multi-dimensional medical data based on cloud computing and artificial intelligence.
Background
Cancer is a major threat to human health, and early cancer screening and diagnosis are well-established effective methods for reducing cancer mortality. However, the relative scarcity of ever-worsening cancer situation and professionals is a sharp pair of contradictions faced in current cancer situations. With the rapid development of medical technology, the variety and quantity of medical data are continuously enriched and increased, and the continuous accumulation of medical data such as image data, clinical data and the like related to tumors provides powerful materials for intelligent screening and diagnosis of tumors. The image data is most common in a plurality of medical data, the format is standard and easy to obtain, and meanwhile, the image plays a key role in the diagnosis process of the tumor, including early diagnosis, curative effect monitoring and prognosis evaluation, which are not distinguishable from the medical image. The high-dimensional image features of the medical image are acquired by extracting the image features of the medical image, and the high-dimensional image features and the clinical data are combined with each other, so that a doctor is helped to analyze the high-dimensional image features and the clinical data more comprehensively and accurately by means of a computer-aided technology, and the method is particularly important in the aspects of clinical diagnosis and treatment. The support vector machine is an important algorithm in machine learning, and the parameter optimization problem becomes a key problem for using the support vector machine because the better performance of the support vector machine can obtain a better classification result when being applied to tumor classification, but the performance of the support vector machine is easily influenced by the parameters of the support vector machine.
Disclosure of Invention
In order to solve the problems, the invention aims to provide a tumor fine classification system based on cloud computing and artificial intelligence and fusing multi-dimensional medical data.
The purpose of the invention is realized by the following technical scheme:
the tumor fine classification system based on cloud computing and artificial intelligence and fusing multi-dimensional medical data comprises a medical data collection module, a medical data management module, a tumor diagnosis model updating module and an intelligent tumor classification module;
the medical data collection module is used for collecting medical data with tumor disease diagnosis labels and inputting the collected medical data into the medical data management module;
the medical data management module comprises a medical data pre-storing unit and a medical data updating and detecting unit, the medical data pre-storing unit divides medical data of the same tumor disease type into one type according to a tumor disease diagnosis label carried by the medical data for storage, the medical data updating and detecting unit is used for detecting the medical data corresponding to each tumor disease type stored in the medical data pre-storing unit, and when the total quantity of the medical data corresponding to one tumor disease type reaches a given updating threshold value, the medical data pre-storing unit inputs the medical data corresponding to the tumor disease type into the tumor diagnosis model updating module;
the tumor diagnosis model updating module comprises a medical data processing unit, a medical database corresponding to each tumor disease type and a tumor diagnosis model updating unit, wherein the medical data processing unit is used for processing the received medical data, the processed medical data is used as medical sample data, the medical sample data is input into the corresponding medical database according to the corresponding tumor disease diagnosis label, the medical database stores the received new medical sample data, and randomly selects the medical sample data with the same quantity as the newly received medical sample data from the previously stored medical sample data and discards the medical sample data so as to realize the updating of the medical sample data in the medical database, the tumor diagnosis model updating unit is used for detecting the corresponding medical database in real time, and when the medical sample data updating exists in the corresponding medical database, calling medical sample data in the corresponding medical database to reconstruct a tumor diagnosis model corresponding to the tumor disease type;
the intelligent tumor classification module is used for processing medical data of a patient to be diagnosed, performing similar detection on the processed medical data of the patient to be diagnosed and medical sample data stored in a medical database corresponding to each tumor disease type, selecting the tumor disease type corresponding to the medical database most similar to the medical data of the patient to be diagnosed as the tumor disease detection type of the patient to be diagnosed, inputting the medical data of the patient to be diagnosed into a tumor diagnosis model corresponding to the tumor disease type, and the output value of the tumor diagnosis model is the tumor disease diagnosis result of the patient.
Further, the medical data includes medical images and clinical medical data of the patient.
Further, the medical data processing unit is used for processing the received medical data and comprises a medical image processing part and a medical data processing part, the medical image processing part is used for carrying out object segmentation and feature extraction on the received medical image so as to construct an image feature vector corresponding to the medical image, and the medical data processing part is used for processing the received clinical medical data and removing noise data in the clinical medical data.
Furthermore, the tumor diagnosis model updating unit calls medical sample data in a corresponding medical database to train and test the support vector machine, the medical sample data is used as an input value of the support vector machine, and a tumor disease diagnosis label corresponding to the medical sample data is used as an output value of the support vector machine, so that the tumor diagnosis model corresponding to each tumor disease type is obtained.
Further, when the tumor diagnosis model updating unit trains the support vector machine through the called medical sample data, the punishment factor and the kernel function parameter of the support vector machine are determined by adopting a firefly algorithm, in the process of optimizing the punishment factor and the kernel function parameter of the support vector machine by adopting the firefly algorithm, each firefly adopts a roulette rule to select to move towards an individual with higher fluorescence brightness than the firefly, the moving distance of each firefly is determined according to attraction, on the basis, the firefly i is selected to move towards the firefly j, and finally the (t +1) th iterative updating is realized, and the specific position updating formula is as follows:
Figure BDA0003637718180000031
