ASL-derived cerebrovascular brain-age improves associations with cognitive decline
Poster No:
2593
Submission Type:
Abstract Submission
Authors:
Mathijs Dijsselhof1,2, Floor Duits3,4,5, Wibeke Nordhøy6, Dani Beck7,8,9, Lars Westlye7,8,10, James Cole11,12, Wiesje Van der Flier3,4,13, Frederik Barkhof1,2,14, Jan Petr1,15, Henk Mutsaerts1,2
Institutions:
1Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit, Amsterdam, Netherlands, 2Amsterdam Neuroscience, Brain Imaging, Amsterdam, Netherlands, 3Alzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, Netherlands, 4Amsterdam Neuroscience, Neurodegeneration, Amsterdam, Netherlands, 5Neurochemistry lab, Department of Clinical Chemistry, Amsterdam Neuroscience, Amsterdam UMC, Amsterdam, Netherlands, 6Physics and Computational Radiology, Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway, 7Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital, Oslo, Norway, 8Department of Psychology, University of Oslo, Oslo, Norway, 9Department of Psychiatric Research, Diakonhjemmet Hospital, Oslo, Norway, 10KG Jebsen Centre for Neurodevelopmental Disorders, University of Oslo, Oslo, Norway, 11Dementia Research Centre, Queen Square Institute of Neurology, UCL, London, United Kingdom, 12Centre for Medical Imaging Computing, Computer Science, UCL, London, United Kingdom, 13Epidemiology and Data Science, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, Netherlands, 14Queen Square Institute of Neurology and Centre for Medical Image Computing, UCL, London, United Kingdom, 15Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiopharmaceutical Cancer Research, Dresden, Germany
First Author:
Mathijs Dijsselhof
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Amsterdam Neuroscience, Brain Imaging
Amsterdam, Netherlands|Amsterdam, Netherlands
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Amsterdam Neuroscience, Brain Imaging
Amsterdam, Netherlands|Amsterdam, Netherlands
Co-Author(s):
Floor Duits
Alzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc|Amsterdam Neuroscience, Neurodegeneration|Neurochemistry lab, Department of Clinical Chemistry, Amsterdam Neuroscience, Amsterdam UMC
Amsterdam, Netherlands|Amsterdam, Netherlands|Amsterdam, Netherlands
Alzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc|Amsterdam Neuroscience, Neurodegeneration|Neurochemistry lab, Department of Clinical Chemistry, Amsterdam Neuroscience, Amsterdam UMC
Amsterdam, Netherlands|Amsterdam, Netherlands|Amsterdam, Netherlands
Wibeke Nordhøy
Physics and Computational Radiology, Radiology and Nuclear Medicine, Oslo University Hospital
Oslo, Norway
Physics and Computational Radiology, Radiology and Nuclear Medicine, Oslo University Hospital
Oslo, Norway
Dani Beck, Dr
Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital|Department of Psychology, University of Oslo|Department of Psychiatric Research, Diakonhjemmet Hospital
Oslo, Norway|Oslo, Norway|Oslo, Norway
Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital|Department of Psychology, University of Oslo|Department of Psychiatric Research, Diakonhjemmet Hospital
Oslo, Norway|Oslo, Norway|Oslo, Norway
Lars Westlye
Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital|Department of Psychology, University of Oslo|KG Jebsen Centre for Neurodevelopmental Disorders, University of Oslo
Oslo, Norway|Oslo, Norway|Oslo, Norway
Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital|Department of Psychology, University of Oslo|KG Jebsen Centre for Neurodevelopmental Disorders, University of Oslo
Oslo, Norway|Oslo, Norway|Oslo, Norway
James Cole, PhD
Dementia Research Centre, Queen Square Institute of Neurology, UCL|Centre for Medical Imaging Computing, Computer Science, UCL
London, United Kingdom|London, United Kingdom
Dementia Research Centre, Queen Square Institute of Neurology, UCL|Centre for Medical Imaging Computing, Computer Science, UCL
London, United Kingdom|London, United Kingdom
Wiesje Van der Flier
Alzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc|Amsterdam Neuroscience, Neurodegeneration|Epidemiology and Data Science, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc
Amsterdam, Netherlands|Amsterdam, Netherlands|Amsterdam, Netherlands
Alzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc|Amsterdam Neuroscience, Neurodegeneration|Epidemiology and Data Science, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc
Amsterdam, Netherlands|Amsterdam, Netherlands|Amsterdam, Netherlands
Frederik Barkhof, MD, Ph. D
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Amsterdam Neuroscience, Brain Imaging|Queen Square Institute of Neurology and Centre for Medical Image Computing, UCL
Amsterdam, Netherlands|Amsterdam, Netherlands|London, United Kingdom
