深度学习在阿尔茨海默病疾病转化预测影像学研究中的应用价值

doi:10.3969/j.issn.1006-5725.2025.09.021

Abstract

Abstract:

Alzheimer's disease （AD）， a neurodegenerative disorder， manifests pathological changes in the brain even during the asymptomatic stage. As the pathological burden intensifies， patients experience functional decline in multiple cognitive domains， including memory， language， spatial perception， executive function， and calculation， and may also exhibit emotional abnormalities. Once AD progresses， treatment becomes extremely challenging. Therefore， early diagnosis and accurate prediction of disease conversion are core tasks in the prevention and treatment of AD， and they are also urgent scientific research challenges to be overcome. Deep learning （DL） models demonstrate considerable advantages in the diagnosis， prediction， classification， and feature extraction of AD， offering new hope for solving this challenging problem. This research commences with a concise introduction to the outcomes of AD and the fundamental knowledge of deep learning. Subsequently， it offers an overview of the imaging studies on the utilization of deep learning for predicting disease transformation from two perspectives. Firstly， it systematically summarizes the existing DL models that have demonstrated innovation in the classification and prediction performance of AD. Secondly， it provides a comprehensive outline of the DL fusion models applied to the diagnosis， classification， and prediction of AD. Finally， this paper expounds upon the impending challenges in the research of this domain. This article demonstrates that deep learning models is cutting-edge trends in the exploration of AD research.

Key words: deep learning, convolutional neural network, Alzheimer's disease, magnetic resonance imaging

CLC Number:

R749.1⁺6

Yingmei HAN,Yijie LI,Heng ZHANG,Weiqing LI,Ze FENG,Feng WANG. The application value of deep learning in imaging studies for predicting the conversion of Alzheimer′s disease[J]. The Journal of Practical Medicine, 2025, 41(9): 1413-1424.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Tab.1

