Explainable machine learning radiomics model for Primary Progressive Aphasia classification.

Introduction: Primary Progressive Aphasia (PPA) is a neurodegenerative disease characterized by linguistic impairment. The two main clinical subtypes are semantic (svPPA) and non-fluent/agrammatic (nfvPPA) variants. Diagnosing and classifying PPA patients represents a complex challenge that requires the integration of multimodal information, including clinical, biological, and radiological features. Structural neuroimaging can play a crucial role in aiding the differential diagnosis of PPA and constructing diagnostic support systems. Methods: In this study, we conducted a white matter texture analysis on T1-weighted images, including 56 patients with PPA (31 svPPA and 25 nfvPPA), and 53 age- and sex-matched controls. We trained a tree-based algorithm over combined clinical/radiomics measures and used Shapley Additive Explanations (SHAP) model to extract the greater impactful measures in distinguishing svPPA and nfvPPA patients from controls and each other. Results: Radiomics-integrated classification models demonstrated an accuracy of 95% in distinguishing svPPA patients from controls and of 93.7% in distinguishing svPPA from nfvPPA. An accuracy of 93.7% was observed in differentiating nfvPPA patients from controls. Moreover, Shapley values showed the strong involvement of the white matter near left entorhinal cortex in patients classification models. Discussion: Our study provides new evidence for the usefulness of radiomics features in classifying patients with svPPA and nfvPPA, demonstrating the effectiveness of an explainable machine learning approach in extracting the most impactful features for assessing PPA.

Deep Learning-based Approach for Brainstem and Ventricular MR Planimetry: Application in Patients with Progressive Supranuclear Palsy.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a fast and fully automated deep learning (DL)-based method for the MRI planimetric segmentation and measurement of the brainstem and ventricular structures most affected in patients with progressive supranuclear palsy (PSP). Materials and Methods In this retrospective study, T1-weighted MR images from healthy controls (n=84) were used to train DL models for segmenting the midbrain, pons, middle cerebellar peduncles (MCP), superior cerebellar peduncle (SCP), third ventricle (3rd V) and frontal horns (FHs). Internal, external and clinical test datasets (n=305) were used to assess segmentation model reliability. DL masks from test datasets were used to automatically extract midbrain and pons areas and the width of MCP, SCP, 3rd V and FHs. Automated measurements were compared with those manually performed by an expert radiologist. Finally, these measures were combined to calculate the midbrain-to-pons area ratio, magnetic resonance parkinsonism index (MRPI) and MRPI 2.0, which were used to differentiate patients with PSP (n=71) from those with Parkinson's disease (PD, n=129). Results Dice coefficients above 0.85 were found for all brain regions when comparing manual and DL-based segmentations. A strong correlation was observed between automated and manual measurements (Spearman's Rho>0.80, p<0.001). DL-based measurements showed excellent performance in differentiating patients with PSP from those with PD, with an area under the receiver operating characteristic curve above 0.92. Conclusion Automated approach successfully segmented and measured the brainstem and ventricular structures. DL-based models may represent a useful approach to support the diagnosis of PSP and potentially other conditions associated with brainstem and ventricular alterations. ©RSNA, 2024.

Sarcopenia in subjects with Alzheimer's disease: prevalence and comparison of agreement between EGWSOP1, EGWSOP2, and FNIH criteria.

BACKGROUND: Sarcopenia is an age-related clinical syndrome characterized by the progressive loss of muscle mass and muscle strength. It appears to be closely linked to dementia, particularly Alzheimer's disease (AD); however, its prevalence among AD patients remains unclear. In this study, we assessed differences in sarcopenia prevalence between non-demented individuals and AD patients. Moreover, we assessed sex-specific differences in sarcopenia prevalence and explored the diagnostic value of the Muscle Quality Index (MQI) for diagnosing sarcopenia among AD patients. METHOD: Cross-sectional study including 145 patients with probable AD and 51 older adults with normal cognition. Sarcopenia was diagnosed according to the criteria of the European Working Group on Sarcopenia in Older People (EWGSOP1 and EWGSOP2) and of the Foundation for the National Institutes of Health (FNIH). The MQI was computed as the ratio of handgrip strength to skeletal muscle mass. RESULTS: No significant difference in sarcopenia prevalence was observed between AD patients and controls. Prevalence ranged from 3.4 to 23.4% in AD patients and from 2 to 11.8% in controls, depending on diagnostic criteria. Prevalence was higher using EWGSOP1 and decreased using EWGSOP2 and FNIH. Prevalence was higher in males than in females with AD. The MQI was lower in AD patients than in controls (95%CI: - 0.23, - 0.05, p < 0.001), but displayed poor diagnostic accuracy in identifying sarcopenia cases. CONCLUSIONS: AD patients and controls show comparable sarcopenia prevalence. Sarcopenia prevalence is higher in males than females among AD patients and higher when using EWGSOP1 compared to FNIH and EWGSOP2 criteria.

