Clinical validity of increased cortical uptake of [18F]flortaucipir on PET as a biomarker for Alzheimer's disease in the context of a structured 5-phase biomarker development framework.

PURPOSE: In 2017, the Geneva Alzheimer's disease (AD) Biomarker Roadmap initiative adapted the framework of the systematic validation of oncological diagnostic biomarkers to AD biomarkers, with the aim to accelerate their development and implementation in clinical practice. With this work, we assess the maturity of [18F]flortaucipir PET and define its research priorities. METHODS: The level of maturity of [18F]flortaucipir was assessed based on the AD Biomarker Roadmap. The framework assesses analytical validity (phases 1-2), clinical validity (phases 3-4), and clinical utility (phase 5). RESULTS: The main aims of phases 1 (rationale for use) and 2 (discriminative ability) have been achieved. [18F]Flortaucipir binds with high affinity to paired helical filaments of tau and has favorable kinetic properties and excellent discriminative accuracy for AD. The majority of secondary aims of phase 2 were fully achieved. Multiple studies showed high correlations between ante-mortem [18F]flortaucipir PET and post-mortem tau (as assessed by histopathology), and also the effects of covariates on tracer binding are well studied. The aims of phase 3 (early detection ability) were only partially or preliminarily achieved, and the aims of phases 4 and 5 were not achieved. CONCLUSION: Current literature provides partial evidence for clinical utility of [18F]flortaucipir PET. The aims for phases 1 and 2 were mostly achieved. Phase 3 studies are currently ongoing. Future studies including representative MCI populations and a focus on healthcare outcomes are required to establish full maturity of phases 4 and 5.

2020 update on the clinical validity of cerebrospinal fluid amyloid, tau, and phospho-tau as biomarkers for Alzheimer's disease in the context of a structured 5-phase development framework.

PURPOSE: In the last decade, the research community has focused on defining reliable biomarkers for the early detection of Alzheimer's disease (AD) pathology. In 2017, the Geneva AD Biomarker Roadmap Initiative adapted a framework for the systematic validation of oncological biomarkers to cerebrospinal fluid (CSF) AD biomarkers-encompassing the 42 amino-acid isoform of amyloid-ß (Aß42), phosphorylated-tau (P-tau), and Total-tau (T-tau)-with the aim to accelerate their development and clinical implementation. The aim of this work is to update the current validation status of CSF AD biomarkers based on the Biomarker Roadmap methodology. METHODS: A panel of experts in AD biomarkers convened in November 2019 at a 2-day workshop in Geneva. The level of maturity (fully achieved, partly achieved, preliminary evidence, not achieved, unsuccessful) of CSF AD biomarkers was assessed based on the Biomarker Roadmap methodology before the meeting and presented and discussed during the workshop. RESULTS: By comparison to the previous 2017 Geneva Roadmap meeting, the primary advances in CSF AD biomarkers have been in the area of a unified protocol for CSF sampling, handling and storage, the introduction of certified reference methods and materials for Aß42, and the introduction of fully automated assays. Additional advances have occurred in the form of defining thresholds for biomarker positivity and assessing the impact of covariates on their discriminatory ability. CONCLUSIONS: Though much has been achieved for phases one through three, much work remains in phases four (real world performance) and five (assessment of impact/cost). To a large degree, this will depend on the availability of disease-modifying treatments for AD, given these will make accurate and generally available diagnostic tools key to initiate therapy.

The validation status of blood biomarkers of amyloid and phospho-tau assessed with the 5-phase development framework for AD biomarkers.

PURPOSE: The development of blood biomarkers that reflect Alzheimer's disease (AD) pathophysiology (phosphorylated tau and amyloid-ß) has offered potential as scalable tests for dementia differential diagnosis and early detection. In 2019, the Geneva AD Biomarker Roadmap Initiative included blood biomarkers in the systematic validation of AD biomarkers. METHODS: A panel of experts convened in November 2019 at a two-day workshop in Geneva. The level of maturity (fully achieved, partly achieved, preliminary evidence, not achieved, unsuccessful) of blood biomarkers was assessed based on the Biomarker Roadmap methodology and discussed fully during the workshop which also evaluated cerebrospinal fluid (CSF) and positron emission tomography (PET) biomarkers. RESULTS: Plasma p-tau has shown analytical validity (phase 2 primary aim 1) and first evidence of clinical validity (phase 3 primary aim 1), whereas the maturity level for Aß remains to be partially achieved. Full and partial achievement has been assigned to p-tau and Aß, respectively, in their associations to ante-mortem measures (phase 2 secondary aim 2). However, only preliminary evidence exists for the influence of covariates, assay comparison and cut-off criteria. CONCLUSIONS: Despite the relative infancy of blood biomarkers, in comparison to CSF biomarkers, much has already been achieved for phases 1 through 3 - with p-tau having greater success in detecting AD and predicting disease progression. However, sufficient data about the effect of covariates on the biomarker measurement is lacking. No phase 4 (real-world performance) or phase 5 (assessment of impact/cost) aim has been tested, thus not achieved.