in the above formula, x i (t +1) denotes the position of firefly i after the (t +1) th iteration update, x i (t) indicates the position of firefly i after the updating of the t-th iteration, x j (t) represents the position of firefly j after the updating of the t-th iteration, β ij (t) denotes the attraction of firefly j to firefly i after the t-th iteration update, α ij (t) represents the random term coefficients of the firefly i moving randomly towards the firefly j after the t-th iteration updating, rand is a random coefficient subject to positive distribution, and rand belongs to [0,1 ]]。
Further, the attraction degree beta of the firefly j to the firefly i after the t iteration is updated ij The value of (t) is set to:
Figure BDA0003637718180000032
in the above-mentioned formula, the compound of formula,
Figure BDA0003637718180000033
represents the original attraction of firefly j to firefly i after the t-th iteration update, and
Figure BDA0003637718180000034
the values of (A) are:
Figure BDA0003637718180000035
wherein, beta 0 When r is 0, the attraction of firefly, that is, the maximum attraction, γ is an optical absorption coefficient, and represents a characteristic that firefly gradually weakens with increasing distance, and r is ij (t) is the Cartesian distance, rho, between firefly i and firefly j after the tth iterative update ij (t) is a historical adjustment coefficient of the attraction of firefly j to firefly i after the tth iteration update, and ρ is ij The value of (t) is:
Figure BDA0003637718180000036
μ (t) represents an iterative correction coefficient, and
Figure BDA0003637718180000037
wherein, T max Is the maximum number of iterations, k ij (t) represents the statistical coefficient of the history of the region between firefly i and firefly j after the t-th iteration update, k ij The value of (t) is:
Figure BDA0003637718180000038
wherein omega ij (t) denotes the position x i (t) is the center, with r ij (t) is a spherical region of radius, x j (τ) is the location of firefly j after the τ -th iteration update, f (x) j (τ),Ω ij (t)) is for position x j (τ) and region Ω ij (t) a region between (t) and
Figure BDA0003637718180000039
m represents the number of fireflies in the population, and t represents the current iteration number.
Further, the random term coefficient alpha of the firefly i moving to the firefly j randomly after the t-th iteration updating ij The value of (t) is set to:
representing a set consisting of the fireflies which are selected as the moving direction when each firefly in the population is subjected to the (t +1) th iteration updating as K (t), and only keeping one of the repeated fireflies when the repeated fireflies exist in the set K (t) as the moving direction, and defining theta K (t) represents a moving direction attribute value of firefly in the set K (t), and θ K The value of (t) is:
Figure BDA0003637718180000041
in the above formula, M K (t) indicates the number of fireflies in the set K (t), M indicates the number of fireflies in the population, y K (t) represents the dominance of the spatial distribution of fireflies in set K (t), and y K The value of (t) is:
Figure BDA0003637718180000042
wherein the fireflies in the set K (t) are increased from high to high according to the absolute fluorescence brightness valueLow rank ordered component sequence L K (t), then x' l (t) represents the sequence L K (t) location of the l firefly in the t iteration updated, x' l+1 (t) represents the sequence L K (t) the position of the (l +1) th firefly in (t) after the updating of the t-th iteration, k is a given positive integer, and k is<M K (t)，x l,a (t) is distance position x 'in the population after the t iteration update' l (t) the position of the firefly at the a-th place,
Figure BDA0003637718180000043
is a sequence L K (t) the spatial distribution of the first firefly in (t) is compared with the function, and
Figure BDA0003637718180000044
when theta is K The value of (t) satisfies: theta K (t)>When 1, then the random term coefficient alpha ij The value of (t) is:
Figure BDA0003637718180000045
when theta is K The value of (t) satisfies: theta K When (t) is less than or equal to 1, the random term coefficient alpha is ij The value of (t) is:
Figure BDA0003637718180000046
in the above formula, α 0 Is given an initial random coefficient value, and alpha 0 ∈[0,1]，ω j (t) local spatial coefficients of firefly j in set K (t) after the t-th iteration update, ω j The value of (t) is:
Figure BDA0003637718180000047
x j (t) indicates the position of firefly j after the t-th iteration update, δ j (t) represents the global optimization coefficient, δ, of firefly j in the set K (t) after the t-th iteration update j The value of (t) is:
Figure BDA0003637718180000048
wherein,
Figure BDA0003637718180000049
shows firefly j in sequence L after the t-th iterative update K (ii) the ordering in (t),
Figure BDA00036377181800000410
represents the sequence L K (t) A
Figure BDA00036377181800000411
The position of each firefly after the t iteration update.
The beneficial effects created by the invention are as follows: the high-dimensional image characteristics of the medical image are obtained by extracting the image characteristics of the medical image, and the tumor diagnosis model corresponding to each tumor disease type is constructed by combining clinical data, so that the high-efficiency and accurate diagnosis of each tumor disease type is realized, and the method has great significance for the diagnosis and early screening of the tumor diseases; the firefly algorithm is applied to the optimization of the parameters of the support vector machine, and the inherent defects of the firefly algorithm are improved, so that the classification precision of the support vector machine can be effectively improved through the parameters determined by the improved firefly algorithm.
Drawings
The invention is further described with the aid of the accompanying drawings, in which, however, the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a schematic diagram of the present invention.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the tumor fine classification system based on cloud computing and artificial intelligence and fusing multidimensional medical data of the embodiment includes a medical data collection module, a medical data management module, a tumor diagnosis model updating module and an intelligent tumor classification module;
the medical data collection module is used for collecting medical data with tumor disease diagnosis labels and inputting the collected medical data into the medical data management module;
the medical data management module comprises a medical data pre-storing unit and a medical data updating and detecting unit, the medical data pre-storing unit divides medical data of the same tumor disease type into one type according to a tumor disease diagnosis label carried by the medical data for storage, the medical data updating and detecting unit is used for detecting the medical data corresponding to each tumor disease type stored in the medical data pre-storing unit, and when the total quantity of the medical data corresponding to one tumor disease type reaches a given updating threshold value, the medical data pre-storing unit inputs the medical data corresponding to the tumor disease type into the tumor diagnosis model updating module;