Nucleus Basalis of Meynert Degeneration Predicts Cognitive Decline in Corticobasal Syndrome.

BACKGROUND: Cognitive changes are common in corticobasal syndrome (CBS) and significantly impact quality of life and caregiver burden. However, relatively few studies have investigated the neural substrates of cognitive changes in CBS, and reliable predictors of cognitive impairment are currently lacking. The nucleus basalis of Meynert (NbM), which serves as the primary source of cortical cholinergic innervation, has been functionally associated with cognition. This study aimed to explore whether patients with CBS exhibit reduced NbM volumes compared with healthy control participants and whether NbM degeneration can serve as a predictor of cognitive impairment in patients with CBS. METHODS: In this study, we investigated in vivo volumetric changes of the NbM in 38 patients with CBS and 84 healthy control participants. Next, we assessed whether gray matter degeneration of the NbM evaluated at baseline could predict cognitive impairment during a 12-month follow-up period in patients with CBS. All volumetric analyses were performed using 3T T1-weighted images obtained from the 4-Repeat Tauopathy Neuroimaging Initiative. RESULTS: Patients with CBS displayed significantly lower NbM volumes than control participants (p < .001). Structural damage of the NbM also predicted the development of cognitive impairment in patients with CBS as assessed by longitudinal measurements of the Clinical Dementia Rating Sum of Boxes (p < .001) and Mini-Mental State Examination (p = .035). CONCLUSIONS: Our findings suggest that NbM atrophy may represent a promising noninvasive in vivo marker of cognitive decline in CBS and provide new insights into the neural mechanisms that underlie cognitive impairment in CBS.

Sleep and circadian rhythm disruptions in behavioral variant frontotemporal dementia.

INTRODUCTION: Sleep and rest-activity rhythm alterations are common in neurodegenerative diseases. However, their characterization in patients with behavioral variant frontotemporal dementia (bvFTD) has proven elusive. We investigated rest-activity rhythm alterations, sleep disturbances, and their neural correlates in bvFTD. METHODS: Twenty-seven bvFTD patients and 25 healthy controls completed sleep questionnaires and underwent 7 days of actigraphy while concurrently maintaining a sleep diary. Cortical complexity and thickness were calculated from T1-weighted magnetic resonance (MR) images. RESULTS: Compared to controls, bvFTD patients showed longer time in bed (95% confidence interval [CI]: 79.31, 321.83) and total sleep time (95% CI: 24.38, 321.88), lower sleep efficiency (95% CI: -12.58, -95.54), and rest-activity rhythm alterations in the morning and early afternoon. Increased sleep duration was associated with reduced cortical thickness in frontal regions. DISCUSSION: Patients with bvFTD showed longer sleep duration, lower sleep quality, and rest-activity rhythm alterations. Actigraphy could serve as a cost-effective and accessible tool for ecologically monitoring changes in sleep duration in bvFTD patients. HIGHLIGHTS: We assessed sleep and circadian rhythms in behavioral variant frontotemporal dementia (bvFTD) using actigraphy. Patients with bvFTD show increased sleep duration and reduced sleep quality. Patients with bvFTD show rest-activity alterations in the morning and early afternoon. Sleep duration is associated with reduced cortical thickness in frontal regions. These alterations may represent an early sign of neurodegeneration.

Grey-matter correlates of empathy in 4-Repeat Tauopathies.