A kinetics-based approach to amyloid PET semi-quantification.

PURPOSE: To develop and validate a semi-quantification method (time-delayed ratio, TDr) applied to amyloid PET scans, based on tracer kinetics information. METHODS: The TDr method requires two static scans per subject: one early (~ 0-10 min after the injection) and one late (typically 50-70 min or 90-100 min after the injection, depending on the tracer). High perfusion regions are delineated on the early scan and applied onto the late scan. A SUVr-like ratio is calculated between the average intensities in the high perfusion regions and the late scan hotspot. TDr was applied to a naturalistic multicenter dataset of 143 subjects acquired with [18F]florbetapir. TDr values are compared to visual evaluation, cortical-cerebellar SUVr, and to the geometrical semi-quantification method ELBA. All three methods are gauged versus the heterogeneity of the dataset. RESULTS: TDr shows excellent agreement with respect to the binary visual assessment (AUC = 0.99) and significantly correlates with both validated semi-quantification methods, reaching a Pearson correlation coefficient of 0.86 with respect to ELBA. CONCLUSIONS: TDr is an alternative approach to previously validated ones (SUVr and ELBA). It requires minimal image processing; it is independent on predefined regions of interest and does not require MR registration. Besides, it takes advantage on the availability of early scans which are becoming common practice while imposing a negligible added patient discomfort.

Resting-state functional connectivity abnormalities in subjective cognitive decline: A 7T MRI study.

Resting-state functional connectivity (FC) MRI is sensitive to brain changes in Alzheimer's disease in preclinical stages, however studies in persons with subjective cognitive decline (SCD) have reported conflicting findings, and no study is available at 7T MRI. In this study, we investigated FC alterations in sixty-six participants recruited at the Geneva Memory Center (24 controls, 14 SCD, 28 cognitively impaired [CI]). Participants were classified as SCD if they reported cognitive complaints without objective cognitive deficits, and underwent 7T fMRI to assess FC in canonical brain networks and their association with cognitive/clinical features. SCD showed normal cognition, a trend for higher depressive symptoms, and normal AD biomarkers. Compared to the other two groups, SCD showed higher FC in frontal default mode network (DMN) and insular and superior temporal nodes of ventral attention network (VAN). Higher FC in the DMN and VAN was associated with worse cognition but not depression, suggesting that hyper-connectivity in these networks may be a signature of age-related cognitive decline in SCD at low risk of developing AD.

Nature versus nurture in frontotemporal lobar degeneration: the interaction of genetic background and education on brain damage.

BACKGROUND: Frontotemporal lobar degeneration (FTLD) is a progressive neurodegenerative disorder with a strong genetic background. It has been reported that modifiable factors, i.e. education (E), might act as proxies for reserve capacity. OBJECTIVE: To evaluate the impact of genetic background (positive family history, FH) on reserve mechanisms, by measuring regional cerebral blood flow (rCBF) correlates in FTLD patients. METHODS: 145 FTLD patients were recruited and underwent clinical, neuropsychological, behavioral assessment, and SPECT study. The main effect of E and FH on rCBF was evaluated. To test the potential interaction between the E and rCBF in FTLD patients with or without positive FH, a difference of slope analysis in the two groups was calculated. All the analyses were controlled for disease severity (Clinical Dementia Rating Scale, FTD-CDR). RESULTS: A main effect of education (E+ < E-) in frontal regions was reported, and high genetic loading (FH+ < FH-) was associated with a greater bilateral temporoparietal hypoperfusion. Evaluating the relationship between E and rCBF, a greater hypoperfusion of cingulate region in FH+ as compared to FH- was observed. DISCUSSION: Reserve mechanisms are available also in presence of an unfavorable genetic status. However, these compensatory mechanisms are modulated by the interaction with genetic factors.