the tumor diagnosis model updating module comprises a medical data processing unit, a medical database corresponding to each tumor disease type and a tumor diagnosis model updating unit, wherein the medical data processing unit is used for processing the received medical data, the processed medical data is used as medical sample data, the medical sample data is input into the corresponding medical database according to the corresponding tumor disease diagnosis label, the medical database stores the received new medical sample data, and randomly selects the medical sample data with the same quantity as the newly received medical sample data from the previously stored medical sample data and discards the medical sample data so as to realize the updating of the medical sample data in the medical database, the tumor diagnosis model updating unit is used for detecting the corresponding medical database in real time, and when the medical sample data updating exists in the corresponding medical database, calling medical sample data in the corresponding medical database to reconstruct a tumor diagnosis model corresponding to the tumor disease type;
the intelligent tumor classification module is used for processing medical data of a patient to be diagnosed, performing similar detection on the processed medical data of the patient to be diagnosed and medical sample data stored in a medical database corresponding to each tumor disease type, selecting the tumor disease type corresponding to the medical database most similar to the medical data of the patient to be diagnosed as the tumor disease detection type of the patient to be diagnosed, inputting the medical data of the patient to be diagnosed into a tumor diagnosis model corresponding to the tumor disease type, and the output value of the tumor diagnosis model is the tumor disease diagnosis result of the patient.
Preferably, the medical data comprises medical images and clinical medical data of the patient.
Preferably, the medical data processing unit is configured to process the received medical data, and includes a medical image processing part and a medical data processing part, the medical image processing part is configured to perform object segmentation and feature extraction on the received medical image to construct an image feature vector corresponding to the medical image, and the medical data processing part is configured to process the received clinical medical data to remove noise data in the clinical medical data.
The embodiment extracts the image features of the medical image to obtain the high-dimensional image features of the medical image, and constructs the tumor diagnosis model corresponding to each tumor disease type by combining clinical data, thereby realizing efficient and accurate diagnosis of each tumor disease type, and having great significance for diagnosis and early screening of tumor diseases.
Preferably, the tumor diagnosis model updating unit calls medical sample data in a corresponding medical database to train and test the support vector machine, the medical sample data is used as an input value of the support vector machine, and the tumor disease diagnosis label corresponding to the medical sample data is used as an output value of the support vector machine, so as to obtain the tumor diagnosis model corresponding to each tumor disease type.
In the embodiment, the firefly algorithm is applied to the optimization of the parameters of the support vector machine, and the inherent defects of the firefly algorithm are improved, so that the classification accuracy of the support vector machine can be effectively improved through the parameters determined by the improved firefly algorithm.
Preferably, when the tumor diagnosis model updating unit trains the support vector machine through the called medical sample data, the punishment factor and the kernel function parameter of the support vector machine are determined by adopting a firefly algorithm, in the process of optimizing the punishment factor and the kernel function parameter of the support vector machine by adopting the firefly algorithm, each firefly adopts a roulette rule to select to move towards an individual with higher fluorescence brightness than the firefly, the moving distance of each firefly is determined according to attraction, on the basis, the firefly i is selected to move towards the firefly j, and finally the (t +1) th iterative updating is realized, and the specific position updating formula is as follows:
Figure BDA0003637718180000061
in the above formula, x i (t +1) denotes the position of firefly i after the (t +1) th iteration update, x i (t) indicates the position of firefly i after the updating of the t-th iteration, x j (t) represents the position of firefly j after the updating of the t-th iteration, β ij (t) denotes the attraction of firefly j to firefly i after the t-th iteration update, α ij (t) represents the random term coefficients of the firefly i moving randomly towards the firefly j after the t-th iteration updating, rand is a random coefficient subject to positive distribution, and rand belongs to [0,1 ]]。
Preferably, the attraction degree beta of the firefly j to the firefly i after the t iteration is updated ij The value of (t) is set to:
Figure BDA0003637718180000071
in the above-mentioned formula, the compound of formula,
Figure BDA0003637718180000072
represents the original attraction of firefly j to firefly i after the t-th iteration update, and
Figure BDA0003637718180000073
the values of (A) are:
Figure BDA0003637718180000074
wherein, beta 0 When r is 0, the attraction degree of firefly, that is, the maximum attraction degree, γ is a light absorption coefficient, and represents a characteristic that firefly gradually decreases with increasing distance, and r is ij (t) is the Cartesian distance, rho, between firefly i and firefly j after the tth iterative update ij (t) is a historical adjustment coefficient of the attraction of firefly j to firefly i after the tth iteration update, and ρ is ij The value of (t) is:
Figure BDA0003637718180000075
μ (t) represents an iterative correction coefficient, and
Figure BDA0003637718180000076
wherein, T max Is the maximum number of iterations, k ij (t) represents the statistical coefficient of the history of the region between firefly i and firefly j after the t-th iteration update, k ij The value of (t) is:
Figure BDA0003637718180000077
wherein omega ij (t) denotes the position x i (t) is the center, with r ij (t) is a spherical region of radius, x j (τ) is the location of firefly j after the τ -th iteration update, f (x) j (τ),Ω ij (t)) is for position x j (τ) and region Ω ij (t) a region between (t) and
Figure BDA0003637718180000078
m represents the number of fireflies in the population, and t represents the current iteration number.
