Deep Learning-based Hierarchical Brain Segmentation with Preliminary Analysis of the Repeatability and Reproducibility.

PURPOSE: We developed new deep learning-based hierarchical brain segmentation (DLHBS) method that can segment T1-weighted MR images (T1WI) into 107 brain subregions and calculate the volume of each subregion. This study aimed to evaluate the repeatability and reproducibility of volume estimation using DLHBS and compare them with those of representative brain segmentation tools such as statistical parametric mapping (SPM) and FreeSurfer (FS). METHODS: Hierarchical segmentation using multiple deep learning models was employed to segment brain subregions within a clinically feasible processing time. The T1WI and brain mask pairs in 486 subjects were used as training data for training of the deep learning segmentation models. Training data were generated using a multi-atlas registration-based method. The high quality of training data was confirmed through visual evaluation and manual correction by neuroradiologists. The brain 3D-T1WI scan-rescan data of the 11 healthy subjects were obtained using three MRI scanners for evaluating the repeatability and reproducibility. The volumes of the eight ROIs-including gray matter, white matter, cerebrospinal fluid, hippocampus, orbital gyrus, cerebellum posterior lobe, putamen, and thalamus-obtained using DLHBS, SPM 12 with default settings, and FS with the "recon-all" pipeline. These volumes were then used for evaluation of repeatability and reproducibility. RESULTS: In the volume measurements, the bilateral thalamus showed higher repeatability with DLHBS compared with SPM. Furthermore, DLHBS demonstrated higher repeatability than FS in across all eight ROIs. Additionally, higher reproducibility was observed with DLHBS in both hemispheres of six ROIs when compared with SPM and in five ROIs compared with FS. The lower repeatability and reproducibility in DLHBS were not observed in any comparisons. CONCLUSION: Our results showed that the best performance in both repeatability and reproducibility was found in DLHBS compared with SPM and FS.

Comparison of Inter-Method Agreement and Reliability for Automatic Brain Volumetry Using Three Different Clinically Available Software Packages.

Background and Objectives: No comparative study has evaluated the inter-method agreement and reliability between Heuron AD and other clinically available brain volumetric software packages. Hence, we aimed to investigate the inter-method agreement and reliability of three clinically available brain volumetric software packages: FreeSurfer (FS), NeuroQuant® (NQ), and Heuron AD (HAD). Materials and Methods: In this study, we retrospectively included 78 patients who underwent conventional three-dimensional (3D) T1-weighed imaging (T1WI) to evaluate their memory impairment, including 21 with normal objective cognitive function, 24 with mild cognitive impairment, and 33 with Alzheimer's disease (AD). All 3D T1WI scans were analyzed using three different volumetric software packages. Repeated-measures analysis of variance, intraclass correlation coefficient, effect size measurements, and Bland-Altman analysis were used to evaluate the inter-method agreement and reliability. Results: The measured volumes demonstrated substantial to almost perfect agreement for most brain regions bilaterally, except for the bilateral globi pallidi. However, the volumes measured using the three software packages showed significant mean differences for most brain regions, with consistent systematic biases and wide limits of agreement in the Bland-Altman analyses. The pallidum showed the largest effect size in the comparisons between NQ and FS (5.20-6.93) and between NQ and HAD (2.01-6.17), while the cortical gray matter showed the largest effect size in the comparisons between FS and HAD (0.79-1.91). These differences and variations between the software packages were also observed in the subset analyses of 45 patients without AD and 33 patients with AD. Conclusions: Despite their favorable reliability, the software-based brain volume measurements showed significant differences and systematic biases in most regions. Thus, these volumetric measurements should be interpreted based on the type of volumetric software used, particularly for smaller structures. Moreover, users should consider the replaceability-related limitations when using these packages in real-world practice.

Longitudinal brain volumetrics in glioma survivors.

