Fingerprints of brain disease: connectome identifiability in Alzheimer's disease.

Functional connectivity patterns in the human brain, like the friction ridges of a fingerprint, can uniquely identify individuals. Does this "brain fingerprint" remain distinct even during Alzheimer's disease (AD)? Using fMRI data from healthy and pathologically ageing subjects, we find that individual functional connectivity profiles remain unique and highly heterogeneous during mild cognitive impairment and AD. However, the patterns that make individuals identifiable change with disease progression, revealing a reconfiguration of the brain fingerprint. Notably, connectivity shifts towards functional system connections in AD and lower-order cognitive functions in early disease stages. These findings emphasize the importance of focusing on individual variability rather than group differences in AD studies. Individual functional connectomes could be instrumental in creating personalized models of AD progression, predicting disease course, and optimizing treatments, paving the way for personalized medicine in AD management.

Longitudinal Analysis of Brain Function-Structure Dependencies in 22q11.2 Deletion Syndrome and Psychotic Symptoms.

BACKGROUND: Compared with conventional unimodal analysis, understanding how brain function and structure relate to one another opens a new biologically relevant assessment of neural mechanisms. However, how function-structure dependencies (FSDs) evolve throughout typical and abnormal neurodevelopment remains elusive. The 22q11.2 deletion syndrome (22q11.2DS) offers an important opportunity to study the development of FSDs and their specific association with the pathophysiology of psychosis. METHODS: Previously, we used graph signal processing to combine brain activity and structural connectivity measures in adults, quantifying FSD. Here, we combined FSD with longitudinal multivariate partial least squares correlation to evaluate FSD alterations across groups and among patients with and without mild to moderate positive psychotic symptoms. We assessed 391 longitudinally repeated resting-state functional and diffusion-weighted magnetic resonance images from 194 healthy control participants and 197 deletion carriers (ages 7-34 years, data collected over a span of 12 years). RESULTS: Compared with control participants, patients with 22q11.2DS showed a persistent developmental offset from childhood, with regions of hyper- and hypocoupling across the brain. Additionally, a second deviating developmental pattern showed an exacerbation during adolescence, presenting hypocoupling in the frontal and cingulate cortices and hypercoupling in temporal regions for patients with 22q11.2DS. Interestingly, the observed aggravation during adolescence was strongly driven by the group with positive psychotic symptoms. CONCLUSIONS: These results confirm a central role of altered FSD maturation in the emergence of psychotic symptoms in 22q11.2DS during adolescence. The FSD deviations precede the onset of psychotic episodes and thus offer a potential early indication for behavioral interventions in individuals at risk.

Functional network centrality indicates interactions between APOE4 and age across the clinical spectrum of Alzheimer's Disease.

Advanced age is the most important risk factor for Alzheimer's disease (AD), and carrier-status of the Apolipoprotein E4 (APOE4) allele is the strongest known genetic risk factor. Many studies have consistently shown a link between APOE4 and synaptic dysfunction, possibly reflecting pathologically accelerated biological aging in persons at risk for AD. To test the hypothesis that distinct functional connectivity patterns characterize APOE4 carriers across the clinical spectrum of AD, we investigated 128 resting state functional Magnetic Resonance Imaging (fMRI) datasets from the Alzheimer's Disease Neuroimaging Initiative database (ADNI), representing all disease stages from cognitive normal to clinical dementia. Brain region centralities within functional networks, computed as eigenvector centrality, were tested for multivariate associations with chronological age, APOE4 carrier status and clinical stage (as well as their interactions) by partial least square analysis (PLSC). By PLSC analysis two distinct brain activity patterns could be identified, which reflected interactive effects of age, APOE4 and clinical disease stage. A first component including sensorimotor regions and parietal regions correlated with age and AD clinical stage (p < 0.001). A second component focused on medial-frontal regions and was specifically related to the interaction between age and APOE4 (p = 0.032). Our findings are consistent with earlier reports on altered network connectivity in APOE4 carriers. Results of our study highlight promise of graph-theory based network centrality to identify brain connectivity linked to genetic risk, clinical stage and age. Our data suggest the existence of brain network activity patterns that characterize APOE4 carriers across clinical stages of AD.

