《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (1): 310-315.DOI: 10.11772/j.issn.1001-9081.2021010132
收稿日期:
2021-01-25
修回日期:
2020-05-31
接受日期:
2020-06-10
发布日期:
2021-07-14
出版日期:
2022-01-10
通讯作者:
王瑜
作者简介:
贾洪飞(1997—),男,吉林通化人,硕士研究生,主要研究方向:图像处理、模式识别基金资助:
Hongfei JIA, Xi LIU, Yu WANG(), Hongbing XIAO, Suxia XING
Received:
2021-01-25
Revised:
2020-05-31
Accepted:
2020-06-10
Online:
2021-07-14
Published:
2022-01-10
Contact:
Yu WANG
About author:
JIA Hongfei, born in 1997, M. S. candidate. His research interests include image processing, pattern recognition.Supported by:
摘要:
阿尔茨海默症(AD)是一种起病隐匿的进行性神经退行性疾病,会使患者的大脑脑区结构发生改变。为辅助医生对AD患者的病情做出正确判断,提出了一种改进的三维主成分分析网络(3DPCANet)模型,并结合被试者全脑均值低频波动振幅(mALFF)图像来对AD进行分类。首先,对功能磁共振成像(fMRI)数据进行预处理,计算出全脑mALFF图像;然后,利用改进的3DPCANet深度学习模型进行特征提取;最后,使用支持向量机(SVM)对不同阶段的AD患者的特征进行分类。实验结果显示,所提模型简单,鲁棒性好,且其在主观记忆衰退(SMD)与AD、SMD与晚期轻度认知障碍(LMCI)以及LMCI与AD上的分类准确率分别达到了92.42%、91.80%和89.33%,验证了提出方法的有效性和可行性。
中图分类号:
贾洪飞, 刘茜, 王瑜, 肖洪兵, 邢素霞. 3DPCANet在阿尔茨海默症功能磁共振成像图像分类中的应用[J]. 计算机应用, 2022, 42(1): 310-315.
Hongfei JIA, Xi LIU, Yu WANG, Hongbing XIAO, Suxia XING. Application of 3DPCANet in image classification of functional magnetic resonance imaging for Alzheimer’s disease[J]. Journal of Computer Applications, 2022, 42(1): 310-315.
fMRI | 人数 | 男/女 | 年龄/岁 | 训练集 | 验证集 |
---|---|---|---|---|---|
AD | 34 | 18/16 | 57~88 | 26 | 8 |
EMCI | 57 | 34/23 | 57~90 | 44 | 13 |
LMCI | 35 | 14/21 | 58~88 | 28 | 7 |
NC | 50 | 28/22 | 66~91 | 40 | 10 |
SMD | 26 | 14/12 | 65~83 | 21 | 5 |
表1 被试者信息统计分析
Tab. 1 Statistical analysis of subject information
fMRI | 人数 | 男/女 | 年龄/岁 | 训练集 | 验证集 |
---|---|---|---|---|---|
AD | 34 | 18/16 | 57~88 | 26 | 8 |
EMCI | 57 | 34/23 | 57~90 | 44 | 13 |
LMCI | 35 | 14/21 | 58~88 | 28 | 7 |
NC | 50 | 28/22 | 66~91 | 40 | 10 |
SMD | 26 | 14/12 | 65~83 | 21 | 5 |
方法 | 评测指标 | NC vs.AD | SMD vs.LMCI | NC vs.EMCI | LMCI vs.AD |
---|---|---|---|---|---|
文献[ | ACC | 83.95 | — | 80.15 (NC vs MCI) | 82.53 (MCI vs AD) |
AUC | 88.42 | — | 81.74 (NC vs MCI) | 81.24 (MCI vs AD) | |
文献[ | ACC | 78.95 | — | — | — |
SEN | 81.25 | — | — | — | |
SPE | 77.27 | — | — | — | |
3DPCANet+SVM+ALFF | ACC | 87.78 | 91.80 | 81.82 | 86.67 |
SEN | 96.00 | 91.43 | 80.00 | 88.57 | |
SPE | 77.50 | 92.67 | 84.00 | 85.00 | |
F1 | 90.05 | 92.72 | 82.62 | 85.35 | |
AUC | 88.50 | 88.09 | 78.17 | 83.93 | |
改进3DPCANet+SVM +ALFF | ACC | 88.89 | 91.80 | 87.27 | 89.33 |
SEN | 86.00 | 94.28 | 80.00 | 85.71 | |
SPE | 92.50 | 88.67 | 96.00 | 92.50 | |
F1 | 89.57 | 92.92 | 87.21 | 88.08 | |
AUC | 82.25 | 90.86 | 89.83 | 83.57 |
表2 不同方法实验结果对比 (%)
Tab.2 Comparison of experimental results of different methods
方法 | 评测指标 | NC vs.AD | SMD vs.LMCI | NC vs.EMCI | LMCI vs.AD |
---|---|---|---|---|---|
文献[ | ACC | 83.95 | — | 80.15 (NC vs MCI) | 82.53 (MCI vs AD) |
AUC | 88.42 | — | 81.74 (NC vs MCI) | 81.24 (MCI vs AD) | |
文献[ | ACC | 78.95 | — | — | — |
SEN | 81.25 | — | — | — | |
