山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (6): 131-138.doi: 10.6040/j.issn.1672-3961.0.2022.130
• 机器学习与数据挖掘 • 上一篇
沈鑫杰,黄嘉爽,丁卫平*,孙颖,王海鹏,鞠恒荣
SHEN Xinjie, HUANG Jiashuang, DING Weiping*, SUN Ying, WANG Haipeng, JU Hengrong
摘要： 采用深度学习对脑龄预测问题进行研究,提出并设计一种基于双通路卷积融合网络的脑龄分布预测模型,以有效预测被试的大脑年龄。将被试静息态功能磁共振成像(rest-state functional MRI, rs-fMRI)数据通过标记分布学习方法,将确定的脑龄标签转化为一组具有高斯分布的概率,设计一个双通路卷积融合网络,包含卷积、批量归一化、池化等步骤,可以同时学习rs-fMRI多类激活图的特征,通过一个低秩融合网络来融合这些特征,利用损失函数对网络更新优化;对预测模型的结果进行详细分析。该模型得到的绝对平均误差和相关系数的指标分别为5.735和0.592 4。试验结果表明,相较于其他模型,该模型取得的平均绝对误差更小,相关系数更高,显著提高了基于rs-fMRI图像的脑龄预测精度。
中图分类号:
| ［1］ THOMPSON P M, HAYASHI K M, DE Z G, et al. Dynamics of gray matter loss in Alzheimer′s disease［J］. Journal of Neuroscience, 2003, 23(3): 9941005. ［2］ SHENG J, XIN Y, ZHANG Q, et al. Predictive classification of Alzheimer′s disease using brain imaging and genetic data［J］. Scientific Reports, 2022, 12(1): 19. ［3］ COLE J H, LEECH R, SHARP D J, et al. Prediction of brain age suggests accelerated atrophy after traumatic brain injury［J］. Annals of Neurology, 2015, 77(4): 571581. ［4］ 黄嘉爽,接标,丁卫平,等.脑网络分析方法及其应用［J］.数据采集与处理, 2021, 36(4):648663. HUANG Jiashuang, JIE Biao, DING Weiping, et al. Brain network analysis methods and their applications［J］. Data Acquisition and Processing, 2021, 36(4):648663. ［5］ WANG Q, HU K, WANG M, et al. Predicting brain age during typical and atypical development based on structural and functional neuroimaging［J］. Human Brain Mapping, 2021, 42(18): 59435955. ［6］ GOLD A L, ABEND R, BRITTON J C, et al. Age differences in the neural correlates of anxiety disorders: an fMRI study of response to learned threat［J］. American Journal of Psychiatry, 2020, 177(5): 454463. ［7］ HUANG J, ZHOU L, WANG L, et al. Attentiondiffusionbilinear neural network for brain network analysis［J］. IEEE Transactions on Medical Imaging, 2020, 39(7): 25412552. ［8］ KONG X, XU S, SUN Y, et al. Electroconvulsive therapy changes the regional resting state function measured by regional homogeneity (ReHo) and amplitude of low frequency fluctuations (ALFF) in elderly major depressive disorder patients: an exploratory study［J］. Psychiatry Research: Neuroimaging, 2017, 264: 1321. ［9］ LIEM F, VAROQUAUX G, KYNAST J, et al. Predicting brainage from multimodal imaging data captures cognitive impairment［J］. Neuroimage, 2017, 148: 179188. ［10］ FRANKE K, LUDERS E, MAY A, et al. Brain maturation: predicting individual BrainAGE in children and adolescents using structural MRI［J］. Neuroimage, 2012, 63(3): 13051312. ［11］ COLE J H. Multimodality neuroimaging brainage in UK biobank: relationship to biomedical, lifestyle, and cognitive factors［J］. Neurobiology of Aging, 2020, 92: 3442. ［12］ WANG Q, HU K, WANG M, et al. Predicting brain age during typical and atypical development based on structural and functional neuroimaging［J］. Human Brain Mapping, 2021, 42(18): 59435955. ［13］ 莫鸿飞,谢振平. 基于双通道深度CNN的烟雾浓度测量方法［J］. 模式识别与人工智能, 2021, 34(9):844852. MO Hongfei, XIE Zhenping. A twochannel deep CNNbased method for measuring smoke concentration［J］. Pattern Recognition and Artificial Intelligence, 2021, 34(9):844852. ［14］ 张昱,高凯龙,李继涛,等. 双通道多核卷积神经网络中文文本情绪分类方法［J］. 内蒙古大学学报(自然科学版), 2021, 52(5):508513. ZHANG Yu, GAO Kailong, LI Jitao, et al. A twochannel multicore convolutional neural network approach to Chinese text emotion classification［J］. Journal of Inner Mongolia University (Natural Science Edition), 2021, 52(5):508513. ［15］ PANIS G, LANITIS A, TSAPATSOULIS N, et al. Overview of research on facial ageing using the FGNET ageing database［J］. Let Biometrics, 2016, 5(2): 3746. ［16］ LURIE D J, KESSLER D, BASSETT D S, et al. Questions and controversies in the study of timevarying functional connectivity in resting fMRI［J］. Network Neuroscience, 2020, 4(1): 3069. ［17］ GENG X. Label distribution learning［J］. IEEE Transactions on Knowledge and Data Engineering, 2016, 28(7): 17341748. ［18］ GAO B B, XING C, XIE C W, et al. Deep label distribution learning with label ambiguity［J］. IEEE Transactions on Image Processing, 2017, 26(6): 28252838. ［19］ LI H, He X, YU Z, et al. Noiserobust image fusion with lowrank sparse decomposition guided by external patch prior［J］. Information Sciences, 2020, 523: 1437. ［20］ DE LANGE A M G, COLE J H. Commentary: correction procedures in brainage prediction［J］. Neuroimage: Clinical, 2020, 26:102229. ［21］ MOORE P J, LYONS T J, GALLACHER J, et al. Random forest prediction of Alzheimer′s disease using pairwise selection from time series data［J］. Plos One, 2019, 14(2): e0211558. ［22］ AYCHEH H M, SEONG J K, SHIN J H, et al. Biological brain age prediction using cortical thickness data: a large scale cohort study［J］. Frontiers in Aging Neuroscience, 2018, 10: 252. ［23］ LIAO L, ZHANG X, ZHAO F, et al. Multibranch deformable convolutional neural network with label distribution learning for fetal brain age prediction［C］//2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). Iowa City, United States: IEEE, 2020: 424427. ［24］ PENG H, GONG W, BECKMANN C F, et al. Accurate brain age prediction with lightweight deep neural networks［J］. Medical Image Analysis, 2021, 68: 101871. ［25］ HE S, PEREIRA D, PEREZ J D, et al. Multichannel attentionfusion neural network for brain age estimation:accuracy, generality, and interpretation with 16705 healthy MRIs across lifespan［J］. Medical Image Analysis, 2021, 72: 102091. |
| [1] | 闵海根,方煜坤,吴霞,王武祺. 网联交通环境下的车-车通信故障诊断方法[J]. 山东大学学报 (工学版), 2021, 51(6): 84-92. |
| [2] | 李崴,王者超,李术才,丁万涛,王琦,宗智,刘克奇. 哈尔滨地铁粉质黏土力学性质与超前支护方式[J]. 山东大学学报(工学版), 2018, 48(2): 61-71. |
| [3] | 于少伟,秦瑞伶,关京京,吉灿,封硕,姜锐,刘英宁. 利用通行能力余量的智能网联车队生态驾驶模型[J]. 山东大学学报 (工学版), 2022, 52(6): 23-29. |
|
||
