biostudies-literatureKe HNIBIB NIH HHSNIDA NIH HHSNIEHS NIH HHSNIMH NIH HHSNINDS NIH HHSNIH HHS908https://www.ebi.ac.uk/biostudies/studies/S-EPMC12467352biostudies-literatureUnknown15(9)<b>Background:</b> Regional cerebral blood flow (rCBF) is a putative biomarker for neuropsychiatric disorders, including major depressive disorder (MDD). <b>Methods:</b> Here, we show that rCBF can be predicted from resting-state functional MRI (rsfMRI) at the voxel level while correcting for partial volume averaging (PVA) artifacts. Cortical patterns of MDD-related CBF differences decoded from rsfMRI using a PVA-corrected approach showed excellent agreement with CBF measured using single-photon emission computed tomography (SPECT) and arterial spin labeling (ASL). A support vector machine algorithm was trained to decode cortical voxel-wise CBF from temporal and power-spectral features of voxel-level rsfMRI time series while accounting for PVA. Three datasets, Amish Connectome Project (<i>N</i> = 300; 179 M/121 F, both rsfMRI and ASL data), UK Biobank (<i>N</i> = 8396; 3097 M/5319 F, rsfMRI data), and Amen Clinics Inc. datasets (<i>N</i> = 372: <i>N</i> = 183 M/189 F, SPECT data), were used. <b>Results:</b> PVA-corrected CBF values predicted from rsfMRI showed significant correlation with the whole-brain (<i>r</i> = 0.54, <i>p</i> = 2 × 10^-5) and 31 out of 34 regional (<i>r</i> = 0.33 to 0.59, <i>p</i> < 1.1 × 10^-3) rCBF measures from 3D ASL. PVA-corrected rCBF values showed significant regional deficits in the UKBB MDD group (Cohen's <i>d</i> = -0.30 to -0.56, <i>p</i> < 10^-28), with the strongest effect sizes observed in the frontal and cingulate areas. The regional deficit pattern of MDD-related hypoperfusion showed excellent agreement with CBF deficits observed in the SPECT data (<i>r</i> = 0.74, <i>p</i> = 4.9 × 10^-7). Consistent with previous findings, this new method suggests that perfusion signals can be predicted using voxel-wise rsfMRI signals. <b>Conclusions:</b> CBF values computed from widely available rsfMRI can be used to study the impact of neuropsychiatric disorders such as MDD on cerebral neurophysiology.Brain sciencesPredicting Regional Cerebral Blood Flow Using Voxel-Wise Resting-State Functional MRI.PMC12467352U01 MH108148R01 MH117601S10 OD023696R01 MH133812R01 ES033961RF1 NS114628R01 MH116948RF1NS114628, R01MH112180, R01MH133812, R01MH116948R01 MH112180R01 EB015611K01 DA059603Ke HPan YAmen DJahanshad NSoares JCMa YMilad MRKeator DBMa TKochunov PTurner JAHong LEDukart JCalhoun VDAdhikari BMThompson PMvan Erp TGMGao SfalsePredicting Regional Cerebral Blood Flow Using Voxel-Wise Resting-State Functional MRI.<b>Background:</b> Regional cerebral blood flow (rCBF) is a putative biomarker for neuropsychiatric disorders, including major depressive disorder (MDD). <b>Methods:</b> Here, we show that rCBF can be predicted from resting-state functional MRI (rsfMRI) at the voxel level while correcting for partial volume averaging (PVA) artifacts. Cortical patterns of MDD-related CBF differences decoded from rsfMRI using a PVA-corrected approach showed excellent agreement with CBF measured using single-photon emission computed tomography (SPECT) and arterial spin labeling (ASL). A support vector machine algorithm was trained to decode cortical voxel-wise CBF from temporal and power-spectral features of voxel-level rsfMRI time series while accounting for PVA. Three datasets, Amish Connectome Project (<i>N</i> = 300; 179 M/121 F, both rsfMRI and ASL data), UK Biobank (<i>N</i> = 8396; 3097 M/5319 F, rsfMRI data), and Amen Clinics Inc. datasets (<i>N</i> = 372: <i>N</i> = 183 M/189 F, SPECT data), were used. <b>Results:</b> PVA-corrected CBF values predicted from rsfMRI showed significant correlation with the whole-brain (<i>r</i> = 0.54, <i>p</i> = 2 × 10^-5) and 31 out of 34 regional (<i>r</i> = 0.33 to 0.59, <i>p</i> < 1.1 × 10^-3) rCBF measures from 3D ASL. PVA-corrected rCBF values showed significant regional deficits in the UKBB MDD group (Cohen's <i>d</i> = -0.30 to -0.56, <i>p</i> < 10^-28), with the strongest effect sizes observed in the frontal and cingulate areas. The regional deficit pattern of MDD-related hypoperfusion showed excellent agreement with CBF deficits observed in the SPECT data (<i>r</i> = 0.74, <i>p</i> = 4.9 × 10^-7). Consistent with previous findings, this new method suggests that perfusion signals can be predicted using voxel-wise rsfMRI signals. <b>Conclusions:</b> CBF values computed from widely available rsfMRI can be used to study the impact of neuropsychiatric disorders such as MDD on cerebral neurophysiology.2025-01-01T00:00:00Z2025 Aug2026-05-02T03:13:37.945Z2026-05-02T03:07:57.84ZS-EPMC124673524100826910.3390/brainsci15090908