SPE | 77.27 | — | — | — | |
3DPCANet+SVM+ALFF | ACC | 87.78 | 91.80 | 81.82 | 86.67 |
SEN | 96.00 | 91.43 | 80.00 | 88.57 | |
SPE | 77.50 | 92.67 | 84.00 | 85.00 | |
F1 | 90.05 | 92.72 | 82.62 | 85.35 | |
AUC | 88.50 | 88.09 | 78.17 | 83.93 | |
改进3DPCANet+SVM +ALFF | ACC | 88.89 | 91.80 | 87.27 | 89.33 |
SEN | 86.00 | 94.28 | 80.00 | 85.71 | |
SPE | 92.50 | 88.67 | 96.00 | 92.50 | |
F1 | 89.57 | 92.92 | 87.21 | 88.08 | |
AUC | 82.25 | 90.86 | 89.83 | 83.57 |
评测 指标 | NC vs. SMD | SMD vs. EMCI | SMD vs. AD | EMCI vs. LMCI | EMCI vs. AD |
---|---|---|---|---|---|
ACC | 89.50 | 88.43 | 92.42 | 84.21 | 88.42 |
SEN | 94.00 | 91.67 | 88.00 | 88.33 | 90.00 |
SPE | 80.67 | 81.33 | 95.00 | 77.14 | 85.71 |
F1 | 90.10 | 91.65 | 89.46 | 87.44 | 90.79 |
AUC | 89.53 | 79.55 | 86.83 | 80.95 | 85.48 |
表3 AD不同阶段患者分类 (%)
Tab.3 Classification of patients with different stages of AD
评测 指标 | NC vs. SMD | SMD vs. EMCI | SMD vs. AD | EMCI vs. LMCI | EMCI vs. AD |
---|---|---|---|---|---|
ACC | 89.50 | 88.43 | 92.42 | 84.21 | 88.42 |
SEN | 94.00 | 91.67 | 88.00 | 88.33 | 90.00 |
SPE | 80.67 | 81.33 | 95.00 | 77.14 | 85.71 |
F1 | 90.10 | 91.65 | 89.46 | 87.44 | 90.79 |
AUC | 89.53 | 79.55 | 86.83 | 80.95 | 85.48 |
1 | 王全英,梁景宏,贾瑞霞,等. 2020—2050年中国阿尔茨海默病患病情况预测研究[J]. 阿尔茨海默病及相关病, 2019, 2(1):289-298. |
WANG Q Y, LIANG J H, JIA R X, et al. Alzheimer disease in China (2015—2050) estimated using the 1% population sampling survey in 2015 [J]. Alzheimer’s Disease and Related Diseases, 2019, 2(1): 289-298. | |
2 | WEINER M W, VEITCH D P, AISEN P S, et al. Recent publications from the Alzheimer’s disease neuroimaging initiative: reviewing progress toward improved AD clinical trials[J]. Alzheimer’s and Dementia, 2017, 13(4): e1-e85. 10.1016/j.jalz.2016.11.007 |
3 | DeYOE E A, BANDETTINI P, NEITZ J, et al. Functional Magnetic Resonance Imaging (FMRI) of the human brain[J]. Journal of Neuroscience Methods, 1994, 54(2): 171-187. 10.1016/0165-0270(94)90191-0 |
4 | LAUTERBUR P C. Image formation by induced local interactions: examples employing nuclear magnetic resonance[J]. Nature, 1973, 242(5394): 190-191. 10.1038/242190a0 |
5 | GOLBABAEI S, VAHID A, HATAMI J, et al. Classification of Alzheimer’s disease and mild cognitive impairment: machine learning applied to rs-fMRI brain graphs[C]// Proceedings of the 23rd Iranian Conference on Biomedical Engineering and the 1st International Iranian Conference on Biomedical Engineering. Piscataway: IEEE, 2016: 35-40. 10.1109/icbme.2016.7890925 |
6 | KHAZAEE A, EBRAHIMZADEH A, BABAJANI-FEREMI A. Identifying patients with Alzheimer’s disease using resting-state fMRI and graph theory[J]. Clinical Neurophysiology, 2015, 126(11): 2132-2141. 10.1016/j.clinph.2015.02.060 |
7 | SHI Y H, ZENG W M, DENG J, et al. The identification of Alzheimer’s disease using functional connectivity between activity voxels in resting-state fMRI data[J]. IEEE Journal of Translational Engineering in Health and Medicine, 2020, 8: No.1400211. 10.1109/jtehm.2020.2985022 |
