CN106066934A - A kind of Alzheimer based on Spark platform assistant diagnosis system in early days - Google Patents
A kind of Alzheimer based on Spark platform assistant diagnosis system in early days Download PDFInfo
- Publication number
- CN106066934A CN106066934A CN201610363245.XA CN201610363245A CN106066934A CN 106066934 A CN106066934 A CN 106066934A CN 201610363245 A CN201610363245 A CN 201610363245A CN 106066934 A CN106066934 A CN 106066934A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- image
- smri
- diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of Alzheimer based on Spark platform assistant diagnosis system in early days, belong to the big market demand field of medical treatment.This system includes image store module, Yunnan snub-nosed monkey module, model training module, it was predicted that diagnostic module.On cluster, set up original sMRI image database by image store module, use HDFS distributed storage;By Yunnan snub-nosed monkey module to raw video pretreatment, obtain valid data and be sent to model training module;Model training module calls the machine learning algorithm of MLlib, and valid data are carried out dimensionality reduction classification, obtains optimal classification model;Last predictive diagnosis module processes the sMRI image of experimenter in real time by Spark Streaming, disaggregated model classify it, provide diagnostic result.Big data technique is combined by the present invention with sMRI technology, and on the basis of processing massive image data, the automatical and efficient sMRI image data to experimenter makes objective diagnosis, provides auxiliary to support for diagnosis Alzheimer, has actual application value.
Description
Technical field
The present invention relates to the big market demand field of medical treatment, particularly relate to a kind of Alzheimer based on Spark platform
Assistant diagnosis system in early days.
Background technology
Alzheimer (Alzheimer ' s Disease, AD) is commonly called senile dementia, show as language,
The cognitive competence such as memory, judgment decline, and belong to nerve gradually moving back property disease, are typically common in old people.Due to Alzheimer
Disease there is no method and thoroughly cures, thus diagnosis AD pathological changes in time, thus carry out early intervention treatment, alleviate pathological changes most important.At present
The method of early diagnosis of AD mainly includes four kinds: early clinic symptom judges, Five neuropsychological tests, and neurobiology detects,
Neuroimaging checks.The wherein nuclear magnetic resonance in neuroimaging (structural magnetic resonance
Imaging, sMRI) technology can the structure three-dimensional image of objective record difference cerebral tissue, measure brain atrophy change, and then reflection
AD lesion degree.Owing to sMRI technology does not has any harm, safely, effectively for human brain, thus it is widely used in AD pathological changes
Auxiliary diagnosis in early days.
But traditional hand dipping sMRI method is the longest, workload is heavy and it needs to user possesses certain elder generation
Testing knowledge, specialty requires higher, is easily affected by subjective factors;And along with improvement and the development of economic level of medical condition,
Normal person and the sMRI image data explosive growth of AD patient's cerebral tissue, using value the hugest in mass data,
But clinic also cannot effectively utilize these data at present;Therefore automatic, objective by big data processing technique and machine learning method,
The efficient sMRI image that processes, statistical analysis, thus provide auxiliary to support for diagnosis AD early lesion, there is important research meaning
Justice.
The big data of Spark being born in University of California Berkeley AMPLab process and Computational frame, with it based on interior
Deposit computing, be suitable for the advantage of machine learning iterative computation, become the handling implement of the biggest data fields main flow, with Spark be
The Berkeley data analysis software stack of core, includes Spark Streaming, the application module such as SQL, MLlib, Graphx,
Can apply to various big data scene.Based on Spark platform, set up the Alzheimer for magnanimity sMRI image data
Assistant diagnosis system in early days, it is possible to excavate the potential value in big data, improves diagnosis efficiency.
