Machine Learning

Machine Learning

Machine learning offers great promise as a tool for providing individualized diagnostic and prognostic biomarkers. Although various imaging measures are affected by diseases in various ways, it is rare to find a single measure that provides sufficient sensitivity and specificity when classifying an individual. Machine learning methods can achieve high classification performance of individuals by leveraging the power of multi-variate pattern analysis. Our group has a long-standing engagement in the development and application of machine learning methods for structural and functional MRI [1-4]. Starting from the conventional supervised learning paradigm, such as finding a discriminative pattern that separates patients form controls, we later moved to semi-supervised learning, in which subtypes of disease are elucidated by different imaging patterns [5-8].

Current Projects


Heterogeneity through Discriminative Analysis — HYDRA and Clustering of Heterogeneous Disease Effects via Distribution Matching of Imaging Patterns —  CHIMERA

— Multivariate inference using discriminatively adaptive smoothing — MIDAS 

— NMF-based Decomposition — NMF

Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy

Individualized functional network modeling 

— Grassmann manifold learning for discriminant analysis of functional connectivity patterns — Functional connectivity patterns

Deep learning of task and resting state fMRI data

Deep learning of structure MRI data for early prediction of Alzheimer's disease dementia

Federated Learning

Past Projects

— Diagnosis and prognosis using brain scans based on robust regional measures — COMPARE

—  Ensemble Classification

  • A method to train an ensemble of experts (classifiers) on the given training data, using a multitude of features to produce a less complex model with better performance. Project Page: work in progress

— Generative-Discriminative Basis Learning —  GONDOLA

— Deriving statistical significance maps from support vector machine (SVM) classifiers, in order to elucidate features that significantly contribute to the classification — SVM Significance 