Fig.7

Tab.2

Tab.3

Fig.8

Fig.9

Tab.4

References 60

1	CHU C S， WANG D Y， LIANG C K， et al. Automated Video Analysis of Audio-Visual Approaches to Predict and Detect Mild Cognitive Impairment and Dementia in Older Adults［J］. J Alzheimers Dis， 2023， 92（3）： 875-886. doi:10.3233/jad-220999 doi: 10.3233/jad-220999
2	YIN C， IMMS P， CHENG M， et al. Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment［J］. Proc Natl Acad Sci U S A， 2023， 120（2）： e2214634120.
3	KAM T E， ZHANG H， JIAO Z， et al. Deep Learning of Static and Dynamic Brain Functional Networks for Early MCI Detection［J］. IEEE Trans Med Imaging， 2020， 39（2）： 478-487. doi:10.1109/tmi.2019.2928790 doi: 10.1109/tmi.2019.2928790
4	MORA-RUBIO A， BRAVO-ORTIZ M A， QUINONES ARREDONDO S， et al. Classification of Alzheimer's disease stages from magnetic resonance images using deep learning［J］. PeerJ Comput Sci， 2023， 9： e1490. doi:10.7717/peerj-cs.1490 doi: 10.7717/peerj-cs.1490
5	郭润财，王蕾，黄振国，等. 基于从头训练模式深度学习卷积神经网络模型评估急性肺栓塞的价值［J］. 实用医学杂志， 2023， 39（22）： 2979-2983. doi:10.3969/j.issn.1006-5725.2023.22.021 doi: 10.3969/j.issn.1006-5725.2023.22.021
6	李欣雨，吴洋，张红梅，等. 深度学习技术在超声心动图图像质量控制中的应用［J］. 实用医学杂志， 2024， 40（1）： 108-113. doi:10.3969/j.issn.1006-5725.2024.01.019 doi: 10.3969/j.issn.1006-5725.2024.01.019
7	谭立玮，张淑军，韩琪，等. 面向医学影像报告生成的门归一化编解码网络［J］. 智能系统学报， 2024， 19（2）： 411-419. doi:10.11992/tis.202207013 doi: 10.11992/tis.202207013
8	韩英妹，李一杰，张衡，等. 基于MRI分析阿尔茨海默病大尺度脑网络研究进展［J］. 实用医学杂志， 2024， 40（4）： 575-579.
9	曾安，贾龙飞，潘丹，等. 基于卷积神经网络和集成学习的阿尔茨海默症早期诊断［J］. 生物医学工程学杂志， 2019， 36（5）： 711-719. doi:10.7507/1001-5515.201809040 doi: 10.7507/1001-5515.201809040
10	OLAIMAT M AL， MARTINEZ J， SAEED F， et al. PPAD： a deep learning architecture to predict progression of Alzheimer's disease［J］. Bioinformatics， 2023， 39（39 ）： i149-i157. doi:10.1093/bioinformatics/btad249 doi: 10.1093/bioinformatics/btad249
11	GKENIOS G， LATSIOU K， DIAMANTARAS K， et al. Diagnosis of Alzheimer's disease and Mild Cognitive Impairment using EEG and Recurrent Neural Networks［J］. Annu Int Conf IEEE Eng Med Biol Soc， 2022， 2022： 3179-3182. doi:10.1109/embc48229.2022.9871302 doi: 10.1109/embc48229.2022.9871302
12	ALESSANDRINI M， BIAGETTI G， CRIPPA P， et al. EEG-Based Alzheimer's Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network［J］. Sensors （Basel）， 2022， 22（10）：3696. doi:10.3390/s22103696 doi: 10.3390/s22103696
13	NARASIMHAN R， GOPALAN M， SIKKANDAR M Y， et al. Employing Deep-Learning Approach for the Early Detection of Mild Cognitive Impairment Transitions through the Analysis of Digital Biomarkers［J］. Sensors （Basel）， 2023， 23（21）：8867. doi:10.3390/s23218867 doi: 10.3390/s23218867
14	AQEEL A， HASSAN A， KHAN M A， et al. A Long Short-Term Memory Biomarker-Based Prediction Framework for Alzheimer's Disease［J］. Sensors （Basel）， 2022， 22（4）：1475. doi:10.3390/s22041475 doi: 10.3390/s22041475
15	FARHATULLAH， CHEN X， ZENG D， et al. A deep learning approach for non-invasive Alzheimer's monitoring using microwave radar data［J］. Neural Netw， 2024， 181： 106778. doi:10.1016/j.neunet.2024.106778 doi: 10.1016/j.neunet.2024.106778
16	QIU S， JOSHI P S， MILLER M I， et al. Development and validation of an interpretable deep learning framework for Alzheimer's disease classification［J］. Brain， 2020， 143（6）： 1920-1933. doi:10.1093/brain/awaa137 doi: 10.1093/brain/awaa137
17	AHMED G， ER M J， FAREED M M S， et al. DAD-Net： Classification of Alzheimer's Disease Using ADASYN Oversampling Technique and Optimized Neural Network［J］. Molecules， 2022， 27（20）：7085. doi:10.3390/molecules27207085 doi: 10.3390/molecules27207085
18	WANG B， LIM J S. Zoom-In Neural Network Deep-Learning Model for Alzheimer's Disease Assessments［J］. Sensors （Basel）， 2022， 22（22）：8887. doi:10.3390/s22228887 doi: 10.3390/s22228887
19	YAN H， MUBONANYIKUZO V， KOMOLAFE T E， et al. Hybrid-RViT： Hybridizing ResNet-50 and Vision Transformer for Enhanced Alzheimer's disease detection［J］. PLoS One， 2025， 20（2）： e0318998. doi:10.1371/journal.pone.0318998 doi: 10.1371/journal.pone.0318998
20	ALP S， AKAN T， BHUIYAN M S， et al. Joint transformer architecture in brain 3D MRI classification： its application in Alzheimer's disease classification［J］. Sci Rep， 2024， 14（1）： 8996. doi:10.1038/s41598-024-59578-3 doi: 10.1038/s41598-024-59578-3
21	QU C， ZOU Y， MA Y， et al. Diagnostic Performance of Generative Adversarial Network-Based Deep Learning Methods for Alzheimer's Disease： A Systematic Review and Meta-Analysis［J］. Front Aging Neurosci， 2022， 14： 841696. doi:10.3389/fnagi.2022.841696 doi: 10.3389/fnagi.2022.841696
22	QIU S， MILLER M I， JOSHI P S， et al. Multimodal deep learning for Alzheimer's disease dementia assessment［J］. Nat Commun， 2022， 13（1）： 3404. doi:10.1038/s41467-022-31037-5 doi: 10.1038/s41467-022-31037-5
23	LOGAN R， WILLIAMS B G， FERREIRA DA SILVA M， et al. Deep Convolutional Neural Networks With Ensemble Learning and Generative Adversarial Networks for Alzheimer's Disease Image Data Classification［J］. Front Aging Neurosci， 2021， 13： 720226. doi:10.3389/fnagi.2021.720226 doi: 10.3389/fnagi.2021.720226
24	CHEN X， TANG M， LIU A， et al. Diagnostic accuracy study of automated stratification of Alzheimer's disease and mild cognitive impairment via deep learning based on MRI［J］. Ann Transl Med， 2022， 10（14）： 765. doi:10.21037/atm-22-2961 doi: 10.21037/atm-22-2961
25	KANG L， JIANG J， HUANG J， et al. Identifying Early Mild Cognitive Impairment by Multi-Modality MRI-Based Deep Learning［J］. Front Aging Neurosci， 2020， 12： 206. doi:10.3389/fnagi.2020.00206 doi: 10.3389/fnagi.2020.00206
26	JIANG J， KANG L， HUANG J， et al. Deep learning based mild cognitive impairment diagnosis using structure MR images［J］. Neurosci Lett， 2020， 730： 134971. doi:10.1016/j.neulet.2020.134971 doi: 10.1016/j.neulet.2020.134971
27	EL-ASSY A M， AMER H M， IBRAHIM H M， et al. A novel CNN architecture for accurate early detection and classification of Alzheimer's disease using MRI data［J］. Sci Rep， 2024， 14（1）： 3463. doi:10.1038/s41598-024-53733-6 doi: 10.1038/s41598-024-53733-6
28	SO J H， MADUSANKA N， CHOI H K， et al. Deep Learning for Alzheimer's Disease Classification using Texture Features［J］. Curr Med Imaging Rev， 2019， 15（7）： 689-698. doi:10.2174/1573405615666190404163233 doi: 10.2174/1573405615666190404163233
29	BALAJI P， CHAURASIA M A， BILFAQIH S M， et al. Hybridized Deep Learning Approach for Detecting Alzheimer's Disease［J］. Biomedicines， 2023， 11（1）：149. doi:10.3390/biomedicines11010149 doi: 10.3390/biomedicines11010149
30	DENG L， WANG Y， Alzheimer's Disease Neuroimaging I. Fully Connected Multi-Kernel Convolutional Neural Network Based on Alzheimer's Disease Diagnosis［J］. J Alzheimers Dis， 2023， 92（1）： 209-228. doi:10.3233/jad-220519 doi: 10.3233/jad-220519
31	GHAFFARI H， TAVAKOLI H， PIRZAD JAHROMI G. Deep transfer learning-based fully automated detection and classification of Alzheimer's disease on brain MRI［J］. Br J Radiol， 2022， 95（1136）： 20211253. doi:10.1259/bjr.20211253 doi: 10.1259/bjr.20211253
32	BALBONI E， NOCETTI L， CARBONE C， et al. The impact of transfer learning on 3D deep learning convolutional neural network segmentation of the hippocampus in mild cognitive impairment and Alzheimer disease subjects［J］. Hum Brain Mapp， 2022， 43（11）： 3427-3438. doi:10.1002/hbm.25858 doi: 10.1002/hbm.25858