Summary of the invention
Deficiency for traditional sMRI manual measurement method of AD auxiliary diagnosis cannot be effective with magnanimity sMIR image data
The problem processed, the present invention proposes a kind of Alzheimer based on Spark platform assistant diagnosis system in early days.The present invention will
The big data processing platform (DPP) of Spark combines with the sMRI technology in medical system, it is achieved a kind of Alzheimer auxiliary in early days
Diagnostic system, this system, on the basis of processing magnanimity sMRI image data, extracts the brain of normal person and AD patient in various degree
The valid data feature of tissue sMRI image, uses distributed sorting algorithm that the data characteristics extracted is carried out classification learning, instruction
Practice optimal classification model, and then the image of unknown experimenter is carried out classification judgement, diagnose this experimenter according to classification results
Whether it is AD patient, provides a kind of automatical and efficient objective aided diagnosis technique support for doctor.
For achieving the above object, the present invention proposes following technical scheme:
A kind of Alzheimer based on Spark platform assistant diagnosis system in early days, this system includes image store mould
Block, Yunnan snub-nosed monkey module, model training module and predictive diagnosis module, it is characterised in that:
Described image store module is for setting up the sMRI Image Database of original normal person and AD patient's cerebral tissue, in a distributed manner
The big data of file system stored images;
Described Yunnan snub-nosed monkey module, for sMRI image is carried out pretreatment, extracts feature from image data, it is thus achieved that
Valid data, are saved in HDFS accumulation layer, carry out data analysis for subsequent module;
Described model training module is used for training optimal classification model, by using distributed sorting algorithm to extraction
Valid data carry out classification based training, arrange algorithm different parameters and obtain optimal classification model, it is possible to distinguish normal person and suffer from AD
The image data of person;
Described predictive diagnosis module carries out, to the image of unknown experimenter, judgement of classifying in real time, examines according to classification results
Whether disconnected experimenter is AD patient;
Described system builds on Spark cluster, batch processing is processed with stream and tie mutually on the big data platform of Spark
Close, mass data is carried out computing, use distributed machines learning algorithm to sMRI image data Treatment Analysis, it is achieved foundation
The function of sMRI diagnostic imaging AD pathological changes.
Especially, image store module utilizes Hadoop distributed file system HDFS to enter the sMRI image data of magnanimity
Row storage, disposes HDFS system in the cluster.
Especially, Yunnan snub-nosed monkey module utilizes Thunder that sMRI image data is carried out pretreatment, obtains effective
Characteristic, transfers three-dimensional data to one-dimensional data, for subsequent module for processing.
Especially, model training module utilizes principal component analysis PCA algorithm to Data Dimensionality Reduction, utilizes distributed support vector
Data are trained thus obtain disaggregated model by machine SVM algorithm, and image data is divided into normal and AD two class, sick for diagnosis AD
Become and foundation is provided.
Especially, it was predicted that diagnostic module utilizes Spark Streaming to carry out data stream type process, processes tested in real time
The sMRI image data of person, and immediately provide diagnostic result.
Beneficial effects of the present invention:
1. system constructing is in Spark distributed treatment Computational frame, is applied in medical applications by big data platform, it is possible to
Efficiently process massive image data, solve conventional art and cannot process the drawback of the big data of medical treatment;
2. use HDFS distributed storage scheme, store increasing image data, safe and efficient;
3. high amount of traffic is processed and combines with batch processing by system, by the study of existing image data is set up classification mould
Type, and the sMRI image data of new experimenter can be processed in real time, provide diagnostic result in real time;
4. utilize distributed machine learning algorithm that sMRI image data carries out excavating study, effectively analyze normal person with
Feature between the sMRI image of AD patient's cerebral tissue, sets up disaggregated model automatically, makes objective diagnosis result, compensate for craft
Measure, the deficiency of subjective judgment.
Accompanying drawing explanation
Fig. 1 is the overall architecture of present invention Alzheimer based on Spark platform assistant diagnosis system in early days;
Fig. 2 is the overall flow of present invention Alzheimer based on Spark platform assistant diagnosis system in early days.
