CN114512236A - Intelligent auxiliary diagnosis system for Alzheimer's disease - Google Patents
Intelligent auxiliary diagnosis system for Alzheimer's disease Download PDFInfo
- Publication number
- CN114512236A CN114512236A CN202210401505.3A CN202210401505A CN114512236A CN 114512236 A CN114512236 A CN 114512236A CN 202210401505 A CN202210401505 A CN 202210401505A CN 114512236 A CN114512236 A CN 114512236A
- Authority
- CN
- China
- Prior art keywords
- alzheimer
- disease
- neural network
- network model
- softmax
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G06F18/21—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention relates to the technical field of deep learning, and discloses an intelligent auxiliary diagnosis system for Alzheimer's disease, which comprises: the model training module is used for training the Softmax recurrent neural network model by adopting a random gradient descent optimization method based on a training set and a regularized cross entropy loss function to obtain a trained Softmax recurrent neural network model; wherein the regularized cross-entropy loss function comprises a cross-entropy loss term and an L2 norm regularization term; the data acquisition module is used for acquiring the characteristics of the user to be diagnosed; the data preprocessing module is used for preprocessing the characteristics of the user to be diagnosed to obtain formatted characteristics; and the diagnosis module is used for inputting the formatting characteristics of the user to be diagnosed into the trained Softmax recurrent neural network model to obtain the pathological stage of the Alzheimer disease of the user to be diagnosed. Provides accurate and effective reference for the diagnosis result of the doctor and the later treatment of the patient.
Description
Technical Field
The invention relates to the technical field of deep learning, in particular to an intelligent auxiliary diagnosis system for Alzheimer's disease.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
Alzheimer's disease is a nervous system disease which is frequently found in the elderly, and patients suffering from Alzheimer's disease are frequently manifested as dysmnesia and cognitive dysfunction, and may be accompanied by symptoms such as hemiplegia and language ability loss. However, the pathogenic cause of alzheimer's disease has not been accurately determined at present, and no effective treatment means still exists, but the early diagnosis and classification of alzheimer's disease is a problem that has been concerned by the medical community because appropriate intervention treatment for the early stage of alzheimer's disease can effectively delay or even change the occurrence of alzheimer's disease.
The non-physiological accumulation of β -amyloid peptides in extracellular plaques and the accumulation of hyperphosphorylated tau protein in intracellular neurofibrillary tangles (NFTs) constitute the neuropathological features of human brain alzheimer's disease. While reliable detection of these pathological changes has traditionally been limited to post-mortem histopathological examination, current Positron Emission Tomography (PET) and cerebrospinal fluid (CSF) biomarkers have enabled accurate assessment of them in vivo. These biomarkers thus provide clinically relevant information for the detection and differential diagnosis of alzheimer's disease. However, these specialized techniques are limited by relatively high cost, invasiveness, and routine clinical availability, which prevents their widespread use in clinical practice, and the diagnostic procedure increases the workload of the physician.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides an intelligent auxiliary diagnosis system for Alzheimer's disease, which realizes the rapid diagnosis and pathological staging of Alzheimer's disease and provides accurate and effective reference for the diagnosis result of a doctor and the later treatment of a patient.
The invention provides an intelligent auxiliary diagnosis system for Alzheimer's disease;
an intelligent auxiliary diagnosis system for Alzheimer's disease, comprising:
the model training module is used for training the Softmax recurrent neural network model by adopting a random gradient descent optimization method based on a training set and a regularized cross entropy loss function to obtain a trained Softmax recurrent neural network model; wherein the regularized cross-entropy loss function comprises a cross-entropy loss term and an L2 norm regularization term;
the data acquisition module is used for acquiring the characteristics of the user to be diagnosed;
the data preprocessing module is used for preprocessing the characteristics of the user to be diagnosed to obtain formatted characteristics;
and the diagnosis module is used for inputting the formatting characteristics of the user to be diagnosed into the trained Softmax recurrent neural network model to obtain the pathological stage of the Alzheimer disease of the user to be diagnosed.
