Advances in functional magnetic resonance imaging-based brain function mapping: a deep learning perspective

Abstract

Functional magnetic resonance imaging (fMRI) provides a powerful tool for studying brain function by capturing neural activity in a non-invasive manner. Mapping brain function from fMRI data enables researchers to investigate the spatial and temporal dynamics of neural processes, providing insights into how the brain responds to various tasks and stimuli. In this review, we explore the evolution of deep learning-based methods for brain function mapping using fMRI. We begin by discussing various network architectures such as convolutional neural networks, recurrent neural networks, and transformers. We further examine supervised, unsupervised, and self-supervised learning paradigms for fMRI-based brain function mapping, highlighting the strengths and limitations of each approach. Additionally, we discuss emerging trends such as fMRI embedding, brain foundation models, and brain-inspired artificial intelligence, emphasizing their potential to revolutionize brain function mapping. Finally, we delve into the real-world applications and prospective impact of these advancements, particularly in the diagnosis of neural disorders, neuroscientific research, and brain-computer interfaces for decoding brain activity. This review aims to provide a comprehensive overview of current techniques and future directions in the field of deep learning and fMRI-based brain function mapping.

Keywords

fMRI / brain function mapping / deep learning

Author contributions

Lin Zhao (Conceptualization, Data curation, Investigation, Methodology, Validation, Visualization, Writing—original draft, Writing—review & editing).

Conflict of interest

None declared.

References

[1] Achiam J, Adler S, Agarwal S, et al. (2023) Gpt-4 technical report. arXiv arXiv:2303.08774.

[2] Affolter N, Egressy B, Pascual D, et al. (2020) Brain2word: decoding brain activity for language generation. arXiv:2009.04765.

[3] Al-Hiyali MI, Yahya N, Faye I, et al. (2021) Classification of bold fmri signals using wavelet transform and transfer learning for detection of autism spectrum disorder. In 2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES) Piscataway, NJ: IEEE, 94-8.

[4] Bassett DS, Bullmore E. (2006) Small-world brain networks. Neurosci. 12:512-23.

[5] Belliveau JW, Kennedy DN, McKinstry RC, et al. (1991) Functional mapping of the human visual cortex by magnetic resonance imaging. Science. 254:716-9.

[6] Berezutskaya J, Freudenburg ZV, Vansteensel MJ, et al. (2023) Direct speech reconstruction from sensorimotor brain activity with optimized deep learning models. J Neural Eng. 20:056010.

[7] Biswal BB, Mennes M, Zuo X-N, et al. (2010) Toward discovery science of human brain function. Proc Natl Acad Sci. 107:4734-9.

[8] Brodmann K. (1909) Vergleichende Lokalisationslehre der Grosshirnrinde in Ihren Prinzipien Dargestellt auf Grund Des Zellenbaues. Barth: Leipzig.

[9] Calhoun VD, Adali T. (2006) Unmixing fmri with independent component analysis. IEEE Eng Med Biol Mag. 25:79-90.

[10] Calhoun VD, Liu J, Adalı T. (2009) A review of group ICA for fMRI data and ICA for joint inference of imaging, genetic, and ERP data. Neuroimage. 45:S163-72.

[11] Casanova R, Lyday RG, Bahrami M, et al. (2021) Embedding functional brain networks in low dimensional spaces using manifold learning techniques. Front Neuroinform. 15:740143.

[12] Caucheteux C, King J-R. (2022) Brains and algorithms partially converge in natural language processing. Commun Biol. 5:134.

[13] Chen Z, Qing J, Xiang T, et al. (2023) Seeing beyond the brain:conditional diffusion model with sparse masked modeling for vision decoding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, BC: IEEE, 22710-20.

[14] Cordes D, Haughton VM, Arfanakis K, et al. (2000) Mapping functionally related regions of brain with functional connectivity MR imaging. Am J Neuroradiol. 21:1636-44.