Detailed description of the invention
In order to more clearly describe the technology contents of the present invention, with embodiment the present invention made below in conjunction with the accompanying drawings into
One step explanation.
A kind of based on Spark platform the Alzheimer of present invention assistant diagnosis system in early days, by the data of Spark
Disposal ability combines, on the big data platform of Spark, with magnanimity with the sMRI diagnostic imaging AD pathological changes technology utilizing cerebral tissue
Based on sMRI image data, utilize machine learning algorithm construct normal person and patient's AD cerebral tissue sMRI image data point
Class model, makes classification with the optimal classification model of training to the sMRI image of experimenter, makes diagnosis according to classification results,
Whether there is AD pathological changes for diagnosis experimenter and Objective support is provided.
Fig. 1 gives the overall architecture of system of the present invention, and whole system is divided into five layers: hardware layer, HDFS accumulation layer,
Spark distributed treatment layer, Spark component layer, assistant diagnosis system application layer.Each layer concrete function is:
(1) hardware layer is positioned at the system architecture bottom, predominantly system provides underlying hardware facility, including building Spark
Computer equipment (work station, server) needed for cluster and the network equipment (router, switch), and it is used for gathering tested
The image modalities of the sMRI of person's cerebral tissue;
(2) HDFS accumulation layer uses HDFS distributed file storage system, is responsible for the cerebral tissue sMRI of storage management magnanimity
Image data, including normal person and the brain sMRI image of AD patient of different age group, and to having after Yunnan snub-nosed monkey
Effect data;
(3) Spark distributed treatment layer is the core data process layer of system, performs the application program generation that user writes
Code, relies on the distributed data processing ability of Spark cluster that data are carried out concrete calculation process, and returns computing for user
Result;
(4) Spark component layer mainly includes Spark Streaming and MLlib, and MLlib provides for upper level applications
Concrete algorithm interface, is called by upper level applications, arranges algorithm parameter, more mutual with Spark cluster, transfers to cluster to hold
Row operation, Spark Streaming provides real-time data stream type to process, for real-time diagnosis for system;
(5) assistant diagnosis system application layer is the specific code that user writes according to system requirements, each including system
Implementing of module, mainly includes image store module, Yunnan snub-nosed monkey module, model training module and predictive diagnosis mould
Block.
A kind of Alzheimer based on Spark platform of the present invention assistant diagnosis system main flow in early days is such as
Shown in Fig. 2.Concretely comprise the following steps:
(1) sMRI image database is set up;Integrate the sMRI image of the cerebral tissue of existing normal person and AD patient, by it
Storage is to HDFS accumulation layer, and utilizes image modalities constantly to obtain new image, and is stored.
(2) Yunnan snub-nosed monkey;Utilize Thunder instrument, read sMRI image from HDFS accumulation layer, three-dimensional matrice is one-dimensional
Change, and utilize specific feature extracting method to obtain valid data, then valid data are saved in HDFS accumulation layer.
(3) model training;Utilize distributed SVM algorithm on the basis of training valid data, build optimal classification model,
It is specifically described as:
A. load valid data, load, from HDFS layer, effective image data that pretreatment obtains;
Valid data are changed into the distributed matrix form that MLlib supports, obtain training data by b. format conversion;
C. dimension-reduction treatment, owing to the dimension of valid data is excessive, utilizes PCA algorithm that data are carried out principal component analysis, reaches
To dimensionality reduction purpose;
D. tag, whether belong to AD patient according to the image that data are taken from, for data plus label, the data of normal person
Being designated as 0, the data of AD patient are designated as 1;
E. divide data set, data are divided into training set, checking collection and test set.
F. disaggregated model training, uses distributed SVM algorithm to carry out the training of disaggregated model in training set, by setting
The different parameters putting algorithm obtains different disaggregated models, calculates the evaluation index of different disaggregated model on checking collection, according to
Best evaluation index determines optimal classification model, and the classifying quality of test optimal classification model on test set, will be optimal
Disaggregated model preserves.