Loss of empathy is an early and central symptom of frontotemporal lobar degeneration spectrum diseases. We aimed to investigate the topographical distribution of morphometric brain changes associated with empathy in Progressive Supranuclear Palsy (PSP) and Corticobasal Syndrome (CBS) patients. Twenty-seven participants with CBS and 31 with PSP were evaluated using Interpersonal Reactivity Index scales in correlation with gray matter atrophy using a voxel-based morphometry approach. Lower levels of empathy were associated with an increased atrophy in fronto-temporal cortical structures. At subcortical level, empathy scores were positively correlated with gray matter volume in the amygdala, hippocampus and the cerebellum. These findings allow to extend the traditional cortico-centric view of cognitive empathy to the cerebellar regions in patients with neurodegenerative disorders and suggest that the cerebellum may play a more prominent role in social cognition than previously appreciated.

Cortical signature of depressive symptoms in frontotemporal dementia: A surface-based analysis.

BACKGROUND AND OBJECTIVES: Depressive symptoms are frequently reported in patients affected by frontotemporal dementia (FTD). At structural MRI, cortical features of depressed FTD patients have been poorly described. Our objective was to investigate correlations between cortical measures and depression severity in FTD patients. METHODS: Data were obtained from the Frontotemporal Lobar Degeneration Neuroimaging Initiative (FTLDNI) database. We included 98 controls and 92 FTD patients, n = 38 behavioral variant FTD (bvFTD), n = 26 non-fluent variant Primary Progressive Aphasia (nfvPPA), and n = 28 semantic variant Primary Progressive Aphasia (svPPA). Patients underwent clinical and cognitive evaluations, as well as a 3D T1-weighted MRI on a 3 Tesla scanner (Siemens, Trio Tim system). Depression was evaluated by means of Geriatric Depression Scale (GDS). Surface-based analysis was performed on T1-weighted images to evaluate cortical thickness, a measure of gray matter integrity, and local gyrification index (lGI), a quantitative metric of cortical folding. RESULTS: Patients affected by svPPA were more depressed than controls at NPI and depression severity at GDS was higher in svPPA and bvFTD. Severity of depression correlated with a decrease in lGI in left precentral and superior frontal gyrus, supramarginal and postcentral gyrus and right precentral, supramarginal, superior parietal and superior frontal gyri. Furthermore, depression severity correlated positively with cortical thickness in the left medial orbitofrontal cortex. DISCUSSION: We found that lGI was associated with depressive symptoms over brain regions involved in the pathophysiology of major depressive disorder. This finding provides novel insights into the mechanisms underlying psychiatric symptoms in FTD.

The impact of upper and lower motor neuron burden on diagnostic certainty, and clinical course of spinal-onset amyotrophic lateral sclerosis: a cluster-based approach.

BACKGROUND: Upper motor neuron (UMN) and lower motor neuron (LMN) involvement represent the core clinical features of amyotrophic lateral sclerosis (ALS). Several studies divided patients into prevalent UMN and LMN impairment phenotypes to investigate the association between motor systems impairments and ALS clinical course. However, this distinction was somehow heterogeneous and significantly affected the comparability across studies. AIMS: This study aimed to investigate whether patients spontaneously segregate based on the extent of UMN and LMN involvement without a-priori categorization and to identify potential clinical and prognostic features of different clusters. METHODS: Eighty-eight consecutive spinal-onset ALS patients were referred to an ALS tertiary center between 2015 and 2022. UMN and LMN burden was assessed with the Penn Upper Motor Neuron scale (PUMNS) and the Devine score, respectively. PUMNS and LMN scores were normalized into 0-1 and analyzed using a two-step cluster analysis and the Euclidean distance measure. The Bayesian Information Criterion was used to determine the cluster number. Demographic and clinical variables were tested for differences among the clusters. RESULTS: Three distinct clusters emerged at cluster analysis. Patients in "cluster-1" showed moderate UMN and severe LMN involvement, corresponding to the typical ALS phenotype. Patients in "cluster-2" showed mild LMN and severe UMN damage, corresponding to a predominant UMN phenotype, while "cluster-3" patients showed mild UMN and moderate LMN damage, corresponding to a predominant LMN phenotype. Patients in "cluster-1" and "cluster-2" showed a higher prevalence of definite ALS than those in "cluster-3" (61% and 46 vs 9%, p < 0.001). "Cluster-1" patients had a lower median ALSFRS-r score compared to both "cluster-2" and 3 patients (27 vs 40 and 35, < 0.001). "Cluster-1" (HR: 8.5; 95% CI 2.1-35.1 and p = 0.003) and 3 (HR: 3.2; 95% CI 1.1-9.1; p = 0.03) were associated with shorter survival than those in "cluster-2". CONCLUSIONS: Spinal-onset ALS can be categorized into three groups according to LMN and UMN burden. The UMN burden is related to higher diagnostic certainty and broader disease spread, while LMN involvement is associated with higher disease severity and shorter survival.

