1
|
Zheng J, Teoh HK, Delco ML, Bonassar LJ, Cohen I. Application of a variational autoencoder for clustering and analyzing in situ articular cartilage cellular response to mechanical stimuli. PLoS One 2024; 19:e0297947. [PMID: 38768116 PMCID: PMC11104615 DOI: 10.1371/journal.pone.0297947] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Accepted: 01/16/2024] [Indexed: 05/22/2024] Open
Abstract
In various biological systems, analyzing how cell behaviors are coordinated over time would enable a deeper understanding of tissue-scale response to physiologic or superphysiologic stimuli. Such data is necessary for establishing both normal tissue function and the sequence of events after injury that lead to chronic disease. However, collecting and analyzing these large datasets presents a challenge-such systems are time-consuming to process, and the overwhelming scale of data makes it difficult to parse overall behaviors. This problem calls for an analysis technique that can quickly provide an overview of the groups present in the entire system and also produce meaningful categorization of cell behaviors. Here, we demonstrate the application of an unsupervised method-the Variational Autoencoder (VAE)-to learn the features of cells in cartilage tissue after impact-induced injury and identify meaningful clusters of chondrocyte behavior. This technique quickly generated new insights into the spatial distribution of specific cell behavior phenotypes and connected specific peracute calcium signaling timeseries with long term cellular outcomes, demonstrating the value of the VAE technique.
Collapse
Affiliation(s)
- Jingyang Zheng
- Department of Physics, Cornell University, Ithaca, NY, United States of America
| | - Han Kheng Teoh
- Department of Physics, Cornell University, Ithaca, NY, United States of America
| | - Michelle L. Delco
- College of Veterinary Medicine, Cornell University, Ithaca, NY, United States of America
| | - Lawrence J. Bonassar
- Meinig School of Biomedical Engineering, Cornell University, Ithaca, NY, United States of America
- Sibley School of Mechanical and Aerospace Engineering, Cornell University, Ithaca, NY, United States of America
| | - Itai Cohen
- Department of Physics, Cornell University, Ithaca, NY, United States of America
| |
Collapse
|
2
|
Markow ZE, Tripathy K, Svoboda AM, Schroeder ML, Rafferty SM, Richter EJ, Eggebrecht AT, Anastasio MA, Chevillet MA, Mugler EM, Naufel SN, Yin A, Trobaugh JW, Culver JP. Identifying Naturalistic Movies from Human Brain Activity with High-Density Diffuse Optical Tomography. bioRxiv 2024:2023.11.27.566650. [PMID: 38076976 PMCID: PMC10705261 DOI: 10.1101/2023.11.27.566650] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/31/2024]
Abstract
Modern neuroimaging modalities, particularly functional MRI (fMRI), can decode detailed human experiences. Thousands of viewed images can be identified or classified, and sentences can be reconstructed. Decoding paradigms often leverage encoding models that reduce the stimulus space into a smaller yet generalizable feature set. However, the neuroimaging devices used for detailed decoding are non-portable, like fMRI, or invasive, like electrocorticography, excluding application in naturalistic use. Wearable, non-invasive, but lower-resolution devices such as electroencephalography and functional near-infrared spectroscopy (fNIRS) have been limited to decoding between stimuli used during training. Herein we develop and evaluate model-based decoding with high-density diffuse optical tomography (HD-DOT), a higher-resolution expansion of fNIRS with demonstrated promise as a surrogate for fMRI. Using a motion energy model of visual content, we decoded the identities of novel movie clips outside the training set with accuracy far above chance for single-trial decoding. Decoding was robust to modulations of testing time window, different training and test imaging sessions, hemodynamic contrast, and optode array density. Our results suggest that HD-DOT can translate detailed decoding into naturalistic use.
Collapse
|
3
|
Dado T, Papale P, Lozano A, Le L, Wang F, van Gerven M, Roelfsema P, Güçlütürk Y, Güçlü U. Brain2GAN: Feature-disentangled neural encoding and decoding of visual perception in the primate brain. PLoS Comput Biol 2024; 20:e1012058. [PMID: 38709818 PMCID: PMC11098503 DOI: 10.1371/journal.pcbi.1012058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2023] [Revised: 05/16/2024] [Accepted: 04/08/2024] [Indexed: 05/08/2024] Open
Abstract
A challenging goal of neural coding is to characterize the neural representations underlying visual perception. To this end, multi-unit activity (MUA) of macaque visual cortex was recorded in a passive fixation task upon presentation of faces and natural images. We analyzed the relationship between MUA and latent representations of state-of-the-art deep generative models, including the conventional and feature-disentangled representations of generative adversarial networks (GANs) (i.e., z- and w-latents of StyleGAN, respectively) and language-contrastive representations of latent diffusion networks (i.e., CLIP-latents of Stable Diffusion). A mass univariate neural encoding analysis of the latent representations showed that feature-disentangled w representations outperform both z and CLIP representations in explaining neural responses. Further, w-latent features were found to be positioned at the higher end of the complexity gradient which indicates that they capture visual information relevant to high-level neural activity. Subsequently, a multivariate neural decoding analysis of the feature-disentangled representations resulted in state-of-the-art spatiotemporal reconstructions of visual perception. Taken together, our results not only highlight the important role of feature-disentanglement in shaping high-level neural representations underlying visual perception but also serve as an important benchmark for the future of neural coding.
Collapse
Affiliation(s)
- Thirza Dado
- Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands
| | - Paolo Papale
- Department of Vision and Cognition, Netherlands Institute for Neuroscience, Amsterdam, Netherlands
| | - Antonio Lozano
- Department of Vision and Cognition, Netherlands Institute for Neuroscience, Amsterdam, Netherlands
| | - Lynn Le
- Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands
| | - Feng Wang
- Department of Vision and Cognition, Netherlands Institute for Neuroscience, Amsterdam, Netherlands
| | - Marcel van Gerven
- Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands
| | - Pieter Roelfsema
- Department of Vision and Cognition, Netherlands Institute for Neuroscience, Amsterdam, Netherlands
- Laboratory of Visual Brain Therapy, Sorbonne University, Paris, France
- Department of Integrative Neurophysiology, VU Amsterdam, Amsterdam, Netherlands
- Department of Psychiatry, Amsterdam UMC, Amsterdam, Netherlands
| | - Yağmur Güçlütürk
- Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands
| | - Umut Güçlü
- Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands
| |
Collapse
|
4
|
Li R, Li J, Wang C, Liu H, Liu T, Wang X, Zou T, Huang W, Yan H, Chen H. Multi-Semantic Decoding of Visual Perception with Graph Neural Networks. Int J Neural Syst 2024; 34:2450016. [PMID: 38372016 DOI: 10.1142/s0129065724500163] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/20/2024]
Abstract
Constructing computational decoding models to account for the cortical representation of semantic information plays a crucial role in understanding visual perception. The human visual system processes interactive relationships among different objects when perceiving the semantic contents of natural visions. However, the existing semantic decoding models commonly regard categories as completely separate and independent visually and semantically and rarely consider the relationships from prior information. In this work, a novel semantic graph learning model was proposed to decode multiple semantic categories of perceived natural images from brain activity. The proposed model was validated on the functional magnetic resonance imaging data collected from five normal subjects while viewing 2750 natural images comprising 52 semantic categories. The results showed that the Graph Neural Network-based decoding model achieved higher accuracies than other deep neural network models. Moreover, the co-occurrence probability among semantic categories showed a significant correlation with the decoding accuracy. Additionally, the results suggested that semantic content organized in a hierarchical way with higher visual areas was more closely related to the internal visual experience. Together, this study provides a superior computational framework for multi-semantic decoding that supports the visual integration mechanism of semantic processing.
Collapse
Affiliation(s)
- Rong Li
- The Center of Psychosomatic Medicine, Sichuan Provincial Center for Mental Health, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Jiyi Li
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Chong Wang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Haoxiang Liu
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Tao Liu
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Xuyang Wang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Ting Zou
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Wei Huang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Hongmei Yan
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| | - Huafu Chen
- The Center of Psychosomatic Medicine, Sichuan Provincial Center for Mental Health, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
- MOE Key Lab for Neuroinformation, High-Field Magnetic Resonance Brain Imaging, Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, P. R. China
| |
Collapse
|
5
|
Csore J, Roy TL, Wright G, Karmonik C. Unsupervised classification of multi-contrast magnetic resonance histology of peripheral arterial disease lesions using a convolutional variational autoencoder with a Gaussian mixture model in latent space: A technical feasibility study. Comput Med Imaging Graph 2024; 115:102372. [PMID: 38581959 DOI: 10.1016/j.compmedimag.2024.102372] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Revised: 02/09/2024] [Accepted: 03/18/2024] [Indexed: 04/08/2024]
Abstract
PURPOSE To investigate the feasibility of a deep learning algorithm combining variational autoencoder (VAE) and two-dimensional (2D) convolutional neural networks (CNN) for automatically quantifying hard tissue presence and morphology in multi-contrast magnetic resonance (MR) images of peripheral arterial disease (PAD) occlusive lesions. METHODS Multi-contrast MR images (T2-weighted and ultrashort echo time) were acquired from lesions harvested from six amputated legs with high isotropic spatial resolution (0.078 mm and 0.156 mm, respectively) at 9.4 T. A total of 4014 pseudo-color combined images were generated, with 75% used to train a VAE employing custom 2D CNN layers. A Gaussian mixture model (GMM) was employed to classify the latent space data into four tissue classes: I) concentric calcified (c), II) eccentric calcified (e), III) occluded with hard tissue (h) and IV) occluded with soft tissue (s). Test image probabilities, encoded by the trained VAE were used to evaluate model performance. RESULTS GMM component classification probabilities ranged from 0.92 to 0.97 for class (c), 1.00 for class (e), 0.82-0.95 for class (h) and 0.56-0.93 for the remaining class (s). Due to the complexity of soft-tissue lesions reflected in the heterogeneity of the pseudo-color images, more GMM components (n=17) were attributed to class (s), compared to the other three (c, e and h) (n=6). CONCLUSION Combination of 2D CNN VAE and GMM achieves high classification probabilities for hard tissue-containing lesions. Automatic recognition of these classes may aid therapeutic decision-making and identifying uncrossable lesions prior to endovascular intervention.
Collapse
Affiliation(s)
- Judit Csore
- DeBakey Heart and Vascular Center, Houston Methodist Hospital, 6565 Fannin Street, Houston, TX 77030, USA; Heart and Vascular Center, Semmelweis University, 68 Városmajor Street, Budapest 1122, Hungary.
| | - Trisha L Roy
- DeBakey Heart and Vascular Center, Houston Methodist Hospital, 6565 Fannin Street, Houston, TX 77030, USA
| | - Graham Wright
- Sunnybrook Research Institute, 2075 Bayview Avenue, Toronto, Ontario M4N 3M5, Canada
| | - Christof Karmonik
- MRI Core, Translational Imaging Center, Houston Methodist Research Institute, 6670 Bertner Avenue, Houston, TX 77030, USA
| |
Collapse
|
6
|
Koide-Majima N, Nishimoto S, Majima K. Mental image reconstruction from human brain activity: Neural decoding of mental imagery via deep neural network-based Bayesian estimation. Neural Netw 2024; 170:349-363. [PMID: 38016230 DOI: 10.1016/j.neunet.2023.11.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2023] [Revised: 09/22/2023] [Accepted: 11/08/2023] [Indexed: 11/30/2023]
Abstract
Visual images observed by humans can be reconstructed from their brain activity. However, the visualization (externalization) of mental imagery is challenging. Only a few studies have reported successful visualization of mental imagery, and their visualizable images have been limited to specific domains such as human faces or alphabetical letters. Therefore, visualizing mental imagery for arbitrary natural images stands as a significant milestone. In this study, we achieved this by enhancing a previous method. Specifically, we demonstrated that the visual image reconstruction method proposed in the seminal study by Shen et al. (2019) heavily relied on low-level visual information decoded from the brain and could not efficiently utilize the semantic information that would be recruited during mental imagery. To address this limitation, we extended the previous method to a Bayesian estimation framework and introduced the assistance of semantic information into it. Our proposed framework successfully reconstructed both seen images (i.e., those observed by the human eye) and imagined images from brain activity. Quantitative evaluation showed that our framework could identify seen and imagined images highly accurately compared to the chance accuracy (seen: 90.7%, imagery: 75.6%, chance accuracy: 50.0%). In contrast, the previous method could only identify seen images (seen: 64.3%, imagery: 50.4%). These results suggest that our framework would provide a unique tool for directly investigating the subjective contents of the brain such as illusions, hallucinations, and dreams.