(4) predictive diagnosis, utilizes Spark Streaming to process the sMRI image of cerebral tissue of experimenter in real time, and leads to
Cross optimal classification model and data made classification judgement, return diagnostic result in real time, be specifically described as:
A. obtain experimenter's cerebral tissue sMRI image, image modalities experimenter is detected, obtain its brain group
The sMRI image knitted, and by Spark Streaming, this image is sent to diagnostic system in real time;
B. to sMRI Yunnan snub-nosed monkey, according to step (2), the image of experimenter is carried out pretreatment, it is thus achieved that characteristic;
C. classify, call optimal classification model and the image data of experimenter is made classification;
D. diagnose, make diagnosis according to classification results, and in real time diagnostic result is returned to doctor, provide auxiliary for doctor
Hold.
Claims (5)
1. Alzheimer based on a Spark platform in early days assistant diagnosis system, this system include image store module,
Yunnan snub-nosed monkey module, model training module and predictive diagnosis module, it is characterised in that:
Described image store module is for setting up the sMRI Image Database of original normal person and AD patient's cerebral tissue, file in a distributed manner
The big data of system stored images;
Described Yunnan snub-nosed monkey module, for sMRI image is carried out pretreatment, extracts feature, it is thus achieved that effectively from image data
Data, are saved in HDFS accumulation layer, carry out data analysis for subsequent module;
Described model training module is used for training optimal classification model, by using distributed sorting algorithm effective to extract
Data carry out classification based training, arrange algorithm different parameters and obtain optimal classification model, it is possible to distinguish normal person and AD patient's
Image data;
Described predictive diagnosis module carries out, to the image of unknown experimenter, judgement of classifying in real time, is subject to according to classification results diagnosis
Whether examination person is AD patient;
Described system builds on Spark cluster, batch processing is processed with stream and combine on the big data platform of Spark, right
Mass data carries out computing, uses distributed machines learning algorithm to sMRI image data Treatment Analysis, it is achieved according to sMRI shadow
Function as diagnosis AD pathological changes.
Alzheimer based on Spark platform the most according to claim 1 assistant diagnosis system in early days, its feature exists
In: image store module utilizes Hadoop distributed file system HDFS to store the sMRI image data of magnanimity, at collection
HDFS system is disposed in Qun.
Alzheimer based on Spark platform the most according to claim 1 assistant diagnosis system in early days, its feature exists
In: Yunnan snub-nosed monkey module utilizes Thunder that sMRI image data is carried out pretreatment, obtains effective characteristic, will
Three-dimensional data transfers one-dimensional data to, for subsequent module for processing.
Alzheimer based on Spark platform the most according to claim 1 assistant diagnosis system in early days, its feature exists
In: model training module utilizes principal component analysis PCA algorithm to Data Dimensionality Reduction, utilizes distributed support vector machines algorithm pair
Data are trained thus obtain disaggregated model, and image data is divided into normal and AD two class, provide foundation for diagnosis AD pathological changes.
