Estimating regional cerebral blood flow using resting-state functional MRI via machine learning

BACKGROUND Perfusion MRI is an important modality in many brain imaging protocols, since it probes cerebrovascular changes in aging and many diseases; however, it may not be always available. NEW METHOD We introduce a new method that seeks to estimate regional perfusion properties using spectral information of resting-state functional MRI (rsfMRI) via machine learning. We used pairs of rsfMRI and arterial spin labeling (ASL) images from the same individuals with normal cognition and mild cognitive impairment (MCI), and built support vector machine models aiming to estimate regional cerebral blood flow (CBF) from the rsfMRI signal alone. RESULTS This method demonstrated higher associations between the estimated CBF and actual CBF (ASL-CBF) at the total lobar gray matter (r = 0.40; FDR-p = 1.9e-03), parietal lobe (r = 0.46, FDR-p = 8e-04), and occipital lobe (r = 0.35; FDR-p = 0.01) using rsfMRI signals of frequencies [0.01-0.15] Hertz compared to frequencies [0.01-0.10] Hertz and [0.01-0.20] Hertz. We further observed significant associations between the estimated CBF and actual CBF in 24 regions of interest (p < 0.05), with the highest association observed in the superior parietal lobule (r = 0.50, FDR-p = 0.002). Moreover, the estimated CBF at superior parietal lobule showed significant correlation with the mini-mental state exam (MMSE) score (r = 0.27; FDR-p = 0.04) and decreased in MCI with lower MMSE score compared to NC group (FDR-p = 0.04). COMPARISON WITH EXISTING METHODS Consistent with previous findings, this new method also suggests that rsfMRI signals contain perfusion information. CONCLUSION The proposed framework can obtain estimates of regional perfusion from rsfMRI, which can serve as surrogate perfusion measures in the absence of ASL.

[1]  David C. Alsop,et al.  Hippocampal hyperperfusion in Alzheimer's disease , 2008, NeuroImage.

[2]  Maurizio Corbetta,et al.  The human brain is intrinsically organized into dynamic, anticorrelated functional networks. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[3]  N. Schuff,et al.  Pattern of cerebral hypoperfusion in Alzheimer disease and mild cognitive impairment measured with arterial spin-labeling MR imaging: initial experience. , 2005, Radiology.

[4]  Joseph V. Hajnal,et al.  Identification and characterisation of midbrain nuclei using optimised functional magnetic resonance imaging , 2012, NeuroImage.

[5]  Christos Davatzikos,et al.  White matter hyperintensities and imaging patterns of brain ageing in the general population. , 2016, Brain : a journal of neurology.

[6]  Kenneth F. Valyear,et al.  Human parietal cortex in action , 2006, Current Opinion in Neurobiology.

[7]  Jeff Duyn,et al.  H215O PET validation of steady‐state arterial spin tagging cerebral blood flow measurements in humans , 2000, Magnetic resonance in medicine.

[8]  Donald S. Williams,et al.  Perfusion imaging , 1992, Magnetic resonance in medicine.

[9]  Ya-Ting Chang,et al.  Cerebral Perfusion Insufficiency and Relationships with Cognitive Deficits in Alzheimer’s Disease: A Multiparametric Neuroimaging Study , 2018, Scientific Reports.

[10]  R. Turner,et al.  Dynamic magnetic resonance imaging of human brain activity during primary sensory stimulation. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Sterling C. Johnson,et al.  Macrovascular and microvascular cerebral blood flow in adults at risk for Alzheimer's disease , 2017, Alzheimer's & dementia.

[12]  Jie Lu,et al.  Detecting perfusion deficit in Alzheimer's disease and mild cognitive impairment patients by resting‐state fMRI , 2018, Journal of magnetic resonance imaging : JMRI.

[13]  J. Detre,et al.  Technical aspects and utility of fMRI using BOLD and ASL , 2002, Clinical Neurophysiology.

[14]  John A Detre,et al.  Arterial spin labeling MRI: an emerging biomarker for Alzheimer's disease and other neurodegenerative conditions. , 2012, Current opinion in neurology.