33	BAE J， STOCKS J， HEYWOOD A， et al. Transfer learning for predicting conversion from mild cognitive impairment to dementia of Alzheimer's type based on a three-dimensional convolutional neural network［J］. Neurobiol Aging， 2021， 99： 53-64. doi:10.1016/j.neurobiolaging.2020.12.005 doi: 10.1016/j.neurobiolaging.2020.12.005
34	BAGHDADI N A， MALKI A， BALAHA H M， et al. A（3）C-TL-GTO： Alzheimer Automatic Accurate Classification Using Transfer Learning and Artificial Gorilla Troops Optimizer［J］. Sensors （Basel）， 2022， 22（11）：4250. doi:10.3390/s22114250 doi: 10.3390/s22114250
35	JIN L， ZHAO K， ZHAO Y， et al. A Hybrid Deep Learning Method for Early and Late Mild Cognitive Impairment Diagnosis With Incomplete Multimodal Data［J］. Front Neuroinform， 2022， 16： 843566. doi:10.3389/fninf.2022.843566 doi: 10.3389/fninf.2022.843566
36	ALI I， SALEEM N， ALHUSSEIN M， et al. DeepCGAN： early Alzheimer's detection with deep convolutional generative adversarial networks［J］. Front Med （Lausanne）， 2024， 11： 1443151. doi:10.3389/fmed.2024.1443151 doi: 10.3389/fmed.2024.1443151
37	SAJJAD M， RAMZAN F， KHAN M U G， et al. Deep convolutional generative adversarial network for Alzheimer's disease classification using positron emission tomography （PET） and synthetic data augmentation［J］. Microsc Res Tech， 2021， 84（12）： 3023-3034. doi:10.1002/jemt.23861 doi: 10.1002/jemt.23861
38	KANG W， LIN L， SUN S， et al. Three-round learning strategy based on 3D deep convolutional GANs for Alzheimer's disease staging［J］. Sci Rep， 2023， 13（1）： 5750. doi:10.1038/s41598-023-33055-9 doi: 10.1038/s41598-023-33055-9
39	ZUO Q， LU L， WANG L， et al. Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis［J］. Front Neurosci， 2022， 16： 1087176. doi:10.3389/fnins.2022.1087176 doi: 10.3389/fnins.2022.1087176
40	BI X A， WANG Y， LUO S， et al. Hypergraph Structural Information Aggregation Generative Adversarial Networks for Diagnosis and Pathogenetic Factors Identification of Alzheimer's Disease With Imaging Genetic Data［J］. IEEE Trans Neural Netw Learn Syst， 2024， 35（6）： 7420-7434. doi:10.1109/tnnls.2022.3212700 doi: 10.1109/tnnls.2022.3212700
41	SINHA S， THOMOPOULOS S I， LAM P， et al. Alzheimer's Disease Classification Accuracy is Improved by MRI Harmonization based on Attention-Guided Generative Adversarial Networks［J］. Proc SPIE Int Soc Opt Eng， 2021， 12088. doi:10.1117/12.2606155 doi: 10.1117/12.2606155
42	SHI R， SHENG C， JIN S， et al. Generative adversarial network constrained multiple loss autoencoder： A deep learning-based individual atrophy detection for Alzheimer's disease and mild cognitive impairment［J］. Hum Brain Mapp， 2023， 44（3）： 1129-1146. doi:10.1002/hbm.26146 doi: 10.1002/hbm.26146
43	PAN Y， LIU M， LIAN C， et al. Synthesizing Missing PET from MRI with Cycle-consistent Generative Adversarial Networks for Alzheimer's Disease Diagnosis［J］. Med Image Comput Comput Assist Interv， 2018， 11072： 455-463. doi:10.1007/978-3-030-00931-1_52 doi: 10.1007/978-3-030-00931-1_52
44	MA D， LU D， POPURI K， et al. Differential Diagnosis of Frontotemporal Dementia， Alzheimer's Disease， and Normal Aging Using a Multi-Scale Multi-Type Feature Generative Adversarial Deep Neural Network on Structural Magnetic Resonance Images［J］. Front Neurosci， 2020， 14： 853. doi:10.3389/fnins.2020.00853 doi: 10.3389/fnins.2020.00853
45	HOANG G M， KIM U H， KIM J G. Vision transformers for the prediction of mild cognitive impairment to Alzheimer's disease progression using mid-sagittal sMRI［J］. Front Aging Neurosci， 2023， 15： 1102869. doi:10.3389/fnagi.2023.1102869 doi: 10.3389/fnagi.2023.1102869
46	KHATRI U， KWON G R. Explainable Vision Transformer with Self-Supervised Learning to Predict Alzheimer's Disease Progression Using 18F-FDG PET［J］. Bioengineering （Basel）， 2023， 10（10）. doi:10.3390/bioengineering10101225 doi: 10.3390/bioengineering10101225
47	HUANG F， QIU A. Ensemble Vision Transformer for Dementia Diagnosis［J］. IEEE J Biomed Health Inform， 2024， 28（9）： 5551-5561. doi:10.1109/jbhi.2024.3412812 doi: 10.1109/jbhi.2024.3412812
48	SHAFFI N， VISWAN V， MAHMUD M. Ensemble of vision transformer architectures for efficient Alzheimer's Disease classification［J］. Brain Inform， 2024， 11（1）： 25. doi:10.1186/s40708-024-00238-7 doi: 10.1186/s40708-024-00238-7
49	TANG C， WEI M， SUN J， et al. CsAGP： Detecting Alzheimer's disease from multimodal images via dual-transformer with cross-attention and graph pooling［J］. J King Saud Univ Comput Inf Sci， 2023， 35（7）： 101618. doi:10.1016/j.jksuci.2023.101618 doi: 10.1016/j.jksuci.2023.101618
50	SAOUD L S， ALMARZOUQI H. Explainable early detection of Alzheimer's disease using ROIs and an ensemble of 138 3D vision transformers［J］. Sci Rep， 2024， 14（1）： 27756. doi:10.1038/s41598-024-76313-0 doi: 10.1038/s41598-024-76313-0
51	ZHAO Z， YEOH P S Q， ZUO X， et al. Vision transformer-equipped Convolutional Neural Networks for automated Alzheimer's disease diagnosis using 3D MRI scans［J］. Front Neurol， 2024， 15： 1490829. doi:10.3389/fneur.2024.1490829 doi: 10.3389/fneur.2024.1490829
52	HONG X， HUANG K， LIN J， et al. Combined Multi-Atlas and Multi-Layer Perception for Alzheimer's Disease Classification［J］. Front Aging Neurosci， 2022， 14： 891433. doi:10.3389/fnagi.2022.891433 doi: 10.3389/fnagi.2022.891433
53	ALMUBARK I， CHANG L C， SHATTUCK K F， et al. A 5-min Cognitive Task With Deep Learning Accurately Detects Early Alzheimer's Disease［J］. Front Aging Neurosci， 2020， 12： 603179. doi:10.3389/fnagi.2020.603179 doi: 10.3389/fnagi.2020.603179
54	MUKHERJI D， MUKHERJI M， MUKHERJI N， et al. Early detection of Alzheimer's disease using neuropsychological tests： a predict-diagnose approach using neural networks［J］. Brain Inform， 2022， 9（1）： 23. doi:10.1186/s40708-022-00169-1 doi: 10.1186/s40708-022-00169-1
55	CHEN K， WENG Y， HOSSEINI A A， et al. A comparative study of GNN and MLP based machine learning for the diagnosis of Alzheimer's Disease involving data synthesis［J］. Neural Netw， 2024， 169： 442-452. doi:10.1016/j.neunet.2023.10.040 doi: 10.1016/j.neunet.2023.10.040
56	LI M， JIANG Y， LI X， et al. Ensemble of convolutional neural networks and multilayer perceptron for the diagnosis of mild cognitive impairment and Alzheimer's disease［J］. Med Phys， 2023， 50（1）： 209-225. doi:10.1002/mp.15985 doi: 10.1002/mp.15985
57	QIANG Y R， ZHANG S W， LI J N， et al. Diagnosis of Alzheimer's disease by joining dual attention CNN and MLP based on structural MRIs， clinical and genetic data［J］. Artif Intell Med， 2023， 145： 102678. doi:10.1016/j.artmed.2023.102678 doi: 10.1016/j.artmed.2023.102678
58	FARHATULLAH， CHEN X， ZENG D， et al. 3-Way hybrid analysis using clinical and magnetic resonance imaging for early diagnosis of Alzheimer's disease［J］. Brain Res， 2024， 1840： 149021. doi:10.1016/j.brainres.2024.149021 doi: 10.1016/j.brainres.2024.149021
59	YAO M， LIU J， PU Y， et al. Multi-class Prediction of Cognitively Normal / Mild Cognitive Impairment / Alzheimer's Disease Status in Dementia Based on Convolutional Neural Networks with Attention Mechanism［J］. Annu Int Conf IEEE Eng Med Biol Soc， 2024， 2024： 1-7. doi:10.1109/embc53108.2024.10781557 doi: 10.1109/embc53108.2024.10781557
60	颜彬. 基于注意力机制与全卷积网络的阿尔茨海默病分类方法研究［D］. 杭州：浙江理工大学，2023.

