Match!

Discriminating schizophrenia using recurrent neural network applied on time courses of multi-site FMRI data

Published on Sep 1, 2019in EBioMedicine6.68
· DOI :10.1016/j.ebiom.2019.08.023
Weizheng Yan2
Estimated H-index: 2
(CAS: Chinese Academy of Sciences),
Vince D. Calhoun93
Estimated H-index: 93
+ 22 AuthorsJing Sui31
Estimated H-index: 31
(CAS: Chinese Academy of Sciences)
Abstract
Abstract Background Current fMRI-based classification approaches mostly use functional connectivity or spatial maps as input, instead of exploring the dynamic time courses directly, which does not leverage the full temporal information. Methods Motivated by the ability of recurrent neural networks (RNN) in capturing dynamic information of time sequences, we propose a multi-scale RNN model, which enables classification between 558 schizophrenia and 542 healthy controls by using time courses of fMRI independent components (ICs) directly. To increase interpretability, we also propose a leave-one-IC-out looping strategy for estimating the top contributing ICs. Findings Accuracies of 83·2% and 80·2% were obtained respectively for the multi-site pooling and leave-one-site-out transfer classification. Subsequently, dorsal striatum and cerebellum components contribute the top two group-discriminative time courses, which is true even when adopting different brain atlases to extract time series. Interpretation This is the first attempt to apply a multi-scale RNN model directly on fMRI time courses for classification of mental disorders, and shows the potential for multi-scale RNN-based neuroimaging classifications. Fund Natural Science Foundation of China, the Strategic Priority Research Program of the Chinese Academy of Sciences, National Institutes of Health Grants, National Science Foundation.
  • References (50)
  • Citations (1)
📖 Papers frequently viewed together
2018
7 Authors (Atif Riaz, ..., Gregory G. Slabaugh)
2 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References50
Newest
#1Christos Davatzikos (UPenn: University of Pennsylvania)H-Index: 82
#2Aristeidis Sotiras (UPenn: University of Pennsylvania)H-Index: 14
Last. Despina Kontos (UPenn: University of Pennsylvania)H-Index: 21
view all 10 authors...
Abstract The complexity of modern multi-parametric MRI has increasingly challenged conventional interpretations of such images. Machine learning has emerged as a powerful approach to integrating diverse and complex imaging data into signatures of diagnostic and predictive value. It has also allowed us to progress from group comparisons to imaging biomarkers that offer value on an individual basis. We review several directions of research around this topic, emphasizing the use of machine learning...
2 CitationsSource
#1Daniel Durstewitz (Heidelberg University)H-Index: 12
#2Georgia Koppe (Heidelberg University)H-Index: 7
Last. Andreas Meyer-Lindenberg (Heidelberg University)H-Index: 88
view all 3 authors...
Machine and deep learning methods, today’s core of artificial intelligence, have been applied with increasing success and impact in many commercial and research settings. They are powerful tools for large scale data analysis, prediction and classification, especially in very data-rich environments (“big data”), and have started to find their way into medical applications. Here we will first give an overview of machine learning methods, with a focus on deep and recurrent neural networks, their re...
6 CitationsSource
#1Shengfeng LiuH-Index: 4
#2Haiying Wang (Harbin University of Science and Technology)H-Index: 1
Last. Jing SuiH-Index: 31
view all 32 authors...
Multimodal fusion has been regarded as a promising tool to discover covarying patterns of multiple imaging types impaired in brain diseases, such as schizophrenia (SZ). In this article, we aim to investigate the covarying abnormalities underlying SZ in a large Chinese Han population (307 SZs, 298 healthy controls [HCs]). Four types of magnetic resonance imaging (MRI) features, including regional homogeneity (ReHo) from resting-state functional MRI, gray matter volume (GM) from structural MRI, fr...
5 CitationsSource
#1Sergey M. Plis (The Mind Research Network)H-Index: 20
#2Faijul Amin (The Mind Research Network)H-Index: 1
Last. Vince D. Calhoun (UNM: University of New Mexico)H-Index: 93
view all 10 authors...
Abstract This work presents a novel approach to finding linkage/association between multimodal brain imaging data, such as structural MRI (sMRI) and functional MRI (fMRI). Motivated by the machine translation domain, we employ a deep learning model, and consider two different imaging views of the same brain like two different languages conveying some common facts. That analogy enables finding linkages between two modalities. The proposed translation-based fusion model contains a computing layer ...
4 CitationsSource
Sep 16, 2018 in MICCAI (Medical Image Computing and Computer-Assisted Intervention)
#1Hongming Li (UPenn: University of Pennsylvania)H-Index: 8
#2Yong Fan (UPenn: University of Pennsylvania)H-Index: 30
Dynamic functional connectivity analysis provides valuable information for understanding brain functional activity underlying different cognitive processes. Besides sliding window based approaches, a variety of methods have been developed to automatically split the entire functional MRI scan into segments by detecting change points of functional signals to facilitate better characterization of temporally dynamic functional connectivity patterns. However, these methods are based on certain assump...
5 CitationsSource
Sep 16, 2018 in MICCAI (Medical Image Computing and Computer-Assisted Intervention)
#1Hongming Li (UPenn: University of Pennsylvania)H-Index: 8
#2Yong Fan (UPenn: University of Pennsylvania)H-Index: 30
Decoding brain functional states underlying different cognitive processes using multivariate pattern recognition techniques has attracted increasing interests in brain imaging studies. Promising performance has been achieved using brain functional connectivity or brain activation signatures for a variety of brain decoding tasks. However, most of existing studies have built decoding models upon features extracted from imaging data at individual time points or temporal windows with a fixed interva...