OBJECTIVE: Radiation therapy (RT) is used selectively for patients with low-grade glioma (LGG) given the concerns for potential cognitive effects in survivors, but prior cognitive outcome studies among LGG survivors have had inconsistent findings. Translational studies that characterize changes in brain anatomy and physiology after treatment of LGG may help to both contextualize cognitive findings and improve the overall understanding of radiation effects in normal brain tissue. This study aimed to investigate the hypothesis that patients with LGG who are treated with RT will experience greater brain volume loss than those who do not receive RT. METHODS: This retrospective longitudinal study included all patients with WHO grade 2 glioma who received posttreatment surveillance MRI at the University of Alabama at Birmingham. Volumetric analysis of contralateral cortical white matter (WM), cortical gray matter (GM), and hippocampus was performed on all posttreatment T1-weighted MRI sequences using the SynthSeg script. The effect of clinical and treatment variables on brain volumes was assessed using two-level hierarchical linear models. RESULTS: The final study cohort consisted of 105 patients with 1974 time points analyzed. The median length of imaging follow-up was 4.6 years (range 0.36-18.9 years), and the median number of time points analyzed per patient was 12 (range 2-40). Resection was performed in 79 (75.2%) patients, RT was administered to 61 (58.1%) patients, and chemotherapy was administered to 66 (62.9%) patients. Age at diagnosis (ß = -0.06, p < 0.001) and use of RT (ß = -1.12, p = 0.002) were associated with the slope of the contralateral cortical GM volume model (i.e., change in GM over time). Age at diagnosis (ß = -0.08, p < 0.001), midline involvement (ß = 1.31, p = 0.006), and use of RT (ß = -1.45, p = 0.001) were associated with slope of the contralateral cortical WM volume model. Age (ß = -0.0027, p = 0.001), tumor resection (ß = -0.069, p < 0.001), use of chemotherapy (ß = -0.0597, p = 0.003), and use of RT (ß = -0.0589, p < 0.001) were associated with the slope of the contralateral hippocampus volume model. CONCLUSIONS: This study demonstrated volume loss in contralateral brain structures among LGG survivors, and patients who received RT experienced greater volume loss than those who did not. The results of this study may help to provide context for cognitive outcome research in LGG survivors and inform the design of future strategies to preserve cognition.

Childhood adversity modulates structural brain changes in borderline personality but not in major depression disorder.

Adverse childhood experiences (ACEs) negatively affect the function and structure of emotion brain circuits, increasing the risk of various psychiatric disorders. It is unclear if ACEs show disorder specificity with respect to their effects on brain structure. We aimed to investigate whether the structural brain effects of ACEs differ between patients with major depression (MDD) and borderline personality disorder (BPD). These disorders share many symptoms but likely have different etiologies. To achieve our goal, we obtained structural 3T-MRI images from 20 healthy controls (HC), 19 MDD patients, and 18 BPD patients, and measured cortical thickness and subcortical gray matter volumes. We utilized the Adverse Childhood Experiences (ACE) questionnaire to quantify self-reported exposure to childhood trauma. Our findings suggest that individuals with MDD exhibit a smaller cortical thickness when compared to those with BPD. However, ACEs showed a significantly affected relationship with cortical thickness in BPD but not in MDD. ACEs were found to be associated with thinning in cortical regions involved in emotional behavior in BPD, whereas HC showed an opposite association. Our results suggest a potential mechanism of ACE effects on psychopathology involving changes in brain structure. These findings highlight the importance of early detection and intervention strategies.

Brain alterations in regions associated with end-organ diabetic microvascular disease in diabetes mellitus: A UK Biobank study.

