Prediction of the information processing speed performance in multiple sclerosis using a machine learning approach in a large multicenter magnetic resonance imaging data set.

Many patients with multiple sclerosis (MS) experience information processing speed (IPS) deficits, and the Symbol Digit Modalities Test (SDMT) has been recommended as a valid screening test. Magnetic resonance imaging (MRI) has markedly improved the understanding of the mechanisms associated with cognitive deficits in MS. However, which structural MRI markers are the most closely related to cognitive performance is still unclear. We used the multicenter 3T-MRI data set of the Italian Neuroimaging Network Initiative to extract multimodal data (i.e., demographic, clinical, neuropsychological, and structural MRIs) of 540 MS patients. We aimed to assess, through machine learning techniques, the contribution of brain MRI structural volumes in the prediction of IPS deficits when combined with demographic and clinical features. We trained and tested the eXtreme Gradient Boosting (XGBoost) model following a rigorous validation scheme to obtain reliable generalization performance. We carried out a classification and a regression task based on SDMT scores feeding each model with different combinations of features. For the classification task, the model trained with thalamus, cortical gray matter, hippocampus, and lesions volumes achieved an area under the receiver operating characteristic curve of 0.74. For the regression task, the model trained with cortical gray matter and thalamus volumes, EDSS, nucleus accumbens, lesions, and putamen volumes, and age reached a mean absolute error of 0.95. In conclusion, our results confirmed that damage to cortical gray matter and relevant deep and archaic gray matter structures, such as the thalamus and hippocampus, is among the most relevant predictors of cognitive performance in MS.

Pulmonary emphysema and coronary artery calcifications at baseline LDCT and long-term mortality in smokers and former smokers of the ITALUNG screening trial.

OBJECTIVES: Cardiovascular disease (CVD), lung cancer (LC), and respiratory diseases are main causes of death in smokers and former smokers undergoing low-dose computed tomography (LDCT) for LC screening. We assessed whether quantification of pulmonary emphysematous changes at baseline LDCT has a predictive value concerning long-term mortality. METHODS: In this longitudinal study, we assessed pulmonary emphysematous changes with densitometry (volume corrected relative area below - 950 Hounsfield units) and coronary artery calcifications (CAC) with a 0-3 visual scale in baseline LDCT of 524 participants in the ITALUNG trial and analyzed their association with mortality after 13.6 years of follow-up using conventional statistics and a machine learning approach. RESULTS: Pulmonary emphysematous changes were present in 32.3% of subjects and were mild (6% ≤ RA950 ≤ 9%) in 14.9% and moderate-severe (RA950 > 9%) in 17.4%. CAC were present in 67% of subjects (mild in 34.7%, moderate-severe in 32.2%). In the follow-up, 81 (15.4%) subjects died (20 of LC, 28 of other cancers, 15 of CVD, 4 of respiratory disease, and 14 of other conditions). After adjusting for age, sex, smoking history, and CAC, moderate-severe emphysema was significantly associated with overall (OR 2.22; 95CI 1.34-3.70) and CVD (OR 3.66; 95CI 1.21-11.04) mortality. Machine learning showed that RA950 was the best single feature predictive of overall and CVD mortality. CONCLUSIONS: Moderate-severe pulmonary emphysematous changes are an independent predictor of long-term overall and CVD mortality in subjects participating in LC screening and should be incorporated in the post-test calculation of the individual mortality risk profile. KEY POINTS: • Densitometry allows quantification of pulmonary emphysematous changes in low-dose CT examinations for lung cancer screening. • Emphysematous lung density changes are an independent predictor of long-term overall and cardio-vascular disease mortality in smokers and former smokers undergoing screening. • Emphysematous changes quantification should be included in the post-test calculation of the individual mortality risk profile.

Cognitive phenotypes and factors associated with cognitive decline in a cohort of older patients with atrial fibrillation: The Strat-AF study.