[15] Cui Y, Zhao S, Chen Y, et al. (2019) Modeling brain diverse and complex hemodynamic response patterns via deep recurrent autoencoder. IEEE Trans Cogn Dev Syst. 12:733-43.

[16] Cui Y, Zhao S, Wang H, et al. (2018a) Identifying brain networks at multiple time scales via deep recurrent neural network. IEEE J Biomed Health Inform. 23:2515-25.

[17] Cui Y, Zhao S, Wang H, et al. (2018b) Identifying brain networks of multiple time scales via deep recurrent neural network. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part III 11. Berlin: Springer, 284-92.

[18] Dai H, Ge F, Li Q, et al. (2020) Optimize CNN model for fMRI signal classification via adanet-based neural architecture search. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, 1399-403.

[19] Dai H, Li Q, Zhao L, et al. (2022) Graph representation neural architecture search for optimal spatial/temporal functional brain network decomposition. In International Workshop on Machine Learning in Medical Imaging. Berlin: Springer, 279-87.

[20] Défossez A, Caucheteux C, Rapin J, et al. (2023) Decoding speech perception from non-invasive brain recordings. Nat Mach Intell. 5:1097-107.

[21] Dong Q, Ge F, Ning Q, et al. (2019) Modeling hierarchical brain networks via volumetric sparse deep belief network. IEEE Trans Biomed Eng. 67:1739-48.

[22] Dong Q, Qiang N, Lv J, et al. (2020a) A novel fMRI representation learning framework with GAN. In Berlin Machine Learning in Medical Imaging: 11th International Workshop, MLMI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Proceedings 11. Springer, 21-9.

[23] Dong Q, Qiang N, Lv J, et al. (2020b) Discovering functional brain networks with 3D residual autoencoder (RESAE). In Medical Image Computing and Computer Assisted Intervention-MICCAI 2020: 23rd International Conference, Lima, Peru, October 4-8, 2020, Proceedings, Part VII 23. Berlin: Springer, 498-507.

[24] Dong Q, Qiang N, Lv J, et al. (2020c) Spatiotemporal attention autoencoder (STAAE) for ADHD classification. In Medical Image Computing and Computer Assisted Intervention—MICCAI 2020: 23rd International Conference, Lima, Peru, October 4-8, 2020, Proceedings, Part VII 23. Berlin: Springer, 508-17.

[25] Dosovitskiy A, Beyer L, Kolesnikov A, et al. (2020) An image is worth 16×16 words: transformers for image recognition at scale. arXiv:2010.11929.

[26] Du Y, Wang L, Guo L, et al. (2023) Topological similarity between artificial and biological neural networks. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, 1-5.

[27] Dubey A, Jauhri A, Pandey A, et al. (2024) The llama 3 herd of models. arXiv:2407.21783.

[28] Fang T, Qi Y, Pan G. (2020) Reconstructing perceptive images from brain activity by shape-semantic gan. Adv Neural Inf Process Syst. 33:13038-48.

[29] Friston KJ, Holmes AP, Worsley KJ, et al. (1994) Statistical parametric maps in functional imaging: a general linear approach. Hum Brain Mapp. 2:189-210.

[30] Gadgil S, Zhao Q, Pfefferbaum A, et al. (2020) Spatio-temporal graph convolution for resting-state fMRI analysis. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2020: 23rd International Conference, Lima, Peru, October 4-8, 2020, Proceedings, Part VII 23. Berlin: Springer, 528-38.

[31] Gauthier J, Ivanova A. (2018) Does the brain represent words? An evaluation of brain decoding studies of language understanding. arXiv:1806.00591.

[32] Goodfellow I, Bengio Y, Courville A. (2016). Deep Learning, Cambridge, MA: Press.

[33] He K, Chen X, Xie S, et al. (2022) Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, LA: IEEE, 16000-9.

[34] He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE, 770-8.