BACKGROUND: Diabetes mellitus (DM) is associated with structural grey matter alterations in the brain, including changes in the somatosensory and pain processing regions seen in association with diabetic peripheral neuropathy. In this case-controlled biobank study, we aimed to ascertain differences in grey and white matter anatomy in people with DM compared with non-diabetic controls (NDC). METHODS: This study utilises the UK Biobank prospective, population-based, multicentre study of UK residents. Participants with diabetes and age/gender-matched controls without diabetes were selected in a three-to-one ratio. We excluded people with underlying neurological/neurodegenerative disease. Whole brain, cortical, and subcortical volumes (188 regions) were compared between participants with diabetes against NDC corrected for age, sex, and intracranial volume using univariate regression models, with adjustment for multiple comparisons. Diffusion tensor imaging analysis of fractional anisotropy (FA) was performed along the length of 50 white matter tracts. RESULTS: We included 2404 eligible participants who underwent brain magnetic resonance imaging (NDC, n = 1803 and DM, n = 601). Participants with DM had a mean (±standard deviation) diagnostic duration of 18 ± 11 years, with adequate glycaemic control (HbA1C 52 ± 13 mmol/mol), low prevalence of microvascular complications (diabetic retinopathy prevalence, 5.8%), comparable cognitive function to controls but greater self-reported pain. Univariate volumetric analyses revealed significant reductions in grey matter volume (whole brain, total, and subcortical grey matter), with mean percentage differences ranging from 2.2% to 7% in people with DM relative to NDC (all p < 0.0002). The subcortical (bilateral cerebellar cortex, brainstem, thalamus, central corpus callosum, putamen, and pallidum) and cortical regions linked to sensorimotor (bilateral superior frontal, middle frontal, precentral, and postcentral gyri) and visual functions (bilateral middle and superior occipital gyri), all had lower grey matter volumes in people with DM relative to NDC. People with DM had significantly reduced FA along the length of the thalamocortical radiations, thalamostriatal projections, and commissural fibres of the corpus callosum (all; p < 0·001). INTERPRETATION: This analysis suggests that anatomic differences in brain regions are present in a cohort with adequately controlled glycaemia without prevalent microvascular disease when compared with volunteers without diabetes. We hypothesise that these differences may predate overt end-organ damage and complications such as diabetic neuropathy and retinopathy. Central nervous system alterations/neuroplasticity may occur early in the natural history of microvascular complications; therefore, brain imaging should be considered in future mechanistic and interventional studies of DM.

Towards validation in clinical routine: a comparative analysis of visual MTA ratings versus the automated ratio between inferior lateral ventricle and hippocampal volumes in Alzheimer's disease diagnosis.

PURPOSE: To assess the performance of the inferior lateral ventricle (ILV) to hippocampal (Hip) volume ratio on brain MRI, for Alzheimer's disease (AD) diagnostics, comparing it to individual automated ILV and hippocampal volumes, and visual medial temporal lobe atrophy (MTA) consensus ratings. METHODS: One-hundred-twelve subjects (mean age ± SD, 66.85 ± 13.64 years) with varying degrees of cognitive decline underwent MRI using a Philips Ingenia 3T. The MTA scale by Scheltens, rated on coronal 3D T1-weighted images, was determined by three experienced radiologists, blinded to diagnosis and sex. Automated volumetry was computed by icobrain dm (v. 5.10) for total, left, right hippocampal, and ILV volumes. The ILV/Hip ratio, defined as the percentage ratio between ILV and hippocampal volumes, was calculated and compared against a normative reference population (n = 1903). Inter-rater agreement, association, classification accuracy, and clinical interpretability on patient level were reported. RESULTS: Visual MTA scores showed excellent inter-rater agreement. Ordinal logistic regression and correlation analyses demonstrated robust associations between automated brain segmentations and visual MTA ratings, with the ILV/Hip ratio consistently outperforming individual hippocampal and ILV volumes. Pairwise classification accuracy showed good performance without statistically significant differences between the ILV/Hip ratio and visual MTA across disease stages, indicating potential interchangeability. Comparison to the normative population and clinical interpretability assessments showed commensurability in classifying MTA "severity" between visual MTA and ILV/Hip ratio measurements. CONCLUSION: The ILV/Hip ratio shows the highest correlation to visual MTA, in comparison to automated individual ILV and hippocampal volumes, offering standardized measures for diagnostic support in different stages of cognitive decline.

The role of visual rating and automated brain volumetry in early detection and differential diagnosis of Alzheimer's disease.

BACKGROUND: Medial temporal lobe atrophy (MTA) is a diagnostic marker for mild cognitive impairment (MCI) and Alzheimer's disease (AD), but the accuracy of quantitative MTA (QMTA) in diagnosing early AD is unclear. This study aimed to investigate the accuracy of QMTA and its related components (inferior lateral ventricle [ILV] and hippocampus) with MTA in the early diagnosis of MCI and AD. METHODS: This study included four groups: normal (NC), MCI stable (MCIs), MCI converted to AD (MCIs), and mild AD (M-AD) groups. Magnetic resonance image analysis software was used to quantify the hippocampus, ILV, and QMTA. MTA was rated by two experienced neurologists. Receiver operating characteristic area under the curve (AUC) analysis was performed to compare their capability in differentiating AD from NC and MCI, and optimal thresholds were determined using the Youden index. RESULTS: QMTA distinguished M-AD from NC and MCI with higher diagnostic accuracy than MTA, hippocampus, and ILV (AUCNC = 0.976, AUCMCI = 0.836, AUCMCIs = 0.894, AUCMCIc = 0.730). The diagnostic accuracy of QMTA was superior to that of MTA, the hippocampus, and ILV in differentiating MCI from AD. The diagnostic accuracy of QMTA was found to remain the best across age, sex, and pathological subgroups analyzed. The sensitivity (92.45%) and specificity (90.64%) were higher in this study when a cutoff value of 0.635 was chosen for QMTA. CONCLUSIONS: QMTA may be a better choice than the MTA scale or the associated quantitative components alone in identifying AD patients and MCI individuals with higher progression risk.