Education and occupation provide reserve in both ApoE ε4 carrier and noncarrier patients with probable Alzheimer's disease.

According to the reserve hypothesis, a high educational/occupational attainment can modulate Alzheimer's disease (AD) clinical expression. The impact of the Apolipoprotein E (ApoE) ε4 allele on the reserve mechanism in AD has not been assessed. Aim of this European multicenter study was to evaluate the metabolic correlates of reserve and ApoE genotype in early probable AD. 51 AD subjects, 27 ε4 carriers, and 24 noncarriers, underwent FDG-PET brain imaging. We used the general linear model as implemented in SPM2 to test for the linear correlation of a reserve index, accounting for both educational and occupational level, with brain glucose metabolism, controlling for demographic variables (age and gender) and for cognitive performance. We found an inverse correlation between a reserve index, accounting for educational/occupational level, and metabolism in the posterior cingulate cortex and precuneus in both ε4 carriers and noncarriers, and no significant difference between the groups. We show that education and occupation act as proxies for reserve in ε4 carriers, compensating for an unfavorable genetic background; we also show that the degree of compensation does not differ significantly by ApoE ε4 status.

Disorganization of anatomical connectivity in obsessive compulsive disorder: a multi-parameter diffusion tensor imaging study in a subpopulation of patients.

Obsessive-compulsive disorder (OCD) is thought to involve large-scale brain systems but the anatomical connectivity via association fibers has not been specifically investigated yet. We evaluated organization and directionality of the major fiber bundles in a subpopulation of OCD, including washers and checkers who presented decision making deficits, by measuring MRI parameters related to water self-diffusion (Fractional Anisotropy, FA) and fiber directionality (Principal Diffusion Direction, PDD) in 15 OCD and 16 control subjects. OCD patients showed significantly lower FA and altered PDD along the corpus callosum, cingulum, superior longitudinal fasciculus, and inferior fronto-occipital fasciculus bilaterally. The track-based analysis of the inferior fronto-occipital fasciculus confirmed a significant bilateral FA reduction. Lower FA values in the inferior fronto-occipital fasciculus, superior longitudinal fasciculus and corpus callosum correlated with symptom severity and neuropsychological performance. This multi-parameter MRI study revealed specific white matter abnormalities in OCD suggesting tract disorganization as main feature, reflected by local changes in fiber directionality. This altered anatomical connectivity might play a specific role in OCD pathophysiology.

Revisiting brain reserve hypothesis in frontotemporal dementia: evidence from a brain perfusion study.

BACKGROUND: Literature data on Alzheimer's disease suggest that years of schooling and occupational level are associated with a reserve mechanism. No data on patients with behavioral variant frontotemporal dementia (bvFTD) are available yet. OBJECTIVE: To evaluate the impact of education, occupation, and midlife leisure activities on brain reserve in bvFTD. METHODS: Fifty-four bvFTD patients entered the study and underwent neuropsychological and behavioral assessment, including the FTD-modified Clinical Dementia Rating for FTD (FTD-modified CDR), and SPECT imaging. We tested for the linear correlation of educational and occupational level, and midlife leisure activities with regional cerebral blood flow (rCBF), controlling for demographic variables (age and gender) and for cognitive performance (FTD-modified CDR) (statistical parametric mapping). RESULTS: A significant relationship between higher educational and occupational attainments and lower rCBF in medial frontal cortex and dorsolateral frontal cortex, bilaterally, was found (p < 0.005). When midlife leisure activities were considered, no correlation was found. The correlation between a reserve index, accounting for both educational and occupational level, and rCBF showed the same pattern of hypoperfusion. CONCLUSIONS: This study suggests that education and occupation act as proxies for reserve capacity in bvFTD. These lifestyle attainments may counteract the onset of this genetic-based disease in at-risk individuals.

Semi-quantification and grading of amyloid PET: A project of the European Alzheimer's Disease Consortium (EADC).