[35] Heeger DJ, Ress D. (2002) What does fMRI tell us about neuronal activity?. Nat Rev Neurosci. 3:142-51.

[36] Hinton GE, Salakhutdinov RR. (2006) Reducing the dimensionality of data with neural networks. Science. 313:504-7.

[37] Hinton GE. (2009) Deep belief networks. Scholarpedia. 4:5947.

[38] Hochreiter S, Schmidhuber J. (1997) Long short-term memory. Neural Comput. 9:1735-80.

[39] Hu X, Huang H, Peng B, et al. (2018) Latent source mining in fmri via restricted boltzmann machine. Hum Brain Mapp. 39:2368-80.

[40] Hu Y, Li W, Yuan Y, et al. (2025) Synthesizing realistic fMRI: a physiological dynamics-driven hierarchical diffusion model for efficient fmri acquisition. In The Thirteenth International Conference on Learning Representations.

[41] Huang H, Hu X, Dong Q, et al. (2018) Modeling task fMRI data via mixture of deep expert networks. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). Piscataway, NJ: IEEE, 82-6.

[42] Huang H, Hu X, Han J, et al. (2016) Latent source mining in fMRI data via deep neural network. In 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, 638-41.

[43] Huang H, Hu X, Zhao Y, et al. (2017) Modeling task fmri data via deep convolutional autoencoder. IEEE Trans Med Imaging. 37:1551-61.

[44] Jiang X, Yan J, Zhao Y, et al. (2023) Characterizing functional brain networks via spatio-temporal attention 4D convolutional neural networks (STA-4DCNNs). Neural Netw. 158:99-110.

[45] Kim P, Kwon J, Joo S, et al. (2023) Swift: Swin 4D fMRI transformer. Adv Neural Inf Process Syst. 36:42015-37.

[46] Kriegeskorte N. (2015) Deep neural networks: a new framework for modeling biological vision and brain information processing. Annu Rev Vis Sci. 1:417-46.

[47] LeCun Y, Bengio Y, et al. (1995) Convolutional networks for images, speech, and time series. BHB or HBBN. 3361:1995.

[48] LeCun Y, Bengio Y, Hinton G. (2015) Deep learning. Nature. 521:436-44.

[49] Li L, Hu X, Huang H, et al. (2018a) Latent source mining of fMRI data via deep belief network. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). Piscataway, NJ: IEEE, 595-8.

[50] Li Q, Dong Q, Ge F, et al. (2019) Simultaneous spatial-temporal decomposition of connectome-scale brain networks by deep sparse recurrent auto-encoders. In Information Processing in Medical Imaging:26th International Conference, IPMI 2019, Hong Kong, China, June 2-7, 2019, Proceedings 26. Berlin: Springer, 579-91.

[51] Li Q, Wu X, Liu T. (2021a) Differentiable neural architecture search for optimal spatial/temporal brain function network decomposition. Med Image Anal. 69:101974.

[52] Li Q, Zhang W, Lv J, et al. (2020) Neural architecture search for optimization of spatial-temporal brain network decomposition. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2020: 23rd International Conference, Lima, Peru, October 4-8, 2020, Proceedings, Part VII 23. Berlin: Springer, 377-86.

[53] Li Q, Zhang W, Zhao L, et al. (2021b) Evolutional neural architecture search for optimization of spatiotemporal brain network decomposition. IEEE Trans Biomed Eng. 69:624-34.

[54] Li Y, Anumanchipalli GK, Mohamed A, et al. (2023) Dissecting neural computations in the human auditory pathway using deep neural networks for speech. Nat Neurosci. 26:2213-25.

[55] Li Y, Huang H, Chen H, et al. (2018b) Deep neural networks for exploration of transcriptome of adult mouse brain. IEEE/ACM Trans Comput Biol Bioinf. 17: 2:536-46.

[56] Liu H, Simonyan K, Yang Y. (2018) Darts: differentiable architecture search. arXiv:1806.09055.