Asymmetry of radiomics features in the white matter of patients with primary progressive aphasia.

Introduction: Primary Progressive Aphasia (PPA) is a neurological disease characterized by linguistic deficits. Semantic (svPPA) and non-fluent/agrammatic (nfvPPA) variants are the two main clinical subtypes. We applied a novel analytical framework, based on radiomic analysis, to investigate White Matter (WM) asymmetry and to examine whether asymmetry is associated with verbal fluency performance. Methods: Analyses were performed on T1-weighted images including 56 patients with PPA (31 svPPA and 25 nfvPPA) and 53 age- and sex-matched controls. Asymmetry Index (AI) was computed for 86 radiomics features in 34 white matter regions. The relationships between AI, verbal fluency performance (semantic and phonemic) and Boston Naming Test score (BNT) were explored through Spearman correlation analysis. Results: Relative to controls, WM asymmetry in svPPA patients involved regions adjacent to middle temporal cortex as part of the inferior longitudinal (ILF), fronto-occipital (IFOF) and superior longitudinal fasciculi. Conversely, nfvPPA patients showed an asymmetry of WM in lateral occipital regions (ILF/IFOF). A higher lateralization involving IFOF, cingulum and forceps minor was found in nfvPPA compared to svPPA patients. In nfvPPA patients, semantic fluency was positively correlated to asymmetry in ILF/IFOF tracts. Performances at BNT were associated with AI values of the middle temporal (ILF/SLF) and parahippocampal (ILF/IFOF) gyri in svPPA patients. Discussion: Radiomics features depicted distinct pathways of asymmetry in svPPA and nfvPPA involving damage of principal fiber tracts associated with speech and language. Assessing asymmetry of radiomics in PPA allows achieving a deeper insight into the neuroanatomical damage and may represent a candidate severity marker for language impairments in PPA patients.

Different patterns of spreading direction and motor neurons involvement in a cohort of limb-onset amyotrophic lateral sclerosis patients from Southern Italy: Potential implication on disease course or progression?

BACKGROUND: Currently, there is a lack of knowledge concerning where the pathological process starts and how the neurodegeneration spreads during the course of amyotrophic lateral sclerosis (ALS). AIMS: This study aims to evaluate the spreading direction of the disease and the corresponding clinical characteristics in a cohort of patients with limb-onset ALS. PATIENTS AND METHODS: Consecutive incident ALS patients referring to an ALS tertiary center from Southern Italy, between 2015 and 2021, were recruited in the study. According to the initial directions of spread, patients were dichotomized into horizontal spreading pattern (HSP) or vertical spreading pattern (VSP) groups. RESULTS: Among 137 newly diagnosed ALS, 87 presented a spinal onset. Ten patients with pure LMN were not included in the study. All cases reported a clear spread direction. The frequency of HSP and VSP spreading was similar overall (47 vs. 30). The prevalence of HSP was higher (74% vs. 50%) in patients with upper limb-onset (UL-ALS), compared to patients with lower limb-onset (LL-ALS; p < .05). Conversely, the occurrence of VSP spread was threefold higher in patients with LL-ALS, compared to UL-ALS (p < .05). Patients with VSP showed a wider upper motor neuron impairment, whereas the involvement of LMN resulted greater in patients with HSP. Patients with HSP exhibited a greater drop of ALSFRS-r sub-score in the region of onset, while VSP showed a slighter but more diffuse reduction of ASLFRS-r subscore in more body districts beyond the site of onset. Patients with VSP were also characterized by a higher median progression rate and an earlier median bulbar involvement, compared to HSP. CONCLUSIONS: Our findings suggested investigating the spreading direction of ALS among patients with spinal onset, to better delineate the clinical profiles of patients with ALS, and predict an earlier impairment of bulbar muscle and a more rapid progression of the disease.

Split-elbow sign in the PRO-ACT and Southern Italy ALS cohorts: a potential marker of disease severity and lower motor neuron involvement?