融合模型	数据集	样本			结果	图像	可解释性
融合模型	数据集	AD	MCI	HC	结果	图像	可解释性
CNN-CNN^［27］	ADNI	171	545	580	三元多类（AD、MCI、HC）准确率99.43%；四元多类（AD、HC、LMCI、EMCI）准确率99.57%；五元多类（AD、HC、LMCI、EMCI、MCI）准确率99.13%	MRI	有
CNN-MLP^［28］	ADNI	-	-	-	AD-MCI、AD-HC、MCI-HC分类准确率分别为72.5%、85%、75%	MRI	-
CNN-LSTM^［29］	-	-	-	-	模型分类准确率高达98.5%	MRI	有
FMCNN（CNN-FCN）^［30］	-	-	-	-	依据DTI图像WM特性准确诊断AD和MCI（准确率高达96.95%），除却分类诊断功能，还可基于确定性纤维追踪生成的光纤概率图来评估AD和MCI风险状态	DTI	-
CNN（ResNet、Xception和InceptionV3）-TL^［31］	ADNI、OASIS、AIBL	94、15、15	126、0、30	85、15、15	分类任务的准确率均在90%以上，但是InceptionV3-TL模型分类性能表现最优	MRI	有
CNN-TL^［32］	意大利摩德纳大学医院、牛津磁共振中心	12	61	-	该模型对于DL-TL临床应用的广泛开展具有重要意义，提高海马体积的精度测量，验证MCI阶段小海马异常的结论	MRI	有
CNN-TL（ResNet50）^［33］	ADNI	1 406	-	2 084	该模型的分类准确率82.4%，预测值与临床评分存在相关性，可预测个体未来认知能力下降状态	sMRI、临床评分
A3C-TL-GTO^［34］	ADNI、AD数据集	17 976	138 105	70 076	该模型对ADNI数据集疾病分类的准确率达96.25%；AD数据集分类准确率96.65%	MRI