BACKGROUND: amyloid-PET reading has been classically implemented as a binary assessment, although the clinical experience has shown that the number of borderline cases is non negligible not only in epidemiological studies of asymptomatic subjects but also in naturalistic groups of symptomatic patients attending memory clinics. In this work we develop a model to compare and integrate visual reading with two independent semi-quantification methods in order to obtain a tracer-independent multi-parametric evaluation. METHODS: We retrospectively enrolled three cohorts of cognitively impaired patients submitted to 18F-florbetaben (53 subjects), 18F-flutemetamol (62 subjects), 18F-florbetapir (60 subjects) PET/CT respectively, in 6 European centres belonging to the EADC. The 175 scans were visually classified as positive/negative following approved criteria and further classified with a 5-step grading as negative, mild negative, borderline, mild positive, positive by 5 independent readers, blind to clinical data. Scan quality was also visually assessed and recorded. Semi-quantification was based on two quantifiers: the standardized uptake value (SUVr) and the ELBA method. We used a sigmoid model to relate the grading with the quantifiers. We measured the readers accord and inconsistencies in the visual assessment as well as the relationship between discrepancies on the grading and semi-quantifications. CONCLUSION: It is possible to construct a map between different tracers and different quantification methods without resorting to ad-hoc acquired cases. We used a 5-level visual scale which, together with a mathematical model, delivered cut-offs and transition regions on tracers that are (largely) independent from the population. All fluorinated tracers appeared to have the same contrast and discrimination ability with respect to the negative-to-positive grading. We validated the integration of both visual reading and different quantifiers in a more robust framework thus bridging the gap between a binary and a user-independent continuous scale.

Brain magnetic resonance imaging structural changes in a pedigree of asymptomatic progranulin mutation carriers.

Mutations in the progranulin (PGRN) gene have been recently demonstrated as a cause of frontotemporal lobar degeneration (FTLD) with ubiquitin-immunoreactive neuronal inclusion (FTD-U). Neuropathologic, clinical, and neuroimaging features associated with PGRN mutations have been carefully described. No studies on asymptomatic subjects carrying pathogenetic PGRN mutations are available yet. These would be crucial for establishing the timing of brain changes and bringing new insight into disease pathogenesis and disease course. The aim of this study was to evaluate structural brain morphology using diffusion tensor imaging (DTI) and voxel-based morphometry (VBM) in asymptomatic carriers of PGRN delCACT mutation belonging to a four-generation FTLD pedigree (mean age, 37.0 +/- 12.0). The evaluation of the family proband presenting with progressive nonfluent aphasia at 53 years of age, revealed left frontotemporal hypoperfusion and atrophy. VBM analysis of gray and white matter reductions revealed no differences between asymptomatic carriers (n = 7) and controls (n = 15), and between no-carriers (n = 10) and controls (p < 0.001). DTI analysis revealed a reduction in fractional anisotropy in healthy PGRN mutation carriers in the left uncinate fasciculus, connecting the orbito-frontal regions to the temporal pole, and in the left inferior occipitofrontal fasciculus, connecting the parieto-occipital cortex to the dorsolateral frontal cortex (p < 0.001). No significant difference in fractional anisotropy between no-carriers and controls was found. Our data indicate loss of white matter integrity as an early preclinical feature in familial FTD that might antedate the onset of specific neurologic features. Alteration of fiber tracts within the perisylvian language network might represent the early hallmark of subsequent aphasia onset. The study of other pedigrees of asymptomatic PGRN mutation carriers is warranted.

Reversible nonfluent aphasia and left frontal hypoperfusion during topiramate treatment.

We report the case of a patient with complex partial seizures who developed a nonfluent aphasia when topiramate was added to his therapy. This emergent adverse effect appeared to be reversible, as language performance improved after discontinuation of topiramate. Interictal SPECT performed when the patient was aphasic revealed a focal perfusion reduction in the left lateral and mesial frontal cortex, which was no longer evident at a follow-up study after language recovery.

Persistent autobiographical amnesia: a case report.

We describe a 47-year-old man who referred to the Emergency Department for sudden global amnesia and left mild motor impairment in the setting of increased arterial blood pressure. The acute episode resolved within 24 hours. Despite general recovery and the apparent transitory nature of the event, a persistent selective impairment in recollecting events from some specific topics of his personal life became apparent. Complete neuropsychological tests one week after the acute onset and 2 months later demonstrated a clear retrograde memory deficit contrasting with the preservation of anterograde memory and learning abilities. One year later, the autobiographical memory deficit was unmodified, except for what had been re-learnt. Brain MRI was normal while H20 brain PET scans demonstrated hypometabolism in the right globus pallidus and putamen after 2 weeks from onset, which was no longer present one year later. The absence of a clear pathomechanism underlying focal amnesia lead us to consider this case as an example of functional retrograde amnesia.