Specifically, in the firefly algorithm, the absolute fluorescence brightness value of the firefly is higher, the solution represented by the firefly is better, the firefly moves towards an individual with higher fluorescence brightness than the firefly, and the firefly is finally gathered around the optimal firefly position through the movement of each generation of firefly, so that the optimal extreme point is found, and the purpose of population optimization is achieved. The moving distance of the firefly is directly related to the convergence rate and the optimization precision of the firefly, in the traditional firefly algorithm, the moving distance of the firefly is determined by the attraction degree between the fireflies, the attraction degree is inversely proportional to the distance between the fireflies, namely the attraction degree is reduced along with the increase of the distance, however, in the actual optimization process, the moving distance of the firefly is determined only by the distance, so that the algorithm lacks self-adaptation, in order to better balance the convergence rate and the optimization precision of the algorithm by adjusting the moving distance of the firefly, the embodiment introduces a historical adjustment coefficient, the historical adjustment coefficient is used for counting the average number of times that the firefly performs optimization on an area formed between the firefly and the optimal firefly selected by the firefly as the moving direction in the historical iteration process, when the area is searched by more fireflies in the historical iteration process, reduce this preferred firefly's attraction degree through historical adjustment coefficient to reduce this preferred firefly region too much repeated search, increase the regional chance of being searched for of other preferred fireflies, thereby increase the variety that the algorithm was solved, on the contrary, when this region was searched for by less firefly in history iterative process, increase this firefly's attraction degree through historical adjustment coefficient, make the firefly excavate this region, improve the local excavation precision of algorithm. Namely, the historical adjustment coefficient is set, so that the movement distance of the firefly can obtain better convergence rate and optimization accuracy when the position is updated according to the actual optimization condition.
Preferably, the random term coefficient α of the firefly i moving randomly toward the firefly j after the t-th iteration update ij The value of (t) is set to:
representing a set consisting of the fireflies which are selected as the moving direction when each firefly in the population is subjected to the (t +1) th iteration updating as K (t), and only keeping one of the repeated fireflies when the repeated fireflies exist in the set K (t) as the moving direction, and defining theta K (t) represents a moving direction attribute value of firefly in the set K (t), and θ K The value of (t) is:
Figure BDA0003637718180000081
in the above formula, M k (t) represents the number of fireflies in the set K (t), M represents the number of fireflies in the population, y K (t) represents the dominance value of the spatial distribution of fireflies in the set K (t), and y K The value of (t) is:
Figure BDA0003637718180000082
wherein the fireflies in the set K (t) are sequenced from high to low according to the absolute fluorescence brightness value to form a sequence L K (t), then x' l (t) represents the sequence L K (t) location of the l firefly in the t iteration updated, x' l+1 (t) represents the sequence L K (t) the position of the (l +1) th firefly in (t) after the updating of the t-th iteration, k is a given positive integer, and k is<M k The value of (t), k may be 10, x l,a (t) is distance position x 'in the population after the t iteration update' l (t) the position of the firefly at the a-th place,
Figure BDA0003637718180000083
is a sequence L K (t) the spatial distribution of the first firefly in (t) is compared with the function, and
Figure BDA0003637718180000084
when theta is K The value of (t) satisfies: theta K (t)>1, then the random term coefficient alpha ij The value of (t) is:
Figure BDA0003637718180000085
when theta is K The value of (t) satisfies: theta K When (t) is less than or equal to 1, the random term coefficient alpha is ij The value of (t) is:
Figure BDA0003637718180000086
in the above formula, α 0 Is given an initial random coefficient value, and alpha 0 ∈[0,1]，ω j (t) represents the local spatial coefficients, ω, of firefly j in the set K (t) after the t-th iteration update j The value of (t) is:
Figure BDA0003637718180000091
x j (t) indicates the position of firefly j after the t-th iteration update, δ j (t) represents the global optimization coefficient, δ, of firefly j in the set K (t) after the t-th iteration update j The value of (t) is:
Figure BDA0003637718180000092
wherein,
Figure BDA0003637718180000093
shows firefly j in sequence L after the t-th iteration update K (ii) the ordering in (t),
Figure BDA0003637718180000094
represents the sequence L K (t) A
Figure BDA0003637718180000095
The location of the individual fireflies after the t-th iteration of updating.
Specifically, in the firefly algorithm, each firefly is selected to move towards an individual with higher fluorescence brightness than the firefly by using the roulette rule, so the firefly selected by using the roulette rule as the moving direction is only related to the current absolute fluorescence brightness of the firefly, and the preferred firefly selected as the moving direction plays a role in guiding the optimizing direction of the population in the optimizing process, so when the selected preferred firefly is too slice-shaped on the basis of the current optimizing, iterative optimizing of the firefly in the population cannot be completely led, the population is easily subjected to the condition of local optimization, therefore, the algorithm is prevented from being subjected to the condition of local optimization by using the random term when the position of the firefly is updated in the population improvement, and the selection of the random term coefficient in the random term is directly related to the disturbance range of the random term, therefore, the random item coefficient in the firefly algorithm is improved, so that the random item is prevented from falling into local optimum, and the searching precision of the algorithm is improved. When the random item coefficient of each firefly in the group during position updating is set, firstly, the better firefly which is currently selected by the group and is taken as the moving direction is detected through the defined moving direction attribute value, when the number of the different better fireflies which are selected by the group and are taken as the moving direction is more, and the distribution among the better fireflies is more dispersed on the basis of current optimization, the better fireflies which is currently selected by the group and is taken as the moving direction can lead the group to carry out more comprehensive optimization, at the moment, the smaller random item coefficient is set, so that the random item in the position updating formula has the function of strengthening the area searching precision of the group, and when the number of the different better fireflies which are selected by the group and are taken as the moving direction is less, or the better fireflies are distributed on the basis of current optimization, the larger random item coefficient is set, and expanding the disturbance range of the random term, so that the random term in the position updating formula has the function of helping the firefly to jump out of the local optimum. The value of the random item coefficient is set according to the actual condition of the firefly selected as the moving direction, so that the search precision of the population is enhanced and the population is helped to jump out of local optimum through the random item coefficient, and the classification precision of the support vector machine can be effectively improved through the parameters determined by the firefly algorithm.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (7)