The hippocampus dissociates present from past and future goals.

Our brain adeptly navigates goals across time frames, distinguishing between urgent needs and those of the past or future. The hippocampus is a region known for supporting mental time travel and organizing information along its longitudinal axis, transitioning from detailed posterior representations to generalized anterior ones. This study investigates the role of the hippocampus in distinguishing goals over time: whether the hippocampus encodes time regardless of detail or abstraction, and whether the hippocampus preferentially activates its anterior region for temporally distant goals (past and future) and its posterior region for immediate goals. We use a space-themed experiment with 7T functional MRI on 31 participants to examine how the hippocampus encodes the temporal distance of goals. During a simulated Mars mission, we find that the hippocampus tracks goals solely by temporal proximity. We show that past and future goals activate the left anterior hippocampus, while current goals engage the left posterior hippocampus. This suggests that the hippocampus maps goals using timestamps, extending its long axis system to include temporal goal organization.

Linking connectivity of deep brain stimulation of nucleus accumbens area with clinical depression improvements: a retrospective longitudinal case series.

Treatment-resistant depression is a severe form of major depressive disorder and deep brain stimulation is currently an investigational treatment. The stimulation's therapeutic effect may be explained through the functional and structural connectivities between the stimulated area and other brain regions, or to depression-associated networks. In this longitudinal, retrospective study, four female patients with treatment-resistant depression were implanted for stimulation in the nucleus accumbens area at our center. We analyzed the structural and functional connectivity of the stimulation area: the structural connectivity was investigated with probabilistic tractography; the functional connectivity was estimated by combining patient-specific stimulation volumes and a normative functional connectome. These structural and functional connectivity profiles were then related to four clinical outcome scores. At 1-year follow-up, the remission rate was 66%. We observed a consistent structural connectivity to Brodmann area 25 in the patient with the longest remission phase. The functional connectivity analysis resulted in patient-specific R-maps describing brain areas significantly correlated with symptom improvement in this patient, notably the prefrontal cortex. But the connectivity analysis was mixed across patients, calling for confirmation in a larger cohort and over longer time periods.

Hippocampal timestamp for goals.

Our brain must manage multiple goals that differ in their temporal proximity. Some goals require immediate attention, while others have already been accomplished, or will be relevant later in time. Here, we examined how the hippocampus represents the temporal distance to different goals using a novel space-themed paradigm during 7T functional MRI (n=31). The hippocampus has an established role in mental time travel and a system in place to stratify information along its longitudinal axis on the basis of representational granularity. Previous work has documented a functional transformation from fine-grained, detail rich representations in the posterior hippocampus to coarse, gist-like representations in the anterior hippocampus. We tested whether the hippocampus uses this long axis system to dissociate goals based upon their temporal distance from the present. We hypothesized that the hippocampus would distinguish goals relevant for ones' current needs from those that are removed in time along the long axis, with temporally removed past and future goals eliciting increasingly anterior activation. We sent participants on a mission to Mars where they had to track goals that differed in when they needed to be accomplished. We observed a long-axis dissociation, where temporally removed past and future goals activated the left anterior hippocampus and current goals activated the left posterior hippocampus. Altogether, this study demonstrates that the timestamp attached to a goal is a key driver in where the goal is represented in the hippocampus. This work extends the scope of the hippocampus' long axis system to the goal-mapping domain.

Prediction of post-stroke motor recovery benefits from measures of sub-acute widespread network damages.