Collapse
Affiliation(s)
- Naoko Koide-Majima
- Center for Information and Neural Networks (CiNet), National Institute of Information and Communications Technology, Osaka 565-0871, Japan; Graduate School of Frontier Biosciences, Osaka University, Osaka 565-0871, Japan
| | - Shinji Nishimoto
- Center for Information and Neural Networks (CiNet), National Institute of Information and Communications Technology, Osaka 565-0871, Japan; Graduate School of Frontier Biosciences, Osaka University, Osaka 565-0871, Japan; Graduate School of Medicine, Osaka University, Osaka 565-0871, Japan
| | - Kei Majima
- Institute for Quantum Life Science, National Institutes for Quantum Science and Technology, Chiba 263-8555, Japan; JST PRESTO, Saitama 332-0012, Japan.
| |
Collapse
|
7
|
Soulos P, Isik L. Disentangled deep generative models reveal coding principles of the human face processing network. PLoS Comput Biol 2024; 20:e1011887. [PMID: 38408105 PMCID: PMC10919870 DOI: 10.1371/journal.pcbi.1011887] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2023] [Revised: 03/07/2024] [Accepted: 02/02/2024] [Indexed: 02/28/2024] Open
Abstract
Despite decades of research, much is still unknown about the computations carried out in the human face processing network. Recently, deep networks have been proposed as a computational account of human visual processing, but while they provide a good match to neural data throughout visual cortex, they lack interpretability. We introduce a method for interpreting brain activity using a new class of deep generative models, disentangled representation learning models, which learn a low-dimensional latent space that "disentangles" different semantically meaningful dimensions of faces, such as rotation, lighting, or hairstyle, in an unsupervised manner by enforcing statistical independence between dimensions. We find that the majority of our model's learned latent dimensions are interpretable by human raters. Further, these latent dimensions serve as a good encoding model for human fMRI data. We next investigate the representation of different latent dimensions across face-selective voxels. We find that low- and high-level face features are represented in posterior and anterior face-selective regions, respectively, corroborating prior models of human face recognition. Interestingly, though, we find identity-relevant and irrelevant face features across the face processing network. Finally, we provide new insight into the few "entangled" (uninterpretable) dimensions in our model by showing that they match responses in the ventral stream and carry information about facial identity. Disentangled face encoding models provide an exciting alternative to standard "black box" deep learning approaches for modeling and interpreting human brain data.
Collapse
Affiliation(s)
- Paul Soulos
- Department of Cognitive Science, Johns Hopkins University, Baltimore, Maryland, United States of America
| | - Leyla Isik
- Department of Cognitive Science, Johns Hopkins University, Baltimore, Maryland, United States of America
| |
Collapse
|
8
|
Endo Y, Takeda K. Performance Evaluation of Matrix Factorization for fMRI Data. Neural Comput 2023; 36:128-150. [PMID: 38052077 DOI: 10.1162/neco_a_01628] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2023] [Accepted: 09/21/2023] [Indexed: 12/07/2023]
Abstract
A hypothesis in the study of the brain is that sparse coding is realized in information representation of external stimuli, which has been experimentally confirmed for visual stimulus recently. However, unlike the specific functional region in the brain, sparse coding in information processing in the whole brain has not been clarified sufficiently. In this study, we investigate the validity of sparse coding in the whole human brain by applying various matrix factorization methods to functional magnetic resonance imaging data of neural activities in the brain. The result suggests the sparse coding hypothesis in information representation in the whole human brain, because extracted features from the sparse matrix factorization (MF) method, sparse principal component analysis (SparsePCA), or method of optimal directions (MOD) under a high sparsity setting or an approximate sparse MF method, fast independent component analysis (FastICA), can classify external visual stimuli more accurately than the nonsparse MF method or sparse MF method under a low sparsity setting.
Collapse
Affiliation(s)
- Yusuke Endo
- Department of Mechanical Systems Engineering, Graduate School of Science and Engineering, Ibaraki University, Ibaraki 316-8511, Japan
| | - Koujin Takeda
- Department of Mechanical Systems Engineering, Graduate School of Science and Engineering, Ibaraki University, Ibaraki 316-8511, Japan
| |
Collapse
|
9
|
Rastegarnia S, St-Laurent M, DuPre E, Pinsard B, Bellec P. Brain decoding of the Human Connectome Project tasks in a dense individual fMRI dataset. Neuroimage 2023; 283:120395. [PMID: 37832707 DOI: 10.1016/j.neuroimage.2023.120395] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 09/21/2023] [Accepted: 09/27/2023] [Indexed: 10/15/2023] Open
Abstract
Brain decoding aims to infer cognitive states from patterns of brain activity. Substantial inter-individual variations in functional brain organization challenge accurate decoding performed at the group level. In this paper, we tested whether accurate brain decoding models can be trained entirely at the individual level. We trained several classifiers on a dense individual functional magnetic resonance imaging (fMRI) dataset for which six participants completed the entire Human Connectome Project (HCP) task battery >13 times over ten separate fMRI sessions. We evaluated nine decoding methods, from Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP) to Graph Convolutional Neural Networks (GCN). All decoders were trained to classify single fMRI volumes into 21 experimental conditions simultaneously, using ∼7 h of fMRI data per participant. The best prediction accuracies were achieved with GCN and MLP models, whose performance (57-67 % accuracy) approached state-of-the-art accuracy (76 %) with models trained at the group level on >1 K hours of data from the original HCP sample. Our SVM model also performed very well (54-62 % accuracy). Feature importance maps derived from MLP -our best-performing model- revealed informative features in regions relevant to particular cognitive domains, notably in the motor cortex. We also observed that inter-subject classification achieved substantially lower accuracy than subject-specific models, indicating that our decoders learned individual-specific features. This work demonstrates that densely-sampled neuroimaging datasets can be used to train accurate brain decoding models at the individual level. We expect this work to become a useful benchmark for techniques that improve model generalization across multiple subjects and acquisition conditions.
Collapse
Affiliation(s)
- Shima Rastegarnia
- Université de Montréal, Montréal, QC, Canada; Centre de Recherche de L'Institut Universitaire de Gériatrie de Montréal, Montréal, Canada.
| | - Marie St-Laurent
- Centre de Recherche de L'Institut Universitaire de Gériatrie de Montréal, Montréal, Canada
| | | | - Basile Pinsard
- Centre de Recherche de L'Institut Universitaire de Gériatrie de Montréal, Montréal, Canada
| | - Pierre Bellec
- Université de Montréal, Montréal, QC, Canada; Centre de Recherche de L'Institut Universitaire de Gériatrie de Montréal, Montréal, Canada
| |
Collapse
|
10
|
Zhu X, Kim Y, Ravid O, He X, Suarez-Jimenez B, Zilcha-Mano S, Lazarov A, Lee S, Abdallah CG, Angstadt M, Averill CL, Baird CL, Baugh LA, Blackford JU, Bomyea J, Bruce SE, Bryant RA, Cao Z, Choi K, Cisler J, Cotton AS, Daniels JK, Davenport ND, Davidson RJ, DeBellis MD, Dennis EL, Densmore M, deRoon-Cassini T, Disner SG, Hage WE, Etkin A, Fani N, Fercho KA, Fitzgerald J, Forster GL, Frijling JL, Geuze E, Gonenc A, Gordon EM, Gruber S, Grupe DW, Guenette JP, Haswell CC, Herringa RJ, Herzog J, Hofmann DB, Hosseini B, Hudson AR, Huggins AA, Ipser JC, Jahanshad N, Jia-Richards M, Jovanovic T, Kaufman ML, Kennis M, King A, Kinzel P, Koch SBJ, Koerte IK, Koopowitz SM, Korgaonkar MS, Krystal JH, Lanius R, Larson CL, Lebois LAM, Li G, Liberzon I, Lu GM, Luo Y, Magnotta VA, Manthey A, Maron-Katz A, May G, McLaughlin K, Mueller SC, Nawijn L, Nelson SM, Neufeld RWJ, Nitschke JB, O'Leary EM, Olatunji BO, Olff M, Peverill M, Phan KL, Qi R, Quidé Y, Rektor I, Ressler K, Riha P, Ross M, Rosso IM, Salminen LE, Sambrook K, Schmahl C, Shenton ME, Sheridan M, Shih C, Sicorello M, Sierk A, Simmons AN, Simons RM, Simons JS, Sponheim SR, Stein MB, Stein DJ, Stevens JS, Straube T, Sun D, Théberge J, Thompson PM, Thomopoulos SI, van der Wee NJA, van der Werff SJA, van Erp TGM, van Rooij SJH, van Zuiden M, Varkevisser T, Veltman DJ, Vermeiren RRJM, Walter H, Wang L, Wang X, Weis C, Winternitz S, Xie H, Zhu Y, Wall M, Neria Y, Morey RA. Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium. Neuroimage 2023; 283:120412. [PMID: 37858907 PMCID: PMC10842116 DOI: 10.1016/j.neuroimage.2023.120412] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2023] [Revised: 09/10/2023] [Accepted: 10/16/2023] [Indexed: 10/21/2023] Open
Abstract
BACKGROUND Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. METHODS We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. RESULTS We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. CONCLUSION These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.