Source-Based Morphometry Multivariate Approach to Analyze [123I]FP-CIT SPECT Imaging.

PURPOSE: [123I]FP-CIT (DaTSCAN®) single-photon emission computed tomography (SPECT) imaging is widely used to study neurodegenerative parkinsonism, by measuring presynaptic dopamine transporter (DAT) in striatal regions. Beyond DAT, [123I]FP-CIT may be considered for other monoaminergic systems, in particular the serotonin transporter (SERT). Independent component analysis (ICA) implemented in source-based morphometry (SBM) could represent an alternative method to explore monoaminergic pathways, studying the relationship among voxels and grouping them into "neurotransmission" networks. PROCEDURES: One hundred forty-three subjects [84 with Parkinson's disease (PD) and 59 control individuals (CG)] underwent DATSCAN® imaging. The [123I]FP-CIT binding was evaluated by multivariate SBM approach, as well as by a whole-brain voxel-wise univariate (statistical parametric mapping, SPM) approach. RESULTS: As compared to the univariate whole-brain approach (SPM) (only demonstrating striatal [123I]FP-CIT binding reduction in PD group), SBM identified six sources of non-artefactual origin, including basal ganglia and cortical regions as well as brainstem. Among them, three sources (basal ganglia and cortical regions) presented loading scores (as index of [123I]FP-CIT binding) significantly different between PD and CG. Notably, even if not significantly different between PD and CG, the remaining three non-artefactual sources were characterized by a predominant frontal, brainstem, and occipito-temporal involvement. CONCLUSION: The concept of source blind separation by the application of ICA (as implemented in SBM) represents a feasible approach to be considered in [123I]FP-CIT (DaTSCAN®) SPECT imaging. Taking advantage of this multivariate analysis, specific patterns of variance can be identified (involving either striatal than extrastriatal regions) that could be useful in differentiating neurodegenerative parkinsonisms.

Combined 99mTc-ECD SPECT and neuropsychological studies in MCI for the assessment of conversion to AD.

Identifying pre-clinical Alzheimer's disease (AD) in subjects with mild cognitive impairment (MCI) is a major issue in clinical diagnosis. Establishing a combination of predictive markers from different fields of research might help in increasing the diagnostic accuracy. Aim of this study was to evaluate the potential role of 99mTc-ECD single photon emission computed tomography (SPECT) and memory scores in predicting conversion to AD in MCI subjects. Thirty-one MCI subjects underwent a clinical and neuropsychological examination, and a regional cerebral blood flow (rCBF) SPECT scan at baseline. Subjects had been followed periodically through 2 years in order to monitor the progression of cognitive symptoms. Canonical variate analysis of principal components was able to separate all subjects who converted to AD from those who remained stable, the former being characterized by a specific hypometabolic pattern, involving the parietal and temporal lobes, precuneus, and posterior cingulate cortex. Canonical correlation analysis of combined baseline memory deficits and rCBF SPECT images identified pre-clinical AD with a sensitivity and specificity of 77.8%. The pattern of hypoperfusion 99mTc-ECD SPECT and the severity of memory deficits predict the risk of progression to probable AD dementia in MCI subjects.

Impulse control disorder in PD: A lateralized monoaminergic frontostriatal disconnection syndrome?

BACKGROUND: Impulse Control Disorder symptoms (ICD) in Parkinson's disease (PD) has been recently associated by magnetic Resonance imaging with impaired cortico-striatal connectivity, especially between left putamen and frontal associative areas. METHODS: 84 patients entered the study (21 PD-ICD+ and 64 PD-ICD-) and underwent DATSCAN imaging. The striatal tracer uptake was evaluated using BRASS software (Hermes, Sweden). The whole-brain analysis was performed with Statistical Parametric Mapping (SPM). RESULTS: PD-ICD+ showed a significant reduction of left putaminal and left inferior frontal gyrus tracer uptake compared to PD-ICD-. Functional covariance analysis using left putamen as the seed point showed that, in contrast to ICD-patients, ICD+ patients had no functional covariance with contralateral basal ganglia and ipsilateral cingulate cortex, as index of an impaired inter- and intra-hemispheric dopamine binding in PD-ICD+. DISCUSSION: the results support and expand the concept of a functional disconnection syndrome linked to ICD symptoms in PD patients through an asymmetric molecular frontostriatal network breakdown with left basal ganglia as central hub.

