Analysis of time-evolving data is crucial to understand the functioning of dynamic systems such as the brain. For instance, analysis of functional magnetic resonance imaging (fMRI) data collected during a task may reveal spatial regions of interest, and how they evolve during the task. However, capturing underlying spatial patterns as well as their change in time is challenging. The traditional approach in fMRI data analysis is to assume that underlying spatial regions of interest are static. In this article, using fractional amplitude of low-frequency fluctuations (fALFF) as an effective way to summarize the variability in fMRI data collected during a task, we arrange time-evolving fMRI data as a subjects by voxels by time windows tensor, and analyze the tensor using a tensor factorization-based approach called a PARAFAC2 model to reveal spatial dynamics. The PARAFAC2 model jointly analyzes data from multiple time windows revealing subject-mode patterns, evolving spatial regions (also referred to as networks) and temporal patterns. We compare the PARAFAC2 model with matrix factorization-based approaches relying on independent components, namely, joint independent component analysis (ICA) and independent vector analysis (IVA), commonly used in neuroimaging data analysis. We assess the performance of the methods in terms of capturing evolving networks through extensive numerical experiments demonstrating their modeling assumptions. In particular, we show that (i) PARAFAC2 provides a compact representation in all modes, i.e., subjects, time , and voxels , revealing temporal patterns as well as evolving spatial networks, (ii) joint ICA is as effective as PARAFAC2 in terms of revealing evolving networks but does not reveal temporal patterns, (iii) IVA's performance depends on sample size, data distribution and covariance structure of underlying networks. When these assumptions are satisfied, IVA is as accurate as the other methods, (iv) when subject-mode patterns differ from one time window to another, IVA is the most accurate. Furthermore, we analyze real fMRI data collected during a sensory motor task, and demonstrate that a component indicating statistically significant group difference between patients with schizophrenia and healthy controls is captured, which includes primary and secondary motor regions, cerebellum, and temporal lobe, revealing a meaningful spatial map and its temporal change.
more »
« less
Efficient estimation via envelope chain in magnetic resonance imaging‐based studies
Magnetic resonance imaging (MRI) is a technique that scans the anatomical structure of the brain, whereas functional magnetic resonance imaging (fMRI) uses the same basic principles of atomic physics as MRI scans but image metabolic function. A major goal of MRI and fMRI study is to precisely delineate various types of tissues, anatomical structure, pathologies, and detect the brain regions that react to outer stimuli (e.g., viewing an image). As a key feature of these MRI‐based neuroimaging data, voxels (cubic pixels of the brain volume) are highly correlated. However, the associations between voxels are often overlooked in the statistical analysis. We adapt a recently proposed dimension reduction method called the envelope method to analyze neuoimaging data taking into account correlation among voxels. We refer to the modified procedure the envelope chain procedure. Because the envelope chain procedure has not been employed before, we demonstrate in simulations the empirical performance of estimator, and examine its sensitivity when our assumptions are violated. We use the estimator to analyze the MRI data from ADHD‐200 study. Data analyses demonstrate that leveraging the correlations among voxels can significantly increase the efficiency of the regression analysis, thus achieving higher detection power with small sample sizes.
more » « less- Award ID(s):
- 1916013
- NSF-PAR ID:
- 10367371
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Scandinavian Journal of Statistics
- Volume:
- 49
- Issue:
- 2
- ISSN:
- 0303-6898
- Page Range / eLocation ID:
- p. 481-501
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Background Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment‐based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal‐to‐noise, contrast‐to‐noise) and segmentation accuracy.
Purpose Deep learning (DL) approaches have shown significant promise for automated segmentation of brain tumors on MRI but depend on the quality of input training images. We sought to evaluate the relationship between IQMs of input training images and DL‐based brain tumor segmentation accuracy toward developing more generalizable models for multi‐institutional data.
Methods We trained a 3D DenseNet model on the BraTS 2020 cohorts for segmentation of tumor subregions enhancing tumor (ET), peritumoral edematous, and necrotic and non‐ET on MRI; with performance quantified via a 5‐fold cross‐validated Dice coefficient. MRI scans were evaluated through the open‐source quality control tool MRQy, to yield 13 IQMs per scan. The Pearson correlation coefficient was computed between whole tumor (WT) dice values and IQM measures in the training cohorts to identify quality measures most correlated with segmentation performance. Each selected IQM was used to group MRI scans as “better” quality (BQ) or “worse” quality (WQ), via relative thresholding. Segmentation performance was re‐evaluated for the DenseNet model when (i) training on BQ MRI images with validation on WQ images, as well as (ii) training on WQ images, and validation on BQ images. Trends were further validated on independent test sets derived from the BraTS 2021 training cohorts.
Results For this study, multimodal MRI scans from the BraTS 2020 training cohorts were used to train the segmentation model and validated on independent test sets derived from the BraTS 2021 cohort. Among the selected IQMs, models trained on BQ images based on inhomogeneity measurements (coefficient of variance, coefficient of joint variation, coefficient of variation of the foreground patch) and the models trained on WQ images based on noise measurement peak signal‐to‐noise ratio (SNR) yielded significantly improved tumor segmentation accuracy compared to their inverse models.