A three-dimensional deep learning model for inter-site harmonization of structural MR images of the brain: Extensive validation with a multicenter dataset.

In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter dataset, unsupervised deep learning methods can be employed. Here, we developed a model based on cycle-consistent adversarial networks for the harmonization of T1-weighted brain MR images. In contrast to previous works, it was designed to process three-dimensional whole-brain images in a stable manner while optimizing computation resources. Using six different MRI datasets for healthy adults (n=1525 in total) with different acquisition parameters, we tested the model in (i) three pairwise harmonizations with site effects of various sizes, (ii) an overall harmonization of the six datasets with different age distributions, and (iii) a traveling-subject dataset. Our results for intensity distributions, brain volumes, image quality metrics and radiomic features indicated that the MRI characteristics at the various sites had been effectively homogenized. Next, brain age prediction experiments and the observed correlation between the gray-matter volume and age showed that thanks to an appropriate training strategy and despite biological differences between the dataset populations, the model reinforced biological patterns. Furthermore, radiologic analyses of the harmonized images attested to the conservation of the radiologic information in the original images. The robustness of the harmonization model (as judged with various datasets and metrics) demonstrates its potential for application in retrospective multicenter studies.

Artificial-intelligence-based MRI brain volumetry in patients with essential tremor and tremor-dominant Parkinson's disease.

Essential tremor and Parkinson's disease patients may present with various tremor types. Overlapping tremor features can be challenging to diagnosis and misdiagnosis is common. Although underlying neurodegenerative mechanisms are suggested, neuroimaging studies arrived at controversial results and often the different tremor types were not considered. We investigated whether different tremor types displayed distinct structural brain features. Structural MRI of 61 patients with essential tremor and 29 with tremor-dominant Parkinson's disease was analysed using a fully automated artificial-intelligence-based brain volumetry to compare volumes of several cortical and subcortical regions. Furthermore, essential tremor subgroups with and without rest tremor or more pronounced postural and kinetic tremor were investigated. Deviations from an internal reference collective of age- and sex-adjusted healthy controls and volumetric differences between groups were examined; regression analysis was used to determine the contribution of disease-related factors on volumetric measurements. Compared with healthy controls, essential tremor and tremor-dominant Parkinson's disease patients displayed deviations in the occipital lobes, hippocampus, putamen, pallidum and mesencephalon while essential tremor patients exhibited decreased volumes within the nucleus caudatus and thalamus. Analysis of covariance revealed similar volumetric patterns in both diseases. Essential tremor patients without rest tremor showed a significant atrophy within the thalamus compared to tremor-dominant Parkinson's disease and atrophy of the mesencephalon and putamen were found in both subgroups compared to essential tremor with rest tremor. Disease-related factors contribute to volumes of occipital lobes in both diseases and to volumes of temporal lobes in essential tremor and the putamen in Parkinson's disease. Fully automated artificial-intelligence-based volumetry provides a fast and rater-independent method to investigate brain volumes in different neurological disorders and allows comparisons with an internal reference collective. Our results indicate that essential tremor and tremor-dominant Parkinson's disease share structural changes, indicative of neurodegenerative mechanisms, particularly of the basal-ganglia-thalamocortical circuitry. A discriminating, possibly disease-specific involvement of the thalamus was found in essential tremor patients without rest tremor and the mesencephalon and putamen in tremor-dominant Parkinson's disease and essential tremor without rest tremor.

Reliability of brain atrophy measurements in multiple sclerosis using MRI: an assessment of six freely available software packages for cross-sectional analyses.