Significance of 18F-fluorocholine PET/CT positive pulmonary lesions in prostate cancer patients.

AIM: To assess the frequency and the significance of incidental pulmonary lesions with 18F-fluorocholine (18F-FCH) PET/CT in prostate cancer (PCa) patients. PATIENTS, METHODS: 225 consecutive PCa patients referred for 18F-FCH PET/CT (median age 68 years) were retrospectively evaluated for the presence of lesions in the lungs: 173 referred for restaging and 52 for initial staging regarding their high risk of extra prostatic extension. The final diagnosis was based on histopathological or on clinical and radiological follow-up. RESULTS: 13 patients had 18F-FCH positive pulmonary and 8 patients malignant lesions: 5 patients (38%) had a primary lung cancer (2 squamous cell carcinomas, 1 papillary adenocarcinoma, 1 typical pulmonary carcinoid, 1 bronchioloalveolar carcinoma) and 3 patients (23%) PCa metastases. Benign lesions were found in 5 subjects (38%). SUVmax and maximum diameter were neither significantly different in primary and metastatic tumors nor between malignant and benign lesions. CONCLUSIONS: Although our results suggest that incidental uptake in the lungs in PCa patients are nonspecific, their detection may have a significant impact on patient management knowing that more than 60% represent malignant disease.

In vivo microglia activation in very early dementia with Lewy bodies, comparison with Parkinson's disease.

BACKGROUND: Reactive microgliosis, hallmark of neuroinflammation, may contribute to neuronal degeneration, as shown in several neurodegenerative diseases. We in vivo evaluated microglia activation in early dementia with Lewy bodies, still not reported, and compared with early Parkinson's disease, to assess possible differential pathological patterns. METHODS: We measured the [(11)C]-PK11195 binding potentials with Positron Emission Tomography, using a simplified reference tissue model, as marker of microglia activation, and cerebral spinal fluid protein carbonylation levels, as marker of oxidative stress. Six dementia with Lewy bodies and 6 Parkinson's disease patients within a year from the onset, and eleven healthy controls were included. Clinical diagnosis was confirmed at a 4-year follow-up. RESULTS: In dementia with Lewy bodies as well as in Parkinson's disease, we found significant (p < 0.001) [(11)C]-PK11195 binding potential increases in the substantia nigra and putamen. Patients with Lewy bodies dementia had extensive additional microglia activation in several associative cortices. This was evident also at a single subject level. Significant increase of Cerebral Spinal Fluid protein carbonylation was shown in both patients' groups. CONCLUSIONS: [(11)C]-PK11195 Positron Emission Tomography imaging revealed neuroinflammation in dementia with Lewy bodies and Parkinson's disease, mirroring, even at a single subject level, the common and the different topographical distribution of neuropathological changes, yet in the earliest stages of the disease process. Focusing on those events that characterize parkinsonisms and Parkinson's disease may be the key to further advancing the understanding of pathogenesis and to taking these mechanisms forward as a means of defining targets for neuroprotection.

Individual detection of patients with Parkinson disease using support vector machine analysis of diffusion tensor imaging data: initial results.

BACKGROUND AND PURPOSE: Brain MR imaging is routinely performed in the work-up of suspected PD, yet its role is essentially limited to the exclusion of other pathologies. We performed a pattern-recognition analysis based on DTI data to detect subjects with PD at the individual level. MATERIALS AND METHODS: We included 40 consecutive patients with Parkinsonism suggestive of PD who had DTI at 3T, brain (123)I ioflupane SPECT (DaTSCAN), and extensive neurologic testing including follow-up (17 PD: age range, 67.8 ± 6.7 years; 9 women; 23 Other: consisting of atypical forms of Parkinsonism; age range, 67.2 ± 9.7 years; 7 women). Data analysis included group-level TBSS and individual-level SVM classification. RESULTS: At the group level, patients with PD versus Other had spatially consistent increase in FA and decrease in RD and MD in a bilateral network, predominantly in the right frontal white matter. At the individual level, SVM correctly classified patients with PD at the individual level with accuracies up to 97%. CONCLUSIONS: Support vector machine-based pattern recognition of DTI data provides highly accurate detection of patients with PD among those with suspected PD at an individual level, which is potentially clinically applicable. Because most suspected subjects with PD undergo brain MR imaging, already existing MR imaging data may be reused; this practice is very cost-efficient.