Following a stroke in regions of the brain responsible for motor activity, patients can lose their ability to control parts of their body. Over time, some patients recover almost completely, while others barely recover at all. It is known that lesion volume, initial motor impairment and cortico-spinal tract asymmetry significantly impact motor changes over time. Recent work suggested that disabilities arise not only from focal structural changes but also from widespread alterations in inter-regional connectivity. Models that consider damage to the entire network instead of only local structural alterations lead to a more accurate prediction of patients' recovery. However, assessing white matter connections in stroke patients is challenging and time-consuming. Here, we evaluated in a data set of 37 patients whether we could predict upper extremity motor recovery from brain connectivity measures obtained by using the patient's lesion mask to introduce virtual lesions in 60 healthy streamline tractography connectomes. This indirect estimation of the stroke impact on the whole brain connectome is more readily available than direct measures of structural connectivity obtained with magnetic resonance imaging. We added these measures to benchmark structural features, and we used a ridge regression regularization to predict motor recovery at 3 months post-injury. As hypothesized, accuracy in prediction significantly increased (R 2 = 0.68) as compared to benchmark features (R 2 = 0.38). This improved prediction of recovery could be beneficial to clinical care and might allow for a better choice of intervention.

On the Spatial Distribution of Temporal Complexity in Resting State and Task Functional MRI.

Measuring the temporal complexity of functional MRI (fMRI) time series is one approach to assess how brain activity changes over time. In fact, hemodynamic response of the brain is known to exhibit critical behaviour at the edge between order and disorder. In this study, we aimed to revisit the spatial distribution of temporal complexity in resting state and task fMRI of 100 unrelated subjects from the Human Connectome Project (HCP). First, we compared two common choices of complexity measures, i.e., Hurst exponent and multiscale entropy, and observed a high spatial similarity between them. Second, we considered four tasks in the HCP dataset (Language, Motor, Social, and Working Memory) and found high task-specific complexity, even when the task design was regressed out. For the significance thresholding of brain complexity maps, we used a statistical framework based on graph signal processing that incorporates the structural connectome to develop the null distributions of fMRI complexity. The results suggest that the frontoparietal, dorsal attention, visual, and default mode networks represent stronger complex behaviour than the rest of the brain, irrespective of the task engagement. In sum, the findings support the hypothesis of fMRI temporal complexity as a marker of cognition.

Neural substrates of psychosis revealed by altered dependencies between brain activity and white-matter architecture in individuals with 22q11 deletion syndrome.

BACKGROUND: Dysconnectivity has been consistently proposed as a major key mechanism in psychosis. Indeed, disruptions in large-scale structural and functional brain networks have been associated with psychotic symptoms. However, brain activity is largely constrained by underlying white matter pathways and the study of function-structure dependency, compared to conventional unimodal analysis, allows a biologically relevant assessment of neural mechanisms. The 22q11.2 deletion syndrome (22q11DS) constitutes a remarkable opportunity to study the pathophysiological processes of psychosis. METHODS: 58 healthy controls and 57 deletion carriers, aged from 16 to 32 years old,underwent resting-state functional and diffusion-weighted magnetic resonance imaging. Deletion carriers were additionally fully assessed for psychotic symptoms. Firstly, we used a graph signal processing method to combine brain activity and structural connectivity measures to obtain regional structural decoupling indexes (SDIs). We use SDI to assess the differences of functional structural dependency (FSD) across the groups. Subsequently we investigated how alterations in FSDs are associated with the severity of positive psychotic symptoms in participants with 22q11DS. RESULTS: In line with previous findings, participants in both groups showed a spatial gradient of FSD ranging from sensory-motor regions (stronger FSD) to regions involved in higher-order function (weaker FSD). Compared to controls, in participants with 22q11DS, and further in deletion carriers with more severe positive psychotic symptoms, the functional activity was more strongly dependent on the structure in parahippocampal gyrus and subcortical dopaminergic regions, while it was less dependent within the cingulate cortex. This analysis revealed group differences not otherwise detected when assessing the structural and functional nodal measures separately. CONCLUSIONS: Our findings point toward a disrupted modulation of functional activity on the underlying structure, which was further associated to psychopathology for candidate critical regions in 22q11DS. This study provides the first evidence for the clinical relevance of function-structure dependency and its contribution to the emergence of psychosis.