BACKGROUND AND PURPOSE: The multifactorial relationship between atrial fibrillation (AF) and cognitive impairment needs to be elucidated. The aim of this study was to assess, in AF patients on oral anticoagulants (OACs), the prevalence of cognitive impairment, defined according to clinical criteria or data-driven phenotypes, the prevalence of cognitive worsening, and factors associated with cognitive outcomes. METHODS: The observational prospective Strat-AF study enrolled AF patients aged ≥ 65 years who were receiving OACs. The baseline and 18-month protocol included clinical, functional, and cognitive assessment, and brain magnetic resonance imaging. Cognitive outcomes were: empirically derived cognitive phenotypes; clinical diagnosis of cognitive impairment; and longitudinal cognitive worsening. RESULTS: Out of 182 patients (mean age 77.7 ± 6.7 years, 63% males), 82 (45%) received a cognitive impairment diagnosis, which was associated with lower education level and functional status, and higher level of atrophy. Cluster analysis identified three cognitive profiles: dysexecutive (17%); amnestic (25%); and normal (58%). Compared to the normal group, the dysexecutive group was older, and had higher CHA2 DS2 -VASc scores, while the amnestic group had worse cognitive and functional abilities, and medial temporal lobe atrophy (MTA). Out of 128 followed-up patients, 35 (27%) had cognitive worsening that was associated with lower education level, worse cognitive efficiency, CHA2 DS2 -VASc score, timing of OAC intake, history of stroke, diabetes, non-lacunar infarcts, white matter hyperintensities and MTA. In multivariate models, belonging to the dysexecutive or amnestic group was a main predictor of cognitive worsening. CONCLUSIONS: In our cohort of older AF patients, CHA2 DS2 -VASc score, timing of OAC intake, and history of stroke influenced presence, type and progression of cognitive impairment. Empirically derived cognitive classification identified three groups with different clinical profiles and better predictive ability for cognitive worsening compared to conventional clinical diagnosis.

Longitudinal study of the effect of a 5-year exercise intervention on structural brain complexity in older adults. A Generation 100 substudy.

Physical inactivity has been identified as an important risk factor for dementia. High levels of cardiorespiratory fitness (CRF) have been shown to reduce the risk of dementia. However, the mechanism by which exercise affects brain health is still debated. Fractal dimension (FD) is an index that quantifies the structural complexity of the brain. The purpose of this study was to investigate the effects of a 5-year exercise intervention on the structural complexity of the brain, measured through the FD, in a subset of 105 healthy older adults participating in the randomized controlled trial Generation 100 Study. The subjects were randomized into control, moderate intensity continuous training, and high intensity interval training groups. Both brain MRI and CRF were acquired at baseline and at 1-, 3- and 5-years follow-ups. Cortical thickness and volume data were extracted with FreeSurfer, and FD of the cortical lobes, cerebral and cerebellar gray and white matter were computed. CRF was measured as peak oxygen uptake (VO2peak) using ergospirometry during graded maximal exercise testing. Linear mixed models were used to investigate exercise group differences and possible CRF effects on the brain's structural complexity. Associations between change over time in CRF and FD were performed if there was a significant association between CRF and FD. There were no effects of group membership on the structural complexity. However, we found a positive association between CRF and the cerebral gray matter FD (p < 0.001) and the temporal lobe gray matter FD (p < 0.001). This effect was not present for cortical thickness, suggesting that FD is a more sensitive index of structural changes. The change over time in CRF was associated with the change in temporal lobe gray matter FD from baseline to 5-year follow-up (p < 0.05). No association of the change was found between CRF and cerebral gray matter FD. These results demonstrated that entering old age with high and preserved CRF levels protected against loss of structural complexity in areas sensitive to aging and age-related pathology.

Brain Structure and Degeneration Staging in Friedreich Ataxia: Magnetic Resonance Imaging Volumetrics from the ENIGMA-Ataxia Working Group.

