CS 230 Final project for Predicting Biological Age and Sex using SpatialTemporal Graph CNN for functional MRI data. Owned by Soham Gadgil, Sun Woo Kang, and Erick Siavichay-Velasco
The sex_clf branch has code for sex classification. The age_clf branch has code for binary age classification using cross entropy loss. The age_clf2 branch has code for age regression using MSELoss.
The master branch has code for getting the results of the analysis in a jupyter notebook analysis.ipynb.
For running the model, please refer to the instructions in the submodule ST-GCN from : https://github.com/yysijie/st-gcn
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition, Sijie Yan, Yuanjun Xiong and Dahua Lin, AAAI 2018. [Arxiv Preprint]
[1]G. H. Glover, “Overview of functional magnetic resonance imaging,”Neurosurgery clinics ofNorth America, vol. 22, no. 2, pp. 133–vii, Apr 2011, 21435566[pmid]. [Online]. Available:https://www.ncbi.nlm.nih.gov/pubmed/21435566
[2]H. M. Aycheh, J.-K. Seong, J.-H. Shin, D. L. Na, B. Kang, S. W. Seo, and K.-A.Sohn, “Biological brain age prediction using cortical thickness data: A large scale cohortstudy,”Frontiers in Aging Neuroscience, vol. 10, p. 252, 2018. [Online]. Available:https://www.frontiersin.org/article/10.3389/fnagi.2018.00252
[3]J. Zhai and K. Li, “Predicting brain age based on spatial and temporal features of humanbrain functional networks,”Frontiers in human neuroscience, vol. 13, pp. 62–62, Feb 2019,30863296[pmid]. [Online]. Available: https://www.ncbi.nlm.nih.gov/pubmed/30863296
[4]S. Weis, K. R. Patil, F. Hoffstaedter, A. Nostro, B. T. T. Yeo, and S. B. Eickhoff, “SexClassification by Resting State Brain Connectivity,”Cerebral Cortex, 06 2019, bhz129.[Online]. Available: https://doi.org/10.1093/cercor/bhz129
[5]D. V. Essen, K. Ugurbil, E. Auerbach, D. Barch, T. Behrens, R. Bucholz, A. Chang,L. Chen, M. Corbetta, S. Curtiss, S. D. Penna, D. Feinberg, M. Glasser, N. Harel, A. Heath,L. Larson-Prior, D. Marcus, G. Michalareas, S. Moeller, R. Oostenveld, S. Petersen, F. Prior,B. Schlaggar, S. Smith, A. Snyder, J. Xu, and E. Yacoub, “The human connectome project: Adata acquisition perspective,”NeuroImage, vol. 62, no. 4, pp. 2222 – 2231, 2012, connectivity.[Online]. Available: http://www.sciencedirect.com/science/article/pii/S1053811912001954
[6]C. Zhang, C. C. Dougherty, S. A. Baum, T. White, and A. M. Michael, “Functional connectivitypredicts gender: Evidence for gender differences in resting brain connectivity,” Apr 2018.[Online]. Available: https://www.ncbi.nlm.nih.gov/pubmed/29322586
[7]M. N. I. Qureshi, J. Oh, and B. Lee, “3d-cnn based discrimination of schizophrenia usingresting-state fmri,”Artificial Intelligence in Medicine, vol. 98, pp. 10 – 17, 2019. [Online].Available: http://www.sciencedirect.com/science/article/pii/S0933365719301393
[8]S. Yan, Y. Xiong, and D. Lin, “Spatial temporal graph convolutional networks for skeleton-basedaction recognition,” 2018.
[9]W. Zheng, P. Jing, and Q. Xu, “Action recognition based on spatial temporal graphconvolutional networks,” inProceedings of the 3rd International Conference on ComputerScience and Application Engineering, ser. CSAE 2019.New York, NY, USA: ACM, 2019, pp.118:1–118:5. [Online]. Available: http://doi.acm.org/10.1145/3331453.33616516
[10]Y. Li, Z. He, X. Ye, Z. He, and K. Han, “Spatial temporal graph convolutional networks forskeleton-based dynamic hand gesture recognition,”EURASIP Journal on Image and VideoProcessing, vol. 2019, no. 1, 2019.
[11]T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,”2016.
[12] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015.