Further, the number of neurons of the input layer of the Softmax regression neural network model is the number of the features.
Further, the number of neurons in an output layer of the Softmax regression neural network model is the number of categories of the pathological stages.
Further, the training of the Softmax recurrent neural network model specifically includes that all the weights and bias parameters of the Softmax recurrent neural network model are continuously updated according to the set training times and learning rate until the exit condition is met.
Further, the number of weights of the Softmax regression neural network model is the product of the number of features and the number of categories of the pathology stage.
Further, the number of the bias parameters of the Softmax regression neural network model is the number of the categories of the pathological stages.
Further, the exit condition is as follows: the training times reach the set training times; or the learning rate reaches a preset value.
Further, the characteristics of the user to be diagnosed include plasma P-tau181 measurement, gender, age, and weight.
Further, the pathological stages include normal, marked memory decline, early mild cognitive impairment, late mild cognitive impairment and alzheimer's disease.
Further, the L2 norm regularization term is a multiple of the sum of the squares of all the weights of the Softmax regression neural network model.
Compared with the prior art, the invention has the beneficial effects that:
according to the intelligent auxiliary diagnosis system for the Alzheimer's disease, the regularized cross entropy loss function comprises a cross entropy loss term and an L2 norm regularization term, and the L2 norm regularization term can prevent a model from being over-fitted in a training process, so that an optimal model is obtained.
The intelligent auxiliary diagnosis system for the Alzheimer's disease is simple and efficient, has quick response, can realize quick diagnosis and pathological staging of the Alzheimer's disease according to the measured value of the concentration of P-tau181 in plasma and by combining the influence factors such as age, sex, weight and the like, and provides accurate and effective reference for the diagnosis result of a doctor and the later treatment of a patient.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a structural diagram of an intelligent assistant diagnosis system for alzheimer's disease according to a first embodiment of the present invention;
fig. 2 is a structural diagram of a Softmax regression neural network model according to a first embodiment of the present invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
All data are obtained according to the embodiment and are legally applied on the data on the basis of compliance with laws and regulations and user consent.
The embodiment provides an intelligent auxiliary diagnosis system for Alzheimer's disease;
as shown in fig. 1, an intelligent assistant diagnosis system for alzheimer's disease comprises:
and the training set acquisition module is used for constructing a training set. Specifically, a training set acquisition module acquires samples in an Alzheimer's disease neuroimaging planning (ADNI) database, and extracts the characteristics and labels of each sample in the ADNI to obtain a training set; characteristics include plasma P-tau181 measurements, gender, age, and body weight; the label is the pathological stage of each sample in ADNI. The pathological stages included 6 categories of normal, markedly reduced memory, early mild cognitive impairment, late mild cognitive impairment and alzheimer's disease.
The method comprises the following specific steps of extracting the label of each sample in the ADNI: the pathological staging for each sample in ADNI was represented using ordered data, where: normal (NC) is marked as "0", apparent memory decline (SMC) is marked as "1", mild cognitive impairment (EMCI) at early stage is marked as "2", Mild Cognitive Impairment (MCI) is marked as "3", mild cognitive impairment (LMCI) at late stage is marked as "4", and Alzheimer's Disease (AD) is marked as "5".
The specific steps for extracting the features of each sample in ADNI are: using an ordered data representation for the gender feature of each sample in ADNI, where: female labeled "0" and male labeled "1"; p-tau181 measurements, age and body weight for each sample in ADNI were represented using serial data, and plasma P-tau181 outliers were excluded from the samples.
And the model training module is used for training the Softmax recurrent neural network model by adopting a random gradient descent optimization method based on the training set and the regularized cross entropy loss function to obtain the trained Softmax recurrent neural network model. Specifically, according to the set training times and learning rate, all weights and bias parameters of the Softmax recurrent neural network model are continuously updated until the exit condition is met.