Collapse
Affiliation(s)
- Xi Zhu
- Department of Psychiatry, Columbia University Medical Center, New York, NY, USA; New York State Psychiatric Institute, New York, NY, USA
| | - Yoojean Kim
- New York State Psychiatric Institute, New York, NY, USA
| | - Orren Ravid
- New York State Psychiatric Institute, New York, NY, USA
| | - Xiaofu He
- Department of Psychiatry, Columbia University Medical Center, New York, NY, USA
| | | | | | | | - Seonjoo Lee
- Department of Psychiatry, Columbia University Medical Center, New York, NY, USA; New York State Psychiatric Institute, New York, NY, USA
| | - Chadi G Abdallah
- Baylor College of Medicine, Houston, TX, USA; Yale University School of Medicine, New Haven, CT, USA
| | | | - Christopher L Averill
- Baylor College of Medicine, Houston, TX, USA; Yale University School of Medicine, New Haven, CT, USA
| | | | - Lee A Baugh
- Sanford School of Medicine, University of South Dakota, Vermillion, SD, USA
| | | | | | - Steven E Bruce
- Center for Trauma Recovery, Department of Psychological Sciences, University of Missouri-St. Louis, St. Louis, MO, USA
| | - Richard A Bryant
- School of Psychology, University of New South Wales, Sydney, NSW, Australia
| | - Zhihong Cao
- Department of Radiology, The Affiliated Yixing Hospital of Jiangsu University, Yixing, Jiangsu, China
| | - Kyle Choi
- University of California San Diego, La Jolla, CA, USA
| | - Josh Cisler
- Department of Psychiatry, University of Texas at Austin, Austin, TX, USA
| | | | | | | | | | | | - Emily L Dennis
- University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Maria Densmore
- Departments of Psychology and Psychiatry, Neuroscience Program, Western University, London, ON, Canada; Department of Psychology, University of British Columbia, Okanagan, Kelowna, British Columbia, Canada
| | | | - Seth G Disner
- Minneapolis VA Health Care System, Minneapolis, MN, USA
| | - Wissam El Hage
- UMR 1253, CIC 1415, University of Tours, CHRU de Tours, INSERM, France
| | | | - Negar Fani
- Emory University Department of Psychiatry and Behavioral Sciences, Atlanta, GA, USA
| | - Kelene A Fercho
- Civil Aerospace Medical Institute, US Federal Aviation Administration, Oklahoma City, OK, USA
| | | | - Gina L Forster
- Brain Health Research Centre, Department of Anatomy, University of Otago, Dunedin, New Zealand
| | - Jessie L Frijling
- Department of Psychiatry, Amsterdam University Medical Centers, Academic Medical Center, University of Amsterdam, Amsterdam, The Netherlands
| | - Elbert Geuze
- Brain Research and Innovation Centre, Ministry of Defence, Utrecht, The Netherlands
| | - Atilla Gonenc
- Cognitive and Clinical Neuroimaging Core, McLean Hospital, Belmont, MA, USA
| | - Evan M Gordon
- Department of Radiology, Washington University School of Medicine, St. Louis, MO, USA
| | - Staci Gruber
- Cognitive and Clinical Neuroimaging Core, McLean Hospital, Belmont, MA, USA
| | | | - Jeffrey P Guenette
- Division of Neuroradiology, Brigham and Women's Hospital, Boston, MA, USA
| | | | - Ryan J Herringa
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI, USA
| | | | | | | | | | | | | | - Neda Jahanshad
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of the University of Southern California, Marina del Rey, CA, USA
| | | | | | - Milissa L Kaufman
- Division of Women's Mental Health, McLean Hospital, Belmont, MA, USA
| | - Mitzy Kennis
- Brain Research and Innovation Centre, Ministry of Defence, Utrecht, The Netherlands
| | | | - Philipp Kinzel
- Department of Child and Adolescent Psychiatry, Psychosomatic and Psychotherapy, Ludwig Maximilian University of Munich, Munich, Germany; Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Boston, MA, USA
| | - Saskia B J Koch
- Donders Institute for Brain, Cognition and Behavior, Centre for Cognitive Neuroimaging, Radboud University Nijmegen, Nijmegen, The Netherlands
| | - Inga K Koerte
- Department of Child and Adolescent Psychiatry, Psychosomatic and Psychotherapy, Ludwig Maximilian University of Munich, Munich, Germany; Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Boston, MA, USA
| | | | | | | | - Ruth Lanius
- Department of Neuroscience, Western University, London, ON, Canada
| | | | - Lauren A M Lebois
- McLean Hospital, Belmont, MA, USA; Harvard Medical School, Boston, MA, USA
| | - Gen Li
- Institute of Psychology, Chinese Academy of Sciences, Beijing, China
| | - Israel Liberzon
- Psychiatry and Behavioral Science, Texas A&M University Health Science Center, College Station, TX, USA
| | - Guang Ming Lu
- Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu, China
| | - Yifeng Luo
- Department of Radiology, The Affiliated Yixing Hospital of Jiangsu University, Yixing, Jiangsu, China
| | | | - Antje Manthey
- Charité Universitätsmedizin Berlin Campus Charite Mitte: Charite Universitatsmedizin Berlin, Berlin, Germany
| | | | - Geoffery May
- VISN 17 Center of Excellence for Research on Returning War Veterans, Waco, TX, USA
| | | | | | - Laura Nawijn
- Department of Psychiatry, Amsterdam University Medical Centers, VU University Medical Center, VU University, Amsterdam, The Netherlands
| | - Steven M Nelson
- Department of Pediatrics, University of Minnesota, Minneapolis, MN, USA
| | - Richard W J Neufeld
- Departments of Psychology and Psychiatry, Neuroscience Program, Western University, London, ON, Canada; Department of Psychology, University of British Columbia, Okanagan, Kelowna, British Columbia, Canada
| | | | | | - Bunmi O Olatunji
- Department of Psychology, Vanderbilt University, Nashville, TN, USA
| | - Miranda Olff
- Department of Psychiatry, Amsterdam University Medical Centers, Academic Medical Center, University of Amsterdam, Amsterdam, The Netherlands
| | | | - K Luan Phan
- Department of Psychiatry and Behavioral Health, Ohio State University, Columbus, OH, USA
| | - Rongfeng Qi
- Department of Medical Imaging, Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu, China
| | - Yann Quidé
- School of Psychology, University of New South Wales, Sydney, NSW, Australia; Neuroscience Research Australia, Randwick, NSW, Australia
| | | | - Kerry Ressler
- McLean Hospital, Belmont, MA, USA; Harvard Medical School, Boston, MA, USA
| | | | - Marisa Ross
- Northwestern Neighborhood and Networks Initiative, Northwestern University Institute for Policy Research, Evanston, IL, USA
| | - Isabelle M Rosso
- McLean Hospital, Belmont, MA, USA; Harvard Medical School, Boston, MA, USA
| | - Lauren E Salminen
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of the University of Southern California, Marina del Rey, CA, USA
| | | | | | - Martha E Shenton
- Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Boston, MA, USA
| | | | | | | | - Anika Sierk
- Charité Universitätsmedizin Berlin Campus Charite Mitte: Charite Universitatsmedizin Berlin, Berlin, Germany
| | - Alan N Simmons
- Center of Excellence for Stress and Mental Health, VA San Diego Healthcare System, San Diego, CA, USA
| | | | | | - Scott R Sponheim
- Minneapolis VA Health Care System, Minneapolis, MN, USA; University of Minnesota, Minneapolis, MN, USA
| | | | - Dan J Stein
- University of Cape Town, Cape Town, South Africa
| | - Jennifer S Stevens
- Emory University Department of Psychiatry and Behavioral Sciences, Atlanta, GA, USA
| | | | | | - Jean Théberge
- Departments of Psychology and Psychiatry, Neuroscience Program, Western University, London, ON, Canada; Department of Psychology, University of British Columbia, Okanagan, Kelowna, British Columbia, Canada
| | - Paul M Thompson
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of the University of Southern California, Marina del Rey, CA, USA
| | - Sophia I Thomopoulos
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of the University of Southern California, Marina del Rey, CA, USA
| | | | | | | | - Sanne J H van Rooij
- Emory University Department of Psychiatry and Behavioral Sciences, Atlanta, GA, USA
| | - Mirjam van Zuiden
- Department of Psychiatry, Amsterdam University Medical Centers, Academic Medical Center, University of Amsterdam, Amsterdam, The Netherlands
| | - Tim Varkevisser
- Brain Research and Innovation Centre, Ministry of Defence, Utrecht, The Netherlands
| | - Dick J Veltman
- Department of Psychiatry, Amsterdam University Medical Centers, VU University Medical Center, VU University, Amsterdam, The Netherlands
| | | | - Henrik Walter
- Charité Universitätsmedizin Berlin Campus Charite Mitte: Charite Universitatsmedizin Berlin, Berlin, Germany
| | - Li Wang
- Institute of Psychology, Chinese Academy of Sciences, Beijing, China; Department of Psychology, University of Chinese Academy of Sciences, Beijing, China
| | - Xin Wang
- University of Toledo, Toledo, OH, USA
| | - Carissa Weis
- Medical College of Wisconsin, Milwaukee, WI, USA
| | - Sherry Winternitz
- Division of Women's Mental Health, McLean Hospital, Belmont, MA, USA
| | - Hong Xie
- University of Toledo, Toledo, OH, USA
| | - Ye Zhu
- Institute of Psychology, Chinese Academy of Sciences, Beijing, China
| | - Melanie Wall
- Department of Psychiatry, Columbia University Medical Center, New York, NY, USA; New York State Psychiatric Institute, New York, NY, USA
| | - Yuval Neria
- Department of Psychiatry, Columbia University Medical Center, New York, NY, USA
| | | |
Collapse
|
11
|
Qiang N, Gao J, Dong Q, Yue H, Liang H, Liu L, Yu J, Hu J, Zhang S, Ge B, Sun Y, Liu Z, Liu T, Li J, Song H, Zhao S. Functional brain network identification and fMRI augmentation using a VAE-GAN framework. Comput Biol Med 2023; 165:107395. [PMID: 37669583 DOI: 10.1016/j.compbiomed.2023.107395] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2023] [Revised: 08/04/2023] [Accepted: 08/26/2023] [Indexed: 09/07/2023]
Abstract
Recently, deep learning models have achieved superior performance for mapping functional brain networks from functional magnetic resonance imaging (fMRI) data compared with traditional methods. However, due to the lack of sufficient data and the high dimensionality of brain volume, deep learning models of fMRI tend to suffer from overfitting. In addition, existing methods rarely studied fMRI data augmentation and its application. To address these issues, we developed a VAE-GAN framework that combined a VAE (variational auto-encoder) with a GAN (generative adversarial net) for functional brain network identification and fMRI augmentation. As a generative model, the VAE-GAN models the distribution of fMRI so that it enables the extraction of more generalized features, and thus relieve the overfitting issue. The VAE-GAN is easier to train on fMRI than a standard GAN since it uses latent variables from VAE to generate fake data rather than relying on random noise that is used in a GAN, and it can generate higher quality of fake data than VAE since the discriminator can promote the training of the generator. In other words, the VAE-GAN inherits the advantages of VAE and GAN and avoids their limitations in modeling of fMRI data. Extensive experiments on task fMRI datasets from HCP have proved the effectiveness and superiority of the proposed VAE-GAN framework for identifying both temporal features and functional brain networks compared with existing models, and the quality of fake data is higher than those from VAE and GAN. The results on resting state fMRI of Attention Deficit Hyperactivity Disorder (ADHD)-200 dataset further demonstrated that the fake data generated by the VAE-GAN can help improve the performance of brain network modeling and ADHD classification.
Collapse
Affiliation(s)
- Ning Qiang
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China; Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, China
| | - Jie Gao
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Qinglin Dong
- Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Huiji Yue
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Hongtao Liang
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Lili Liu
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Jingjing Yu
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Jing Hu
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Shu Zhang
- Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, China
| | - Bao Ge
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China; Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, China
| | - Yifei Sun
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Zhengliang Liu
- Cortical Architecture Imaging and Discovery Lab, Department of Computer Science and Bioimaging Research Center, The University of Georgia, Athens, GA, USA
| | - Tianming Liu
- Cortical Architecture Imaging and Discovery Lab, Department of Computer Science and Bioimaging Research Center, The University of Georgia, Athens, GA, USA
| | - Jin Li
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China.
| | - Hujie Song
- Xi'an TCM Hospital of Encephalopathy, Shaanxi University of Chinese Medicine, Xi'an, China.
| | - Shijie Zhao
- School of Automation, Northwestern Polytechnical University, Xi'an, China.
| |
Collapse
|
12
|
Abstract
The allocation of attention to objects raises several intriguing questions: What are objects, how does attention access them, what anatomical regions are involved? Here, we review recent progress in the field to determine the mechanisms underlying object-based attention. First, findings from unconscious priming and cueing suggest that the preattentive targets of object-based attention can be fully developed object representations that have reached the level of identity. Next, the control of object-based attention appears to come from ventral visual areas specialized in object analysis that project downward to early visual areas. How feedback from object areas can accurately target the object's specific locations and features is unknown but recent work in autoencoding has made this plausible. Finally, we suggest that the three classic modes of attention may not be as independent as is commonly considered, and instead could all rely on object-based attention. Specifically, studies show that attention can be allocated to the separated members of a group-without affecting the space between them-matching the defining property of feature-based attention. At the same time, object-based attention directed to a single small item has the properties of space-based attention. We outline the architecture of object-based attention, the novel predictions it brings, and discuss how it works in parallel with other attention pathways.