1. The tumor fine classification system based on cloud computing and artificial intelligence and fusing multi-dimensional medical data is characterized by comprising a medical data collection module, a medical data management module, a tumor diagnosis model updating module and an intelligent tumor classification module;
the medical data collection module is used for collecting medical data with tumor disease diagnosis labels and inputting the collected medical data into the medical data management module;
the medical data management module comprises a medical data pre-storing unit and a medical data updating and detecting unit, the medical data pre-storing unit divides medical data of the same tumor disease type into one type according to a tumor disease diagnosis label carried by the medical data for storage, the medical data updating and detecting unit is used for detecting the medical data corresponding to each tumor disease type stored in the medical data pre-storing unit, and when the total quantity of the medical data corresponding to one tumor disease type reaches a given updating threshold value, the medical data pre-storing unit inputs the medical data corresponding to the tumor disease type into the tumor diagnosis model updating module;
the tumor diagnosis model updating module comprises a medical data processing unit, a medical database corresponding to each tumor disease type and a tumor diagnosis model updating unit, wherein the medical data processing unit is used for processing the received medical data, the processed medical data is used as medical sample data, the medical sample data is input into the corresponding medical database according to the corresponding tumor disease diagnosis label, the medical database stores the received new medical sample data, and randomly selects the medical sample data with the same quantity as the newly received medical sample data from the previously stored medical sample data and discards the medical sample data so as to realize the updating of the medical sample data in the medical database, the tumor diagnosis model updating unit is used for detecting the corresponding medical database in real time, and when the medical sample data updating exists in the corresponding medical database, calling medical sample data in the corresponding medical database to reconstruct a tumor diagnosis model corresponding to the tumor disease type;
the intelligent tumor classification module is used for processing medical data of a patient to be diagnosed, performing similar detection on the processed medical data of the patient to be diagnosed and medical sample data stored in a medical database corresponding to each tumor disease type, selecting the tumor disease type corresponding to the medical database most similar to the medical data of the patient to be diagnosed as the tumor disease detection type of the patient to be diagnosed, inputting the medical data of the patient to be diagnosed into a tumor diagnosis model corresponding to the tumor disease type, and the output value of the tumor diagnosis model is the tumor disease diagnosis result of the patient.
2. The cloud computing and artificial intelligence based tumor fine classification system fusing multi-dimensional medical data according to claim 1, characterized in that the medical data comprises medical images and clinical medical data of patients.
3. The system for tumor fine classification based on fusion of cloud computing and artificial intelligence according to claim 2, wherein the medical data processing unit is configured to process the received medical data and comprises a medical image processing part and a medical data processing part, the medical image processing part is configured to perform object segmentation and feature extraction on the received medical image so as to construct an image feature vector corresponding to the medical image, and the medical data processing part is configured to process the received clinical medical data so as to remove noise data in the clinical medical data.
4. The system for finely classifying tumors based on cloud computing and artificial intelligence fusion with multi-dimensional medical data according to claim 1, wherein the tumor diagnosis model updating unit retrieves medical sample data in a corresponding medical database thereof as input values of the support vector machine to train and test the support vector machine, and the tumor disease diagnosis label corresponding to the medical sample data is used as an output value of the support vector machine, so as to obtain the tumor diagnosis model corresponding to each tumor disease type.
5. The cloud computing and artificial intelligence based tumor fine classification system cabinet fusing multi-dimensional medical data according to claim 4, wherein when the tumor diagnosis model updating unit trains the support vector machine through the called medical sample data, the penalty factor and the kernel function parameter of the support vector machine are determined by using the firefly algorithm, during the process of optimizing the penalty factor and the kernel function parameter of the support vector machine by using the firefly algorithm, each firefly uses the roulette rule to select to move towards an individual with higher fluorescence intensity than self, and determines the moving distance of each firefly according to the attraction, on the basis, the firefly i is set to select to move towards the firefly j, and finally the (t +1) th iterative update is realized, and the specific position updating formula is as follows:
Figure FDA0003637718170000021