[57] Liu H, Zhang S, Jiang X, et al. (2019) The cerebral cortex is bisectionally segregated into two fundamentally different functional units of gyri and sulci. Cereb Cortex. 29:4238-52.

[58] Liu S, Wang S, Zhang H, et al. (2023a) An ASD classification based on a pseudo 4D resnet: utilizing spatial and temporal convolution. IEEE Syst Man Cybern Mag. 9:9-18.

[59] Liu X, Zhou M, Shi G, et al., (2023b) Coupling artificial neurons in bert and biological neurons in the human brain. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, Washington, DC: AAAI Press, 8888-96.

[60] Liu Y, Ge E, He M, et al. (2024a) Mapping dynamic spatial patterns of brain function with spatial-wise attention. J Neural Eng. 21:2:026005.

[61] Liu Y, Ge E, Kang Z, et al. (2024b) Spatial-temporal convolutional attention for discovering and characterizing functional brain networks in task fmri. Neuroimage. 287:120519.

[62] Liu Y, Ge E, Qiang N, et al. (2023c) Spatial-temporal convolutional attention for mapping functional brain networks. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). Cartagena, Colombia: IEEE, 1-4.

[63] Logothetis NK, Pauls J, Augath M, et al. (2001) Neurophysiological investigation of the basis of the fMRI signal. Nature. 412:150-7.

[64] Logothetis NK. (2008) What we can do and what we cannot do with fMRI. Nature. 453:869-78.

[65] Lv J, Jiang X, Li X, et al. (2014) Holistic atlases of functional networks and interactions reveal reciprocal organizational architecture of cortical function. IEEE Trans Biomed Eng. 62:1120-31.

[66] Lv J, Jiang X, Li X, et al. (2015) Sparse representation of whole-brain fmri signals for identification of functional networks. Med Image Anal. 20:112-34.

[67] Lyu Y, Wu Z, Zhang L, et al. (2024) GP-GPT: large language model for gene-phenotype mapping. arXiv:2409.09825.

[68] Makkie M, Huang H, Zhao Y, et al. (2019) Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics. Neurocomputing. 325:20-30.

[69] Malkiel I, Rosenman G, Wolf L, et al. (2022) Self-supervised transformers for fmri representation. In International Conference on Medical Imaging with Deep Learning. Zürich, Switzerland: PMLR, 895-913.

[70] Mao W, Chen Y, He Z, et al. (2024) Brain structural connectivity guided vision transformers for identification of functional connectivity characteristics in preterm neonates. IEEE J Biomed Health Inform. 28:2223-34.

[71] Mao Z, Su Y, Xu G, et al. (2019) Spatio-temporal deep learning method for ADHD fMRI classification. Inf Sci. 499:1-11.

[72] Millet J, Caucheteux C, Boubenec Y, et al. (2022) Toward a realistic model of speech processing in the brain with self-supervised learning. Adv Neural Inf Process Syst. 35:33428-43.

[73] O'Craven KM, Downing PE, Kanwisher N. (1999) fMRI evidence for objects as the units of attentional selection. Nature. 401:584-7.

[74] Oquab M, Darcet T, Moutakanni T, et al. (2023) Dinov2: learning robust visual features without supervision. arXiv:2304.07193.

[75] Ortega Caro J, Oliveira Fonseca AH, Averill C, et al. (2024) Brainlm: a foundation model for brain activity recordings. The Twelfth International Conference on Learning Representations, Vienna, Austria: ICLR 2024.

[76] Pang T, Zhao S, Han J, et al. (2022a) Gumbel- softmax based neural architecture search for hierarchical brain networks decomposition. Med Image Anal. 82:102570.

[77] Pang T, Zhu D, Liu T, et al. (2022b) Hierarchical brain networks decomposition via prior knowledge guided deep belief network. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 251-60.