OBJECTIVE: Friedreich ataxia (FRDA) is an inherited neurological disease defined by progressive movement incoordination. We undertook a comprehensive characterization of the spatial profile and progressive evolution of structural brain abnormalities in people with FRDA. METHODS: A coordinated international analysis of regional brain volume using magnetic resonance imaging data charted the whole-brain profile, interindividual variability, and temporal staging of structural brain differences in 248 individuals with FRDA and 262 healthy controls. RESULTS: The brainstem, dentate nucleus region, and superior and inferior cerebellar peduncles showed the greatest reductions in volume relative to controls (Cohen d = 1.5-2.6). Cerebellar gray matter alterations were most pronounced in lobules I-VI (d = 0.8), whereas cerebral differences occurred most prominently in precentral gyri (d = 0.6) and corticospinal tracts (d = 1.4). Earlier onset age predicted less volume in the motor cerebellum (rmax  = 0.35) and peduncles (rmax  = 0.36). Disease duration and severity correlated with volume deficits in the dentate nucleus region, brainstem, and superior/inferior cerebellar peduncles (rmax  = -0.49); subgrouping showed these to be robust and early features of FRDA, and strong candidates for further biomarker validation. Cerebral white matter abnormalities, particularly in corticospinal pathways, emerge as intermediate disease features. Cerebellar and cerebral gray matter loss, principally targeting motor and sensory systems, preferentially manifests later in the disease course. INTERPRETATION: FRDA is defined by an evolving spatial profile of neuroanatomical changes beyond primary pathology in the cerebellum and spinal cord, in line with its progressive clinical course. The design, interpretation, and generalization of research studies and clinical trials must consider neuroanatomical staging and associated interindividual variability in brain measures. ANN NEUROL 2021;90:570-583.

Role of Biological Markers for Cerebral Bleeding Risk STRATification in Patients with Atrial Fibrillation on Oral Anticoagulants for Primary or Secondary Prevention of Ischemic Stroke (Strat-AF Study): Study Design and Methodology.

Background and Objectives: In anticoagulated atrial fibrillation (AF) patients, the validity of models recommended for the stratification of the risk ratio between benefits and hemorrhage risk is limited. Cerebral small vessel disease (SVD) represents the pathologic substrate for primary intracerebral hemorrhage and ischemic stroke. We hypothesize that biological markers-both circulating and imaging-based-and their possible interaction, might improve the prediction of bleeding risk in AF patients under treatment with any type of oral anticoagulant. Materials and Methods: The Strat-AF study is an observational, prospective, single-center hospital-based study enrolling patients with AF, aged 65 years or older, and with no contraindications to magnetic resonance imaging (MRI), referring to Center of Thrombosis outpatient clinic of our University Hospital for the management of oral anticoagulation therapy. Recruited patients are evaluated by means of a comprehensive protocol, with clinical, cerebral MRI, and circulating biomarkers assessment at baseline and after 18 months. The main outcome is SVD progression-particularly microbleeds-as a selective surrogate marker of hemorrhagic complication. Stroke occurrence (ischemic or hemorrhagic) and the progression of functional, cognitive, and motor status will be evaluated as secondary outcomes. Circulating biomarkers may further improve predictive potentials. Results: Starting from September 2017, 194 patients (mean age 78.1 ± 6.7, range 65-97; 61% males) were enrolled. The type of AF was paroxysmal in 93 patients (48%), and persistent or permanent in the remaining patients. Concerning the type of oral anticoagulant, 57 patients (29%) were on vitamin K antagonists, and 137 (71%) were on direct oral anticoagulants. Follow-up clinical evaluation and brain MRI are ongoing. Conclusions: The Strat-AF study may be an essential step towards the exploration of the role of a combined clinical biomarker or multiple biomarker models in predicting stroke risk in AF, and might sustain the incorporation of such new markers in the existing stroke prediction schemes by the demonstration of a greater incremental value in predicting stroke risk and improvement in clinical outcomes in a cost-effective fashion.

Efficacy of MRI data harmonization in the age of machine learning: a multicenter study across 36 datasets.

Pooling publicly-available MRI data from multiple sites allows to assemble extensive groups of subjects, increase statistical power, and promote data reuse with machine learning techniques. The harmonization of multicenter data is necessary to reduce the confounding effect associated with non-biological sources of variability in the data. However, when applied to the entire dataset before machine learning, the harmonization leads to data leakage, because information outside the training set may affect model building, and potentially falsely overestimate performance. We propose a 1) measurement of the efficacy of data harmonization; 2) harmonizer transformer, i.e., an implementation of the ComBat harmonization allowing its encapsulation among the preprocessing steps of a machine learning pipeline, avoiding data leakage by design. We tested these tools using brain T1-weighted MRI data from 1740 healthy subjects acquired at 36 sites. After harmonization, the site effect was removed or reduced, and we showed the data leakage effect in predicting individual age from MRI data, highlighting that introducing the harmonizer transformer into a machine learning pipeline allows for avoiding data leakage by design.