in the above formula, x i (t +1) denotes the position of firefly i after the (t +1) th iteration update, x i (t) indicates the position of firefly i after the updating of the t-th iteration, x j (t) represents the position of firefly j after the updating of the t-th iteration, β ij (t) denotes the attraction of firefly j to firefly i after the t-th iteration update, α ij (t) represents the random term coefficients of the firefly i moving randomly towards the firefly j after the t-th iteration updating, rand is a random coefficient subject to positive distribution, and rand belongs to [0,1 ]]。
6. The cloud computing and artificial intelligence based tumor fine classification system fusing multi-dimensional medical data according to claim 5, characterized in that the attraction degree β of firefly j to firefly i after the t-th iteration update ij The value of (t) is set to:
Figure FDA0003637718170000022
in the above-mentioned formula, the compound of formula,
Figure FDA0003637718170000023
represents the original of firefly j to firefly i after the t-th iterative updateDegree of attraction, and
Figure FDA0003637718170000024
the values of (A) are:
Figure FDA0003637718170000025
wherein, beta 0 When r is 0, the attraction degree of firefly, that is, the maximum attraction degree, γ is a light absorption coefficient, and represents a characteristic that firefly gradually decreases with increasing distance, and r is ij (t) is the Cartesian distance, rho, between firefly i and firefly j after the tth iterative update ij (t) is a historical adjustment coefficient of the attraction of firefly j to firefly i after the tth iteration update, and ρ is ij The value of (t) is:
Figure FDA0003637718170000026
μ (t) represents an iterative correction coefficient, and
Figure FDA0003637718170000027
wherein, T max Is the maximum number of iterations, k ij (t) represents the statistical coefficient of the history of the region between firefly i and firefly j after the t-th iteration update, k ij The value of (t) is:
Figure FDA0003637718170000031
wherein omega ij (t) denotes the position x i (t) is the center, with r ij (t) is a spherical region of radius, x j (τ) is the location of firefly j after the τ -th iteration update, f (x) j (τ)，Ω ij (t)) is for position x j (τ) and region Ω ij (t) a region between (t) and
Figure FDA0003637718170000032
m represents the number of fireflies in the population, and t represents the current iteration number.
7. The cloud-based computing and artificial intelligence of claim 5The tumor fine classification system fusing the multi-dimensional medical data is characterized in that the random term coefficient alpha of the firefly i moving randomly towards the firefly j after the t-th iteration update ij The value of (t) is set to:
representing a set consisting of the fireflies which are selected as the moving direction when each firefly in the population is subjected to the (t +1) th iteration updating as K (t), and only keeping one of the repeated fireflies when the repeated fireflies exist in the set K (t) as the moving direction, and defining theta K (t) represents a moving direction attribute value of firefly in the set K (t), and θ K The value of (t) is:
Figure FDA0003637718170000033
in the above formula, M K (t) indicates the number of fireflies in the set K (t), M indicates the number of fireflies in the population, y K (t) represents the dominance value of the spatial distribution of fireflies in the set K (t), and y K The value of (t) is:
Figure FDA0003637718170000034
wherein the fireflies in the set K (t) are sequenced from high to low according to the absolute fluorescence brightness value to form a sequence L K (t), then x' l (t) represents the sequence L K (t) location of the l firefly in the t iteration updated, x' l+1 (t) represents the sequence L K (t) the position of the (l +1) th firefly in (t) after the updating of the t-th iteration, k is a given positive integer, and k < M K (t)，x l，a (t) is distance position x 'in the population after the t iteration update' l (t) the position of the firefly at a-th place,
Figure FDA0003637718170000035
is a sequence L K (t) the spatial distribution of the first firefly in (t) is compared with the function, and
Figure FDA0003637718170000036
when theta is K The value of (t) satisfies: theta K When (t) > 1, the random term coefficient alpha ij The value of (t) is:
Figure FDA0003637718170000041
when theta is K The value of (t) satisfies: theta K When t is less than or equal to 1, the random term coefficient alpha ij The value of (t) is:
Figure FDA0003637718170000042
in the above formula, α 0 Is given an initial random coefficient value, and alpha 0 ∈[0，1]，ω j (t) represents the local spatial coefficients, ω, of firefly j in the set K (t) after the t-th iteration update j The value of (t) is:
Figure FDA0003637718170000043
x j (t) denotes firefly j Position after the t-th iteration update, δ j (t) represents the global optimization coefficient, δ, of firefly j in the set K (t) after the t-th iteration update j The value of (t) is:
Figure FDA0003637718170000044
wherein,
Figure FDA0003637718170000045
shows firefly j in sequence L after the t-th iterative update K (ii) the ordering in (t),
Figure FDA0003637718170000046
represents the sequence L K (t) A
Figure FDA0003637718170000047
One fireflyLocation of the worm after the t-th iteration update.
CN202210506871.5A 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data Active CN114822823B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202211657024.5A CN115810130A (en) 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data and application
CN202210506871.5A CN114822823B (en) 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210506871.5A CN114822823B (en) 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CN202211657024.5A Division CN115810130A (en) 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data and application

