面向自闭症辅助诊断的深度对比模糊神经网络

doi:10.19678/j.issn.1000-3428.0063521

摘要/Abstract

摘要： 静息态功能磁共振成像（rs-fMRI）可有效反映大脑活动状况，然而rs-fMRI数据的高随机性和自闭症谱系障碍（ASD）内在的高异质性给ASD计算机辅助诊断带来了不确定性。提出一种基于对比损失的Takagi-Sugeno-Kang （TSK）深度模糊神经网络CL-DeepTSK，结合多输出TSK （MO-TSK）模糊系统与多层感知机（MLP）有效缓解数据不确定性对模型的影响，提升TSK模糊系统的表达能力，并使模型更具可解释性。使用对比损失目标学习准则对MO-TSK与MLP进行联合优化，提高训练样本缺乏时的模型泛化性能。在ABIDE数据集上的实验结果表明，CL-DeepTSK的平均正确率和AUC指标分别达到70.0%和0.773，同时获得了30个最具鉴别性的功能连接。上述实验结果证明了CL-DeepTSK能够有效地进行自闭症辅助诊断，并且具有较高的可解释性。

关键词: 自闭症谱系障碍, 静息态功能性磁共振成像, Takagi-Sugeno-Kang模糊系统, 对比损失, 计算机辅助诊断

Abstract: Resting-state functional Magnetic Resonance Imaging(rs-fMRI) can effectively reflect brain activity.However, the high randomness in rs-fMRI data and high heterogeneity in autism cases cause high uncertainty in the diagnosis of Autism Spectrum Disorder(ASD). Hence, this study integrates a fuzzy system with a deep neural network and proposes a Takagi-Sugeno-Kang(TSK) deep fuzzy neural network based on Comparative Loss(CL), which is abbreviated as CL-DeepTSK.CL-DeepTSK combines the Multi-Output TSK(MO-TSK) fuzzy system with a Multilayer Perceptron(MLP), which effectively reduces the effect of data uncertainty on the model, improves the expression ability of the TSK fuzzy system, and renders the model interpretable. Additionally, MO-TSK and MLP are jointly optimized using a novel CL objective-learning criterion, which improves the generalization performance of the model when the training samples are insufficient. For the Autism Brain Imaging Data Exchange(ABIDE) dataset, the accuracy and Area Under Curve(AUC) of the CL-DeepTSK are 70.0% and 0.77, respectively, and the 30 most discriminative functional connections are obtained. Experimental results show that the proposed CL-DeepTSK model can be effective and interpretable for the auxiliary diagnosis of ASD.

Key words: Autism Spectrum Disorder(ASD), resting state functional Magnetic Resonance Imaging(rs-fMRI), Takagi-Sugeno-Kang(TSK) fuzzy system, Comparative Loss(CL), computer aided diagnosis

中图分类号:

TP391.4

陆昭吾, 王骏, 施俊. 面向自闭症辅助诊断的深度对比模糊神经网络[J]. 计算机工程, 2023, 49(4): 263-271.

LU Zhaowu, WANG Jun, SHI Jun. Deep Contrastive Fuzzy Neural Network for Aided Diagnosis of Autism[J]. Computer Engineering, 2023, 49(4): 263-271.