Collapse
Affiliation(s)
- Patrick Cavanagh
- Department of Psychology, Glendon College, 2275 Bayview Avenue, North York, ON, M4N 3M6, Canada.
- CVR, York University, Toronto, ON, Canada.
| | | | | | | | | | - David L Sheinberg
- Department of Neuroscience, Brown University, Providence, RI, USA
- Carney Institute for Brain Science, Brown University, Providence, RI, USA
| |
Collapse
|
13
|
Meng L, Yang C. Dual-Guided Brain Diffusion Model: Natural Image Reconstruction from Human Visual Stimulus fMRI. Bioengineering (Basel) 2023; 10:1117. [PMID: 37892847 PMCID: PMC10604156 DOI: 10.3390/bioengineering10101117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2023] [Revised: 09/20/2023] [Accepted: 09/21/2023] [Indexed: 10/29/2023] Open
Abstract
The reconstruction of visual stimuli from fMRI signals, which record brain activity, is a challenging task with crucial research value in the fields of neuroscience and machine learning. Previous studies tend to emphasize reconstructing pixel-level features (contours, colors, etc.) or semantic features (object category) of the stimulus image, but typically, these properties are not reconstructed together. In this context, we introduce a novel three-stage visual reconstruction approach called the Dual-guided Brain Diffusion Model (DBDM). Initially, we employ the Very Deep Variational Autoencoder (VDVAE) to reconstruct a coarse image from fMRI data, capturing the underlying details of the original image. Subsequently, the Bootstrapping Language-Image Pre-training (BLIP) model is utilized to provide a semantic annotation for each image. Finally, the image-to-image generation pipeline of the Versatile Diffusion (VD) model is utilized to recover natural images from the fMRI patterns guided by both visual and semantic information. The experimental results demonstrate that DBDM surpasses previous approaches in both qualitative and quantitative comparisons. In particular, the best performance is achieved by DBDM in reconstructing the semantic details of the original image; the Inception, CLIP and SwAV distances are 0.611, 0.225 and 0.405, respectively. This confirms the efficacy of our model and its potential to advance visual decoding research.
Collapse
Affiliation(s)
- Lu Meng
- College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;
| | | |
Collapse
|
14
|
Ren Z, Li J, Xue X, Li X, Yang F, Jiao Z, Gao X. Reconstructing controllable faces from brain activity with hierarchical multiview representations. Neural Netw 2023; 166:487-500. [PMID: 37574622 DOI: 10.1016/j.neunet.2023.07.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2022] [Revised: 05/21/2023] [Accepted: 07/12/2023] [Indexed: 08/15/2023]
Abstract
Reconstructing visual experience from brain responses measured by functional magnetic resonance imaging (fMRI) is a challenging yet important research topic in brain decoding, especially it has proved more difficult to decode visually similar stimuli, such as faces. Although face attributes are known as the key to face recognition, most existing methods generally ignore how to decode facial attributes more precisely in perceived face reconstruction, which often leads to indistinguishable reconstructed faces. To solve this problem, we propose a novel neural decoding framework called VSPnet (voxel2style2pixel) by establishing hierarchical encoding and decoding networks with disentangled latent representations as media, so that to recover visual stimuli more elaborately. And we design a hierarchical visual encoder (named HVE) to pre-extract features containing both high-level semantic knowledge and low-level visual details from stimuli. The proposed VSPnet consists of two networks: Multi-branch cognitive encoder and style-based image generator. The encoder network is constructed by multiple linear regression branches to map brain signals to the latent space provided by the pre-extracted visual features and obtain representations containing hierarchical information consistent to the corresponding stimuli. We make the generator network inspired by StyleGAN to untangle the complexity of fMRI representations and generate images. And the HVE network is composed of a standard feature pyramid over a ResNet backbone. Extensive experimental results on the latest public datasets have demonstrated the reconstruction accuracy of our proposed method outperforms the state-of-the-art approaches and the identifiability of different reconstructed faces has been greatly improved. In particular, we achieve feature editing for several facial attributes in fMRI domain based on the multiview (i.e., visual stimuli and evoked fMRI) latent representations.
Collapse
Affiliation(s)
- Ziqi Ren
- School of Electronic Engineering, Xidian University, Xi'an 710071, China
| | - Jie Li
- School of Electronic Engineering, Xidian University, Xi'an 710071, China
| | - Xuetong Xue
- School of Electronic Engineering, Xidian University, Xi'an 710071, China
| | - Xin Li
- Group 42 (G42), Abu Dhabi, United Arab Emirates
| | - Fan Yang
- Group 42 (G42), Abu Dhabi, United Arab Emirates
| | - Zhicheng Jiao
- The Warren Alpert Medical School, Brown University, RI, USA; Department of Diagnostic Imaging, Rhode Island Hospital, RI, USA
| | - Xinbo Gao
- School of Electronic Engineering, Xidian University, Xi'an 710071, China.
| |
Collapse
|
15
|
Wang C, Yan H, Huang W, Sheng W, Wang Y, Fan YS, Liu T, Zou T, Li R, Chen H. Neural encoding with unsupervised spiking convolutional neural network. Commun Biol 2023; 6:880. [PMID: 37640808 PMCID: PMC10462614 DOI: 10.1038/s42003-023-05257-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Accepted: 08/18/2023] [Indexed: 08/31/2023] Open
Abstract
Accurately predicting the brain responses to various stimuli poses a significant challenge in neuroscience. Despite recent breakthroughs in neural encoding using convolutional neural networks (CNNs) in fMRI studies, there remain critical gaps between the computational rules of traditional artificial neurons and real biological neurons. To address this issue, a spiking CNN (SCNN)-based framework is presented in this study to achieve neural encoding in a more biologically plausible manner. The framework utilizes unsupervised SCNN to extract visual features of image stimuli and employs a receptive field-based regression algorithm to predict fMRI responses from the SCNN features. Experimental results on handwritten characters, handwritten digits and natural images demonstrate that the proposed approach can achieve remarkably good encoding performance and can be utilized for "brain reading" tasks such as image reconstruction and identification. This work suggests that SNN can serve as a promising tool for neural encoding.
Collapse
Affiliation(s)
- Chong Wang
- The Center of Psychosomatic Medicine, Sichuan Provincial Center for Mental Health, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, 611731, China
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Hongmei Yan
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China.
| | - Wei Huang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Wei Sheng
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Yuting Wang
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Yun-Shuang Fan
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Tao Liu
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Ting Zou
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Rong Li
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China.
| | - Huafu Chen
- The Center of Psychosomatic Medicine, Sichuan Provincial Center for Mental Health, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, 611731, China.
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 610054, China.
| |
Collapse
|
16
|
Pan H, Fu Y, Li Z, Wen F, Hu J, Wu B. Images Reconstruction from Functional Magnetic Resonance Imaging Patterns Based on the Improved Deep Generative Multiview Model. Neuroscience 2023; 509:103-112. [PMID: 36460220 DOI: 10.1016/j.neuroscience.2022.11.021] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2022] [Revised: 11/02/2022] [Accepted: 11/20/2022] [Indexed: 12/03/2022]
Abstract
Reconstructing visual stimulus images from the brain activity signals is an important research task in the field of brain decoding. Many methods of reconstructing visual stimulus images mainly focus on how to use deep learning to classify the brain activities measured by functional magnetic resonance imaging or identify visual stimulus images. Accurate reconstruction of visual stimulus images by using deep learning still remains challenging. This paper proposes an improved deep generative multiview model to further promote the accuracy of reconstructing visual stimulus images. Firstly, an encoder based on residual-in-residual dense blocks is designed to fit the deep and multiview visual features of human natural state, and extract the features of visual stimulus images. Secondly, the structure of original decoder is extended to a deeper network in the deep generative multiview model, which makes the features obtained by each deconvolution layer more distinguishable. Finally, we configure the parameters of the optimizer and compare the performance of various optimizers under different parameter values, and then the one with the best performance is chosen and adopted to the whole model. The performance evaluations conducted on two publicly available datasets demonstrate that the improved model has more accurate reconstruction effectiveness than the original deep generative multiview model.
Collapse
Affiliation(s)
- Hongguang Pan
- College of Electrical and Control Engineering, Xi'an University of Science and Technology, Xi'an 710054, China; Key Laboratory of Industrial Internet of Things & Networked Control, Ministry of Education, Chongqing 400065, China.
| | - Yunpeng Fu
- Key Laboratory of Industrial Internet of Things & Networked Control, Ministry of Education, Chongqing 400065, China.
| | - Zhuoyi Li
- Key Laboratory of Industrial Internet of Things & Networked Control, Ministry of Education, Chongqing 400065, China.
| | - Fan Wen
- Xingtang Telecommunication Technology Co., LTD, Datang Telecom Technology & Industry Group, Xi'an 710054, China.
| | - Jianchen Hu
- School of Automation Science and Engineering, Xi'an Jiaotong University, Xi'an 710049, China.
| | - Bo Wu
- Sunny Science and Technology Co., LTD, Xi'an 710049, China.
| |
Collapse
|
17
|
Lin B, Tan Z, Mo Y, Yang X, Liu Y, Xu B. Intelligent oncology: The convergence of artificial intelligence and oncology. Journal of the National Cancer Center 2022. [DOI: 10.1016/j.jncc.2022.11.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
|
18
|
Wang Z, Liu Z, Chen L, Liu S, Xu M, He F, Ming D. Resting-state electroencephalogram microstate to evaluate post-stroke rehabilitation and associate with clinical scales. Front Neurosci 2022; 16:1032696. [PMID: 36466159 PMCID: PMC9715736 DOI: 10.3389/fnins.2022.1032696] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2022] [Accepted: 11/07/2022] [Indexed: 01/02/2024] Open
Abstract
INTRODUCTION Stroke is usually accompanied by a range of complications, like post-stroke motor disorders. So far, its evaluation of motor function is developed on clinical scales, such as Fugl-Meyer Assessment (FMA), Instrumental Activities of Daily Living (IADL), etc. These scale results from behavior and kinematic assessment are inevitably influenced by subjective factors, like the experience of patients and doctors, lacking neurological correlations and evidence. METHODS This paper applied a microstate model based on modified k-means clustering to analyze 64-channel electroencephalogram (EEG) from 12 stroke patients and 12 healthy volunteers, respectively, to explore the feasibility of applying microstate analysis to stroke patients. We aimed at finding some possible differences between stroke and healthy individuals in resting-state EEG microstate features. We further explored the correlations between EEG microstate features and scales within the stroke group. RESULTS AND DISCUSSION By statistical analysis, we obtained significant differences in EEG microstate features between the stroke and healthy groups and significant correlations between microstate features and scales within the stroke group. These results might provide some neurological evidence and correlations in the perspective of EEG microstate analysis for post-stroke rehabilitation and evaluation of motor disorders. Our work suggests that microstate analysis of resting-state EEG is a promising method to assist clinical and assessment applications.
Collapse
Affiliation(s)
- Zhongpeng Wang
- Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin, China
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
| | - Zhaoyang Liu
- Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin, China
| | - Long Chen
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
| | - Shuang Liu
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
| | - Minpeng Xu
- Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin, China
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
- Tianjin International Joint Research Center for Neural Engineering, Tianjin, China
| | - Feng He
- Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin, China
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
- Tianjin International Joint Research Center for Neural Engineering, Tianjin, China
| | - Dong Ming
- Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin, China
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
- Tianjin International Joint Research Center for Neural Engineering, Tianjin, China
| |
Collapse
|
19
|
Le L, Ambrogioni L, Seeliger K, Güçlütürk Y, van Gerven M, Güçlü U. Brain2Pix: Fully convolutional naturalistic video frame reconstruction from brain activity. Front Neurosci 2022; 16:940972. [DOI: 10.3389/fnins.2022.940972] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2022] [Accepted: 09/09/2022] [Indexed: 11/16/2022] Open
Abstract
Reconstructing complex and dynamic visual perception from brain activity remains a major challenge in machine learning applications to neuroscience. Here, we present a new method for reconstructing naturalistic images and videos from very large single-participant functional magnetic resonance imaging data that leverages the recent success of image-to-image transformation networks. This is achieved by exploiting spatial information obtained from retinotopic mappings across the visual system. More specifically, we first determine what position each voxel in a particular region of interest would represent in the visual field based on its corresponding receptive field location. Then, the 2D image representation of the brain activity on the visual field is passed to a fully convolutional image-to-image network trained to recover the original stimuli using VGG feature loss with an adversarial regularizer. In our experiments, we show that our method offers a significant improvement over existing video reconstruction techniques.