Mapping of Structure-Function Age-Related Connectivity Changes on Cognition Using Multimodal MRI.

The relationship between age-related changes in brain structural connectivity (SC) and functional connectivity (FC) with cognition is not well understood. Furthermore, it is not clear whether cognition is represented via a similar spatial pattern of FC and SC or instead is mapped by distinct sets of distributed connectivity patterns. To this end, we used a longitudinal, within-subject, multimodal approach aiming to combine brain data from diffusion-weighted MRI (DW-MRI), and functional MRI (fMRI) with behavioral evaluation, to better understand how changes in FC and SC correlate with changes in cognition in a sample of older adults. FC and SC measures were derived from the multimodal scans acquired at two time points. Change in FC and SC was correlated with 13 behavioral measures of cognitive function using Partial Least Squares Correlation (PLSC). Two of the measures indicate an age-related change in cognition and the rest indicate baseline cognitive performance. FC and SC-cognition correlations were expressed across several cognitive measures, and numerous structural and functional cortical connections, mainly cingulo-opercular, dorsolateral prefrontal, somatosensory and motor, and temporo-parieto-occipital, contributed both positively and negatively to the brain-behavior relationship. Whole-brain FC and SC captured distinct and independent connections related to the cognitive measures. Overall, we examined age-related function-structure associations of the brain in a comprehensive and integrated manner, using a multimodal approach. We pointed out the behavioral relevance of age-related changes in FC and SC. Taken together, our results highlight that the heterogeneity in distributed FC and SC connectivity patterns provide unique information about the variable nature of healthy cognitive aging.

CSF tap test in idiopathic normal pressure hydrocephalus: still a necessary prognostic test?

OBJECTIVE: To assess whether gait, neuropsychological, and multimodal MRI parameters predict short-term symptom reversal after cerebrospinal fluid (CSF) tap test in idiopathic normal pressure hydrocephalus (iNPH). METHODS: Thirty patients (79.3 ± 5.9 years, 12 women) with a diagnosis of probable iNPH and 46 healthy controls (74.7 ± 5.4 years, 35 women) underwent comprehensive neuropsychological, quantitative gait, and multimodal MRI assessments of brain morphology, periventricular white-matter microstructure, cortical and subcortical blood perfusion, default mode network function, and white-matter lesion load. Responders were defined as an improvement of at least 10% in walking speed or timed up and go test 24 h after tap test. Univariate and multivariable tap test outcome prediction models were evaluated with logistic regression and linear support vector machine classification. RESULTS: Sixteen patients (53%) respondedpositively to tap test. None of the gait, neuropsychological, or neuroimaging parameters considered separately predicted outcome. A multivariable classifier achieved modest out-of-sample outcome prediction accuracy of 70% (p = .028); gait parameters, white-matter lesion load and periventricular microstructure were the main contributors. CONCLUSIONS: Our negative findings show that short-term symptom reversal after tap test cannot be predicted from single gait, neuropsychological, or MRI parameters, thus supporting the use of tap test as prognostic procedure. However, multivariable approaches integrating non-invasive multimodal data are informative of outcome and may be included in patient-screening procedures. Their value in predicting shunting outcome should be further explored, particularly in relation to gait and white-matter parameters.

Brain structure-function coupling provides signatures for task decoding and individual fingerprinting.