INTRODUCTION: Split phenomena in ALS refers to the preferential dysfunction of some groups of muscles over others. The split-elbow sign (SE) is characterized by the predominant weakness of the biceps compared to the triceps, but available results are conflicting. OBJECTIVES: To evaluate the prevalence of the SE in two independent cohorts: the randomized controlled trial-based PRO-ACT cohort (n = 500) and a monocentric cohort of patients with ALS from Southern Italy (n = 144); to investigate the demographic and clinical variables associated with the SE sign. METHODS: Wilcoxon signed-rank test was used to compare biceps with triceps power in the same limb measured by hand-held dynamometry in the PRO-ACT cohort and Medical Research Council (MRC) in our cohort. Each limb was considered independently and not paired within the same individual. The arm where the triceps was stronger than the biceps was defined SE + , whereas the arm where the biceps was stronger than the triceps was considered SE-. A backward stepwise multivariate logistic regression was used to analyze the relationship between clinical and demographic variables and SE. PENN Upper Motor Neuron and Devine scales were used to evaluate the different upper (UMN) and lower (LMN) motor neuron impairments between the SE + and SE- arms. RESULTS: In both cohorts, the biceps were on average stronger than the triceps, and the SE sign was present in 41% of the PRO-ACT cohort and just 30% of the Southern Italy cohort. The multivariate logistic regression revealed that older age (OR: 1.45; p = 0.01), male gender (OR: 1.55; p = 0.002), spinal onset (OR: 1.59; p = 0.007), and higher disease severity (OR: 1.70; p = 0.001) were significant predictors of the SE sign in the PRO-ACT cohort. Conversely, in Southern Italy patients, only a lower ALSFRS-R score was a significant determinant of the SE (OR: 8.47; p = 0.008). Finally, SE + arms exhibited a significantly higher median Devine sub-score compared to SE- [1 vs 0, p = < 0.05], while arms SE- showed a significantly higher median PUMNS sub-score [2 vs 0; p = < 0.05)]. CONCLUSION: In our study, most patients with ALS do not show SE. Patients with SE are more likely older, males, with spinal onset, a higher degree of disease severity, and predominant and wider LMN impairment.

Heritability of human "directed" functional connectome.

INTRODUCTION: The functional connectivity patterns in the brain are highly heritable; however, it is unclear how genetic factors influence the directionality of such "information flows." Studying the "directionality" of the brain functional connectivity and assessing how heritability modulates it can improve our understanding of the human connectome. METHODS: Here, we investigated the heritability of "directed" functional connections using a state-space formulation of Granger causality (GC), in conjunction with blind deconvolution methods accounting for local variability in the hemodynamic response function. Such GC implementation is ideal to explore the directionality of functional interactions across a large number of networks. Resting-state functional magnetic resonance imaging data were drawn from the Human Connectome Project (total n = 898 participants). To add robustness to our findings, the dataset was randomly split into a "discovery" and a "replication" sample (each with n = 449 participants). The two cohorts were carefully matched in terms of demographic variables and other confounding factors (e.g., education). The effect of shared environment was also modeled. RESULTS: The parieto- and prefronto-cerebellar, parieto-prefrontal, and posterior-cingulate to hippocampus connections showed the highest and most replicable heritability effects with little influence by shared environment. In contrast, shared environmental factors significantly affected the visuo-parietal and sensory-motor directed connectivity. CONCLUSION: We suggest a robust role of heritability in influencing the directed connectivity of some cortico-subcortical circuits implicated in cognition. Further studies, for example using task-based fMRI and GC, are warranted to confirm the asymmetric effects of genetic factors on the functional connectivity within cognitive networks and their role in supporting executive functions and learning.

Behavioral variant frontotemporal dementia in patients with primary psychiatric disorder: A magnetic resonance imaging study.