Collapse
|
20
|
Zhang YJ, Yu ZF, Liu JK, Huang TJ. Neural Decoding of Visual Information Across Different Neural Recording Modalities and Approaches. Mach Intell Res 2022. [PMCID: PMC9283560 DOI: 10.1007/s11633-022-1335-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
Vision plays a peculiar role in intelligence. Visual information, forming a large part of the sensory information, is fed into the human brain to formulate various types of cognition and behaviours that make humans become intelligent agents. Recent advances have led to the development of brain-inspired algorithms and models for machine vision. One of the key components of these methods is the utilization of the computational principles underlying biological neurons. Additionally, advanced experimental neuroscience techniques have generated different types of neural signals that carry essential visual information. Thus, there is a high demand for mapping out functional models for reading out visual information from neural signals. Here, we briefly review recent progress on this issue with a focus on how machine learning techniques can help in the development of models for contending various types of neural signals, from fine-scale neural spikes and single-cell calcium imaging to coarse-scale electroencephalography (EEG) and functional magnetic resonance imaging recordings of brain signals.
Collapse
|
21
|
Kim SG. On the encoding of natural music in computational models and human brains. Front Neurosci 2022; 16:928841. [PMID: 36203808 PMCID: PMC9531138 DOI: 10.3389/fnins.2022.928841] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Accepted: 08/15/2022] [Indexed: 11/13/2022] Open
Abstract
This article discusses recent developments and advances in the neuroscience of music to understand the nature of musical emotion. In particular, it highlights how system identification techniques and computational models of music have advanced our understanding of how the human brain processes the textures and structures of music and how the processed information evokes emotions. Musical models relate physical properties of stimuli to internal representations called features, and predictive models relate features to neural or behavioral responses and test their predictions against independent unseen data. The new frameworks do not require orthogonalized stimuli in controlled experiments to establish reproducible knowledge, which has opened up a new wave of naturalistic neuroscience. The current review focuses on how this trend has transformed the domain of the neuroscience of music.
Collapse
|
22
|
Higashi T, Maeda K, Ogawa T, Haseyama M. Brain Decoding of Multiple Subjects for Estimating Visual Information Based on a Probabilistic Generative Model. Sensors (Basel) 2022; 22:6148. [PMID: 36015909 PMCID: PMC9416613 DOI: 10.3390/s22166148] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/18/2022] [Revised: 08/10/2022] [Accepted: 08/14/2022] [Indexed: 06/15/2023]
Abstract
Brain decoding is a process of decoding human cognitive contents from brain activities. However, improving the accuracy of brain decoding remains difficult due to the unique characteristics of the brain, such as the small sample size and high dimensionality of brain activities. Therefore, this paper proposes a method that effectively uses multi-subject brain activities to improve brain decoding accuracy. Specifically, we distinguish between the shared information common to multi-subject brain activities and the individual information based on each subject's brain activities, and both types of information are used to decode human visual cognition. Both types of information are extracted as features belonging to a latent space using a probabilistic generative model. In the experiment, an publicly available dataset and five subjects were used, and the estimation accuracy was validated on the basis of a confidence score ranging from 0 to 1, and a large value indicates superiority. The proposed method achieved a confidence score of 0.867 for the best subject and an average of 0.813 for the five subjects, which was the best compared to other methods. The experimental results show that the proposed method can accurately decode visual cognition compared with other existing methods in which the shared information is not distinguished from the individual information.
Collapse
Affiliation(s)
- Takaaki Higashi
- Graduate School of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan
| | - Keisuke Maeda
- Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan
| | - Takahiro Ogawa
- Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan
| | - Miki Haseyama
- Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan
| |
Collapse
|
23
|
Qiang N, Dong Q, Liang H, Li J, Zhang S, Zhang C, Ge B, Sun Y, Gao J, Liu T, Yue H, Zhao S. Learning brain representation using recurrent Wasserstein generative adversarial net. Comput Methods Programs Biomed 2022; 223:106979. [PMID: 35792364 DOI: 10.1016/j.cmpb.2022.106979] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Revised: 04/26/2022] [Accepted: 06/26/2022] [Indexed: 06/15/2023]
Abstract
BACKGROUND AND OBJECTIVE To understand brain cognition and disorders, modeling the mapping between mind and brain has been of great interest to the neuroscience community. The key is the brain representation, including functional brain networks (FBN) and their corresponding temporal features. Recently, it has been proven that deep learning models have superb representation power on functional magnetic resonance imaging (fMRI) over traditional machine learning methods. However, due to the lack of high-quality data and labels, deep learning models tend to suffer from overfitting in the training process. METHODS In this work, we applied a recurrent Wasserstein generative adversarial net (RWGAN) to learn brain representation from volumetric fMRI data. Generative adversarial net (GAN) is widely used in natural image generation and is able to capture the distribution of the input data, which enables the extraction of generalized features from fMRI and thus relieves the overfitting issue. The recurrent layers in RWGAN are designed to better model the local temporal features of the fMRI time series. The discriminator of RWGAN works as a deep feature extractor. With LASSO regression, the RWGAN model can decompose the fMRI data into temporal features and spatial features (FBNs). Furthermore, the generator of RWGAN can generate high-quality new data for fMRI augmentation. RESULTS The experimental results on seven tasks from the HCP dataset showed that the RWGAN can learn meaningful and interpretable temporal features and FBNs, compared to HCP task designs and general linear model (GLM) derived networks. Besides, the results on different training datasets showed that the RWGAN performed better on small datasets than other deep learning models. Moreover, we used the generator of RWGAN to yield fake subjects. The result showed that the fake data can also be used to learn meaningful representation compared to those learned from real data. CONCLUSIONS To our best knowledge, this work is among the earliest attempts of applying generative deep learning for modeling fMRI data. The proposed RWGAN offers a novel methodology for learning brain representation from fMRI, and it can generate high-quality fake data for the potential use of fMRI data augmentation.
Collapse
Affiliation(s)
- Ning Qiang
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China; Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, China
| | - Qinglin Dong
- Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Hongtao Liang
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Jin Li
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Shu Zhang
- Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, China
| | - Cheng Zhang
- School of Electronics Engineering and Computer Science, Peking University, Beijing, China
| | - Bao Ge
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China; Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, China
| | - Yifei Sun
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Jie Gao
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China
| | - Tianming Liu
- Cortical Architecture Imaging and Discovery Lab, Department of Computer Science and Bioimaging Research Center, The University of Georgia, Athens, GA, Greece
| | - Huiji Yue
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, China.
| | - Shijie Zhao
- School of Automation, Northwestern Polytechnical University, Xi'an, China.
| |
Collapse
|
24
|
Xu H, Liu M, Zhang D. How does the brain represent the semantic content of an image? Neural Netw 2022; 154:31-42. [DOI: 10.1016/j.neunet.2022.06.034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Revised: 04/13/2022] [Accepted: 06/28/2022] [Indexed: 11/24/2022]
|
25
|
Gaziv G, Beliy R, Granot N, Hoogi A, Strappini F, Golan T, Irani M. Self-supervised Natural Image Reconstruction and Large-scale Semantic Classification from Brain Activity. Neuroimage 2022; 254:119121. [PMID: 35342004 PMCID: PMC9133799 DOI: 10.1016/j.neuroimage.2022.119121] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2021] [Revised: 01/19/2022] [Accepted: 03/19/2022] [Indexed: 11/24/2022] Open
Abstract
Reconstructing natural images and decoding their semantic category from fMRI brain recordings is challenging. Acquiring sufficient pairs of images and their corresponding fMRI responses, which span the huge space of natural images, is prohibitive. We present a novel self-supervised approach that goes well beyond the scarce paired data, for achieving both: (i) state-of-the art fMRI-to-image reconstruction, and (ii) first-ever large-scale semantic classification from fMRI responses. By imposing cycle consistency between a pair of deep neural networks (from image-to-fMRI & from fMRI-to-image), we train our image reconstruction network on a large number of "unpaired" natural images (images without fMRI recordings) from many novel semantic categories. This enables to adapt our reconstruction network to a very rich semantic coverage without requiring any explicit semantic supervision. Specifically, we find that combining our self-supervised training with high-level perceptual losses, gives rise to new reconstruction & classification capabilities. In particular, this perceptual training enables to classify well fMRIs of never-before-seen semantic classes, without requiring any class labels during training. This gives rise to: (i) Unprecedented image-reconstruction from fMRI of never-before-seen images (evaluated by image metrics and human testing), and (ii) Large-scale semantic classification of categories that were never-before-seen during network training. Such large-scale (1000-way) semantic classification from fMRI recordings has never been demonstrated before. Finally, we provide evidence for the biological consistency of our learned model.
Collapse
Affiliation(s)
- Guy Gaziv
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel.
| | - Roman Beliy
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel
| | - Niv Granot
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel
| | - Assaf Hoogi
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel
| | | | - Tal Golan
- Zuckerman Institute, Columbia University, New York, NY USA
| | - Michal Irani
- Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel.
| |
Collapse
|
26
|
Bousbai K, Merah M. Enhancement of Hand gesture recognition using convolutional neural networks integrating a combination of an AutoEncoder network and PCA. INT J PATTERN RECOGN 2022. [DOI: 10.1142/s0218001422560158] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
27
|
Abstract
The objective of this study is to propose MD-VAE: a multi-task disentangled variational autoencoders (VAE) for exploring characteristics of latent representations (LR) and exploiting LR for diverse tasks including glucose forecasting, event detection, and temporal clustering.
Collapse
|
28
|
Huang Q, Qiao C, Jing K, Zhu X, Ren K. Biomarkers identification for Schizophrenia via VAE and GSDAE-based data augmentation. Comput Biol Med 2022; 146:105603. [PMID: 35588680 DOI: 10.1016/j.compbiomed.2022.105603] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2022] [Revised: 04/13/2022] [Accepted: 05/07/2022] [Indexed: 11/24/2022]
Abstract
Deep learning has made great progress in analyzing MRI data, while the MRI data with high dimensional but small sample size (HDSSS) brings many limitations to biomarkers identification. Few-shot learning has been proposed to solve such problems and data augmentation is a typical method of it. The variational auto-encoder (VAE) is a generative method based on variational Bayesian inference that is used for data augmentation. Graph regularized sparse deep autoencoder (GSDAE) can reconstruct sparse samples and keep the manifold structure of data which will facilitate biomarkers selection greatly. To generate better HDSSS data for biomarkers identification, a data augmentation method based on VAE and GSDAE is proposed in this paper, termed GS-VDAE. Instead of utilizing the final products of GSDAE, our proposed model embeds the generation procedure into GSDAE for augmentation. In this way, the augmented samples will be rooted in the significant features extracted from the original samples, which can ensure the newly formed samples contain the most significant characteristics of the original samples. The classification accuracy of the samples generated directly from VAE is 0.74, while the classification accuracy of the samples generated from GS-VDAE is 0.84, which proves the validity of our model. Additionally, a regression feature selection method with truncated nuclear norm regularization is chosen for biomarkers selection. The biomarkers selection results of schizophrenia data reveal that the augmented samples obtained by our proposed method can get higher classification accuracy with less ranked features compared with original samples, which proves the validation of our model.