As shown in FIG. 2, the Softmax recurrent neural network model uses the pathological stage of Alzheimer's disease as an output label and uses plasma P-tau181 concentration, gender, age and weight as input features. The Softmax recurrent neural network model is a network model which is based on a PyTorch framework and comprises an input layer and an output layer; the number of neurons in the input layer is the number of features (i.e., 4), and the number of neurons in the output layer is the number of classes (i.e., 6) of pathological stages. The Softmax recurrent neural network model adopts a full-connection mode, because the output result of the model is divided into 6 types, the number of the offset parameters is set to be 6, meanwhile, the input layer has 4 neurons, and the weight number after full connection is 24. That is, the number of weights of the Softmax recurrent neural network model is the number of featuresmProduct with the number of categories C of the pathological stage; the number of the bias parameters is the category number of pathological stagesC. Specifically, the method comprises the following steps: the weights are expressed as:
the bias is expressed as:
the model training module is specifically configured to:
acquiring initialization parameters of a Softmax regression neural network model: all weight parametersw ij =0, offsetb i =0, training times epochs =100, learning rate α =0.1, regularization coefficient λ = 0.01;
according to a regularized cross entropy loss function, adopting a random gradient descent optimization method, and according to a learning rate (alpha), performing (a) on all weights of the Softmax regression neural network modelW={w ij }，i=1,…,C，j=1,…,m) And an offset ofb={b i }，i=1,…,C) Updating is carried out; the regularized cross-entropy loss function comprises a cross-entropy loss term and an L2 norm regularization term, wherein the L2 norm regularization term is a multiple of the square sum of all weights of the Softmax regression neural network model, and specifically comprises the following steps:
wherein the content of the first and second substances,Nin order to train the number of samples in the set,
is as followsnThe authenticity of the label of the individual specimen,
is as followsnPrediction labels for the Softmax regression neural network model for individual samples,
in order to regularize the terms for the loss function,
as a weight coefficient of the regularization term,mis the number of features of the sample,Cthe number of categories representing the stage of the pathology,
is composed ofWTo middlejA characteristic ofiThe square of the weighting coefficient of the class pathology stage; by adding an L2 norm regularization term, the Softmax recurrent neural network model is restrained, overfitting of the model in the training process is prevented, and the optimal Softmax recurrent neural network model is obtained;
judging whether an exit condition is reached (the training times epochs reach the set training times 100 or the learning rate alpha reaches a preset value), if so, exiting the training process, and if not, exitingThen, the training times epochs are increased by 1, and the learning rate α = α × 0.95 is updatedepochsAnd continuing to adopt a random gradient descent optimization method according to the regularized cross entropy loss function to carry out model weight (W) And an offset ofb) Updating until the exit condition is satisfied, training is completed, and the loss L of each training is returned (W,b) And accuracy (accuracycacy), selecting a multi-classification neural network model with the highest accuracy as an optimal model, namely a trained Softmax regression neural network model.
The data acquisition module is used for acquiring the characteristics of a user to be diagnosed, and specifically comprises a plasma characteristic acquisition module and a basic characteristic acquisition module, wherein the plasma characteristic acquisition module is connected with a Simoa HD-X (Quanterix) instrument and is used for acquiring a blood sample of the user to be diagnosed, and the Simoa HD-X (Quanterix) instrument is used for detecting the blood sample of the user to be diagnosed to obtain the plasma P-tau concentration of the blood sample and uploading the plasma P-tau concentration to the plasma characteristic acquisition module; the basic feature acquisition module is connected with the input equipment, the age, the sex and the weight of the user to be diagnosed are input through the input equipment, and the input equipment uploads the age, the sex and the weight of the user to be diagnosed to the basic feature acquisition module.
And the data preprocessing module is used for preprocessing the characteristics of the user to be diagnosed to obtain formatted characteristic data. Specifically, the gender characteristics of the user to be diagnosed are represented using ordered data, wherein: female labeled "0" and male labeled "1"; p-tau181 measurements, age and weight of the user to be diagnosed are represented using continuous data.
The diagnosis module is connected with the model training module and used for acquiring a trained Softmax recurrent neural network model; the system is also connected with a data preprocessing module and used for acquiring the formatting characteristics of a user to be diagnosed; and the method is used for inputting the formatting characteristics of the user to be diagnosed into the trained Softmax recurrent neural network model to obtain the pathological stage of the Alzheimer disease of the user to be diagnosed.