Fractal dimension of the cortical gray matter outweighs other brain MRI features as a predictor of transition to dementia in patients with mild cognitive impairment and leukoaraiosis.

Background: The relative contribution of changes in the cerebral white matter (WM) and cortical gray matter (GM) to the transition to dementia in patients with mild cognitive impairment (MCI) is not yet established. In this longitudinal study, we aimed to analyze MRI features that may predict the transition to dementia in patients with MCI and T2 hyperintensities in the cerebral WM, also known as leukoaraiosis. Methods: Sixty-four participants with MCI and moderate to severe leukoaraiosis underwent baseline MRI examinations and annual neuropsychological testing over a 2 year period. The diagnosis of dementia was based on established criteria. We evaluated demographic, neuropsychological, and several MRI features at baseline as predictors of the clinical transition. The MRI features included visually assessed MRI features, such as the number of lacunes, microbleeds, and dilated perivascular spaces, and quantitative MRI features, such as volumes of the cortical GM, hippocampus, T2 hyperintensities, and diffusion indices of the cerebral WM. Additionally, we examined advanced quantitative features such as the fractal dimension (FD) of cortical GM and WM, which represents an index of tissue structural complexity derived from 3D-T1 weighted images. To assess the prediction of transition to dementia, we employed an XGBoost-based machine learning system using SHapley Additive exPlanations (SHAP) values to provide explainability to the machine learning model. Results: After 2 years, 18 (28.1%) participants had transitioned from MCI to dementia. The area under the receiving operator characteristic curve was 0.69 (0.53, 0.85) [mean (90% confidence interval)]. The cortical GM-FD emerged as the top-ranking predictive feature of transition. Furthermore, aggregated quantitative neuroimaging features outperformed visually assessed MRI features in predicting conversion to dementia. Discussion: Our findings confirm the complementary roles of cortical GM and WM changes as underlying factors in the development of dementia in subjects with MCI and leukoaraiosis. FD appears to be a biomarker potentially more sensitive than other brain features.

Collinearity and Dimensionality Reduction in Radiomics: Effect of Preprocessing Parameters in Hypertrophic Cardiomyopathy Magnetic Resonance T1 and T2 Mapping.

Radiomics and artificial intelligence have the potential to become a valuable tool in clinical applications. Frequently, radiomic analyses through machine learning methods present issues caused by high dimensionality and multicollinearity, and redundant radiomic features are usually removed based on correlation analysis. We assessed the effect of preprocessing-in terms of voxel size resampling, discretization, and filtering-on correlation-based dimensionality reduction in radiomic features from cardiac T1 and T2 maps of patients with hypertrophic cardiomyopathy. For different combinations of preprocessing parameters, we performed a dimensionality reduction of radiomic features based on either Pearson's or Spearman's correlation coefficient, followed by the computation of the stability index. With varying resampling voxel size and discretization bin width, for both T1 and T2 maps, Pearson's and Spearman's dimensionality reduction produced a slightly different percentage of remaining radiomic features, with a relatively high stability index. For different filters, the remaining features' stability was instead relatively low. Overall, the percentage of eliminated radiomic features through correlation-based dimensionality reduction was more dependent on resampling voxel size and discretization bin width for textural features than for shape or first-order features. Notably, correlation-based dimensionality reduction was less sensitive to preprocessing when considering radiomic features from T2 compared with T1 maps.

Impact of seed amplification assay and surface-enhanced Raman spectroscopy combined approach on the clinical diagnosis of Alzheimer's disease.

BACKGROUND: The current diagnosis of Alzheimer's disease (AD) is based on a series of analyses which involve clinical, instrumental and laboratory findings. However, signs, symptoms and biomarker alterations observed in AD might overlap with other dementias, resulting in misdiagnosis. METHODS: Here we describe a new diagnostic approach for AD which takes advantage of the boosted sensitivity in biomolecular detection, as allowed by seed amplification assay (SAA), combined with the unique specificity in biomolecular recognition, as provided by surface-enhanced Raman spectroscopy (SERS). RESULTS: The SAA-SERS approach supported by machine learning data analysis allowed efficient identification of pathological Aß oligomers in the cerebrospinal fluid of patients with a clinical diagnosis of AD or mild cognitive impairment due to AD. CONCLUSIONS: Such analytical approach can be used to recognize disease features, thus allowing early stratification and selection of patients, which is fundamental in clinical treatments and pharmacological trials.