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Amsterdam Neuroscience, Brain Imaging|Queen Square Institute of Neurology and Centre for Medical Image Computing, UCL
Amsterdam, Netherlands|Amsterdam, Netherlands|London, United Kingdom
Jan Petr
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiopharmaceutical Cancer Research
Amsterdam, Netherlands|Dresden, Germany
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiopharmaceutical Cancer Research
Amsterdam, Netherlands|Dresden, Germany
Henk Mutsaerts
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Amsterdam Neuroscience, Brain Imaging
Amsterdam, Netherlands|Amsterdam, Netherlands
Radiology and Nuclear Medicine, Amsterdam University Medical Centers, Vrije Universiteit|Amsterdam Neuroscience, Brain Imaging
Amsterdam, Netherlands|Amsterdam, Netherlands
Introduction:
Accelerated brain ageing is associated with cognitive decline and dementia[1], and can be estimated using structural brain MRI and machine learning methods, which subtracted with the chronological age results in the brain-predicted age difference (brain-PAD). However, structural MRI is mostly sensitive to irreversible structural changes, and there is increasing evidence that accelerated cerebrovascular compromise is an important factor for cognitive dysfunction[2]. The addition of arterial spin labelling (ASL) perfusion scans has been shown to improve brain-PAD accuracy in healthy ageing and brain-PAD-based classification of Alzheimer's Disease (AD)[3,4]. However, the added value of cerebrovascular ageing, its underlying mechanisms, and their relation to (domain-specific) cognitive decline are not yet fully understood.
In this study, we assessed the relationship between brain-PAD and 1) stages of cognitive decline, and 2) global cognitive scores and domain-specific cognitive tests. We compared brain-PAD results between structural-only (T1w+FLAIR), ASL-only, and structural+ASL models.
In this study, we assessed the relationship between brain-PAD and 1) stages of cognitive decline, and 2) global cognitive scores and domain-specific cognitive tests. We compared brain-PAD results between structural-only (T1w+FLAIR), ASL-only, and structural+ASL models.
Methods:
Study design/data: Healthy controls (HC, n=1107, 52% male, 49±16.9 years, 17.7–94.7 years) were drawn from the StrokeMRI and TOP datasets[5]. From the Amsterdam Dementia Cohort[6] (ADC; n=213, 54.9% male, 63.9±7.5 years, 43-97 years), patients with Subjective Cognitive Decline (SCD, n=77), Mild Cognitive Impairment (MCI, n=63), and probable Alzheimer's Disease (AD, n=73) were selected. All ASL datasets were acquired with the same 3D spiral-FSE PCASL protocol (3T GE MR750, post-labelling delay=2025ms, labelling duration=1450ms) and processed with ExploreASL. Cognitive tests (ADC only) were z-scored and averaged per domain[7]. Features[3] were created from: GM and WM volumetrics (T1w), WMH volumetrics (FLAIR), and vascular territory-based CBF and spatial coefficient of variation (sCoV; ASL).
Brain-age predictions: The three brain-age estimation models (T1w+FLAIR+ASL, T1w+FLAIR, or ASL-only) were trained on the HC dataset, and ADC Brain-PADs were determined. Model performance was compared using the mean absolute error (MAE), and (absolute) Brain-PAD group differences were assessed per model, using one-way ANOVA with Tukey's HSD post-hoc test. Relationships between cognitive performance, per domain, and brain-PADs, per model, were assessed using linear regression.
Brain-age predictions: The three brain-age estimation models (T1w+FLAIR+ASL, T1w+FLAIR, or ASL-only) were trained on the HC dataset, and ADC Brain-PADs were determined. Model performance was compared using the mean absolute error (MAE), and (absolute) Brain-PAD group differences were assessed per model, using one-way ANOVA with Tukey's HSD post-hoc test. Relationships between cognitive performance, per domain, and brain-PADs, per model, were assessed using linear regression.
Results:
The T1w+FLAIR+ASL model performed best (MAE=7.8 years), and model performance did not differ between diagnostic groups (p>0.05, all models, Figure 1).
Brain-PADs differed (p<0.05, Figure 1) between SCD and AD (all models) and between SCD and MCI (ASL model). The T1w+FLAIR+ASL brain-PADs were associated with MMSE (ß=-0.031,p<0.001), language (ß=-0.013,p=0.04), attention & executive (ß=-0.012,p=0.02) and visuospatial (ß=-0.02,p<0.001) domains (Figure 2). The T1w+FLAIR Brain-PADs were associated with MMSE (ß=-0.021,p<0.001), attention & executive (ß=-0.010,p=0.03) and visuospatial (ß=-0.020,p=0.006) domains (Figure 2). The ASL-only brain-PADs were associated with the memory domain (ß=0.20,p=0.01; Figure 2).