创新模型	数据集	样本			结果	影像	文献
创新模型	数据集	AD	MCI	HC	结果	影像	文献
DeepCGAN	ADNI	3 370	-	1 643	准确率97.3%；AUC99.51%	-	［36］
DeepCGAN	ADNI	30	64	42	准确率72%；AD的PSNR82分；SSIM25.6分	PET	［37］
3D-DCGAN	ADNI	187	382	229	准确率：AD-HC 92.8%、AD-MCI78.1%、MCI-HC76.4%，解决掉过拟合问题	sMRI	［38］
ATAT	ADNI	-	162	86	ATAT模型为脑功能网络提供新视角，可评估不同阶段与疾病相关的影像特征	fMRI	［39］
HSIA-GAN	ADNI	233	400		阶段诊断率74.2%；风险预测84.5%	sMRI/fMRI/DTI	［40］
注意力引导的GAN	ADNI、AIBL、OASIS	329、628、47	-	687、0、188	准确率84.79%	3D-MRI	［41］
GANCMLAE	ADNI	292	309	712	SSIM、PSNR以及MSE指标具有较好性能，AD-HC和MCI-HC的ROC分别是86.7%和75.2%	sMRI	［42］
3D-cGAN、LM3IL	ADNI	358	670	429	在AD诊断方面优于最先进的方法	PET/MRI	［43］
多尺度多类型特征生成对抗性深度神经网络	ADNI、NIFD	459	-	1 063	准确率88.28%	sMRI	［44］