PURPOSE: Volume measurement using MRI is important to assess brain atrophy in multiple sclerosis (MS). However, differences between scanners, acquisition protocols, and analysis software introduce unwanted variability of volumes. To quantify theses effects, we compared within-scanner repeatability and between-scanner reproducibility of three different MR scanners for six brain segmentation methods. METHODS: Twenty-one people with MS underwent scanning and rescanning on three 3 T MR scanners (GE MR750, Philips Ingenuity, Toshiba Vantage Titan) to obtain 3D T1-weighted images. FreeSurfer, FSL, SAMSEG, FastSurfer, CAT-12, and SynthSeg were used to quantify brain, white matter and (deep) gray matter volumes both from lesion-filled and non-lesion-filled 3D T1-weighted images. We used intra-class correlation coefficient (ICC) to quantify agreement; repeated-measures ANOVA to analyze systematic differences; and variance component analysis to quantify the standard error of measurement (SEM) and smallest detectable change (SDC). RESULTS: For all six software, both between-scanner agreement (ICCs ranging 0.4-1) and within-scanner agreement (ICC range: 0.6-1) were typically good, and good to excellent (ICC > 0.7) for large structures. No clear differences were found between filled and non-filled images. However, gray and white matter volumes did differ systematically between scanners for all software (p < 0.05). Variance component analysis yielded within-scanner SDC ranging from 1.02% (SAMSEG, whole-brain) to 14.55% (FreeSurfer, CSF); and between-scanner SDC ranging from 4.83% (SynthSeg, thalamus) to 29.25% (CAT12, thalamus). CONCLUSION: Volume measurements of brain, GM and WM showed high repeatability, and high reproducibility despite substantial differences between scanners. Smallest detectable change was high, especially between different scanners, which hampers the clinical implementation of atrophy measurements.

Development and validation of deep learning-based automatic brain segmentation for East Asians: A comparison with Freesurfer.

Purpose: To develop and validate deep learning-based automatic brain segmentation for East Asians with comparison to data for healthy controls from Freesurfer based on a ground truth. Methods: A total of 30 healthy participants were enrolled and underwent T1-weighted magnetic resonance imaging (MRI) using a 3-tesla MRI system. Our Neuro I software was developed based on a three-dimensional convolutional neural networks (CNNs)-based, deep-learning algorithm, which was trained using data for 776 healthy Koreans with normal cognition. Dice coefficient (D) was calculated for each brain segment and compared with control data by paired t-test. The inter-method reliability was assessed by intraclass correlation coefficient (ICC) and effect size. Pearson correlation analysis was applied to assess the relationship between D values for each method and participant ages. Results: The D values obtained from Freesurfer (ver6.0) were significantly lower than those from Neuro I. The histogram of the Freesurfer results showed remarkable differences in the distribution of D values from Neuro I. Overall, D values obtained by Freesurfer and Neuro I showed positive correlations, but the slopes and intercepts were significantly different. It was showed the largest effect sizes ranged 1.07-3.22, and ICC also showed significantly poor to moderate correlations between the two methods (0.498 ≤ ICC ≤ 0.688). For Neuro I, D values resulted in reduced residuals when fitting data to a line of best fit, and indicated consistent values corresponding to each age, even in young and older adults. Conclusion: Freesurfer and Neuro I were not equivalent when compared to a ground truth, where Neuro I exhibited higher performance. We suggest that Neuro I is a useful alternative for the assessment of the brain volume.

Combining semi-quantitative rating and automated brain volumetry in MRI evaluation of patients with probable behavioural variant of fronto-temporal dementia: an added value for clinical practise?