8 | GUI R Z, CHEN T J, NIE H. Classification of task-state fMRI data based on circle-EMD and machine learning[J]. Computational Intelligence and Neuroscience, 2020, 2020: No.791294. 10.1155/2020/7691294 |
9 | 周文,王瑜,肖红兵,等. 基于KPCA算法的阿尔茨海默症辅助诊断[J]. 中国医学物理学杂志, 2018, 35(4):404-409. 10.3969/j.issn.1005-202X.2018.04.007 |
ZHOU Q, WANG Y, XIAO H B, et al. Assisted diagnosis of Alzheimer’s disease based on KPCA algorithm[J]. Chinese Journal of Medical Physics, 2018, 35(4): 404-409. 10.3969/j.issn.1005-202X.2018.04.007 | |
10 | 李长胜,王瑜,肖洪兵,等. KPCA和Adaboost算法在阿尔茨海默症功能磁共振影像分类中的应用[J]. 中国医学物理学杂志, 2019, 36(7):784-788. 10.3969/j.issn.1005-202X.2019.07.008 |
LI C S, WANG Y, XIAO H B, et al. Application of KPCA and Adaboost algorithm in the classification of functional magnetic resonance images of Alzheimer’s disease[J]. Chinese Journal of Medical Physics, 2019, 36(7): 784-788. 10.3969/j.issn.1005-202X.2019.07.008 | |
11 | HOSSEINI-ASL E, KEYNTON R, El-BAZ A. Alzheimer’s disease diagnostics by adaptation of 3D convolutional network[C]// Proceedings of the 2016 IEEE International Conference on Image Processing. Piscataway: IEEE, 2016: 126-130. 10.1109/icip.2016.7532332 |
12 | LIAN C F, LIU M X, ZHANG J, et al. Hierarchical fully convolutional network for joint atrophy localization and Alzheimer’s disease diagnosis using structural MRI[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(4): 880-893. 10.1109/tpami.2018.2889096 |
13 | HOSSEINI ASL E, GHAZAL M, MAHMOUD A. Alzheimer’s disease diagnostics by a deeply supervised adaptable 3D convolutional network[J]. Frontiers in Bioscience-Landmark, 2018, 23(3): 584-596. |
14 | LAO H, ZHANG X, TANG Y, et al. Alzheimer’s disease diagnosis based on the visual attention model and equal-distance ring shape context features[J]. IET Image Processing, 2021,15(4):1-12. |
15 | JAIN R, JAIN N, AGGARWAL A, et al. Convolutional neural network based Alzheimer’s disease classification from magnetic resonance brain images[J]. Cognitive Systems Research, 2019, 57: 147-159. 10.1016/j.cogsys.2018.12.015 |
16 | ZHANG F, LI Z Z, ZHANG B Y, et al. Multi-modal deep learning model for auxiliary diagnosis of Alzheimer’s disease[J]. Neurocomputing, 2019, 361: 185-195. 10.1016/j.neucom.2019.04.093 |
17 | CHAN T H, JIA K, GAO S H, et al. PCANet: a simple deep learning baseline for image classification?[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5017-5032. 10.1109/tip.2015.2475625 |
18 | 李书通,肖斌,李伟生,等. 基于3D-PCANet的阿尔兹海默病辅助诊断[J]. 计算机科学, 2018, 45(6A): 140-142, 156. 10.11896/j.issn.1002-137X.2018.Z6.029 |
LI S T, XIAO B, LI W S, et al. Diagnosis of Alzheimer’s disease based on 3D-PCANet[J]. Computer Science, 2018, 45(6A): 140-142, 156. 10.11896/j.issn.1002-137X.2018.Z6.029 | |