9 CitationsSource
#1Jing SuiH-Index: 31
#2Shile Qi (CAS: Chinese Academy of Sciences)H-Index: 5
Last. Vince D. Calhoun (UNM: University of New Mexico)H-Index: 93
view all 25 authors...
Cognitive impairment is a feature of many psychiatric diseases, including schizophrenia. Here we aim to identify multimodal biomarkers for quantifying and predicting cognitive performance in individuals with schizophrenia and healthy controls. A supervised learning strategy is used to guide three-way multimodal magnetic resonance imaging (MRI) fusion in two independent cohorts including both healthy individuals and individuals with schizophrenia using multiple cognitive domain scores. Results hi...
21 CitationsSource
#1Ling-Li Zeng (National University of Defense Technology)H-Index: 17
#2Huaning Wang (Fourth Military Medical University)H-Index: 18
Last. Dewen Hu (National University of Defense Technology)H-Index: 35
view all 12 authors...
Abstract Background A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classif...
25 CitationsSource
#1Subhrajit RoyH-Index: 10
Last. Stefan HarrerH-Index: 12
view all 3 authors...
Brain-related disorders such as epilepsy can be diagnosed by analyzing electroencephalograms (EEG). However, manual analysis of EEG data requires highly trained clinicians, and is a procedure that is known to have relatively low inter-rater agreement (IRA). Moreover, the volume of the data and the rate at which new data becomes available make manual interpretation a time-consuming, resource-hungry, and expensive process. In contrast, automated analysis of EEG data offers the potential to improve...
10 Citations
#1Qingbao Yu (The Mind Research Network)H-Index: 20
#2Yuhui Du (Shanxi University)H-Index: 15
Last. Vince D. Calhoun (Yale University)H-Index: 93
view all 7 authors...
Abstract Background A key challenge in building a brain graph using fMRI data is how to define the nodes. Spatial brain components estimated by independent components analysis (ICA) and regions of interest (ROIs) determined by brain atlas are two popular methods to define nodes in brain graphs. It is difficult to evaluate which method is better in real fMRI data. New method Here we perform a simulation study and evaluate the accuracies of a few graph metrics in graphs with nodes of ICA component...
15 CitationsSource
Cited By1
Newest
#1Jianlong Zhao (CAS: Chinese Academy of Sciences)H-Index: 21
#2Jinjie Huang (Harbin University of Science and Technology)
Last. Vince D. Calhoun (Georgia Institute of Technology)H-Index: 93
view all 11 authors...
Abstract As a popular deep learning method, generative adversarial networks (GAN) have achieved outstanding performance in multiple classifications and segmentation tasks. However, the application of GANs to fMRI data is relatively rare. In this work, we proposed a functional network connectivity (FNC) based GAN for classifying psychotic disorders from healthy controls (HCs), in which FNC matrices were calculated by correlation of time courses derived from non-artefactual fMRI independent compon...
Source
#1Kyoungseob Byeon (SKKU: Sungkyunkwan University)H-Index: 1
Last. Hyunjin Park (SKKU: Sungkyunkwan University)H-Index: 17
view all 4 authors...
Distinguishing the autism spectrum disorder (ASD) from typical control (TC) using resting-state functional magnetic resonance imaging (rs-fMRI) is very difficult because ASD has heterogenetic properties and induce small changes in the brain structure. Moreover, distinguishing ASD from TC using the data obtained from many sites is even more difficult because many factors might negatively affect the classification model leading to unstable results. This difficulty is especially true for existing r...
Source
#1Jing Sui (CAS: Chinese Academy of Sciences)H-Index: 1
#1Jing Sui (CAS: Chinese Academy of Sciences)H-Index: 31
Last. Vince D. Calhoun (Georgia Institute of Technology)H-Index: 2
view all 5 authors...
1 CitationsSource
#1Jing SuiH-Index: 31
#2Rongtao JiangH-Index: 6
Last. Vince D. CalhounH-Index: 93
view all 4 authors...
Abstract The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move towards a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely-used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continu...
4 CitationsSource
#1Jing Sui (CAS: Chinese Academy of Sciences)H-Index: 31
#2Rongtao Jiang (CAS: Chinese Academy of Sciences)H-Index: 6
Last. Vince D. Calhoun (Georgia Institute of Technology)H-Index: 93
view all 4 authors...
The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move towards a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely-used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continuously beh...
Source
#2Daniel Remondini (UNIBO: University of Bologna)H-Index: 20
Last. Enrico GiampieriH-Index: 11
view all 3 authors...
WISDoM (Wishart Distributed Matrices) is a new framework for the characterization of symmetric positive-definite matrices associated to experimental samples, like covariance or correlation matrices, based on the Wishart distribution as a null model. WISDoM can be applied to tasks of supervised learning, like classification, even when such matrices are generated by data of different dimensionality (e.g. time series with same number of variables but different time sampling). In particular, we show...
#1Jianlong Zhao (CAS: Chinese Academy of Sciences)
#2Dongmei Zhi (CAS: Chinese Academy of Sciences)H-Index: 1
Last. Jing Sui (CAS: Chinese Academy of Sciences)H-Index: 31
view all 5 authors...
Functional network connectivity (FNC) obtained from resting-state functional magnetic resonance imaging (fMRI) data have been commonly used to study mental disorders in neuroimaging applications. Likewise, generative adversarial networks (GANs) have performed well in multiple classification benchmark tasks. However, the application of GANs to fMRI is relatively rare. In this work, we proposed an FNC-based GAN for classifying brain disorders from healthy controls (HCs), in which FNC matrices were...
Source