模型	数据集	样本	结果	影像	文献
Hybrid-ViT （ResNet-50和ViT）	OASIS	AD有64例，HC有86例	在训练期间准确率97%，验证数据集准确率94%，该模型优于先进模型（如ViT模型）	MRI	［19］
SSL-ViT-DINO-ELM	ADNI	MCI共469例	该模型准确率92.31%，特异度90.21%，敏感度95.50%。融合SSL、DINO、ELM以及注意力机制，使该模型更具有预测性和可解释性	PET	［46］
MC-ViT	ADNI、OASIS-3	ADNI数据集共7 199例，OASIS-3共1 992例	该模型克服了3D补丁卷积神经网络的局限性，通过最低成本，对AD分类准确率90%，超过2D和3DCNN模型	MRI	［47］
ViT-集成技术	ADNI、OASIS	ADNI共1 056，其中AD223，MCI737，HC96；OASIS共6 400，非痴呆3 200，非常轻度痴呆症2 240，轻度痴呆症896，中度痴呆症64	ViT-集成技术分类准确性86%，成为CNN等传统模型的替代方案，通过多头注意力机制，在多个数据集中表现出较高的分类精度，模型具有可解释性。	MRI	［48］
ViT-CsAGP	ADNI	-	该模型的AD-HC、AD-MCI、HC-MCI、AD-HC-MCI的分类准确率分别受99.04%、97.43%、98.57%、98.72%。通过土池算法Reshape-Pooling-Reshape （RPR）减少模型的令牌冗余	PET/MRI	［49］
3D-ViTs-DBN	ADNI	AD有117例，MCI有247例，HC有168例	模型与基于感兴趣区的分析方法提取特定大脑区域特征，并用DBN模型进行预测。该模型的准确性、可解释性以及分类性能均表现良好	MRI	［50］
VECNN	ADNI	ADNI数据集中共2248张3DMRI图像	该模型在区分AD、MCI、HC的准确率达92.14%，敏感度93.27%，特异度89.95%	3DMRI	［51］