https://www.ecice06.com/CN/Y2023/V49/I4/263

图/表 6

20230417190309

20230417190312

20230417190315

20230417190319

20230417190322

20230417190325

参考文献

[1] PARK H R, LEE J M, MOON H E, et al.A short review on the current understanding of autism spectrum disorders[J].Experimental Neurobiology, 2016, 25(1):1-13.
[2] RICE C.Prevalence of autism spectrum disorders-autism and developmental disabilities monitoring network, United States, 2006[J].Morbidity and Mortality Weekly Report Surveillance Summaries, 2009, 58(10):1-20.
[3] BAIO J, WIGGINS L, CHRISTENSEN D L, et al.Prevalence of autism spectrum disorder among children aged 8 years-autism and developmental disabilities monitoring network, 11 sites, United States, 2014[J].Morbidity and Mortality Weekly Report Surveillance Summaries, 2018, 67(6):1-23.
[4] WANG F, LU L, WANG S B, et al.The prevalence of autism spectrum disorders in China:a comprehensive meta-analysis[J].International Journal of Biological Sciences, 2018, 14(7):717-725.
[5] LORD C, BRUGHA T S, CHARMAN T, et al.Autism spectrum disorder[J].Nature Reviews Disease Primers, 2020, 6:5.
[6] LÜ H, WANG Z, TONG E, et al.Resting-state functional MRI:everything that nonexperts have always wanted to know[J].AJNR American Journal of Neuroradiology, 2018, 39(8):1390-1399.
[7] HULL J V, DOKOVNA L B, JACOKES Z J, et al.Resting-state functional connectivity in autism spectrum disorders:a review[J].Frontiers in Psychiatry, 2016, 7:205.
[8] DE ZWART J A, GELDEREN P V, FUKUNAGA M, et al.Reducing correlated noise in fMRI data[J].Magnetic Resonance in Medicine, 2008, 59(4):939-945.
[9] LUND T E.Non-white noise in fMRI:does modelling have an impact?[J].NeuroImage, 2006, 29(1):54-66.
[10] DENG Z H, CHOI K S, CHUNG F L, et al.Scalable TSK fuzzy modeling for very large datasets using minimal-enclosing-ball approximation[J].IEEE Transactions on Fuzzy Systems, 2011, 19(2):210-226.
[11] HU Z Y, WANG J, ZHANG C X, et al.Uncertainty modeling for multicenter autism spectrum disorder classification using Takagi-Sugeno-Kang fuzzy systems[J].IEEE Transactions on Cognitive and Developmental Systems, 2022, 14(2):730-739.
[12] TURNER B O, PAUL E J, MILLER M B, et al.Small sample sizes reduce the replicability of task-based fMRI studies[J].Communications Biology, 2018, 1:62.
[13] TAKAGI T, SUGENO M.Fuzzy identification of systems and its applications to modeling and control[J].IEEE Transactions on Systems, Man, and Cybernetics, 1985, SMC-15(1):116-132.
[14] XU P, DENG Z H, CUI C, et al.Concise fuzzy system modeling integrating soft subspace clustering and sparse learning[J].IEEE Transactions on Fuzzy Systems, 2019, 27(11):2176-2189.
[15] GU X Q, CHUNG F L, ISHIBUCHI H, et al.Imbalanced TSK fuzzy classifier by cross-class Bayesian fuzzy clustering and imbalance learning[J].IEEE Transactions on Systems, Man, and Cybernetics, 2017, 47(8):2005-2020.
[16] CERVANTES J, YU W, SALAZAR S, et al.Takagi-Sugeno dynamic neuro-fuzzy controller of uncertain nonlinear systems[J].IEEE Transactions on Fuzzy Systems, 2017, 25(6):1601-1615.
[17] DENG Z H, XU P, XIE L X, et al.Transductive joint-knowledge-transfer TSK FS for recognition of epileptic EEG signals[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26(8):1481-1494.
[18] WANG J, ZHANG Y, ZHOU T, et al.Interpretable feature learning using multi-output Takagi-Sugeno-Kang fuzzy system for multi-center ASD diagnosis[M].Berlin, Germany:Springer, 2019.
[19] KARIMU R Y, AZADI S.Diagnosing the ADHD using a mixture of expert fuzzy models[J].International Journal of Fuzzy Systems, 2018, 20(4):1282-1296.
[20] WANG G M.A sparse deep belief network with efficient fuzzy learning framework[J].Neural Networks, 2020, 121:430-440.
[21] SHABAN W M.Detecting COVID-19 patients based on fuzzy inference engine and deep neural network[J].Applied Soft Computing, 2021, 99:106906.
[22] LIU X, ZHANG F J, HOU Z Y, et al.Self-supervised learning:generative or contrastive[J].IEEE Transactions on Knowledge and Data Engineering, 2023, 35(1):857-876.
[23] FANG H C, WANG S C, ZHOU M, et al.CERT:contrastive self-supervised learning for language understanding[EB/OL].[2021-11-04].https://arxiv.org/abs/2005.12766.
[24] CHEN T, KORNBLITH S, NOROUZI M, et al.A simple framework for contrastive learning of visual representations[EB/OL].[2021-11-04].https://arxiv.org/abs/2002.05709.
[25] DUNN J C.A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters[J].Journal of Cybernetics, 1973, 3(3):32-57.
[26] WINKLER R, KLAWONN F, KRUSE R.Fuzzy C-means in high dimensional spaces[J].International Journal of Fuzzy System Applications, 2011, 1(1):1-16.
[27] WANG Z W, LIU C Y, CHENG D P, et al.Automated detection of clinically significant prostate cancer in mp-MRI images based on an end-to-end deep neural network[J].IEEE Transactions on Medical Imaging, 2018, 37(5):1127-1139.
[28] DI MARTINO A, YAN C G, LI Q, et al.The autism brain imaging data exchange:towards a large-scale evaluation of the intrinsic brain architecture in autism[J].Molecular Psychiatry, 2014, 19(6):659-667.
[29] HE K M, ZHANG X Y, REN S Q, et al.Delving deep into rectifiers:surpassing human-level performance on ImageNet classification[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2015:1026-1034.
[30] CORTES C, VAPNIK V.Support-vector networks[J].Machine Learning, 1995, 20(3):273-297.
[31] CUTLER A, CUTLER D R, STEVENS J R.Random forests[M].Berlin, Germany:Springer, 2012.
[32] DOMINGOS P M, PAZZANI M.On the optimality of the simple Bayesian classifier under zero-one loss[J].Machine Learning, 1997, 29:103-130.
[33] HINTON G E, SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science, 2006, 313(5786):504-507.
[34] NG A.Sparse autoencoder[EB/OL].[2021-11-04].https://www.doc88.com/p-3562925983842.html.
[35] JANG J S.ANFIS:adaptive-network-based fuzzy inference system[J].IEEE Transactions on Systems, Man, and Cybernetics, 1993, 23(3):665-685.
[36] JUANG C F, CHIU S H, SHIU S J.Fuzzy system learned through fuzzy clustering and support vector machine for human skin color segmentation[J].IEEE Transactions on Systems, Man, and Cybernetics, 2007, 37(6):1077-1087.
[37] DENG Y, REN Z Q, KONG Y Y, et al.A hierarchical fused fuzzy deep neural network for data classification[J].IEEE Transactions on Fuzzy Systems, 2017, 25(4):1006-1012.

选择文件类型/文献管理软件名称

选择包含的内容