BACKGROUND: The clinical diagnosis of behavioral variant frontotemporal dementia (bvFTD) in patients with a history of primary psychiatric disorder (PPD) is challenging. PPD shows the typical cognitive impairments observed in patients with bvFTD. Therefore, the correct identification of bvFTD onset in patients with a lifetime history of PPD is pivotal for an optimal management. METHODS: Twenty-nine patients with PPD were included in this study. After clinical and neuropsychological evaluations, 16 patients with PPD were clinically classified as bvFTD (PPD-bvFTD+), while in 13 cases clinical symptoms were associated with the typical course of the psychiatric disorder itself (PPD-bvFTD-). Voxel- and surface-based investigations were used to characterize gray matter changes. Volumetric and cortical thickness measures were used to predict the clinical diagnosis at a single-subject level using a support vector machine (SVM) classification framework. Finally, we compared classification performances of magnetic resonance imaging (MRI) data with automatic visual rating scale of frontal and temporal atrophy. RESULTS: PPD-bvFTD+ showed a gray matter decrease in thalamus, hippocampus, temporal pole, lingual, occipital, and superior frontal gyri compared to PPD-bvFTD- (p < .05, family-wise error-corrected). SVM classifier showed a discrimination accuracy of 86.2% in differentiating PPD patients with bvFTD from those without bvFTD. CONCLUSIONS: Our study highlights the utility of machine learning applied to structural MRI data to support the clinician in the diagnosis of bvFTD in patients with a history of PPD. Gray matter atrophy in temporal, frontal, and occipital brain regions may represent a useful hallmark for a correct identification of dementia in PPD at a single-subject level.

The impact of harmonization on radiomic features in Parkinson's disease and healthy controls: A multicenter study.

Radiomics is a challenging development area in imaging field that is greatly capturing interest of radiologists and neuroscientists. However, radiomics features show a strong non-biological variability determined by different facilities and imaging protocols, limiting the reproducibility and generalizability of analysis frameworks. Our study aimed to investigate the usefulness of harmonization to reduce site-effects on radiomics features over specific brain regions. We selected T1-weighted magnetic resonance imaging (MRI) by using the MRI dataset Parkinson's Progression Markers Initiative (PPMI) from different sites with healthy controls (HC) and Parkinson's disease (PD) patients. First, the investigation of radiomics measure discrepancies were assessed on healthy brain regions-of-interest (ROIs) via a classification pipeline based on LASSO feature selection and support vector machine (SVM) model. Then, a ComBat-based harmonization approach was applied to correct site-effects. Finally, a validation step on PD subjects evaluated diagnostic accuracy before and after harmonization of radiomics data. Results on healthy subjects demonstrated a dependence from site-effects that could be corrected with ComBat harmonization. LASSO regressor after harmonization was unable to select any feature to distinguish controls by site. Moreover, harmonized radiomics features achieved an area under the receiving operating characteristic curve (AUC) of 0.77 (compared to AUC of 0.71 for raw radiomics measures) in distinguish Parkinson's patients from HC. We found a not-negligible site-effect studying radiomics of HC pre- and post-harmonization of features. Our validation study on PD patients demonstrated a significant influence of non-biological noise source in diagnostic performances. Finally, harmonization of multicenter radiomic data represent a necessary step to make analysis pipelines reliable and replicable for multisite neuroimaging studies.

Deep networks for behavioral variant frontotemporal dementia identification from multiple acquisition sources.

Behavioral variant frontotemporal dementia (bvFTD) is a neurodegenerative syndrome whose clinical diagnosis remains a challenging task especially in the early stage of the disease. Currently, the presence of frontal and anterior temporal lobe atrophies on magnetic resonance imaging (MRI) is part of the diagnostic criteria for bvFTD. However, MRI data processing is usually dependent on the acquisition device and mostly require human-assisted crafting of feature extraction. Following the impressive improvements of deep architectures, in this study we report on bvFTD identification using various classes of artificial neural networks, and present the results we achieved on classification accuracy and obliviousness on acquisition devices using extensive hyperparameter search. In particular, we will demonstrate the stability and generalization of different deep networks based on the attention mechanism, where data intra-mixing confers models the ability to identify the disorder even on MRI data in inter-device settings, i.e., on data produced by different acquisition devices and without model fine tuning, as shown from the very encouraging performance evaluations that dramatically reach and overcome the 90% value on the AuROC and balanced accuracy metrics.

Radiomics Model for Frontotemporal Dementia Diagnosis Using T1-Weighted MRI.