[78] Pei S, Wang C, Cao S, et al. (2022) Data augmentation for fmri- based functional connectivity and its application to cross-site adhd classification. IEEE Trans Instrum Meas. 72:1-15.

[79] Power JD, Cohen AL, Nelson SM, et al. (2011) Functional network organization of the human brain. Neuron. 72:665-78.

[80] Qiang N, Dong Q, Liang H, et al. (2021) Modeling and augmenting of fmri data using deep recurrent variational auto-encoder. J Neural Eng. 18:0460b6.

[81] Qiang N, Dong Q, Liang H, et al. (2022) Learning brain representation using recurrent wasserstein generative adversarial net. Comput Methods Programs Biomed. 223:106979.

[82] Qiang N, Dong Q, Sun Y, et al. (2020a) Deep variational autoencoder for modeling functional brain networks and ADHD identification. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, 554-7.

[83] Qiang N, Dong Q, Zhang W, et al. (2020b) Modeling task-based fMRI data via deep belief network with neural architecture search. Comput Med Imaging Graph. 83:101747.

[84] Qiang N, Gao J, Dong Q, et al. (2023) Functional brain network identification and fMRI augmentation using a VAE-GAN framework. Comput Biol Med. 165:107395.

[85] Radford A, Narasimhan K, Salimans T, et al. (2018) Improving language understanding by generative pre-training. https://www.mikecaptain.com/resources/pdf/GPT-1.pdf

[86] Raichle ME, MacLeod AM, Snyder AZ, et al. (2001) A default mode of brain function. Proc Natl Acad Sci. 98:676-82.

[87] Ren D, Zhao Y, Chen H, et al. (2017) 3-D functional brain network classification using convolutional neural networks. In 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). Piscataway, NJ: IEEE, 1217-21.

[88] Ren Y, Tao Z, Zhang W, et al. (2021) Modeling hierarchical spatial and temporal patterns of naturalistic fMRI volume via volumetric deep belief network with neural architecture search. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, 130-4.

[89] Scarselli F, Gori M, Chung Tsoi Ah, et al. (2008) The graph neural network model. IEEE Trans Neural Netw. 20:61-80.

[90] Schrimpf M, Blank IA, Tuckute G, et al. (2021) The neural architecture of language: integrative modeling converges on predictive processing. Proc Natl Acad Sci. 118:e2105646118.

[91] Smucny J, Shi G, Lesh TA, et al. (2022) Data augmentation with mixup: enhancing performance of a functional neuroimaging-based prognostic deep learning classifier in recent onset psychosis. NeuroImage Clinical. 36:103214.

[92] Svanera M, Savardi M, Benini S, et al. (2019) Transfer learning of deep neural network representations for fMRI decoding. J Neurosci Methods. 328:108319.

[93] Takagi Y, Nishimoto S. (2023) High-resolution image reconstruction with latent diffusion models from human brain activity. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, BC: IEEE, 14453-63.

[94] Thomas A, R´e C, Poldrack R. (2022) Self-supervised learning of brain dynamics from broad neuroimaging data. Adv Neural Inf Process Syst. 35:21255-69.

[95] Van Den Heuvel MP, Hulshoff Pol HE. (2010) Exploring the brain network: a review on resting-state fMRI functional connectivity. Eur Neuropsychopharmacol. 20:519-34.

[96] Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. Adv Neural Inf Process Syst. 30, https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html

[97] Von Der Malsburg C. (1994) The correlation theory of brain function. In Models of Neural Networks:Temporal Aspects of Coding and Information Processing in Biological Systems. Berlin: Springer, 95-119.

[98] Wang H, Zhao S, Dong Q, et al. (2018) Recognizing brain states using deep sparse recurrent neural network. IEEE Trans Med Imaging. 38:1058-68.

[99] Wang L, Hu X, Liu H, et al. (2019) Explore the hierarchical auditory information processing via deep convolutional autoencoder. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). . Piscataway, NJ: IEEE, 1788-91.