Resting-state functional MRI in multicenter studies on multiple sclerosis: a report on raw data quality and functional connectivity features from the Italian Neuroimaging Network Initiative.

The Italian Neuroimaging Network Initiative (INNI) is an expanding repository of brain MRI data from multiple sclerosis (MS) patients recruited at four Italian MRI research sites. We describe the raw data quality of resting-state functional MRI (RS-fMRI) time-series in INNI and the inter-site variability in functional connectivity (FC) features after unified automated data preprocessing. MRI datasets from 489 MS patients and 246 healthy control (HC) subjects were retrieved from the INNI database. Raw data quality metrics included temporal signal-to-noise ratio (tSNR), spatial smoothness (FWHM), framewise displacement (FD), and differential variation in signals (DVARS). Automated preprocessing integrated white-matter lesion segmentation (SAMSEG) into a standard fMRI pipeline (fMRIPrep). FC features were calculated on pre-processed data and harmonized between sites (Combat) prior to assessing general MS-related alterations. Across centers (both groups), median tSNR and FWHM ranged from 47 to 84 and from 2.0 to 2.5, and median FD and DVARS ranged from 0.08 to 0.24 and from 1.06 to 1.22. After preprocessing, only global FC-related features were significantly correlated with FD or DVARS. Across large-scale networks, age/sex/FD-adjusted and harmonized FC features exhibited both inter-site and site-specific inter-group effects. Significant general reductions were obtained for somatomotor and limbic networks in MS patients (vs. HC). The implemented procedures provide technical information on raw data quality and outcome of fully automated preprocessing that might serve as reference in future RS-fMRI studies within INNI. The unified pipeline introduced little bias across sites and appears suitable for multisite FC analyses on harmonized network estimates.

The Role of Extracellular Matrix and Inflammation in the Stratification of Bleeding and Thrombotic Risk of Atrial Fibrillation on Oral Anticoagulant Therapy: Insights from Strat-Af Study.

In anticoagulated atrial fibrillation (AF) patients, the validity of models recommended for the stratification of the risk ratio between benefits and hemorrhage risk is limited. We hypothesize that both circulating and neuroimaging-based markers might improve the prediction of bleeding and thrombotic risk in anticoagulated AF patients. The Strat-AF study is an observational, prospective, single-center study enrolling 170 patients with AF; recruited patients are evaluated by means of a comprehensive protocol, with clinical, cerebral magnetic resonance imaging and circulating biomarkers assessment. The main outcome is the evaluation of cerebral microangiopathy related to the levels of circulating biomarkers of inflammation and extracellular matrix (ECM) remodeling. At multivariate logistic regression analysis adjusted for age, sex, CHA2DS2-VASc, HAS-BLED and type of anticoagulant, matrix metalloproteinases (MMP)-2 levels were significantly and positively associated with the presence of cerebral microbleeds (CMBs). A significant association between MMP-2, tissue inhibitor of metalloproteinases (TIMP)-1,-2,-4 levels and white matter hyperintensity was also found. Concerning the small vessel disease (SVD) score, MMP-2 and TIMP-1,-2 levels were associated with the presence of two and three or more signs of SVD, whereas TIMP-4 levels were associated with the presence of three signs of SVD with respect to patients with no instrumental signs of SVD. As regarding the presence of enlarged perivascular spaces (EPVS), a significant association was found for high levels of interleukin (IL)-8 and TIMP 1-2-3. These results demonstrate that patients with AF have evidence of impaired ECM degradation, which is an independent risk factor for thrombotic complications of AF patients on oral anticoagulant therapy. The incorporation of these markers in the prognostic schemes might improve their clinical capability in predicting stroke risk and thrombotic complications.

Image resampling and discretization effect on the estimate of myocardial radiomic features from T1 and T2 mapping in hypertrophic cardiomyopathy.