PURPOSE: To evaluate the diagnostic value of combined semiquantitative and quantitative assessment of brain atrophy in the diagnostic workup of the behavioural-variant of frontotemporal dementia (bvFTD). METHODS: Three neuroradiologists defined brain atrophy grading and identified atrophy pattern suggestive of bvFTD on 3D-T1 brain MRI of 112 subjects using a semiquantitative rating scale (Kipps'). A quantitative atrophy assessment was performed using two different automated software (Quantib® ND and Icometrix®). A combined semiquantitative and quantitative assessment of brain atrophy was made to evaluate the improvement in brain atrophy grading to identify probable bvFTD patients. RESULTS: Observers' performances in the diagnosis of bvFTD were very good for Observer 1 (k value = 0.881) and 2 (k value = 0.867), substantial for Observer 3 (k value = 0.741). Semiquantitative atrophy grading of all the observers showed a moderate and a poor correlation with the volume values calculated by Icometrix® and by Quantib® ND, respectively. For the definition of neuroradiological signs presumptive of bvFTD, the use of Icometrix® software improved the diagnostic accuracy for Observer 1 resulting in an AUC of 0.974, and for Observer 3 resulting in a AUC of 0.971 (p-value < 0.001). The use of Quantib® ND software improved the diagnostic accuracy for Observer 1 resulting in an AUC of 0.974, and for Observer 3 resulting in a AUC of 0.977 (p-value < 0.001). No improvement was observed for Observer 2. CONCLUSION: Combining semiquantitative and quantitative brain imaging evaluation allows to reduce discrepancies in the neuroradiological diagnostic workup of bvFTD by different readers.

Structural MRI predicts clinical progression in presymptomatic genetic frontotemporal dementia: findings from the GENetic Frontotemporal dementia Initiative cohort.

Biomarkers that can predict disease progression in individuals with genetic frontotemporal dementia are urgently needed. We aimed to identify whether baseline MRI-based grey and white matter abnormalities are associated with different clinical progression profiles in presymptomatic mutation carriers in the GENetic Frontotemporal dementia Initiative. Three hundred eighty-seven mutation carriers were included (160 GRN, 160 C9orf72, 67 MAPT), together with 240 non-carrier cognitively normal controls. Cortical and subcortical grey matter volumes were generated using automated parcellation methods on volumetric 3T T1-weighted MRI scans, while white matter characteristics were estimated using diffusion tensor imaging. Mutation carriers were divided into two disease stages based on their global CDR®+NACC-FTLD score: presymptomatic (0 or 0.5) and fully symptomatic (1 or greater). The w-scores in each grey matter volumes and white matter diffusion measures were computed to quantify the degree of abnormality compared to controls for each presymptomatic carrier, adjusting for their age, sex, total intracranial volume, and scanner type. Presymptomatic carriers were classified as 'normal' or 'abnormal' based on whether their grey matter volume and white matter diffusion measure w-scores were above or below the cut point corresponding to the 10th percentile of the controls. We then compared the change in disease severity between baseline and one year later in both the 'normal' and 'abnormal' groups within each genetic subtype, as measured by the CDR®+NACC-FTLD sum-of-boxes score and revised Cambridge Behavioural Inventory total score. Overall, presymptomatic carriers with normal regional w-scores at baseline did not progress clinically as much as those with abnormal regional w-scores. Having abnormal grey or white matter measures at baseline was associated with a statistically significant increase in the CDR®+NACC-FTLD of up to 4 points in C9orf72 expansion carriers, and 5 points in the GRN group as well as a statistically significant increase in the revised Cambridge Behavioural Inventory of up to 11 points in MAPT, 10 points in GRN, and 8 points in C9orf72 mutation carriers. Baseline regional brain abnormalities on MRI in presymptomatic mutation carriers are associated with different profiles of clinical progression over time. These results may be helpful to inform stratification of participants in future trials.

The Unresolved Methodological Challenge of Detecting Neuroplastic Changes in Astronauts.

After completing a spaceflight, astronauts display a salient upward shift in the position of the brain within the skull, accompanied by a redistribution of cerebrospinal fluid. Magnetic resonance imaging studies have also reported local changes in brain volume following a spaceflight, which have been cautiously interpreted as a neuroplastic response to spaceflight. Here, we provide evidence that the grey matter volume changes seen in astronauts following spaceflight are contaminated by preprocessing errors exacerbated by the upwards shift of the brain within the skull. While it is expected that an astronaut's brain undergoes some neuroplastic adaptations during spaceflight, our findings suggest that the brain volume changes detected using standard processing pipelines for neuroimaging analyses could be contaminated by errors in identifying different tissue types (i.e., tissue segmentation). These errors may undermine the interpretation of such analyses as direct evidence of neuroplastic adaptation, and novel or alternate preprocessing or experimental paradigms are needed in order to resolve this important issue in space health research.

Minimizing the effect of white matter lesions on deep learning based tissue segmentation for brain volumetry.