模型	数据集	样本	结果	数据	可解释性
MLP-RNN（LSTM）^［54］	ADNI	AD200； MCI400； HC200	该模型可作为预测AD进展的有效工具。在预测评估受试者未来2年认知状态正常准确率为84.62%，未来2年认知状态异常准确率78.9%；未来4年认知状态正常准确率为83.33%，未来4年认知状态异常准确率为82.8%	临床评分	有
MLP-GNN^［55］	ADNI	1092	该模型分类性能准确率90.18%，还可以根据MRI图像衍生出FDG-PET图像并进行分析	MRI、PET	进行10倍交叉验证，具有可解释性
MLP-CNN^［56］（还借助TL）	ADNI	-	AD诊断准确率98.61%，MCI-AD预测准确率高达84.49%。可准确诊断AD并预测MCI转化	MRI	有
MLP-CNN^［57］	ADNI	-	该模型对AD-MCI和MCI-HC的分类准确率分别是93%和82.4%	MRI、临床数据以及APOE遗传数据	引入双注意力机制，增加模型可解释性
MLP-AlexNet^［58］	ADNI、 OASIS、 EEG	-	在EEG数据集，该模型分类准确率97.71%；在ADNI数据集，该模型分类准确率92.59%	MRI、临床数据	具有可解释性
MLP-AD_Net（阿尔茨海默病定向预测3D卷积模型）^［59］	ADNI	-	该模型的准确率89%，预测性能良好且稳定	MRI、临床数据	引入注意力机制，模型具有可解释性
MLP-FCN^［60］	ADNI	AD307、 HC243	注意力机制、FCN和MLP的融合应用可获取精确的疾病概率图特征信息，提升模型的分类性能	3D-MRI	引入注意力机制，模型具有可解释性