[100] Wang L, Yang Y, Hu X, et al. (2024) Frequency-specific functional difference between gyri and sulci in naturalistic paradigm fmri. BS&F. 229:431-442.

[101] Wang Q, Zhao S, He Z, et al. (2023) Modeling functional difference between gyri and sulci within intrinsic connectivity networks. Cereb Cortex. 33:933-47.

[102] Worsley KJ. (1997) An overview and some new developments in the statistical analysis of pet and fmri data. Hum Brain Mapp. 5:254-8.

[103] Wu Z, Pan S, Chen F, et al. (2020) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learning Syst. 32:4-24.

[104] Yamins DL, DiCarlo JJ. (2016) Using goal-driven deep learning models to understand sensory cortex. Nat Neurosci. 19:356-65.

[105] Yan J, Chen Y, Xiao Z, et al. (2022) Modeling spatio-temporal patterns of holistic functional brain networks via multi-head guided attention graph neural networks (multi-head GAGNNs). Med Image Anal. 80:102518.

[106] Yan J, Chen Y, Yang S, et al. (2021a) Multi- head GAGNN: a multi-head guided attention graph neural network for modeling spatio-temporal patterns of holistic brain functional networks. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2021: 24th International Conference, Strasbourg, France, September 27- October 1, 2021, Proceedings, Part VII 24. Berlin: Springer, 564-73.

[107] Yan J, Zhao Y, Jiang M, et al. (2021b) A guided attention 4D convolutional neural network for modeling spatio-temporal patterns of functional brain networks. In Pattern Recognition and Computer Vision:4th Chinese Conference, PRCV 2021, Beijing, China, October 29-November 1, 2021, Proceedings, Part III 4. Berlin: Springer, 350-61.

[108] Yang Y, Mao Y, Liu X, et al. (2024) Brainmae: a region-aware self-supervised learning framework for brain signals. arXiv:2406.17086.

[109] Yu S, Shi E, Wang R, et al. (2022) A hybrid learning framework for fine-grained interpretation of brain spatiotemporal patterns during naturalistic functional magnetic resonance imaging. Front Hum Neurosci. 16:944543.

[110] Yu X, Wu Z, Zhang L, et al. (2024) Cp- clip:core-periphery feature alignment clip for zero-shot medical image analysis. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 88-97.

[111] Yu X, Zhang L, Dai H, et al. (2023a) Core-periphery principle guided redesign of self- attention in transformers. arXiv:2303.15569.

[112] Yu X, Zhang L, Dai H, et al. (2023b) Gyri vs. sulci: disentangling brain core-periphery functional networks via twin-transformer. arXiv:2302.00146

[113] Yu X, Zhang L, Lyu Y, et al. (2023c) Supervised deep tree in Alzheimer's disease. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, 1-5.

[114] Yuan J, Li X, Zhang J, et al. (2018) Spatio-temporal modeling of connectome-scale brain network interactions via time-evolving graphs. Neuroimage. 180:350-69.

[115] Zhang H, Chen P-H, Ramadge P. (2018a) Transfer learning on fmri datasets. In International Conference on Artificial Intelligence and Statistics. PMLR, 595-603.

[116] Zhang L, Wang L, Gao J, et al. (2021a) Deep fusion of brain structure- function in mild cognitive impairment. Med Image Anal. 72:102082.

[117] Zhang L, Wang L, Liu T, et al. (2021b) Disease2vec: representing Alzheimer's progression via disease embedding tree. arXiv:2102.06847.

[118] Zhang L, Yu X, Lyu Y, et al. (2023) Representative functional connectivity learning for multiple clinical groups in Alzheimer's disease. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). Piscataway, NJ: IEEE, 1-5.

[119] Zhang S, Dong Q, Zhang W, et al. (2019a) Discovering hierarchical common brain networks via multimodal deep belief network. Med Image Anal. 54:238-52.