And the display module is used for displaying the pathological stage of the Alzheimer disease of the user to be diagnosed.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An intelligent auxiliary diagnosis system for Alzheimer's disease, which is characterized by comprising:
the model training module is used for training the Softmax recurrent neural network model by adopting a random gradient descent optimization method based on a training set and a regularized cross entropy loss function to obtain a trained Softmax recurrent neural network model; wherein the regularized cross-entropy loss function comprises a cross-entropy loss term and an L2 norm regularization term;
the data acquisition module is used for acquiring the characteristics of the user to be diagnosed;
the data preprocessing module is used for preprocessing the characteristics of the user to be diagnosed to obtain formatted characteristics;
and the diagnosis module is used for inputting the formatting characteristics of the user to be diagnosed into the trained Softmax recurrent neural network model to obtain the pathological stage of the Alzheimer disease of the user to be diagnosed.
2. The intelligent aided diagnosis system for Alzheimer's disease of claim 1, wherein the number of neurons in the input layer of the Softmax recurrent neural network model is the number of features.
3. The intelligent aided diagnosis system for Alzheimer's disease of claim 1, wherein the number of neurons in the output layer of the Softmax recurrent neural network model is the number of classes of the pathological stages.
4. The intelligent aided diagnosis system for Alzheimer's disease according to claim 1, wherein the training of the Softmax recurrent neural network model is to continuously update all the weights and bias parameters of the Softmax recurrent neural network model according to the set training times and learning rate until an exit condition is met.
5. The intelligent aided diagnosis system for Alzheimer's disease of claim 4, wherein the number of the weights of the Softmax recurrent neural network model is the product of the number of the features and the number of the categories of the pathological stages.
6. The intelligent aided diagnosis system for Alzheimer's disease as claimed in claim 4, wherein the number of bias parameters of the Softmax recurrent neural network model is the number of categories of the pathological stages.
7. The intelligent aided diagnosis system for Alzheimer's disease as claimed in claim 4, wherein the exit condition is: the training times reach the set training times; or the learning rate reaches a preset value.
8. The intelligent aided diagnosis system for Alzheimer's disease as claimed in claim 1, wherein the characteristics of the user to be diagnosed include plasma P-tau181 measurement, gender, age and weight.
9. The system of claim 1, wherein the pathological stages include normal, significantly decreased memory, early mild cognitive impairment, late mild cognitive impairment and Alzheimer's disease.
10. The intelligent aided diagnosis system for Alzheimer's disease of claim 1, wherein the L2 norm regularization term is a multiple of the sum of the squares of all the weights of the Softmax regression neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210401505.3A CN114512236A (en) | 2022-04-18 | 2022-04-18 | Intelligent auxiliary diagnosis system for Alzheimer's disease |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210401505.3A CN114512236A (en) | 2022-04-18 | 2022-04-18 | Intelligent auxiliary diagnosis system for Alzheimer's disease |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114512236A true CN114512236A (en) | 2022-05-17 |
Family
ID=81555092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210401505.3A Pending CN114512236A (en) | 2022-04-18 | 2022-04-18 | Intelligent auxiliary diagnosis system for Alzheimer's disease |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114512236A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115547484A (en) * | 2022-07-05 | 2022-12-30 | 深圳市镜象科技有限公司 | Method and device for detecting Alzheimer's disease based on voice analysis |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506797A (en) * | 2017-08-25 | 2017-12-22 | 电子科技大学 | One kind is based on deep neural network and multi-modal image alzheimer disease sorting technique |