Radiomics is emerging as a promising and useful tool in cardiac magnetic resonance (CMR) imaging applications. Accordingly, the purpose of this study was to investigate, for the first time, the effect of image resampling/discretization and filtering on radiomic features estimation from quantitative CMR T1 and T2 mapping. Specifically, T1 and T2 maps of 26 patients with hypertrophic cardiomyopathy (HCM) were used to estimate 98 radiomic features for 7 different resampling voxel sizes (at fixed bin width), 9 different bin widths (at fixed resampling voxel size), and 7 different spatial filters (at fixed resampling voxel size/bin width). While we found a remarkable dependence of myocardial radiomic features from T1 and T2 mapping on image filters, many radiomic features showed a limited sensitivity to resampling voxel size/bin width, in terms of intraclass correlation coefficient (> 0.75) and coefficient of variation (< 30%). The estimate of most textural radiomic features showed a linear significant (p < 0.05) correlation with resampling voxel size/bin width. Overall, radiomic features from T2 maps have proven to be less sensitive to image preprocessing than those from T1 maps, especially when varying bin width. Our results might corroborate the potential of radiomics from T1/T2 mapping in HCM and hopefully in other myocardial diseases.

Can CHA2DS2-VASc and HAS-BLED Foresee the Presence of Cerebral Microbleeds, Lacunar and Non-Lacunar Infarcts in Elderly Patients With Atrial Fibrillation? Data From Strat-AF Study.

Anticoagulants reduce embolic risk in atrial fibrillation (AF), despite increasing hemorrhagic risk. In this context, validity of congestive heart failure, hypertension, age ≥ 75 years, diabetes, stroke, vascular disease, age 65-74 years and sex category (CHA2DS2-VASc) and hypertension, abnormal renal/liver function, stroke, bleeding history or predisposition, labile international normalized ratio, elderly, drugs/alcohol concomitantly (HAS-BLED) scales, used to respectively evaluate thrombotic and hemorrhagic risks, is incomplete. In patients with AF, brain MRI has led to the increased detection of "asymptomatic" brain changes, particularly those related to small vessel disease, which also represent the pathologic substrate of intracranial hemorrhage, and silent brain infarcts, which are considered risk factors for ischemic stroke. Routine brain MRI in asymptomatic patients with AF is not yet recommended. Our aim was to test predictive ability of risk stratification scales on the presence of cerebral microbleeds, lacunar, and non-lacunar infarcts in 170 elderly patients with AF on oral anticoagulants. Ad hoc developed R algorithms were used to evaluate CHA2DS2-VASc and HAS-BLED sensitivity and specificity on the prediction of cerebrovascular lesions: (1) Maintaining original items' weights; (2) augmenting weights' range; (3) adding cognitive, motor, and depressive scores. Accuracy was poor for each outcome considering both scales either in phase 1 or phase 2. Accuracy was never improved by the addition of cognitive scores. The addition of motor and depressive scores to CHA2DS2-VASc improved accuracy for non-lacunar infarcts (sensitivity = 0.70, specificity = 0.85), and sensitivity for lacunar-infarcts (sensitivity = 0.74, specificity = 0.61). Our results are a very first step toward the attempt to identify those elderly patients with AF who would benefit most from brain MRI in risk stratification.

NAVIGATOR: an Italian regional imaging biobank to promote precision medicine for oncologic patients.

NAVIGATOR is an Italian regional project boosting precision medicine in oncology with the aim of making it more predictive, preventive, and personalised by advancing translational research based on quantitative imaging and integrative omics analyses. The project's goal is to develop an open imaging biobank for the collection and preservation of a large amount of standardised imaging multimodal datasets, including computed tomography, magnetic resonance imaging, and positron emission tomography data, together with the corresponding patient-related and omics-related relevant information extracted from regional healthcare services using an adapted privacy-preserving model. The project is based on an open-source imaging biobank and an open-science oriented virtual research environment (VRE). Available integrative omics and multi-imaging data of three use cases (prostate cancer, rectal cancer, and gastric cancer) will be collected. All data confined in NAVIGATOR (i.e., standard and novel imaging biomarkers, non-imaging data, health agency data) will be used to create a digital patient model, to support the reliable prediction of the disease phenotype and risk stratification. The VRE that relies on a well-established infrastructure, called D4Science.org, will further provide a multiset infrastructure for processing the integrative omics data, extracting specific radiomic signatures, and for identification and testing of novel imaging biomarkers through big data analytics and artificial intelligence.