[1]        Z. Lao, D. Shen, Z. Xue, B. Karacali, S. M. Resnick, and C. Davatzikos, "Morphological classification of brains via high-dimensional shape transformations and machine learning methods," Neuroimage, vol. 21, pp. 46-57, Jan 2004.
[2]        C. Davatzikos, K. Ruparel, Y. Fan, D. Shen, M. Acharyya, J. Loughead, et al., "Classifying spatial patterns of brain activity for lie-detection," Neuroimage, vol. 28, pp. 663-668, November 15, 2005 2005.
[3]        C. Davatzikos, D. G. Shen, R. C. Gur, X. Y. Wu, D. F. Liu, Y. Fan, et al., "Whole-brain morphometric study of schizophrenia revealing a spatially complex set of focal abnormalities," Archives of General Psychiatry, vol. 62, pp. 1218-1227, Nov 2005.
[4]        C. Davatzikos, Y. Fan, X. Wu, D. Shen, and S. M. Resnick, "Detection of prodromal Alzheimer's disease via pattern classification of magnetic resonance imaging," Neurobiology of Aging, vol. 29, pp. 514-523, Apr 2008.
[5]        R. Filipovych and C. Davatzikos, "Semi-supervised Pattern Classification of Medical Images: Application to Mild Cognitive Impairment (MCI)," Neuroimage, vol. 55, pp. 1109-19, 2011.
[6]        R. Filipovych, S. Resnick, and C. Davatzikos, "JointMMCC: Joint Maximum-Margin Classification and Clustering of Imaging Data," IEEE Transactions on Medical Imaging, vol. 31, pp. 1124-1140, 2012.
[7]        E. Varol, A. Sotiras, C. Davatzikos, and I. Alzheimer's Disease Neuroimaging, "HYDRA: Revealing heterogeneity of imaging and genetic patterns through a multiple max-margin discriminative analysis framework," Neuroimage, vol. 145, pp. 346-364, Jan 15 2017.
[8]        A. Dong, N. Honnorat, B. Gaonkar, and C. Davatzikos, "CHIMERA: Clustering of heterogeneous disease effects via distribution matching of imaging patterns," IEEE Trans Med Imaging, vol. 35, pp. 612-621, Oct 6 2016.
[9]        H. Li, M. Galperin-Aizenberg, D. Pryma, C. B. S. II, and Y. Fan, "Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy," Radiotherapy and Oncology, 2018.
[10]      Hangfan Liu, Hongming Li, Yuemeng Li, Shi Yin, Pamela Boimel, James Janopaul-Naylor, et al., "Adaptive Sparsity Regularization Based Collaborative Clustering for Cancer Prognosis," Lecture Notes in Computer Science vol. 11767, pp. 583-592, 2019.
[11]      Y. H. Du and Y. Fan, "Group information guided ICA for fMRI data analysis," Neuroimage, vol. 69, pp. 157-197, Apr 1 2013.
[12]      H. Li, T. D. Satterthwaite, and Y. Fan, "Large-scale sparse functional networks from resting state fMRI," Neuroimage, vol. 156, pp. 1-13, Aug 1 2017.
[13]      H. Li, X. Zhu, and Y. Fan, "Identification of Multi-scale Hierarchical Brain Functional Networks Using Deep Matrix Factorization," Cham, 2018, pp. 223-231.
[14]      Y. Fan, Y. Liu, H. Wu, Y. H. Hao, H. H. Liu, Z. N. Liu, et al., "Discriminant analysis of functional connectivity patterns on Grassmann manifold," Neuroimage, vol. 56, pp. 2058-2067, Jun 15 2011.
[15]      R. Jing, P. Li, Z. Ding, X. Lin, R. Zhao, L. Shi, et al., "Machine learning identifies unaffected first-degree relatives with functional network patterns and cognitive impairment similar to those of schizophrenia patients," Human Brain Mapping vol. 40, pp. 3930-3939, 2019.
[16]      Rixing Jing, Yongsheng Han, Hewei Cheng, Yongzhu Han, Kai Wang, Daniel Weintraub, et al., "Altered large-scale functional brain networks in neurological Wilson’s disease," Brain Imaging and Behavior, 2019.
[17]      R. R. Wetherill, H. Rao, N. Hager, J. Wang, T. R. Franklin, and Y. Fan, "Classifying and characterizing nicotine use disorder with high accuracy using machine learning and resting-state fMRI," Addict Biol, vol. 24, pp. 811-821, Jul 2019.
[18]      H. Li and Y. Fan, "Interpretable, highly accurate brain decoding of subtly distinct brain states from functional MRI using intrinsic functional networks and long short-term memory recurrent neural networks," Neuroimage, vol. 202, p. 116059, Nov 15 2019.
[19]      H. Li, T. D. Satterthwaite, and Y. Fan, "Brain Age Prediction Based on Resting-State Functional Connectivity Patterns Using Convolutional Neural Networks," Proc IEEE Int Symp Biomed Imaging, vol. 2018, pp. 101-104, Apr 2018.
[20]      H. Li, M. Habes, D. A. Wolk, Y. Fan, I. Alzheimer's Disease Neuroimaging, B. the Australian Imaging, et al., "A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data," Alzheimers Dement, vol. 15, pp. 1059-1070, Aug 2019.
[21]      H. Li, Y. Fan, and I. Alzheimer's Disease Neuroimaging, "Early Prediction of Alzheimer's Disease Dementia Based on Baseline Hippocampal Mri and 1-Year Follow-up Cognitive Measures Using Deep Recurrent Neural Networks," Proc IEEE Int Symp Biomed Imaging, vol. 2019, pp. 368-371, Apr 2019.
[22]      C. Davatzikos, F. Xu, Y. An, Y. Fan, and S. M. Resnick, "Longitudinal progression of Alzheimer's-like patterns of atrophy in normal older adults: the SPARE-AD index," Brain, vol. 132, pp. 2026-35, Aug 2009.
[23]      X. Da, J. B. Toledo, J. Zee, D. A. Wolk, S. X. Xie, Y. Ou, et al., "Integration and relative value of biomarkers for prediction of MCI to AD progression: spatial patterns of brain atrophy, cognitive scores, APOE genotype and CSF biomarkers," Neuroimage Clin, vol. 4, pp. 164-73, 2014.
[24]      H. Eavani, M. Habes, T. D. Satterthwaite, Y. An, M. K. Hsieh, N. Honnorat, et al., "Heterogeneity of structural and functional imaging patterns of advanced brain aging revealed via machine learning methods," Neurobiol Aging, vol. 71, pp. 41-50, Nov 2018.
[25]      A. Dong, J. B. Toledo, N. Honnorat, J. Doshi, E. Varol, A. Sotiras, et al., "Heterogeneity of neuroanatomical patterns in prodromal Alzheimer's disease: links to cognition, progression and biomarkers," Brain, vol. 140, pp. 735-747, Mar 01 2017.
[26]      N. Koutsouleris, E. M. Meisenzahl, S. Borgwardt, A. Riecher-Rossler, T. Frodl, J. Kambeitz, et al., "Individualized differential diagnosis of schizophrenia and mood disorders using neuroanatomical biomarkers," Brain, vol. 138, pp. 2059-73, Jul 2015.
[27]      N. Koutsouleris, E. M. Meisenzahl, C. Davatzikos, R. Bottlender, T. Frodl, J. Scheuerecker, et al., "Use of neuroanatomical pattern classification to identify subjects in at-risk mental States of psychosis and predict disease transition," Archives of General Psychiatry, vol. 66, pp. 700-712, Jul 2009.
[28]      Chand GB, Dwyer DB, Erus G, Sotiras A, Varol E, Srinivasan D, et al., "Neuroanatomical heterogeneity of schizophrenia quantified via semi-supervised machine learning reveals two distinct subtypes: results from the PHENOM consortium," in Society of Biological Psychiatry (SOBP), 2019.
[29]      A. Sotiras, S. M. Resnick, and C. Davatzikos, "Finding imaging patterns of structural covariance via Non-Negative Matrix Factorization," Neuroimage, vol. 108, pp. 1-16, MArch 2015.
[30]      A. Sotiras, J. B. Toledo, R. E. Gur, R. C. Gur, T. D. Satterthwaite, and C. Davatzikos, "Patterns of coordinated cortical remodeling during adolescence and their associations with functional specialization and evolutionary expansion," Proc Natl Acad Sci U S A, vol. 114, pp. 3527-3532, Mar 28 2017.