19 | JU R H, HU C H, ZHOU P, et al. Early diagnosis of Alzheimer’s disease based on resting-state brain networks and deep learning[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019, 16(2): 244-257. 10.1109/tcbb.2017.2776910 |
20 | PERAZA L R, COLLOBY S J, DEBOYS L, et al. Regional functional synchronizations in dementia with Lewy bodies and Alzheimer’s disease[J]. International Psychogeriatrics, 2016, 28(7): 1143-1151. 10.1017/s1041610216000429 |
21 | JIANG L L, ZUO X N. Regional homogeneity: a multimodal, multiscale neuroimaging marker of the human connectome[J]. The Neuroscientist, 2016, 22(5): 486-505. 10.1177/1073858415595004 |
22 | ZANG Y F, HE Y, ZHU C Z, et al. Altered baseline brain activity in children with ADHD revealed by resting-state functional MRI[J]. Brain and Development, 2007, 29(2): 83-91. 10.1016/j.braindev.2006.07.002 |
23 | YAN C G, WANG X D, ZUO X N, et al. DPABI: data processing & analysis for (resting-state) brain imaging[J]. Neuroinformatics, 2016, 14(3): 339-351. 10.1007/s12021-016-9299-4 |
24 | DAI Z J, YAN C G, WANG Z Q, et al. Discriminative analysis of early Alzheimer’s disease using Multi-modal imaging and Multi-level characterization with Multi-classifier (M3)[J]. NeuroImage, 2012, 59(3): 2187-2195. 10.1016/j.neuroimage.2011.10.003 |
[1] | 孙敏, 成倩, 丁希宁. 基于CBAM-CGRU-SVM的Android恶意软件检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1539-1545. |
[2] | 沈嫣然, 温昕, 张瑾昊, 张帅, 曹锐, 高保禄. 轻量级多尺度卷积网络的功能磁共振成像脑龄预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3949-3957. |
[3] | 乔恩保, 高向阳, 程俊. 基于支持向量机的自恢复自适应蒙特卡洛定位算法[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3246-3251. |
[4] | 黄学雨, 贺怀宇, 林慧敏, 陈金水. 基于特征聚合的铜合金金相图分类识别方法[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2593-2601. |
[5] | 温祥西, 彭娅婷, 毕可心, 衡宇铭, 吴明功. 基于最优样本集在线模糊最小二乘支持向量机的飞行冲突网络态势预测[J]. 《计算机应用》唯一官方网站, 2023, 43(11): 3632-3640. |
[6] | 张仲华, 赵福媛, 郭钧枫, 赵高长. 柯西自适应回溯搜索与最小二乘支持向量机的集成预测模型[J]. 《计算机应用》唯一官方网站, 2022, 42(6): 1829-1836. |
[7] | 杨磊, 赵红东, 于快快. 基于多头注意力机制的端到端语音情感识别[J]. 《计算机应用》唯一官方网站, 2022, 42(6): 1869-1875. |
[8] | 屈震, 李堃婷, 冯志玺. 基于有效通道注意力的遥感图像场景分类[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1431-1439. |
[9] | 乔桂芳, 侯守明, 刘彦彦. 基于改进卷积神经网络与支持向量机结合的面部表情识别算法[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1253-1259. |
[10] | 邱云志, 汪廷华, 戴小路. 双重特征加权模糊支持向量机[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 683-687. |
[11] | 谭旺, 李轶. 循环程序的界函数合成[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 565-573. |
[12] | 祁祥洲, 邢红杰. 基于中心核对齐的多核单类支持向量机[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 349-356. |
[13] | 葛倩, 张光斌, 张小凤. 基于最大信息系数的ReliefF和支持向量机交互的自动特征选择算法[J]. 《计算机应用》唯一官方网站, 2022, 42(10): 3046-3053. |
[14] | 祝承, 赵晓琦, 赵丽萍, 焦玉宏, 朱亚飞, 陈建英, 周伟, 谭颖. 基于谱聚类半监督特征选择的功能磁共振成像数据分类[J]. 计算机应用, 2021, 41(8): 2288-2293. |
[15] | 贾鹤鸣, 姜子超, 李瑶, 孙康健. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298. |
阅读次数 | ||||||
全文 128
|
|
|||||
摘要 372
|
|
|||||