Brain signatures of functional activity have shown promising results in both decoding brain states, meaning distinguishing between different tasks, and fingerprinting, that is identifying individuals within a large group. Importantly, these brain signatures do not account for the underlying brain anatomy on which brain function takes place. Structure-function coupling based on graph signal processing (GSP) has recently revealed a meaningful spatial gradient from unimodal to transmodal regions, on average in healthy subjects during resting-state. Here, we explore the specificity of structure-function coupling to distinct brain states (tasks) and to individual subjects. We used multimodal magnetic resonance imaging of 100 unrelated healthy subjects from the Human Connectome Project both during rest and seven different tasks and adopted a support vector machine classification approach for both decoding and fingerprinting, with various cross-validation settings. We found that structure-function coupling measures allow accurate classifications for both task decoding and fingerprinting. In particular, key information for fingerprinting is found in the more liberal portion of functional signals, with contributions strikingly localized to the fronto-parietal network. Moreover, the liberal portion of functional signals showed a strong correlation with cognitive traits, assessed with partial least square analysis, corroborating its relevance for fingerprinting. By introducing a new perspective on GSP-based signal filtering and FC decomposition, these results show that brain structure-function coupling provides a new class of signatures of cognition and individual brain organization at rest and during tasks. Further, they provide insights on clarifying the role of low and high spatial frequencies of the structural connectome, leading to new understanding of where key structure-function information for characterizing individuals can be found across the structural connectome graph spectrum.

Altered anterior default mode network dynamics in progressive multiple sclerosis.

BACKGROUND: Modifications in brain function remain relatively unexplored in progressive multiple sclerosis (PMS), despite their potential to provide new insights into the pathophysiology of the disease at this stage. OBJECTIVES: To characterize the dynamics of functional networks at rest in patients with PMS, and the relation with clinical disability. METHODS: Thirty-two patients with PMS underwent clinical and cognitive assessment. The dynamic properties of functional networks, retrieved from transient brain activity, were obtained from patients and 25 healthy controls (HCs). Sixteen HCs and 19 patients underwent a 1-year follow-up (FU) clinical and imaging assessment. Differences in the dynamic metrics between groups, their longitudinal changes, and the correlation with clinical disability were explored. RESULTS: PMS patients, compared to HCs, showed a reduced dynamic functional activation of the anterior default mode network (aDMN) and a decrease in its opposite-signed co-activation with the executive control network (ECN), at baseline and FU. Processing speed and visuo-spatial memory negatively correlated to aDMN dynamic activity. The anti-couplings between aDMN and auditory/sensory-motor network, temporal-pole/amygdala, or salience networks were differently associated with separate cognitive domains. CONCLUSION: Patients with PMS presented an altered aDMN functional recruitment and anti-correlation with ECN. The aDMN dynamic functional activity and interaction with other networks explained cognitive disability.

When makes you unique: Temporality of the human brain fingerprint.

The extraction of "fingerprints" from human brain connectivity data has become a new frontier in neuroscience. However, the time scales of human brain identifiability are still largely unexplored. We here investigate the dynamics of brain fingerprints along two complementary axes: (i) What is the optimal time scale at which brain fingerprints integrate information and (ii) when best identification happens. Using dynamic identifiability, we show that the best identification emerges at longer time scales; however, short transient "bursts of identifiability," associated with neuronal activity, persist even when looking at shorter functional interactions. Furthermore, we report evidence that different parts of connectome fingerprints relate to different time scales, i.e., more visual-somatomotor at short temporal windows and more frontoparietal-DMN driven at increasing temporal windows. Last, different cognitive functions appear to be meta-analytically implicated in dynamic fingerprints across time scales. We hope that this investigation will advance our understanding of what makes our brains unique.

Dynamics of amygdala connectivity in bipolar disorders: a longitudinal study across mood states.