Collapse
Affiliation(s)
- Qi Huang
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, 710049, China.
| | - Chen Qiao
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, 710049, China.
| | - Kaili Jing
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, 710049, China; Department of Mathematics and Statistics, University of Ottawa, Ottawa, K7L 3P7, Canada.
| | - Xu Zhu
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, 710049, China.
| | - Kai Ren
- Xijing Hospital, Fourth Military Medical University, Xi'an, 710032, China.
| |
Collapse
|
29
|
Zheng H, Yao L, Long Z. Reconstruction of 3D Images from Human Activity by a Compound Reconstruction Model. Cognit Comput 2022. [DOI: 10.1007/s12559-022-09992-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
30
|
|
31
|
Qiao K, Chen J, Wang L, Zhang C, Tong L, Yan B. Reconstructing natural images from human fMRI by alternating encoding and decoding with shared autoencoder regularization. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2021.103397] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
32
|
Qureshi MB, Azad L, Qureshi MS, Aslam S, Aljarbouh A, Fayaz M. Brain Decoding Using fMRI Images for Multiple Subjects through Deep Learning. Comput Math Methods Med 2022; 2022:1124927. [PMID: 35273647 PMCID: PMC8904097 DOI: 10.1155/2022/1124927] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/08/2022] [Revised: 02/06/2022] [Accepted: 02/11/2022] [Indexed: 12/02/2022]
Abstract
Substantial information related to human cerebral conditions can be decoded through various noninvasive evaluating techniques like fMRI. Exploration of the neuronal activity of the human brain can divulge the thoughts of a person like what the subject is perceiving, thinking, or visualizing. Furthermore, deep learning techniques can be used to decode the multifaceted patterns of the brain in response to external stimuli. Existing techniques are capable of exploring and classifying the thoughts of the human subject acquired by the fMRI imaging data. fMRI images are the volumetric imaging scans which are highly dimensional as well as require a lot of time for training when fed as an input in the deep learning network. However, the hassle for more efficient learning of highly dimensional high-level features in less training time and accurate interpretation of the brain voxels with less misclassification error is needed. In this research, we propose an improved CNN technique where features will be functionally aligned. The optimal features will be selected after dimensionality reduction. The highly dimensional feature vector will be transformed into low dimensional space for dimensionality reduction through autoadjusted weights and combination of best activation functions. Furthermore, we solve the problem of increased training time by using Swish activation function, making it denser and increasing efficiency of the model in less training time. Finally, the experimental results are evaluated and compared with other classifiers which demonstrated the supremacy of the proposed model in terms of accuracy.
Collapse
Affiliation(s)
- Muhammad Bilal Qureshi
- Department of Computer Science & IT, University of Lakki Marwat, Lakki Marwat 28420, KPK, Pakistan
| | - Laraib Azad
- Department of Computer Science, Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad 44000, Pakistan
| | - Muhammad Shuaib Qureshi
- Department of Computer Science, School of Arts and Sciences, University of Central Asia, Kyrgyzstan
| | - Sheraz Aslam
- Department of Electrical Engineering, Computer Engineering, and Informatics, Cyprus University of Technology, Cyprus
| | - Ayman Aljarbouh
- Department of Computer Science, School of Arts and Sciences, University of Central Asia, Kyrgyzstan
| | - Muhammad Fayaz
- Department of Computer Science, School of Arts and Sciences, University of Central Asia, Kyrgyzstan
| |
Collapse
|
33
|
Shon K, Sung KR, Kwak J, Shin JW, Lee JY. Development of a β-Variational Autoencoder for Disentangled Latent Space Representation of Anterior Segment Optical Coherence Tomography Images. Transl Vis Sci Technol 2022; 11:11. [PMID: 35133405 PMCID: PMC8842480 DOI: 10.1167/tvst.11.2.11] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
Purpose To investigate the feasibility of extracting a low-dimensional latent structure of anterior segment optical coherence tomography (AS-OCT) images by use of a β-variational autoencoder (β-VAE). Methods We retrospectively collected 2111 AS-OCT images from 2111 eyes of 1261 participants from the ongoing Asan Glaucoma Progression Study. After hyperparameter optimization, the images were analyzed with β-VAE. Results The mean participant age was 64.4 years, with mean values of visual field index and mean deviation of 86.4% and −5.33 dB, respectively. After experiments, a latent space size of 6 and β value of 53 were selected for latent space analysis with β-VAE. Latent variables were successfully disentangled, showing readily interpretable distinct characteristics, such as the overall depth and area of the anterior chamber (η1), pupil diameter (η2), iris profile (η3 and η4), and corneal curvature (η5). Conclusions β-VAE can successfully be applied for disentangled latent space representation of AS-OCT images, revealing the high possibility of applying unsupervised learning in the medical image analysis. Translational Relevance This study demonstrates that a deep learning–based latent space model can be applied for the analysis of AS-OCT images.
Collapse
Affiliation(s)
- Kilhwan Shon
- Department of Ophthalmology, Gangneung Asan Hospital, Gangneung, Korea.,Asan Artificial Intelligence Institute, Hwaseong-si, Gyeonggi-do, Korea
| | - Kyung Rim Sung
- Department of Ophthalmology, College of Medicine, University of Ulsan, Asan Medical Center, Seoul, Korea
| | - Jiehoon Kwak
- Department of Ophthalmology, College of Medicine, University of Ulsan, Asan Medical Center, Seoul, Korea
| | - Joong Won Shin
- Department of Ophthalmology, College of Medicine, University of Ulsan, Asan Medical Center, Seoul, Korea
| | - Joo Yeon Lee
- Asan Artificial Intelligence Institute, Hwaseong-si, Gyeonggi-do, Korea.,Camp 9 Orthopedic Clinic, Hwaseong-si, Gyeonggi-do, Korea
| |
Collapse
|
34
|
Du C, Du C, Huang L, Wang H, He H. Structured Neural Decoding With Multitask Transfer Learning of Deep Neural Network Representations. IEEE Trans Neural Netw Learn Syst 2022; 33:600-614. [PMID: 33074832 DOI: 10.1109/tnnls.2020.3028167] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
The reconstruction of visual information from human brain activity is a very important research topic in brain decoding. Existing methods ignore the structural information underlying the brain activities and the visual features, which severely limits their performance and interpretability. Here, we propose a hierarchically structured neural decoding framework by using multitask transfer learning of deep neural network (DNN) representations and a matrix-variate Gaussian prior. Our framework consists of two stages, Voxel2Unit and Unit2Pixel. In Voxel2Unit, we decode the functional magnetic resonance imaging (fMRI) data to the intermediate features of a pretrained convolutional neural network (CNN). In Unit2Pixel, we further invert the predicted CNN features back to the visual images. Matrix-variate Gaussian prior allows us to take into account the structures between feature dimensions and between regression tasks, which are useful for improving decoding effectiveness and interpretability. This is in contrast with the existing single-output regression models that usually ignore these structures. We conduct extensive experiments on two real-world fMRI data sets, and the results show that our method can predict CNN features more accurately and reconstruct the perceived natural images and faces with higher quality.
Collapse
|
35
|
Wang C, Yan H, Huang W, Li J, Wang Y, Fan YS, Sheng W, Liu T, Li R, Chen H. Reconstructing Rapid Natural Vision with fMRI-Conditional Video Generative Adversarial Network. Cereb Cortex 2022; 32:4502-4511. [PMID: 35078227 DOI: 10.1093/cercor/bhab498] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Revised: 10/24/2021] [Accepted: 12/03/2021] [Indexed: 11/14/2022] Open
Abstract
Recent functional magnetic resonance imaging (fMRI) studies have made significant progress in reconstructing perceived visual content, which advanced our understanding of the visual mechanism. However, reconstructing dynamic natural vision remains a challenge because of the limitation of the temporal resolution of fMRI. Here, we developed a novel fMRI-conditional video generative adversarial network (f-CVGAN) to reconstruct rapid video stimuli from evoked fMRI responses. In this model, we employed a generator to produce spatiotemporal reconstructions and employed two separate discriminators (spatial and temporal discriminators) for the assessment. We trained and tested the f-CVGAN on two publicly available video-fMRI datasets, and the model produced pixel-level reconstructions of 8 perceived video frames from each fMRI volume. Experimental results showed that the reconstructed videos were fMRI-related and captured important spatial and temporal information of the original stimuli. Moreover, we visualized the cortical importance map and found that the visual cortex is extensively involved in the reconstruction, whereas the low-level visual areas (V1/V2/V3/V4) showed the largest contribution. Our work suggests that slow blood oxygen level-dependent signals describe neural representations of the fast perceptual process that can be decoded in practice.
Collapse
Affiliation(s)
- Chong Wang
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Hongmei Yan
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Wei Huang
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Jiyi Li
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Yuting Wang
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Yun-Shuang Fan
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Wei Sheng
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Tao Liu
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Rong Li
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Huafu Chen
- The Clinical Hospital of Chengdu Brain Science Institute, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China
- MOE Key Lab for Neuroinformation; High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 610054, China
- The Center of Psychosomatic Medicine, Sichuan Provincial Center for Mental Health, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu 611731, China
| |
Collapse
|
36
|
|
37
|
Wang H, Huang L, Du C, Li D, Wang B, He H. Neural Encoding for Human Visual Cortex With Deep Neural Networks Learning “What” and “Where”. IEEE Trans Cogn Dev Syst 2021. [DOI: 10.1109/tcds.2020.3007761] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|
38
|
Hržić F, Žužić I, Tschauner S, Štajduhar I. Cast suppression in radiographs by generative adversarial networks. J Am Med Inform Assoc 2021; 28:2687-2694. [PMID: 34613393 DOI: 10.1093/jamia/ocab192] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2021] [Revised: 08/06/2021] [Accepted: 08/30/2021] [Indexed: 11/14/2022] Open
Abstract
Injured extremities commonly need to be immobilized by casts to allow proper healing. We propose a method to suppress cast superimpositions in pediatric wrist radiographs based on the cycle generative adversarial network (CycleGAN) model. We retrospectively reviewed unpaired pediatric wrist radiographs (n = 9672) and sampled them into 2 equal groups, with and without cast. The test subset consisted of 718 radiographs with cast. We evaluated different quadratic input sizes (256, 512, and 1024 pixels) for U-Net and ResNet-based CycleGAN architectures in cast suppression, quantitatively and qualitatively. The mean age was 11 ± 3 years in images containing cast (n = 4836), and 11 ± 4 years in castless samples (n = 4836). A total of 5956 X-rays had been done in males and 3716 in females. A U-Net 512 CycleGAN performed best (P ≤ .001). CycleGAN models successfully suppressed casts in pediatric wrist radiographs, allowing the development of a related software tool for radiology image viewers.