| CN108921233A (en) * | 2018-07-31 | 2018-11-30 | 武汉大学 | A kind of Raman spectrum data classification method based on autoencoder network |
| 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 |
| CN111292853A (en) * | 2020-01-15 | 2020-06-16 | 长春理工大学 | Cardiovascular disease risk prediction network model based on multiple parameters and construction method thereof |
| CN111466876A (en) * | 2020-03-24 | 2020-07-31 | 山东大学 | Alzheimer's disease auxiliary diagnosis system based on fNIRS and graph neural network |
| US20200303075A1 (en) * | 2019-03-18 | 2020-09-24 | Kundan Krishna | System and a method to predict occurrence of a chronic diseases |
| CN111738363A (en) * | 2020-07-24 | 2020-10-02 | 温州大学 | Alzheimer disease classification method based on improved 3D CNN network |
| WO2021012225A1 (en) * | 2019-07-24 | 2021-01-28 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligence system for medical diagnosis based on machine learning |
| US20210035689A1 (en) * | 2018-04-17 | 2021-02-04 | Bgi Shenzhen | Modeling method and apparatus for diagnosing ophthalmic disease based on artificial intelligence, and storage medium |
| US20210042916A1 (en) * | 2018-02-07 | 2021-02-11 | Ai Technologies Inc. | Deep learning-based diagnosis and referral of diseases and disorders |
| WO2021172864A1 (en) * | 2020-02-27 | 2021-09-02 | 이화여자대학교 산학협력단 | Alzheimer's disease diagnosis and prediction using epigenetic methylation modification of gene |
| CN113392938A (en) * | 2021-07-30 | 2021-09-14 | 广东工业大学 | Classification model training method, Alzheimer disease classification method and device |
| CN113763343A (en) * | 2021-08-31 | 2021-12-07 | 同济大学 | Alzheimer's disease detection method based on deep learning and computer readable medium |
| CN114121266A (en) * | 2021-12-06 | 2022-03-01 | 天津科技大学 | Intelligent auxiliary diagnosis method and system |
-
2022
- 2022-04-18 CN CN202210401505.3A patent/CN114512236A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506797A (en) * | 2017-08-25 | 2017-12-22 | 电子科技大学 | One kind is based on deep neural network and multi-modal image alzheimer disease sorting technique |
| US20210042916A1 (en) * | 2018-02-07 | 2021-02-11 | Ai Technologies Inc. | Deep learning-based diagnosis and referral of diseases and disorders |
| US20210035689A1 (en) * | 2018-04-17 | 2021-02-04 | Bgi Shenzhen | Modeling method and apparatus for diagnosing ophthalmic disease based on artificial intelligence, and storage medium |
| CN108921233A (en) * | 2018-07-31 | 2018-11-30 | 武汉大学 | A kind of Raman spectrum data classification method based on autoencoder network |
| US20200303075A1 (en) * | 2019-03-18 | 2020-09-24 | Kundan Krishna | System and a method to predict occurrence of a chronic diseases |
| 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 |
| WO2021012225A1 (en) * | 2019-07-24 | 2021-01-28 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligence system for medical diagnosis based on machine learning |
| CN111292853A (en) * | 2020-01-15 | 2020-06-16 | 长春理工大学 | Cardiovascular disease risk prediction network model based on multiple parameters and construction method thereof |
| WO2021172864A1 (en) * | 2020-02-27 | 2021-09-02 | 이화여자대학교 산학협력단 | Alzheimer's disease diagnosis and prediction using epigenetic methylation modification of gene |
| CN111466876A (en) * | 2020-03-24 | 2020-07-31 | 山东大学 | Alzheimer's disease auxiliary diagnosis system based on fNIRS and graph neural network |
| CN111738363A (en) * | 2020-07-24 | 2020-10-02 | 温州大学 | Alzheimer disease classification method based on improved 3D CNN network |
| CN113392938A (en) * | 2021-07-30 | 2021-09-14 | 广东工业大学 | Classification model training method, Alzheimer disease classification method and device |