Conclusions Our results suggest that a significant correlation may exist between specific MR IQMs and DenseNet‐based brain tumor segmentation performance. The selection of MRI scans for model training based on IQMs may yield more accurate and generalizable models in unseen validation.
-
more » « less
Abstract Objective . Spontaneous fluctuations of cerebral hemodynamics measured by functional magnetic resonance imaging (fMRI) are widely used to study the network organization of the brain. The temporal correlations among the ultra-slow, <0.1 Hz fluctuations across the brain regions are interpreted as functional connectivity maps and used for diagnostics of neurological disorders. However, despite the interest narrowed in the ultra-slow fluctuations, hemodynamic activity that exists beyond the ultra-slow frequency range could contribute to the functional connectivity, which remains unclear.Approach . In the present study, we have measured the brain-wide hemodynamics in the human participants with functional near-infrared spectroscopy (fNIRS) in a whole-head, cap-based and high-density montage at a sampling rate of 6.25 Hz. In addition, we have acquired resting state fMRI scans in the same group of participants for cross-modal evaluation of the connectivity maps. Then fNIRS data were deliberately down-sampled to a typical fMRI sampling rate of ∼0.5 Hz and the resulted differential connectivity maps were subject to a k-means clustering.Main results . Our diffuse optical topographical analysis of fNIRS data have revealed a default mode network (DMN) in the spontaneous deoxygenated and oxygenated hemoglobin changes, which remarkably resemble the same fMRI network derived from participants. Moreover, we have shown that the aliased activities in the down-sampled optical signals have altered the connectivity patterns, resulting in a network organization of aliased functional connectivity in the cerebral hemodynamics.Significance. The results have for the first time demonstrated that fNIRS as a broadly accessible modality can image the resting-state functional connectivity in the posterior midline, prefrontal and parietal structures of the DMN in the human brain, in a consistent pattern with fMRI. Further empowered by the fast sampling rate of fNIRS, our findings suggest the presence of aliased connectivity in the current understanding of the human brain organization. -
Brain large-scale dynamics is constrained by the heterogeneity of intrinsic anatomical substrate. Little is known how the spatiotemporal dynamics adapt for the heterogeneous structural connectivity (SC). Modern neuroimaging modalities make it possible to study the intrinsic brain activity at the scale of seconds to minutes. Diffusion magnetic resonance imaging (dMRI) and functional MRI reveals the large-scale SC across different brain regions. Electrophysiological methods (i.e. MEG/EEG) provide direct measures of neural activity and exhibits complex neurobiological temporal dynamics which could not be solved by fMRI. However, most of existing multimodal analytical methods collapse the brain measurements either in space or time domain and fail to capture the spatio-temporal circuit dynamics. In this paper, we propose a novel spatio-temporal graph Transformer model to integrate the structural and functional connectivity in both spatial and temporal domain. The proposed method learns the heterogeneous node and graph representation via contrastive learning and multi-head attention based graph Transformer using multimodal brain data (i.e. fMRI, MRI, MEG and behavior performance). The proposed contrastive graph Transformer representation model incorporates the heterogeneity map constrained by T1-to-T2-weighted (T1w/T2w) to improve the model fit to structurefunction interactions. The experimental results with multimodal resting state brain measurements demonstrate the proposed method could highlight the local properties of large-scale brain spatio-temporal dynamics and capture the dependence strength between functional connectivity and behaviors. In summary, the proposed method enables the complex brain dynamics explanation for different modal variants.more » « less
-
more » « less
Abstract There is growing evidence that rather than using a single brain imaging modality to study its association with physiological or symptomatic features, the field is paying more attention to fusion of multimodal information. However, most current multimodal fusion approaches that incorporate functional magnetic resonance imaging (fMRI) are restricted to second‐level 3D features, rather than the original 4D fMRI data. This trade‐off is that the valuable temporal information is not utilized during the fusion step. Here we are motivated to propose a novel approach called “parallel group ICA+ICA” that incorporates temporal fMRI information from group independent component analysis (GICA) into a parallel independent component analysis (ICA) framework, aiming to enable direct fusion of first‐level fMRI features with other modalities (e.g., structural MRI), which thus can detect linked functional network variability and structural covariations. Simulation results show that the proposed method yields accurate intermodality linkage detection regardless of whether it is strong or weak. When applied to real data, we identified one pair of significantly associated fMRI‐sMRI components that show group difference between schizophrenia and controls in both modalities, and this linkage can be replicated in an independent cohort. Finally, multiple cognitive domain scores can be predicted by the features identified in the linked component pair by our proposed method. We also show these multimodal brain features can predict multiple cognitive scores in an independent cohort. Overall, results demonstrate the ability of parallel GICA+ICA to estimate joint information from 4D and 3D data without discarding much of the available information up front, and the potential for using this approach to identify imaging biomarkers to study brain disorders.