Brain-PADs differed (p<0.05, Figure 1) between SCD and AD (all models) and between SCD and MCI (ASL model). The T1w+FLAIR+ASL brain-PADs were associated with MMSE (ß=-0.031,p<0.001), language (ß=-0.013,p=0.04), attention & executive (ß=-0.012,p=0.02) and visuospatial (ß=-0.02,p<0.001) domains (Figure 2). The T1w+FLAIR Brain-PADs were associated with MMSE (ß=-0.021,p<0.001), attention & executive (ß=-0.010,p=0.03) and visuospatial (ß=-0.020,p=0.006) domains (Figure 2). The ASL-only brain-PADs were associated with the memory domain (ß=0.20,p=0.01; Figure 2).
·Figure 1: Boxplots showing model performance (absolute brain-PAD) in years (row 1), and brain-PAD in years (row 2) per diagnosis group for each model.
·Figure 2: Associations between global and domain-specific cognitive composites and brain-PADs per model.
Conclusions:
SCD brain-PADS were similar to HC, and increased with cognitive decline staging, confirming previous studies[1]. The addition of ASL improved Brain-age sensitivity to global and domain-specific cognitive decline.
Only the ASL-only model was associated with cognitive staging and memory, which is unexpected as structural derivatives such as hippocampal and parietal volume usually show stronger effects[8]. Also unexpectedly, a lower ASL-only brain-PAD (i.e., a biologically younger brain) was related with poorer cognition. Perhaps, the observed relationships might be explained by early-stage compensatory perfusion effects described in initial stages of AD-related cognitive decline[9], or because ADC contains many young-onset AD patients. These findings encourage larger multi-stage AD studies to assess if and how ASL mediates the association between structural and cognitive changes.
Only the ASL-only model was associated with cognitive staging and memory, which is unexpected as structural derivatives such as hippocampal and parietal volume usually show stronger effects[8]. Also unexpectedly, a lower ASL-only brain-PAD (i.e., a biologically younger brain) was related with poorer cognition. Perhaps, the observed relationships might be explained by early-stage compensatory perfusion effects described in initial stages of AD-related cognitive decline[9], or because ADC contains many young-onset AD patients. These findings encourage larger multi-stage AD studies to assess if and how ASL mediates the association between structural and cognitive changes.
Disorders of the Nervous System:
Neurodegenerative/ Late Life (eg. Parkinson’s, Alzheimer’s) 2
Physiology, Metabolism and Neurotransmission :
Cerebral Metabolism and Hemodynamics 1
Keywords:
Aging
Cerebral Blood Flow
Cognition
Degenerative Disease
Machine Learning
MRI
Other - Arterial Spin Labeling
1|2Indicates the priority used for review
Provide references using author date format
[2] Franke, K., et al. (2019). Ten Years of BrainAGE as a Neuroimaging Biomarker of Brain Aging: What Insights Have We Gained? Frontiers in Neurology, 10, 789.
[3] Hänggi, J., et al. (2011). Volumes of lateral temporal and parietal structures distinguish between healthy aging, mild cognitive impairment, and Alzheimer’s disease. Journal of Alzheimer’s Disease: JAD, 26(4), 719–734.
[4] Iadecola, C., et al. (2019). Neurovascular and Cognitive Dysfunction in Hypertension. Circulation Research, 124(7), 1025–1044.
[5] Richard, G., et al. (2018). Assessing distinct patterns of cognitive aging using tissue-specific brain age prediction based on diffusion tensor imaging and brain morphometry. PeerJ, 6, e5908.
[6] Rokicki, J., et al. (2021). Multimodal imaging improves brain age prediction and reveals distinct abnormalities in patients with psychiatric and neurological disorders. Human Brain Mapping, 42(6), 1714–1726.
[7] Scheltens, N. M. E., et al. (2017). Cognitive subtypes of probable Alzheimer’s disease robustly identified in four cohorts. Alzheimer’s & Dementia: The Journal of the Alzheimer's Association, 13(11), 1226–1236.
[8] Thomas, K. R., et al. (2021). Regional hyperperfusion in older adults with objectively-defined subtle cognitive decline. Journal of Cerebral Blood Flow and Metabolism: Official Journal of the International Society of Cerebral Blood Flow and Metabolism, 41(5), 1001–1012.
[9] van der Flier, W. M., et al. (2018). Amsterdam Dementia Cohort: Performing Research to Optimize Care. Journal of Alzheimer’s Disease: JAD, 62(3), 1091–1111.