Alterations in activity and connectivity of brain circuits implicated in emotion processing and emotion regulation have been observed during resting-state for different clinical phases of bipolar disorders (BD), but longitudinal investigations across different mood states in the same patients are still rare. Furthermore, measuring dynamics of functional connectivity patterns offers a powerful method to explore changes in the brain's intrinsic functional organization across mood states. We used a novel co-activation pattern (CAP) analysis to explore the dynamics of amygdala connectivity at rest in a cohort of 20 BD patients prospectively followed-up and scanned across distinct mood states: euthymia (20 patients; 39 sessions), depression (12 patients; 18 sessions), or mania/hypomania (14 patients; 18 sessions). We compared them to 41 healthy controls scanned once or twice (55 sessions). We characterized temporal aspects of dynamic fluctuations in amygdala connectivity over the whole brain as a function of current mood. We identified six distinct networks describing amygdala connectivity, among which an interoceptive-sensorimotor CAP exhibited more frequent occurrences during hypomania compared to other mood states, and predicted more severe symptoms of irritability and motor agitation. In contrast, a default-mode CAP exhibited more frequent occurrences during depression compared to other mood states and compared to controls, with a positive association with depression severity. Our results reveal distinctive interactions between amygdala and distributed brain networks in different mood states, and foster research on interoception and default-mode systems especially during the manic and depressive phase, respectively. Our study also demonstrates the benefits of assessing brain dynamics in BD.

Tapping into Multi-Faceted Human Behavior and Psychopathology Using fMRI Brain Dynamics.

Human behavior comprises many aspects that stand out by their dynamic nature. To quantify its neural underpinnings, time-resolved fMRI methods have blossomed over the past decade. In this review we conceptually organize a broad repertoire of dynamic analytical pipelines and extract general observations on their application to the study of behavior and brain disorders. We aim to provide an extensive overview instead of examining only selected methodological families or specific behavioral domains. We consider behavioral aspects with distinct long-term stability (e.g., physiological state versus personality), and also address selected brain disorders with complementary genetics and symptomatology. This synthesis exposes the somewhat limited consistency of dynamic findings in the literature, as well as the unbalanced application of the multitude of available approaches which would, owing to their technical specificities, have potential to reveal distinct aspects of dynamics. We call for further comparative and collaborative efforts in the future.

Generative Adversarial Networks Improve the Reproducibility and Discriminative Power of Radiomic Features.

PURPOSE: To assess the contribution of a generative adversarial network (GAN) to improve intermanufacturer reproducibility of radiomic features (RFs). MATERIALS AND METHODS: The authors retrospectively developed a cycle-GAN to translate texture information from chest radiographs acquired using one manufacturer (Siemens) to chest radiographs acquired using another (Philips), producing fake chest radiographs with different textures. The authors prospectively evaluated the ability of this texture-translation cycle-GAN to reduce the intermanufacturer variability of RFs extracted from the lung parenchyma. This study assessed the cycle-GAN's ability to fool several machine learning (ML) classifiers tasked with recognizing the manufacturer on the basis of chest radiography inputs. The authors also evaluated the cycle-GAN's ability to mislead radiologists who were asked to perform the same recognition task. Finally, the authors tested whether the cycle-GAN had an impact on radiomic diagnostic accuracy for chest radiography in patients with congestive heart failure (CHF). RESULTS: RFs, extracted from chest radiographs after the cycle-GAN's texture translation (fake chest radiographs), showed decreased intermanufacturer RF variability. Using cycle-GAN-generated chest radiographs as inputs, ML classifiers categorized the fake chest radiographs as belonging to the target manufacturer rather than to a native one. Moreover, cycle-GAN fooled two experienced radiologists who identified fake chest radiographs as belonging to a target manufacturer class. Finally, reducing intermanufacturer RF variability with cycle-GAN improved the discriminative power of RFs for patients without CHF versus patients with CHF (from 55% to 73.5%, P < .001). CONCLUSION: Both ML classifiers and radiologists had difficulty recognizing the chest radiographs' manufacturer. The cycle-GAN improved RF intermanufacturer reproducibility and discriminative power for identifying patients with CHF. This deep learning approach may help counteract the sensitivity of RFs to differences in acquisition.Supplemental material is available for this article.© RSNA, 2020See also the commentary by Alderson in this issue.