[15]  G. Zaharchuk,et al.  Recommended implementation of arterial spin-labeled perfusion MRI for clinical applications: A consensus of the ISMRM perfusion study group and the European consortium for ASL in dementia. , 2015, Magnetic resonance in medicine.

[16]  Paul A. Yushkevich,et al.  A brain stress test: Cerebral perfusion during memory encoding in mild cognitive impairment , 2016, NeuroImage: Clinical.

[17]  John A. Detre,et al.  Relations between BOLD fMRI-Derived Resting Brain Activity and Cerebral Blood Flow , 2012, PloS one.

[18]  Danny J. J. Wang,et al.  Reliability comparison of spontaneous brain activities between BOLD and CBF contrasts in eyes-open and eyes-closed resting states , 2015, NeuroImage.

[19]  R. Petersen Mild cognitive impairment as a diagnostic entity , 2004, Journal of internal medicine.

[20]  Ganesh B Chand,et al.  Disrupted interactions among the hippocampal, dorsal attention, and central‐executive networks in amnestic mild cognitive impairment , 2018, Human brain mapping.

[21]  Yunjie Tong,et al.  Tracking cerebral blood flow in BOLD fMRI using recursively generated regressors , 2014, Human brain mapping.

[22]  P. Fransson Spontaneous low‐frequency BOLD signal fluctuations: An fMRI investigation of the resting‐state default mode of brain function hypothesis , 2005, Human brain mapping.

[23]  G. Buzsáki,et al.  Neuronal Oscillations in Cortical Networks , 2004, Science.

[24]  Christian Windischberger,et al.  Toward discovery science of human brain function , 2010, Proceedings of the National Academy of Sciences.

[25]  Sven Haller,et al.  Arterial Spin Labeling Perfusion of the Brain: Emerging Clinical Applications. , 2016, Radiology.

[26]  C. Jack,et al.  Mild cognitive impairment: ten years later. , 2009, Archives of neurology.

[27]  Christos Davatzikos,et al.  MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection , 2016, NeuroImage.

[28]  John A. Detre,et al.  Characterizing a perfusion-based periventricular small vessel region of interest , 2019, NeuroImage: Clinical.

[29]  D. Pandya,et al.  Dorsolateral prefrontal cortex: comparative cytoarchitectonic analysis in the human and the macaque brain and corticocortical connection patterns , 1999, The European journal of neuroscience.

[30]  J. Haxby,et al.  Localization of Cardiac-Induced Signal Change in fMRI , 1999, NeuroImage.

[31]  Abass Alavi,et al.  Comparison of PASL, PCASL, and background‐suppressed 3D PCASL in mild cognitive impairment , 2017, Human brain mapping.

[32]  R. Petersen,et al.  Mild cognitive impairment , 2006, The Lancet.

[33]  R Nick Bryan,et al.  Comparison of non-invasive MRI measurements of cerebral blood flow in a large multisite cohort , 2016, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[34]  Arno Villringer,et al.  Identifying the perfusion deficit in acute stroke with resting‐state functional magnetic resonance imaging , 2013, Annals of neurology.

[35]  Pina C Sanelli,et al.  Neuroimaging of cerebrovascular disease in the aging brain. , 2012, Aging and disease.

[36]  J. Detre,et al.  Arterial spin labeling blood flow MRI: its role in the early characterization of Alzheimer's disease. , 2010, Journal of Alzheimer's disease : JAD.

[37]  Ze Wang,et al.  Improving cerebral blood flow quantification for arterial spin labeled perfusion MRI by removing residual motion artifacts and global signal fluctuations. , 2012, Magnetic resonance imaging.

[38]  G. Rizzolatti,et al.  Parietal Lobe: From Action Organization to Intention Understanding , 2005, Science.

[39]  Richard Frayne,et al.  Cerebrovascular MRI: a review of state‐of‐the‐art approaches, methods and techniques , 2015, NMR in biomedicine.