Publications (2)

Publication Number Publication Date
CN114822823A true CN114822823A (en) 2022-07-29
CN114822823B CN114822823B (en) 2022-11-29

Family

ID=82513893

Family Applications (2)

Application Number Title Priority Date Filing Date
CN202211657024.5A Pending CN115810130A (en) 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data and application
CN202210506871.5A Active CN114822823B (en) 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN202211657024.5A Pending CN115810130A (en) 2022-05-11 2022-05-11 Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data and application

Country Status (1)

Country Link
CN (2) CN115810130A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582370A (en) * 2020-05-08 2020-08-25 重庆工贸职业技术学院 Brain metastasis tumor prognostic index reduction and classification method based on rough set optimization
CN115584313A (en) * 2022-12-09 2023-01-10 云南升玥信息技术有限公司 Detection kit for detecting infectious agent sample

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107192951A (en) * 2017-07-31 2017-09-22 湖南科技大学 A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current
WO2017173428A1 (en) * 2016-04-01 2017-10-05 20/20 Genesystems Inc. Methods and compositions for aiding in distinguishing between benign and maligannt radiographically apparent pulmonry nodules
CN107330238A (en) * 2016-08-12 2017-11-07 中国科学院上海技术物理研究所 Medical information collection, processing, storage and display methods and device
CN108828436A (en) * 2018-06-27 2018-11-16 桂林电子科技大学 Analog-circuit fault diagnosis method based on the adaptive glowworm swarm algorithm of chaos cloud
CN109102884A (en) * 2018-07-19 2018-12-28 南京邮电大学 Parkinson disease diagnostic method based on mixed kernel function supporting vector machine model
CN110084316A (en) * 2019-05-06 2019-08-02 安徽工业大学 A kind of method for diagnosing faults based on the multiple dimensioned arrangement entropy and glowworm swarm algorithm Support Vector Machines Optimized of fine time shift
CN110299202A (en) * 2019-07-01 2019-10-01 泰康保险集团股份有限公司 Intelligent methods for the diagnosis of diseases, device, equipment and storage medium
CN110363277A (en) * 2019-07-15 2019-10-22 南京工业大学 Power transformer fault diagnosis method and system based on improved firefly algorithm optimized probabilistic neural network
CN110909158A (en) * 2019-07-05 2020-03-24 重庆信科设计有限公司 Text classification method based on improved firefly algorithm and K nearest neighbor
US10614318B1 (en) * 2019-10-25 2020-04-07 7-Eleven, Inc. Sensor mapping to a global coordinate system using a marker grid
AU2020101065A4 (en) * 2020-06-19 2020-07-23 Hubei University Of Technology Method for scheduling UAVs based on chaotic adaptive firefly algorithm
CN112345253A (en) * 2020-11-20 2021-02-09 昆明理工大学 Rolling bearing fault diagnosis method based on IFA-SVM

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017173428A1 (en) * 2016-04-01 2017-10-05 20/20 Genesystems Inc. Methods and compositions for aiding in distinguishing between benign and maligannt radiographically apparent pulmonry nodules
CN107330238A (en) * 2016-08-12 2017-11-07 中国科学院上海技术物理研究所 Medical information collection, processing, storage and display methods and device
CN107192951A (en) * 2017-07-31 2017-09-22 湖南科技大学 A kind of micro- method for diagnosing faults of wind-driven generator three-phase rotor current
CN108828436A (en) * 2018-06-27 2018-11-16 桂林电子科技大学 Analog-circuit fault diagnosis method based on the adaptive glowworm swarm algorithm of chaos cloud
CN109102884A (en) * 2018-07-19 2018-12-28 南京邮电大学 Parkinson disease diagnostic method based on mixed kernel function supporting vector machine model
CN110084316A (en) * 2019-05-06 2019-08-02 安徽工业大学 A kind of method for diagnosing faults based on the multiple dimensioned arrangement entropy and glowworm swarm algorithm Support Vector Machines Optimized of fine time shift
CN110299202A (en) * 2019-07-01 2019-10-01 泰康保险集团股份有限公司 Intelligent methods for the diagnosis of diseases, device, equipment and storage medium
CN110909158A (en) * 2019-07-05 2020-03-24 重庆信科设计有限公司 Text classification method based on improved firefly algorithm and K nearest neighbor
CN110363277A (en) * 2019-07-15 2019-10-22 南京工业大学 Power transformer fault diagnosis method and system based on improved firefly algorithm optimized probabilistic neural network
US10614318B1 (en) * 2019-10-25 2020-04-07 7-Eleven, Inc. Sensor mapping to a global coordinate system using a marker grid
AU2020101065A4 (en) * 2020-06-19 2020-07-23 Hubei University Of Technology Method for scheduling UAVs based on chaotic adaptive firefly algorithm
CN112345253A (en) * 2020-11-20 2021-02-09 昆明理工大学 Rolling bearing fault diagnosis method based on IFA-SVM