Alzheimer based on Spark platform the most according to claim 1 assistant diagnosis system in early days, its feature exists
In: predictive diagnosis module utilizes Spark Streaming to carry out data stream type process, processes the sMRI image of tester in real time
Data, and immediately provide diagnostic result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610363245.XA CN106066934A (en) | 2016-05-27 | 2016-05-27 | A kind of Alzheimer based on Spark platform assistant diagnosis system in early days |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610363245.XA CN106066934A (en) | 2016-05-27 | 2016-05-27 | A kind of Alzheimer based on Spark platform assistant diagnosis system in early days |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106066934A true CN106066934A (en) | 2016-11-02 |
Family
ID=57420358
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610363245.XA Pending CN106066934A (en) | 2016-05-27 | 2016-05-27 | A kind of Alzheimer based on Spark platform assistant diagnosis system in early days |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106066934A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106599549A (en) * | 2016-11-25 | 2017-04-26 | 上海联影医疗科技有限公司 | Computer-aided diagnosis system and method, and medical system |
CN107590806A (en) * | 2017-09-19 | 2018-01-16 | 陈烨 | A kind of detection method and system based on brain medical imaging |
CN108717875A (en) * | 2018-05-18 | 2018-10-30 | 贵州大学 | A kind of chronic disease intelligent management system based on big data |
WO2019042200A1 (en) * | 2017-08-30 | 2019-03-07 | 第四范式(北京)技术有限公司 | Distributed system for executing machine learning and method therefor |
CN109581867A (en) * | 2017-09-29 | 2019-04-05 | 罗克韦尔自动化技术公司 | For monitoring, diagnosing the classification model construction of optimization and control |
CN109657803A (en) * | 2018-03-23 | 2019-04-19 | 新华三大数据技术有限公司 | The building of machine learning model |
CN110059124A (en) * | 2019-04-22 | 2019-07-26 | 上海飞未信息技术有限公司 | A kind of quickly extensive image data distributed pipeline processing method and system |
CN110908994A (en) * | 2018-09-14 | 2020-03-24 | 北京京东金融科技控股有限公司 | Data model processing method, system, electronic device and readable medium |
CN111009321A (en) * | 2019-08-14 | 2020-04-14 | 电子科技大学 | Application method of machine learning classification model in juvenile autism auxiliary diagnosis |
WO2023161830A1 (en) * | 2022-02-23 | 2023-08-31 | Chernobelsky Ivgenia | Distributed electronic ledger storage including reduced images |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345633A (en) * | 2013-06-27 | 2013-10-09 | 山东大学 | Structural nuclear magnetic resonance image processing method used for Alzheimer disease early detection |
US8873836B1 (en) * | 2012-06-29 | 2014-10-28 | Emc Corporation | Cluster-based classification of high-resolution data |
CN104679895A (en) * | 2015-03-18 | 2015-06-03 | 成都影泰科技有限公司 | Medical image data storing method |
CN104881568A (en) * | 2015-04-27 | 2015-09-02 | 苏州敏宇医疗科技有限公司 | Cloud computation based early oncotherapy efficacy evaluation system and method |
CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
-
2016
- 2016-05-27 CN CN201610363245.XA patent/CN106066934A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8873836B1 (en) * | 2012-06-29 | 2014-10-28 | Emc Corporation | Cluster-based classification of high-resolution data |
CN103345633A (en) * | 2013-06-27 | 2013-10-09 | 山东大学 | Structural nuclear magnetic resonance image processing method used for Alzheimer disease early detection |
CN104679895A (en) * | 2015-03-18 | 2015-06-03 | 成都影泰科技有限公司 | Medical image data storing method |
CN104881568A (en) * | 2015-04-27 | 2015-09-02 | 苏州敏宇医疗科技有限公司 | Cloud computation based early oncotherapy efficacy evaluation system and method |
CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
Non-Patent Citations (3)
Title |
---|
吴辉群 等;: "《医学影像大数据的存储与挖掘技术研究》", 《中国数字医学》 * |
赵小杰 等;: "《阿尔茨海默氏症研究中的磁共振成像数据分析》", 《软件学报》 * |
闫瑾: "《多类型磁共振影像特征融合算法用于阿尔兹海默病早期诊断》", 《万方学位论文库》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106599549A (en) * | 2016-11-25 | 2017-04-26 | 上海联影医疗科技有限公司 | Computer-aided diagnosis system and method, and medical system |