| CN113763343A (en) * | 2021-08-31 | 2021-12-07 | 同济大学 | Alzheimer's disease detection method based on deep learning and computer readable medium |
| CN114121266A (en) * | 2021-12-06 | 2022-03-01 | 天津科技大学 | Intelligent auxiliary diagnosis method and system |
Non-Patent Citations (10)
| Title |
|---|
| LONG HAO 等: "Classification of Cardiovascular Disease via A New SoftMax Model", 《2018 40TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)》 * |
| SHAHINDA MOHAMED MOSTAFA ELKHOLY 等: "Early Prediction of Chronic Kidney Disease Using Deep Belief Network", 《IEEE ACCESS 》 * |
| 刘倩玉等: "基于HTML的早期阿尔兹海默症智能辅助诊断平台开发", 《电子技术与软件工程》 * |
| 刘树春 等: "《深度实践OCR 基于深度学习的文字识别》", 31 May 2020 * |
| 刘磊 等: "《高校核心实验课程丛书 化学生物学实验》", 31 August 2015 * |
| 徐克虎 等: "《智能计算方法及其应用》", 31 July 2019 * |
| 李雪斌 等: "《 "十三五"规划教材 神经病学 第2版》", 31 August 2018 * |
| 林伟铭等: "基于极限学习机的阿尔兹海默病辅助诊断", 《中国生物医学工程学报》 * |
| 郁松 等: "基于3D-ResNet的阿尔兹海默症分类算法研究_郁松", 《计算机工程与科学》 * |
| 陈云霁等: "《神经网络与深度学习》", 30 April 2020 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115547484A (en) * | 2022-07-05 | 2022-12-30 | 深圳市镜象科技有限公司 | Method and device for detecting Alzheimer's disease based on voice analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Oh et al. | Identifying schizophrenia using structural MRI with a deep learning algorithm | |
| CN109447183B (en) | Prediction model training method, device, equipment and medium | |
| US10898125B2 (en) | Deep learning architecture for cognitive examination subscore trajectory prediction in Alzheimer's disease | |
| Bron et al. | Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: the CADDementia challenge | |
| Guo et al. | Resting state fMRI and improved deep learning algorithm for earlier detection of Alzheimer’s disease | |
| Becker et al. | Gaussian process uncertainty in age estimation as a measure of brain abnormality | |
| Mofrad et al. | A predictive framework based on brain volume trajectories enabling early detection of Alzheimer's disease | |
| Arafa et al. | Early detection of Alzheimer’s disease based on the state-of-the-art deep learning approach: a comprehensive survey | |
| CN114999629A (en) | AD early prediction method, system and device based on multi-feature fusion | |
| Al-Adhaileh | Diagnosis and classification of Alzheimer's disease by using a convolution neural network algorithm | |
| Vural et al. | Retinal degeneration is associated with brain volume reduction and prognosis in radiologically isolated syndrome | |
| Nabizadeh et al. | Artificial intelligence in the diagnosis of multiple sclerosis: A systematic review | |
| Ghafoori et al. | Predicting conversion from MCI to AD by integration of rs-fMRI and clinical information using 3D-convolutional neural network | |
| CN114512236A (en) | Intelligent auxiliary diagnosis system for Alzheimer's disease | |
| Narayanan et al. | Leveraging machine learning methods for multiple disease prediction using Python ML libraries and flask API | |
| US11712192B2 (en) | Biomarker for early detection of alzheimer disease | |
| Schoemaker et al. | The hippocampal-to-ventricle ratio (HVR): Presentation of a manual segmentation protocol and preliminary evidence | |
| CN112233805A (en) | Mining method for biomarkers based on multi-map neuroimaging data | |
| WO2023216293A1 (en) | System and method for predicting dementia or mild cognitive disorder | |
| CN115424067A (en) | System, method, processor and storage medium for realizing classification processing of depression subtypes based on multiple fusion brain network diagram technology | |
| Nisha et al. | SGD-DABiLSTM based MRI Segmentation for Alzheimer’s disease Detection | |
| Mikhalskii et al. | Application of data analysis methods in research of neurodegenerative diseases | |
| Kolte et al. | Early Alzheimer’s Detection Using Random Forest Algorithm | |
| Subasi et al. | Alzheimer’s disease detection using artificial intelligence | |
| Abi Nader et al. | SimulAD: a dynamical model for personalized simulation and disease staging in Alzheimer’s disease |
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 |