[120] Zhang S, Liu H, Huang H, et al. (2018b) Deep learning models unveiled functional difference between cortical gyri and sulci. IEEE Trans Biomed Eng. 66:1297-308.

[121] Zhang W, Zhao L, Li Q, et al. (2019b) Identify hierarchical structures from task-based fMRI data via hybrid spatiotemporal neural architecture search net. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13-17, 2019, Proceedings, Part III 22. Berlin: Springer, 745-53.

[122] Zhang Y, Hu X, He C, et al. (2019c) A two-stage DBN-based method to exploring functional brain networks in naturalistic paradigm fMRI. In 2019 Ieee 16th International Symposium on Biomedical Imaging (Isbi 2019). Piscataway, NJ: IEEE, 1594-7.

[123] Zhao L, Dai H, Jiang X, et al. (2021) Exploring the functional difference of gyri/sulci via hierarchical interpretable autoencoder. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2021: 24th International Conference, Strasbourg, France, September 27- October 1, 2021, Proceedings, Part VII 24. Berlin: Springer, 701-9.

[124] Zhao L, Dai H, Wu Z, et al. (2023a) Coupling visual semantics of artificial neural networks and human brain function via synchronized activations. IEEE Trans Cogn Dev Syst. 16:584-94.

[125] Zhao L, Dai H, Wu Z, et al. (2023b) CP-CNN: core- periphery principle guided convolutional neural network. arXiv:2304.10515.

[126] Zhao L, Dai H, Wu Z, et al. (2024) Hierarchical functional differences between gyri and sulci at different scales. Cereb Cortex. 34:bhae057.

[127] Zhao L, Wu Z, Dai H, et al. (2022) Embedding human brain function via Transformer. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 366-75.

[128] Zhao L, Wu Z, Dai H, et al. (2023c) A generic framework for embedding human brain function with temporally correlated autoencoder. Med Image Anal. 89:102892.

[129] Zhao L, Zhang L, Wu Z, et al. (2023d) When brain-inspired AI meets AGI. Meta-Radiology. 1:100005,

[130] Zhao Y, Dai H, Zhang W, et al. (2019) Two-stage spatial temporal deep learning framework for functional brain network modeling. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). Venice, Italy: IEEE, 1576-80.

[131] Zhao Y, Dong Q, Chen H, et al. (2017a) Constructing fine-granularity functional brain network atlases via deep convolutional autoencoder. Med Image Anal. 42:200-11.

[132] Zhao Y, Dong Q, Zhang S, et al. (2017b) Automatic recognition of fMRI-derived functional networks using 3-D convolutional neural networks. IEEE Trans Biomed Eng. 65:1975-84.

[133] Zhao Y, Ge F, Liu T. (2018a) Automatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initialization. Med Image Anal. 47:111-26.

[134] Zhao Y, Ge F, Zhang S, et al. (2018b) 3D deep convolutional neural network revealed the value of brain network overlap in differentiating autism spectrum disorder from healthy controls. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part III 11. Berlin: Springer, 172-80.

[135] Zhao Y, Li X, Zhang W, et al. (2018c) Modeling 4D fMRI data via spatio-temporal convolutional neural networks (ST-CNN). In Medical Image Computing and Computer Assisted Intervention—MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part III 11. Berlin: Springer, 181-9.

[136] Zhou M, Liu X, Liu D, et al. (2023) Fine-grained artificial neurons in audio-transformers for disentangling neural auditory encoding. In Findings of the Association for Computational Linguistics: ACL 2023. Toronto, Canada: Association for Computational Linguistics, 7943-56.

[137] Zhuang P, Schwing AG, Koyejo O. (2019) FMRI data augmentation via synthesis. In 2019 IEEE 16th International symposium on Biomedical Imaging (ISBI 2019). Venice, Italy: IEEE, 1783-7.

[138] Zoph B, Le QV. (2016) Neural architecture search with reinforcement learning. arXiv:1611.01578.