Resting state alpha oscillatory activity is a valid and reliable marker of schizotypy.

Schizophrenia is among the most debilitating neuropsychiatric disorders. However, clear neurophysiological markers that would identify at-risk individuals represent still an unknown. The aim of this study was to investigate possible alterations in the resting alpha oscillatory activity in normal population high on schizotypy trait, a physiological condition known to be severely altered in patients with schizophrenia. Direct comparison of resting-state EEG oscillatory activity between Low and High Schizotypy Group (LSG and HSG) has revealed a clear right hemisphere alteration in alpha activity of the HSG. Specifically, HSG shows a significant slowing down of right hemisphere posterior alpha frequency and an altered distribution of its amplitude, with a tendency towards a reduction in the right hemisphere in comparison to LSG. Furthermore, altered and reduced connectivity in the right fronto-parietal network within the alpha range was found in the HSG. Crucially, a trained pattern classifier based on these indices of alpha activity was able to successfully differentiate HSG from LSG on tested participants further confirming the specific importance of right hemispheric alpha activity and intrahemispheric functional connectivity. By combining alpha activity and connectivity measures with a machine learning predictive model optimized in a nested stratified cross-validation loop, current research offers a promising clinical tool able to identify individuals at-risk of developing psychosis (i.e., high schizotypy individuals).

Effect of data leakage in brain MRI classification using 2D convolutional neural networks.

In recent years, 2D convolutional neural networks (CNNs) have been extensively used to diagnose neurological diseases from magnetic resonance imaging (MRI) data due to their potential to discern subtle and intricate patterns. Despite the high performances reported in numerous studies, developing CNN models with good generalization abilities is still a challenging task due to possible data leakage introduced during cross-validation (CV). In this study, we quantitatively assessed the effect of a data leakage caused by 3D MRI data splitting based on a 2D slice-level using three 2D CNN models to classify patients with Alzheimer's disease (AD) and Parkinson's disease (PD). Our experiments showed that slice-level CV erroneously boosted the average slice level accuracy on the test set by 30% on Open Access Series of Imaging Studies (OASIS), 29% on Alzheimer's Disease Neuroimaging Initiative (ADNI), 48% on Parkinson's Progression Markers Initiative (PPMI) and 55% on a local de-novo PD Versilia dataset. Further tests on a randomly labeled OASIS-derived dataset produced about 96% of (erroneous) accuracy (slice-level split) and 50% accuracy (subject-level split), as expected from a randomized experiment. Overall, the extent of the effect of an erroneous slice-based CV is severe, especially for small datasets.

Altered Regional Brain Homogeneity of BOLD Signal in CADASIL: A Resting State fMRI Study.

BACKGROUND AND PURPOSE: The cognitive decline in cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) is assumed to be due to a cortical-subcortical disconnection secondary to damage to the cerebral white matter (WM). Using resting state functional MRI (rsfMRI) and analysis of the regional homogeneity (ReHo), we examined a group of CADASIL patients and a group of healthy subjects in order to: (1) explore possible differences between the two groups; and (2) to assess, in CADASIL patients, whether any ReHo abnormalities correlate with individual burdens of WM T2 -weighted hyperintensity and diffusion tensor imaging (DTI)-derived index of mean diffusivity (MD) of the cerebral WM, an index reflecting microstructural damage in CADASIL. METHODS: Twenty-three paucisymptomatic CADASIL patients (13 females; age mean ± standard deviation = 43.6 ± 11.1 years; three symptomatic and 20 with no or few symptoms) and 16 healthy controls (nine females; age 46.6 ± 11.0 years) were examined with T1 -weighted, T2 -weighted fluid attenuated inversion recovery images, DTI, and rsfMRI. RESULTS: When compared to controls, CADASIL patients showed four clusters of significantly lower ReHo values in cortical areas belonging to networks involved in inhibition and attention, including the right insula, the left superior frontal gyrus, and the bilateral anterior cingulated cortex. ReHo changes did not correlate with an individual patient's lesion burden or MD. CONCLUSIONS: This study reveals decreased ReHo of rsfMRI signals in cortical areas involved in inhibition and attention processes, suggesting a potential role for these functional cortical changes in CADASIL.

Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI.

Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.