[40]  Gerald Langner,et al.  The oscillating brain , 2015 .

[41]  Yunjie Tong,et al.  Perfusion information extracted from resting state functional magnetic resonance imaging , 2017, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[42]  R. Buckner,et al.  Resting-state networks link invasive and noninvasive brain stimulation across diverse psychiatric and neurological diseases , 2014, Proceedings of the National Academy of Sciences.

[43]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[44]  Seth Love,et al.  Cerebrovascular disease in ageing and Alzheimer’s disease , 2015, Acta Neuropathologica.

[45]  James T Becker,et al.  Mild cognitive impairment and alzheimer disease: patterns of altered cerebral blood flow at MR imaging. , 2009, Radiology.

[46]  B. Biswal,et al.  Functional connectivity in the motor cortex of resting human brain using echo‐planar mri , 1995, Magnetic resonance in medicine.

[47]  Hesamoddin Jahanian,et al.  Comparison of cerebral blood flow measurement with [15O]-water positron emission tomography and arterial spin labeling magnetic resonance imaging: A systematic review , 2016, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[48]  Ravi S. Menon,et al.  Functional brain mapping by blood oxygenation level-dependent contrast magnetic resonance imaging. A comparison of signal characteristics with a biophysical model. , 1993, Biophysical journal.

[49]  M. Raichle The restless brain: how intrinsic activity organizes brain function , 2015, Philosophical Transactions of the Royal Society B: Biological Sciences.

[50]  Hengyi Rao,et al.  Applications of arterial spin labeled MRI in the brain , 2012, Journal of magnetic resonance imaging : JMRI.

[51]  Daniel L. Kimmel,et al.  Neuroimaging insights into network-based neurodegeneration. , 2012, Current opinion in neurology.

[52]  Bharat B. Biswal,et al.  The oscillating brain: Complex and reliable , 2010, NeuroImage.

[53]  John A. Detre,et al.  Arterial spin labeled MRI in prodromal Alzheimer's disease: A multi-site study☆ , 2013, NeuroImage: Clinical.

[54]  Janet S. Reddin,et al.  Voxel-level comparison of arterial spin-labeled perfusion MRI and FDG-PET in Alzheimer disease , 2011, Neurology.

[55]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[56]  C. Jack,et al.  Mild cognitive impairment – beyond controversies, towards a consensus: report of the International Working Group on Mild Cognitive Impairment , 2004, Journal of internal medicine.

[57]  Emily Kilroy,et al.  Reliability of two‐dimensional and three‐dimensional pseudo‐continuous arterial spin labeling perfusion MRI in elderly populations: Comparison with 15o‐water positron emission tomography , 2014, Journal of magnetic resonance imaging : JMRI.

[58]  Ravi S. Menon,et al.  Intrinsic signal changes accompanying sensory stimulation: functional brain mapping with magnetic resonance imaging. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[59]  Yong He,et al.  Coupling of functional connectivity and regional cerebral blood flow reveals a physiological basis for network hubs of the human brain , 2013, Proceedings of the National Academy of Sciences.

[60]  H. Duvernoy,et al.  Cortical blood vessels of the human brain , 1981, Brain Research Bulletin.

[61]  E. Miller,et al.  An integrative theory of prefrontal cortex function. , 2001, Annual review of neuroscience.

[62]  M. Raichle Behind the scenes of functional brain imaging: a historical and physiological perspective. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[63]  F. Pasquier,et al.  Alzheimer disease with cerebrovascular disease and vascular dementia: clinical features and course compared with Alzheimer disease , 2008, Journal of Neurology, Neurosurgery, and Psychiatry.

[64]  A. Anderson,et al.  Respiratory effects in human functional magnetic resonance imaging due to bulk susceptibility changes. , 2001, Physics in medicine and biology.

[65]  Mike P. Wattjes,et al.  Cerebral perfusion and glucose metabolism in Alzheimer’s disease and frontotemporal dementia: two sides of the same coin? , 2015, European Radiology.

[66]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.