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘慧等: "基于改进萤火虫算法的高光谱遥感多特征优化方法", 《遥感技术与应用》 *
徐令仪等: "基于磁共振图像与波谱的专家辅助诊断系统的设计", 《中国生物医学工程学报》 *
徐浩等: "云萤火虫算法改进二维Tsallis熵的医学图像分割", 《电子技术应用》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582370A (en) * 2020-05-08 2020-08-25 重庆工贸职业技术学院 Brain metastasis tumor prognostic index reduction and classification method based on rough set optimization
CN111582370B (en) * 2020-05-08 2023-04-07 重庆工贸职业技术学院 Brain metastasis tumor prognostic index reduction and classification method based on rough set optimization
CN115584313A (en) * 2022-12-09 2023-01-10 云南升玥信息技术有限公司 Detection kit for detecting infectious agent sample

Also Published As

Publication number Publication date
CN115810130A (en) 2023-03-17
CN114822823B (en) 2022-11-29

Similar Documents

Publication Publication Date Title
Abd Elaziz et al. An improved marine predators algorithm with fuzzy entropy for multi-level thresholding: real world example of COVID-19 CT image segmentation
CN107563381B (en) Multi-feature fusion target detection method based on full convolution network
CN110680326B (en) Pneumoconiosis identification and grading judgment method based on deep convolutional neural network
CN106778687B (en) Fixation point detection method based on local evaluation and global optimization
CN114822823B (en) Tumor fine classification system based on cloud computing and artificial intelligence fusion multi-dimensional medical data
Jain et al. Lung nodule segmentation using salp shuffled shepherd optimization algorithm-based generative adversarial network
CN111524140B (en) Medical image semantic segmentation method based on CNN and random forest method
CN105139430A (en) Medical image clustering method based on entropy
CN111110192A (en) Skin abnormal symptom auxiliary diagnosis system
Liu et al. Flooding-based MobileNet to identify cucumber diseases from leaf images in natural scenes
CN112183237A (en) Automatic white blood cell classification method based on color space adaptive threshold segmentation
Rajendran et al. An improved pre-processing technique with image mining approach for the medical image classification
Jamazi et al. Mutated Aquila Optimizer for assisting brain tumor segmentation
Mahadevan et al. Automatic recognition of Rice Plant leaf diseases detection using deep neural network with improved threshold neural network
Zhou et al. Automatic segmentation of lung noudles using improved U-Net NetWork
Vidyarthi et al. Brain tumor segmentation approaches: Review, analysis and anticipated solutions in machine learning
Oguntoye et al. Predicting COVID-19 From Chest X-Ray Images using Optimized Convolution Neural Network
CN116824141A (en) Livestock image instance segmentation method and device based on deep learning
CN114155251B (en) Full brain three-dimensional anatomical structure segmentation method of context-aware convolutional neural network
CN116433679A (en) Inner ear labyrinth multi-level labeling pseudo tag generation and segmentation method based on spatial position structure priori
Karthikeyan et al. Machine Learning based Algorithmic approach for Detection and Classification of Leukemia
Lydia et al. An automatic lung nodule detection and classification using an optimized convolutional neural network and enhanced k-means clustering
CN111401519B (en) Deep neural network unsupervised learning method based on similarity distance in object and between objects
Lakshmana et al. Hybrid kernel fuzzy C-means clustering segmentation algorithm for content based medical image retrieval application
Himaja et al. Leukemia Cancer Detection in Microscopic Blood Samples using Optimized Convolutional Neural Network

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
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: A Fine Classification System for Tumors Based on Cloud Computing and Artificial Intelligence Fusion of Multidimensional Medical Data

Granted publication date: 20221129

Pledgee: Hua Xia Bank Co.,Ltd. Kunming Branch

Pledgor: Yunnan Shengyue Information Technology Co.,Ltd.

Registration number: Y2024980005240

PE01 Entry into force of the registration of the contract for pledge of patent right
PC01 Cancellation of the registration of the contract for pledge of patent right

Granted publication date: 20221129

Pledgee: Hua Xia Bank Co.,Ltd. Kunming Branch

Pledgor: Yunnan Shengyue Information Technology Co.,Ltd.

Registration number: Y2024980005240

PC01 Cancellation of the registration of the contract for pledge of patent right