Radiomics has been proposed as a useful approach to extrapolate novel morphological and textural information from brain Magnetic resonance images (MRI). Radiomics analysis has shown unique potential in the diagnostic work-up and in the follow-up of patients suffering from neurodegenerative diseases. However, the potentiality of this technique in distinguishing frontotemporal dementia (FTD) subtypes has so far not been investigated. In this study, we explored the usefulness of radiomic features in differentiating FTD subtypes, namely, the behavioral variant of FTD (bvFTD), the non-fluent and/or agrammatic (PNFA) and semantic (svPPA) variants of a primary progressive aphasia (PPA). Classification analyses were performed on 3 Tesla T1-weighted images obtained from the Frontotemporal Lobar Degeneration Neuroimaging Initiative. We included 49 patients with bvFTD, 25 patients with PNFA, 34 patients with svPPA, and 60 healthy controls. Texture analyses were conducted to define the first-order statistic and textural features in cortical and subcortical brain regions. Recursive feature elimination was used to select the radiomics signature for each pairwise comparison followed by a classification framework based on a support vector machine. Finally, 10-fold cross-validation was used to assess classification performances. The radiomics-based approach successfully identified the brain regions typically involved in each FTD subtype, achieving a mean accuracy of more than 80% in distinguishing between patient groups. Note mentioning is that radiomics features extracted in the left temporal regions allowed achieving an accuracy of 91 and 94% in distinguishing patients with svPPA from those with PNFA and bvFTD, respectively. Radiomics features show excellent classification performances in distinguishing FTD subtypes, supporting the clinical usefulness of this approach in the diagnostic work-up of FTD.

The Role of Graph Theory in Evaluating Brain Network Alterations in Frontotemporal Dementia.

Frontotemporal dementia (FTD) is a spectrum of clinical syndromes that affects personality, behavior, language, and cognition. The current diagnostic criteria recognize three main clinical subtypes: the behavioral variant of FTD (bvFTD), the semantic variant of primary progressive aphasia (svPPA), and the non-fluent/agrammatic variant of PPA (nfvPPA). Patients with FTD display heterogeneous clinical and neuropsychological features that highly overlap with those presented by psychiatric syndromes and other types of dementia. Moreover, up to now there are no reliable disease biomarkers, which makes the diagnosis of FTD particularly challenging. To overcome this issue, different studies have adopted metrics derived from magnetic resonance imaging (MRI) to characterize structural and functional brain abnormalities. Within this field, a growing body of scientific literature has shown that graph theory analysis applied to MRI data displays unique potentialities in unveiling brain network abnormalities of FTD subtypes. Here, we provide a critical overview of studies that adopted graph theory to examine the topological changes of large-scale brain networks in FTD. Moreover, we also discuss the possible role of information arising from brain network organization in the diagnostic algorithm of FTD-spectrum disorders and in investigating the neural correlates of clinical symptoms and cognitive deficits experienced by patients.

The Relationship Between Muscle Strength and Cognitive Performance Across Alzheimer's Disease Clinical Continuum.

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by a progressive cognitive decline, mostly prominent in the domain of memory, but also associated with other cognitive deficits and non-cognitive symptoms. Reduced muscle strength is common in AD. However, the current understanding of its relationship with cognitive decline is limited. This study investigates the relationship between muscle strength and cognition in patients with AD and mild cognitive impairment (MCI). We enrolled 148 consecutive subjects, including 74 patients with probable AD dementia, 37 MCI, and 37 controls. Participants underwent neuropsychological evaluation focused on attention, working memory, declarative memory and learning. Muscle strength and muscle mass were measured through hand dynamometer and bio-electrical impedance analysis, respectively. Patients with AD dementia were divided with respect to the severity of cognitive impairment into mild and moderate-to-severe patients. Moderate-to-severe patients with AD presented lower handgrip strength than MCI and controls. No differences were observed in muscle mass. In MCI and AD dementia, handgrip strength was associated with overall cognitive functioning, attentional and memory performance. The routine implementation of handgrip strength assessment in the clinical work-up of patients with MCI and AD could potentially represent a simple method to monitor functional and cognitive decline along the disease course.

A Machine Learning Approach to Parkinson's Disease Blood Transcriptomics.

The increased incidence and the significant health burden associated with Parkinson's disease (PD) have stimulated substantial research efforts towards the identification of effective treatments and diagnostic procedures. Despite technological advancements, a cure is still not available and PD is often diagnosed a long time after onset when irreversible damage has already occurred. Blood transcriptomics represents a potentially disruptive technology for the early diagnosis of PD. We used transcriptome data from the PPMI study, a large cohort study with early PD subjects and age matched controls (HC), to perform the classification of PD vs. HC in around 550 samples. Using a nested feature selection procedure based on Random Forests and XGBoost we reached an AUC of 72% and found 493 candidate genes. We further discussed the importance of the selected genes through a functional analysis based on GOs and KEGG pathways.