WO2019042200A1 (en) * | 2017-08-30 | 2019-03-07 | 第四范式(北京)技术有限公司 | Distributed system for executing machine learning and method therefor |
CN107590806A (en) * | 2017-09-19 | 2018-01-16 | 陈烨 | A kind of detection method and system based on brain medical imaging |
CN107590806B (en) * | 2017-09-19 | 2021-06-01 | 陈烨 | Detection method and system based on brain medical imaging |
CN109581867A (en) * | 2017-09-29 | 2019-04-05 | 罗克韦尔自动化技术公司 | For monitoring, diagnosing the classification model construction of optimization and control |
CN109657803A (en) * | 2018-03-23 | 2019-04-19 | 新华三大数据技术有限公司 | The building of machine learning model |
CN109657803B (en) * | 2018-03-23 | 2020-04-03 | 新华三大数据技术有限公司 | Construction of machine learning models |
CN108717875A (en) * | 2018-05-18 | 2018-10-30 | 贵州大学 | A kind of chronic disease intelligent management system based on big data |
CN110908994A (en) * | 2018-09-14 | 2020-03-24 | 北京京东金融科技控股有限公司 | Data model processing method, system, electronic device and readable medium |
CN110059124A (en) * | 2019-04-22 | 2019-07-26 | 上海飞未信息技术有限公司 | A kind of quickly extensive image data distributed pipeline processing method and system |
CN111009321A (en) * | 2019-08-14 | 2020-04-14 | 电子科技大学 | Application method of machine learning classification model in juvenile autism auxiliary diagnosis |
WO2023161830A1 (en) * | 2022-02-23 | 2023-08-31 | Chernobelsky Ivgenia | Distributed electronic ledger storage including reduced images |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106066934A (en) | A kind of Alzheimer based on Spark platform assistant diagnosis system in early days | |
ALEnezi | A method of skin disease detection using image processing and machine learning | |
WO2020151536A1 (en) | Brain image segmentation method, apparatus, network device and storage medium | |
Giovannucci et al. | CaImAn an open source tool for scalable calcium imaging data analysis | |
CN109447183B (en) | Prediction model training method, device, equipment and medium | |
Esmaeilzadeh et al. | End-to-end Parkinson disease diagnosis using brain MR-images by 3D-CNN | |
CN109447998B (en) | Automatic segmentation method based on PCANet deep learning model | |
Zhang et al. | Automated semantic segmentation of red blood cells for sickle cell disease | |
CN113808738B (en) | Disease identification system based on self-identification image | |
CN104361318A (en) | Disease diagnosis auxiliary system and disease diagnosis auxiliary method both based on diffusion tensor imaging technology | |
CN110910377B (en) | Cerebral infarction MRI image identification method based on neural network | |
CN110859624A (en) | Brain age deep learning prediction system based on structural magnetic resonance image | |
CN112348785B (en) | Epileptic focus positioning method and system | |
CN113688862B (en) | Brain image classification method based on semi-supervised federal learning and terminal equipment | |
Alqudah et al. | Lightweight Deep Learning for Malaria Parasite Detection Using Cell-Image of Blood Smear Images. | |
CN116110597B (en) | Digital twinning-based intelligent analysis method and device for patient disease categories | |
Feng et al. | A review of methods for classification and recognition of ASD using fMRI data | |
Waweru et al. | Deep learning in skin lesion analysis towards cancer detection | |
Chatchaiwatkul et al. | Lung disease detection and classification with deep learning approach | |
CN117352164A (en) | Multi-mode tumor detection and diagnosis platform based on artificial intelligence and processing method thereof | |
WO2023198224A1 (en) | Method for constructing magnetic resonance image preliminary screening model for mental disorders | |
Mirchandani et al. | Comparing the Architecture and Performance of AlexNet Faster R-CNN and YOLOv4 in the Multiclass Classification of Alzheimer Brain MRI Scans | |
Goenka et al. | Patch-based classification for Alzheimer disease using sMRI | |
Thomas et al. | Diabetic retinopathy detection using EADBSC and improved dilated ensemble CNN-based classification | |
Cárdenas et al. | Ecg arrhythmia classification for comparing pre-trained deep learning models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161102 |