Decoupling of brain function from structure reveals regional behavioral specialization in humans.

The brain is an assembly of neuronal populations interconnected by structural pathways. Brain activity is expressed on and constrained by this substrate. Therefore, statistical dependencies between functional signals in directly connected areas can be expected higher. However, the degree to which brain function is bound by the underlying wiring diagram remains a complex question that has been only partially answered. Here, we introduce the structural-decoupling index to quantify the coupling strength between structure and function, and we reveal a macroscale gradient from brain regions more strongly coupled, to regions more strongly decoupled, than expected by realistic surrogate data. This gradient spans behavioral domains from lower-level sensory function to high-level cognitive ones and shows for the first time that the strength of structure-function coupling is spatially varying in line with evidence derived from other modalities, such as functional connectivity, gene expression, microstructural properties and temporal hierarchy.

Guided graph spectral embedding: Application to the C. elegans connectome.

Graph spectral analysis can yield meaningful embeddings of graphs by providing insight into distributed features not directly accessible in nodal domain. Recent efforts in graph signal processing have proposed new decompositions-for example, based on wavelets and Slepians-that can be applied to filter signals defined on the graph. In this work, we take inspiration from these constructions to define a new guided spectral embedding that combines maximizing energy concentration with minimizing modified embedded distance for a given importance weighting of the nodes. We show that these optimization goals are intrinsically opposite, leading to a well-defined and stable spectral decomposition. The importance weighting allows us to put the focus on particular nodes and tune the trade-off between global and local effects. Following the derivation of our new optimization criterion, we exemplify the methodology on the C. elegans structural connectome. The results of our analyses confirm known observations on the nematode's neural network in terms of functionality and importance of cells. Compared with Laplacian embedding, the guided approach, focused on a certain class of cells (sensory neurons, interneurons, or motoneurons), provides more biological insights, such as the distinction between somatic positions of cells, and their involvement in low- or high-order processing functions.

Classification of degenerative parkinsonism subtypes by support-vector-machine analysis and striatal 123I-FP-CIT indices.

OBJECTIVES: To provide an automated classification method for degenerative parkinsonian syndromes (PS) based on semiquantitative 123I-FP-CIT SPECT striatal indices and support-vector-machine (SVM) analysis. METHODS: 123I-FP-CIT SPECT was performed at a single-center level on 370 individuals with PS, including 280 patients with Parkinson's disease (PD), 21 with multiple system atrophy-parkinsonian type (MSA-P), 41 with progressive supranuclear palsy (PSP) and 28 with corticobasal syndrome (CBS) (mean age 70.3 years, 47% female, mean disease duration at scan 1.4 year), as well as 208 age- and gender-matched control subjects. Striatal volumes-of-interest (VOIs) uptake, VOIs asymmetry indices (AIs) and caudate/putamen (C/P) ratio were used as input for SVM individual classification using fivefold cross-validation. RESULTS: Univariate analyses showed significantly lower VOIs uptake, higher striatal AI and C/P ratio for each PS in comparison to controls (all p < 0.001). Among PS, higher degree of striatal impairment was observed in MSA-P and PSP, while CBS showed moderate uptake reduction and higher AI. Binary SVM classification showed 92.9% accuracy in distinguishing PS from controls. Classification based on each binary combination of PS ranged 62.9-83.7% accuracy with the most satisfactory results when separating CBS from the other PS. Sensitivity and specificity values were high and balanced ranging from 60 to 80% for all analyses with > 70% accuracy. Overall, striatal AI and C/P ratio on the more affected side had the highest weighting factors. CONCLUSION: Semiquantitative 123I-FP-CIT SPECT striatal evaluation combined with SVM represents a promising approach to disentangle PD from non-degenerative conditions and from atypical PS at the early stage.