Collapse
Affiliation(s)
- Franko Hržić
- Department of Computer Engineering, Faculty of Engineering, University of Rijeka, Rijeka, Croatia.,Center for Artificial Intelligence and Cybersecurity, University of Rijeka, Rijeka, Croatia
| | - Ivana Žužić
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Sebastian Tschauner
- Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria
| | - Ivan Štajduhar
- Department of Computer Engineering, Faculty of Engineering, University of Rijeka, Rijeka, Croatia.,Center for Artificial Intelligence and Cybersecurity, University of Rijeka, Rijeka, Croatia
| |
Collapse
|
39
|
Guo X, Wang J. Low-Dimensional Dynamics of Brain Activity Associated with Manual Acupuncture in Healthy Subjects. Sensors (Basel) 2021; 21:s21227432. [PMID: 34833508 PMCID: PMC8619579 DOI: 10.3390/s21227432] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Revised: 11/03/2021] [Accepted: 11/06/2021] [Indexed: 11/24/2022]
Abstract
Acupuncture is one of the oldest traditional medical treatments in Asian countries. However, the scientific explanation regarding the therapeutic effect of acupuncture is still unknown. The much-discussed hypothesis it that acupuncture’s effects are mediated via autonomic neural networks; nevertheless, dynamic brain activity involved in the acupuncture response has still not been elicited. In this work, we hypothesized that there exists a lower-dimensional subspace of dynamic brain activity across subjects, underpinning the brain’s response to manual acupuncture stimulation. To this end, we employed a variational auto-encoder to probe the latent variables from multichannel EEG signals associated with acupuncture stimulation at the ST36 acupoint. The experimental results demonstrate that manual acupuncture stimuli can reduce the dimensionality of brain activity, which results from the enhancement of oscillatory activity in the delta and alpha frequency bands induced by acupuncture. Moreover, it was found that large-scale brain activity could be constrained within a low-dimensional neural subspace, which is spanned by the “acupuncture mode”. In each neural subspace, the steady dynamics of the brain in response to acupuncture stimuli converge to topologically similar elliptic-shaped attractors across different subjects. The attractor morphology is closely related to the frequency of the acupuncture stimulation. These results shed light on probing the large-scale brain response to manual acupuncture stimuli.
Collapse
Affiliation(s)
- Xinmeng Guo
- School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China;
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China
- Correspondence:
| | - Jiang Wang
- School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China;
| |
Collapse
|
40
|
Kim JH, Zhang Y, Han K, Wen Z, Choi M, Liu Z. Representation learning of resting state fMRI with variational autoencoder. Neuroimage 2021; 241:118423. [PMID: 34303794 PMCID: PMC8485214 DOI: 10.1016/j.neuroimage.2021.118423] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2020] [Revised: 07/18/2021] [Accepted: 07/21/2021] [Indexed: 11/24/2022] Open
Abstract
Resting state functional magnetic resonance imaging (rsfMRI) data exhibits complex but structured patterns. However, the underlying origins are unclear and entangled in rsfMRI data. Here we establish a variational auto-encoder, as a generative model trainable with unsupervised learning, to disentangle the unknown sources of rsfMRI activity. After being trained with large data from the Human Connectome Project, the model has learned to represent and generate patterns of cortical activity and connectivity using latent variables. The latent representation and its trajectory represent the spatiotemporal characteristics of rsfMRI activity. The latent variables reflect the principal gradients of the latent trajectory and drive activity changes in cortical networks. Representational geometry captured as covariance or correlation between latent variables, rather than cortical connectivity, can be used as a more reliable feature to accurately identify subjects from a large group, even if only a short period of data is available in each subject. Our results demonstrate that VAE is a valuable addition to existing tools, particularly suited for unsupervised representation learning of resting state fMRI activity.
Collapse
Affiliation(s)
- Jung-Hoon Kim
- Department of Biomedical Engineering, University of Michigan, United States; Weldon School of Biomedical Engineering, Purdue University, United States
| | - Yizhen Zhang
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Kuan Han
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Zheyu Wen
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Minkyu Choi
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Zhongming Liu
- Department of Biomedical Engineering, University of Michigan, United States; Department of Electrical Engineering and Computer Science, University of Michigan, United States.
| |
Collapse
|
41
|
Huang W, Yan H, Cheng K, Wang C, Li J, Wang Y, Li C, Li C, Li Y, Zuo Z, Chen H. A neural decoding algorithm that generates language from visual activity evoked by natural images. Neural Netw 2021; 144:90-100. [PMID: 34478941 DOI: 10.1016/j.neunet.2021.08.006] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2021] [Revised: 06/22/2021] [Accepted: 08/05/2021] [Indexed: 11/23/2022]
Abstract
Transforming neural activities into language is revolutionary for human-computer interaction as well as functional restoration of aphasia. Present rapid development of artificial intelligence makes it feasible to decode the neural signals of human visual activities. In this paper, a novel Progressive Transfer Language Decoding Model (PT-LDM) is proposed to decode visual fMRI signals into phrases or sentences when natural images are being watched. The PT-LDM consists of an image-encoder, a fMRI encoder and a language-decoder. The results showed that phrases and sentences were successfully generated from visual activities. Similarity analysis showed that three often-used evaluation indexes BLEU, ROUGE and CIDEr reached 0.182, 0.197 and 0.680 averagely between the generated texts and the corresponding annotated texts in the testing set respectively, significantly higher than the baseline. Moreover, we found that higher visual areas usually had better performance than lower visual areas and the contribution curve of visual response patterns in language decoding varied at successively different time points. Our findings demonstrate that the neural representations elicited in visual cortices when scenes are being viewed have already contained semantic information that can be utilized to generate human language. Our study shows potential application of language-based brain-machine interfaces in the future, especially for assisting aphasics in communicating more efficiently with fMRI signals.
Collapse
|
42
|
Abstract
Movies, audio stories, and virtual reality are increasingly used as stimuli for functional brain imaging. Such naturalistic paradigms are in sharp contrast to the tradition of experimental reductionism in neuroscience research. Being complex, dynamic, and diverse, naturalistic stimuli set up a more ecologically relevant condition and induce highly reproducible brain responses across a wide range of spatiotemporal scales. Here, we review recent technical advances and scientific findings on imaging the brain under naturalistic stimuli. Then we elaborate on the premise of using naturalistic paradigms for multi-scale, multi-modal, and high-throughput functional characterization of the human brain. We further highlight the growing potential of using deep learning models to infer neural information processing from brain responses to naturalistic stimuli. Lastly, we advocate large-scale collaborations to combine brain imaging and recording data across experiments, subjects, and labs that use the same set of naturalistic stimuli.
Collapse
Affiliation(s)
- Yizhen Zhang
- Department of Electrical Engineering and Computer Science, University of Michigan
| | - Jung-Hoon Kim
- Department of Biomedical Engineering, University of Michigan
- Weldon School of Biomedical Engineering, Purdue University
| | - David Brang
- Department of Psychology, University of Michigan
| | - Zhongming Liu
- Department of Electrical Engineering and Computer Science, University of Michigan
- Department of Biomedical Engineering, University of Michigan
| |
Collapse
|
43
|
Misra J, Surampudi SG, Venkatesh M, Limbachia C, Jaja J, Pessoa L. Learning brain dynamics for decoding and predicting individual differences. PLoS Comput Biol 2021; 17:e1008943. [PMID: 34478442 PMCID: PMC8445454 DOI: 10.1371/journal.pcbi.1008943] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2021] [Revised: 09/16/2021] [Accepted: 08/19/2021] [Indexed: 12/04/2022] Open
Abstract
Insights from functional Magnetic Resonance Imaging (fMRI), as well as recordings of large numbers of neurons, reveal that many cognitive, emotional, and motor functions depend on the multivariate interactions of brain signals. To decode brain dynamics, we propose an architecture based on recurrent neural networks to uncover distributed spatiotemporal signatures. We demonstrate the potential of the approach using human fMRI data during movie-watching data and a continuous experimental paradigm. The model was able to learn spatiotemporal patterns that supported 15-way movie-clip classification (∼90%) at the level of brain regions, and binary classification of experimental conditions (∼60%) at the level of voxels. The model was also able to learn individual differences in measures of fluid intelligence and verbal IQ at levels comparable to that of existing techniques. We propose a dimensionality reduction approach that uncovers low-dimensional trajectories and captures essential informational (i.e., classification related) properties of brain dynamics. Finally, saliency maps and lesion analysis were employed to characterize brain-region/voxel importance, and uncovered how dynamic but consistent changes in fMRI activation influenced decoding performance. When applied at the level of voxels, our framework implements a dynamic version of multivariate pattern analysis. Our approach provides a framework for visualizing, analyzing, and discovering dynamic spatially distributed brain representations during naturalistic conditions.
Collapse
Affiliation(s)
- Joyneel Misra
- Department of Electrical and Computer Engineering, University of Maryland, College Park, Maryland, United States of America
| | - Srinivas Govinda Surampudi
- Department of Electrical and Computer Engineering, University of Maryland, College Park, Maryland, United States of America
| | - Manasij Venkatesh
- Department of Electrical and Computer Engineering, University of Maryland, College Park, Maryland, United States of America
| | - Chirag Limbachia
- Department of Psychology and Maryland Neuroimaging Center, University of Maryland, College Park, Maryland, United States of America
| | - Joseph Jaja
- Department of Electrical and Computer Engineering, University of Maryland, College Park, Maryland, United States of America
| | - Luiz Pessoa
- Department of Electrical and Computer Engineering, University of Maryland, College Park, Maryland, United States of America
- Department of Psychology and Maryland Neuroimaging Center, University of Maryland, College Park, Maryland, United States of America
| |
Collapse
|
44
|
Çelik E, Keles U, Kiremitçi İ, Gallant JL, Çukur T. Cortical networks of dynamic scene category representation in the human brain. Cortex 2021; 143:127-147. [PMID: 34411847 DOI: 10.1016/j.cortex.2021.07.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2020] [Revised: 06/28/2021] [Accepted: 07/14/2021] [Indexed: 10/20/2022]
Abstract
Humans have an impressive ability to rapidly process global information in natural scenes to infer their category. Yet, it remains unclear whether and how scene categories observed dynamically in the natural world are represented in cerebral cortex beyond few canonical scene-selective areas. To address this question, here we examined the representation of dynamic visual scenes by recording whole-brain blood oxygenation level-dependent (BOLD) responses while subjects viewed natural movies. We fit voxelwise encoding models to estimate tuning for scene categories that reflect statistical ensembles of objects and actions in the natural world. We find that this scene-category model explains a significant portion of the response variance broadly across cerebral cortex. Cluster analysis of scene-category tuning profiles across cortex reveals nine spatially-segregated networks of brain regions consistently across subjects. These networks show heterogeneous tuning for a diverse set of dynamic scene categories related to navigation, human activity, social interaction, civilization, natural environment, non-human animals, motion-energy, and texture, suggesting that the organization of scene category representation is quite complex.
Collapse
Affiliation(s)
- Emin Çelik
- Neuroscience Program, Sabuncu Brain Research Center, Bilkent University, Ankara, Turkey; National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey.
| | - Umit Keles
- National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey; Division of Humanities and Social Sciences, California Institute of Technology, Pasadena, CA, USA
| | - İbrahim Kiremitçi
- Neuroscience Program, Sabuncu Brain Research Center, Bilkent University, Ankara, Turkey; National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey
| | - Jack L Gallant
- Helen Wills Neuroscience Institute, University of California, Berkeley, Berkeley, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA; Department of Psychology, University of California, Berkeley, CA, USA
| | - Tolga Çukur
- Neuroscience Program, Sabuncu Brain Research Center, Bilkent University, Ankara, Turkey; National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey; Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Turkey
| |
Collapse
|
45
|
Russ BE, Petkov CI, Kwok SC, Zhu Q, Belin P, Vanduffel W, Hamed SB. Common functional localizers to enhance NHP & cross-species neuroscience imaging research. Neuroimage 2021; 237:118203. [PMID: 34048898 PMCID: PMC8529529 DOI: 10.1016/j.neuroimage.2021.118203] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2020] [Revised: 05/15/2021] [Accepted: 05/24/2021] [Indexed: 11/25/2022] Open
Abstract
Functional localizers are invaluable as they can help define regions of interest, provide cross-study comparisons, and most importantly, allow for the aggregation and meta-analyses of data across studies and laboratories. To achieve these goals within the non-human primate (NHP) imaging community, there is a pressing need for the use of standardized and validated localizers that can be readily implemented across different groups. The goal of this paper is to provide an overview of the value of localizer protocols to imaging research and we describe a number of commonly used or novel localizers within NHPs, and keys to implement them across studies. As has been shown with the aggregation of resting-state imaging data in the original PRIME-DE submissions, we believe that the field is ready to apply the same initiative for task-based functional localizers in NHP imaging. By coming together to collect large datasets across research group, implementing the same functional localizers, and sharing the localizers and data via PRIME-DE, it is now possible to fully test their robustness, selectivity and specificity. To do this, we reviewed a number of common localizers and we created a repository of well-established localizer that are easily accessible and implemented through the PRIME-RE platform.