[1]	Li TANG,Yurong GONG,Liye ZENG,Yanfang GAO,Chengzhe. DENG. Application value of 3.0T magnetic resonance imaging T2 mapping sequence combined with serum nesfatin⁃1 level detection in the diagnosis of elderly knee early osteoarthritis [J]. The Journal of Practical Medicine, 2025, 41(8): 1238-1242.
[2]	Huiling YE,Zhengchaoyi CHEN,Yihan HUANG,Yingjie ZHANG,Xiangbin ZHANG,Yuehu PU,Renming ZHONG. Radiotherapy treatment comparison of liver SBRT between 4D⁃CT and deep inspiration breath hold troughmagnetic resonance imaging [J]. The Journal of Practical Medicine, 2025, 41(7): 1044-1049.
[3]	Gaokai HU,Ya'nan NIU,Yukang GONG,Yang HU,Ruixuan XU,Wenshan. GAO. Research progress on the application of deep learning in lumbar spine disease [J]. The Journal of Practical Medicine, 2025, 41(6): 921-928.
[4]	Zhilong SI,Hao WANG,Fei XIAO. Feasibility of modified LIFT guided by magnetic resonance imaging in the treatment of deep anorectal abscess [J]. The Journal of Practical Medicine, 2025, 41(1): 65-70.
[5]	Xi HU,Yan LI,Yang. LIU. Recent advances on the application of deep learning in assisted reproductive technology [J]. The Journal of Practical Medicine, 2024, 40(7): 893-897.
[6]	Yingmei HAN,Yijie LI,Heng ZHANG,Jing LV,Yi ZHANG,Yingbo QIAO,Nan LIN,Huiyong XU,Feng. WANG. Research progress of large-scale brain network of Alzheimer’s disease based on MRI analysis [J]. The Journal of Practical Medicine, 2024, 40(4): 575-579.
[7]	Yuke SONG,Jinfan XU,Xiaoming HE,Tianye LIN,Mincong HE,Qiushi. WEI. Correlation of high signal intensity of infrapatellar fat pad on symptoms and structure of knee osteoarthritis [J]. The Journal of Practical Medicine, 2024, 40(23): 3373-3378.
[8]	Huiling YE,Renming. ZHONG. Progress in assessing the treatment accuracy of liver stereotactic body radiotherapy through post-therapeutic magnetic resonance imaging morphologic alterations [J]. The Journal of Practical Medicine, 2024, 40(22): 3119-3123.
[9]	Cheng CHEN,Xinyang YU,Hua. ZHANG. Advances in imaging diagnosis of placenta accreta spectrum [J]. The Journal of Practical Medicine, 2024, 40(21): 2976-2981.
[10]	Jiarui ZHAO,Yulai GONG. Effectiveness of resting-state fMRI in the diagnosis of temporal lobe epilepsy-associated cognitive impairment： A review of literature [J]. The Journal of Practical Medicine, 2024, 40(20): 2954-2959.
[11]	Jia XIANG,Qiantong CHEN,Yingxin LU,Sijie ZHENG,Junjie HUANG,Yingying CHEN,Suidan HUANG,Huai. CHEN. Study on diffuse cystic lung disease based on deep learning [J]. The Journal of Practical Medicine, 2024, 40(19): 2747-2754.
[12]	Di WANG,Dan LIAO,Yuancheng LIU,Rui XU,Qinghong. DUAN. Analysis of global local consistency changes in first-episode depression with childhood maltreatment based on resting-state magnetic resonance [J]. The Journal of Practical Medicine, 2024, 40(16): 2311-2315.
[13]	Zhe ZENG,Lin LUO,Qiang CHEN,Siqi HOU,Shengzhe. JIANG. Default mode network analysis associated with memory impairment in acute mild traumatic brain injury [J]. The Journal of Practical Medicine, 2024, 40(10): 1412-1417.
[14]	Xinyu LI,Yang WU,Hongmei ZHANG,Lixue YIN,Bo PENG,Shenghua. XIE. Deep learning technology for quality control of echocardiography images [J]. The Journal of Practical Medicine, 2024, 40(1): 108-113.
[15]	LV Xiaoli, CHEN Yilei, TAN Wenli, MIAO Wanhong.. Cerebral cortex activation patterns under different accommodative loads of human eye ciliary muscles [J]. The Journal of Practical Medicine, 2023, 39(6): 706-712.

The application value of deep learning in imaging studies for predicting the conversion of Alzheimer′s disease

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 60

Related Articles 15

Recommended Articles

Metrics

Comments