Collapse
Affiliation(s)
- Brian E Russ
- Center for Biomedical Imaging and Neuromodulation, Nathan Kline Institute, Orangeburg, NY, United States; Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York City, NY, United States; Department of Psychiatry, New York University at Langone, New York City, NY, United States.
| | - Christopher I Petkov
- Biosciences Institute, Newcastle University Medical School, Newcastle upon Tyne, United Kingdom
| | - Sze Chai Kwok
- Shanghai Key Laboratory of Brain Functional Genomics, Key Laboratory of Brain Functional Genomics Ministry of Education, Shanghai Key Laboratory of Magnetic Resonance, Affiliated Mental Health Center (ECNU), School of Psychology and Cognitive Science, East China Normal University, Shanghai, China; Division of Natural and Applied Sciences, Duke Kunshan University, Kunshan, Jiangsu, China; NYU-ECNU Institute of Brain and Cognitive Science at NYU Shanghai, Shanghai, China
| | - Qi Zhu
- Cognitive Neuroimaging Unit, INSERM, CEA, Université Paris-Saclay, NeuroSpin Center, 91191 Gif/Yvette, France; Laboratory for Neuro-and Psychophysiology, Department of Neurosciences, KU Leuven Medical School, Leuven, 3000, Belgium
| | - Pascal Belin
- Institut de Neurosciences de La Timone, Aix-Marseille Université et CNRS, Marseille, 13005, France
| | - Wim Vanduffel
- Laboratory for Neuro-and Psychophysiology, Department of Neurosciences, KU Leuven Medical School, Leuven, 3000, Belgium; Leuven Brain Institute, KU Leuven, Leuven, 3000, Belgium; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA 02129, United States; Department of Radiology, Harvard Medical School, Boston, MA 02144, United States.
| | - Suliann Ben Hamed
- Institut des Sciences Cognitives Marc Jeannerod, UMR 5229, Université de Lyon - CNRS, France.
| |
Collapse
|
46
|
Li J, Zhang C, Wang L, Ding P, Hu L, Yan B, Tong L. A Visual Encoding Model Based on Contrastive Self-Supervised Learning for Human Brain Activity along the Ventral Visual Stream. Brain Sci 2021; 11:1004. [PMID: 34439623 DOI: 10.3390/brainsci11081004] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2021] [Revised: 07/23/2021] [Accepted: 07/26/2021] [Indexed: 11/30/2022] Open
Abstract
Visual encoding models are important computational models for understanding how information is processed along the visual stream. Many improved visual encoding models have been developed from the perspective of the model architecture and the learning objective, but these are limited to the supervised learning method. From the view of unsupervised learning mechanisms, this paper utilized a pre-trained neural network to construct a visual encoding model based on contrastive self-supervised learning for the ventral visual stream measured by functional magnetic resonance imaging (fMRI). We first extracted features using the ResNet50 model pre-trained in contrastive self-supervised learning (ResNet50-CSL model), trained a linear regression model for each voxel, and finally calculated the prediction accuracy of different voxels. Compared with the ResNet50 model pre-trained in a supervised classification task, the ResNet50-CSL model achieved an equal or even relatively better encoding performance in multiple visual cortical areas. Moreover, the ResNet50-CSL model performs hierarchical representation of input visual stimuli, which is similar to the human visual cortex in its hierarchical information processing. Our experimental results suggest that the encoding model based on contrastive self-supervised learning is a strong computational model to compete with supervised models, and contrastive self-supervised learning proves an effective learning method to extract human brain-like representations.
Collapse
|
47
|
Qiang N, Dong Q, Liang H, Ge B, Zhang S, Sun Y, Zhang C, Zhang W, Gao J, Liu T. Modeling and augmenting of fMRI data using deep recurrent variational auto-encoder. J Neural Eng 2021; 18. [PMID: 34229310 DOI: 10.1088/1741-2552/ac1179] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2020] [Accepted: 07/06/2021] [Indexed: 11/11/2022]
Abstract
Objective. Recently, deep learning models have been successfully applied in functional magnetic resonance imaging (fMRI) modeling and associated applications. However, there still exist at least two challenges. Firstly, due to the lack of sufficient data, deep learning models tend to suffer from overfitting in the training process. Secondly, it is still challenging to model the temporal dynamics from fMRI, due to that the brain state is continuously changing over scan time. In addition, existing methods rarely studied and applied fMRI data augmentation.Approach. In this work, we construct a deep recurrent variational auto-encoder (DRVAE) that combined variational auto-encoder and recurrent neural network, aiming to address all of the above mentioned challenges. The encoder of DRVAE can extract more generalized temporal features from assumed Gaussian distribution of input data, and the decoder of DRVAE can generate new data to increase training samples and thus partially relieve the overfitting issue. The recurrent layers in DRVAE are designed to effectively model the temporal dynamics of functional brain activities. LASSO (least absolute shrinkage and selection operator) regression is applied on the temporal features and input fMRI data to estimate the corresponding spatial networks.Main results. Extensive experimental results on seven tasks from HCP dataset showed that the DRVAE and LASSO framework can learn meaningful temporal patterns and spatial networks from both real data and generated data. The results on group-wise data and single subject suggest that the brain activities may follow certain distribution. Moreover, we applied DRVAE on four resting state fMRI datasets from ADHD-200 for data augmentation, and the results showed that the classification performances on augmented datasets have been considerably improved.Significance. The proposed method can not only derive meaningful temporal features and spatial networks from fMRI, but also generate high-quality new data for fMRI data augmentation and associated applications.
Collapse
Affiliation(s)
- Ning Qiang
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, People's Republic of China.,Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, People's Republic of China
| | - Qinglin Dong
- Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States of America
| | - Hongtao Liang
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, People's Republic of China
| | - Bao Ge
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, People's Republic of China.,Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, People's Republic of China
| | - Shu Zhang
- Center for Brain and Brain-Inspired Computing Research, Department of Computer Science, Northwestern Polytechnical University, Xi'an, People's Republic of China
| | - Yifei Sun
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, People's Republic of China
| | - Cheng Zhang
- School of Electronics Engineering and Computer Science, Peking University, Beijing, People's Republic of China
| | - Wei Zhang
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States of America
| | - Jie Gao
- School of Physics and Information Technology, Shaanxi Normal University, Xi'an, People's Republic of China
| | - Tianming Liu
- Cortical Architecture Imaging and Discovery Lab, Department of Computer Science and Bioimaging Research Center, The University of Georgia, Athens, GA, United States of America
| |
Collapse
|
48
|
Abstract
Current data generation capabilities in the life sciences render scientists in an apparently contradicting situation. While it is possible to simultaneously measure an ever-increasing number of systems parameters, the resulting data are becoming increasingly difficult to interpret. Latent variable modeling allows for such interpretation by learning non-measurable hidden variables from observations. This review gives an overview over the different formal approaches to latent variable modeling, as well as applications at different scales of biological systems, such as molecular structures, intra- and intercellular regulatory up to physiological networks. The focus is on demonstrating how these approaches have enabled interpretable representations and ultimately insights in each of these domains. We anticipate that a wider dissemination of latent variable modeling in the life sciences will enable a more effective and productive interpretation of studies based on heterogeneous and high-dimensional data modalities.
Collapse
Affiliation(s)
- Andreas Kopf
- Institute of Molecular Systems Biology, ETH Zürich, 8093 Zürich, Switzerland
| | - Manfred Claassen
- Division of Clinical Bioinformatics, Department of Internal Medicine I, University Hospital Tübingen, 72076 Tübingen, Germany
- Computer Science Department, Eberhard Karls University of Tübingen, 72076 Tübingen, Germany
- Cluster of Excellence Machine Learning (EXC 2064), Eberhard Karls University of Tübingen, 72076 Tübingen, Germany
| |
Collapse
|
49
|
Huang W, Yan H, Wang C, Yang X, Li J, Zuo Z, Zhang J, Chen H. Deep Natural Image Reconstruction from Human Brain Activity Based on Conditional Progressively Growing Generative Adversarial Networks. Neurosci Bull 2021; 37:369-379. [PMID: 33222145 PMCID: PMC7954952 DOI: 10.1007/s12264-020-00613-4] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2020] [Accepted: 06/16/2020] [Indexed: 01/01/2023] Open
Abstract
Brain decoding based on functional magnetic resonance imaging has recently enabled the identification of visual perception and mental states. However, due to the limitations of sample size and the lack of an effective reconstruction model, accurate reconstruction of natural images is still a major challenge. The current, rapid development of deep learning models provides the possibility of overcoming these obstacles. Here, we propose a deep learning-based framework that includes a latent feature extractor, a latent feature decoder, and a natural image generator, to achieve the accurate reconstruction of natural images from brain activity. The latent feature extractor is used to extract the latent features of natural images. The latent feature decoder predicts the latent features of natural images based on the response signals from the higher visual cortex. The natural image generator is applied to generate reconstructed images from the predicted latent features of natural images and the response signals from the visual cortex. Quantitative and qualitative evaluations were conducted with test images. The results showed that the reconstructed image achieved comparable, accurate reproduction of the presented image in both high-level semantic category information and low-level pixel information. The framework we propose shows promise for decoding the brain activity.
Collapse
Affiliation(s)
- Wei Huang
- The MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Hongmei Yan
- The MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, 610054, China.
| | - Chong Wang
- The MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Xiaoqing Yang
- The MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Jiyi Li
- The MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, 610054, China
| | - Zhentao Zuo
- State Key Laboratory of Brain and Cognitive Science, Beijing MR Center for Brain Research, Institute of Biophysics, Chinese Academy of Sciences, Beijing, 100101, China.
| | - Jiang Zhang
- Department of Medical Information Engineering, Sichuan University, Chengdu, 610065, China
| | - Huafu Chen
- The MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, 610054, China.
| |
Collapse
|
50
|
Cui Y, Qiao K, Zhang C, Wang L, Yan B, Tong L. GaborNet Visual Encoding: A Lightweight Region-Based Visual Encoding Model With Good Expressiveness and Biological Interpretability. Front Neurosci 2021; 15:614182. [PMID: 33613179 PMCID: PMC7893978 DOI: 10.3389/fnins.2021.614182] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2020] [Accepted: 01/04/2021] [Indexed: 11/17/2022] Open
Abstract
Computational visual encoding models play a key role in understanding the stimulus-response characteristics of neuronal populations in the brain visual cortex. However, building such models typically faces challenges in the effective construction of non-linear feature spaces to fit the neuronal responses. In this work, we propose the GaborNet visual encoding (GaborNet-VE) model, a novel end-to-end encoding model for the visual ventral stream. This model comprises a Gabor convolutional layer, two regular convolutional layers, and a fully connected layer. The key design principle for the GaborNet-VE model is to replace regular convolutional kernels in the first convolutional layer with Gabor kernels with learnable parameters. One GaborNet-VE model efficiently and simultaneously encodes all voxels in one region of interest of functional magnetic resonance imaging data. The experimental results show that the proposed model achieves state-of-the-art prediction performance for the primary visual cortex. Moreover, the visualizations demonstrate the regularity of the region of interest fitting to the visual features and the estimated receptive fields. These results suggest that the lightweight region-based GaborNet-VE model based on combining handcrafted and deep learning features exhibits good expressiveness and biological interpretability.
Collapse
Affiliation(s)
| | | | | | | | | | - Li Tong
- Henan Key Laboratory of Imaging and Intelligent Processing, PLA Strategic Support Force Information Engineering University, Zhengzhou, China
| |
Collapse
|