Automated methods for segmentation-based brain volumetry may be confounded by the presence of white matter (WM) lesions, which introduce abnormal intensities that can alter the classification of not only neighboring but also distant brain tissue. These lesions are common in pathologies where brain volumetry is also an important prognostic marker, such as in multiple sclerosis (MS), and thus reducing their effects is critical for improving volumetric accuracy and reliability. In this work, we analyze the effect of WM lesions on deep learning based brain tissue segmentation methods for brain volumetry and introduce techniques to reduce the error these lesions produce on the measured volumes. We propose a 3D patch-based deep learning framework for brain tissue segmentation which is trained on the outputs of a reference classical method. To deal more robustly with pathological cases having WM lesions, we use a combination of small patches and a percentile-based input normalization. To minimize the effect of WM lesions, we also propose a multi-task double U-Net architecture performing end-to-end inpainting and segmentation, along with a training data generation procedure. In the evaluation, we first analyze the error introduced by artificial WM lesions on our framework as well as in the reference segmentation method without the use of lesion inpainting techniques. To the best of our knowledge, this is the first analysis of WM lesion effect on a deep learning based tissue segmentation approach for brain volumetry. The proposed framework shows a significantly smaller and more localized error introduced by WM lesions than the reference segmentation method, that displays much larger global differences. We also evaluated the proposed lesion effect minimization technique by comparing the measured volumes before and after introducing artificial WM lesions to healthy images. The proposed approach performing end-to-end inpainting and segmentation effectively reduces the error introduced by small and large WM lesions in the resulting volumetry, obtaining absolute volume differences of 0.01 ± 0.03% for GM and 0.02 ± 0.04% for WM. Increasing the accuracy and reliability of automated brain volumetry methods will reduce the sample size needed to establish meaningful correlations in clinical studies and allow its use in individualized assessments as a diagnostic and prognostic marker for neurodegenerative pathologies.

Long term effects of red wine consumption in brain: an MRI, fMRI and neuropsychological evaluation study.

Red wine (RW) consumption has been proposed to have a potential health benefit. However, the effect of RW consumption on the brain is not entirely known, mainly when associated with aging. Regular red wine consumers (n = 30) and abstainers (ABST; n = 27) without cognitive impairment were evaluated for brain structural characteristics (Fazekas score and voxel-based morphometry) and for functional adaptations assessed by fMRI (using the Word Tasks Color Stroop (WCST) and Two-Back (TBT)), as well as by neuropsychological tests in different domains. There were no significant differences regarding brain morphological features. RW consumers showed greater activation in the thalamus during WCST and in paracingulate/anterior cingulate cortices, left superior frontal gyrus and frontal pole during TBT. ABST required higher activation of different cortical areas in the left parietal lobe during WCST. Age and intelligence quotient influenced those activations. In Stroop and trail-making neuropsychological tests, RW consumers performed slightly better than ABST. This study should be viewed as hypothesis-generating rather than conclusive.HighlightsWhite matter hyperintensities and gray matter volume did not differ between the RW and ABST groups.RW consumers could depend more on right thalamus during WSCT due to its role in visual integration.ABST could depend more on left parietal lobe during WSCT due to its role in sensory and phonological encoding.RW consumers with inferior cognitive abilities could depend more on letter recognition to solve a TBT correctly.Younger abstainers could depend more on different areas involved in integrating cognitive processes and attention regulation to solve a TBT correctly.

Brain morphological variability between whites and African Americans: the importance of racial identity in brain imaging research.

In a segregated society, marked by a historical background of inequalities, there is a consistent under-representation of ethnic and racial minorities in biomedical research, causing disparities in understanding genetic and acquired diseases as well as in the effectiveness of clinical treatments affecting different groups. The repeated inclusion of small and non-representative samples of the population in neuroimaging research has led to generalization bias in the morphological characterization of the human brain. A few brain morphometric studies between Whites and African Americans have reported differences in orbitofrontal volumetry and insula cortical thickness. Nevertheless, these studies are mostly conducted in small samples and populations with cognitive impairment. For this reason, this study aimed to identify brain morphological variability due to racial identity in representative samples. We hypothesized that, in neurotypical young adults, there are differences in brain morphometry between participants with distinct racial identities. We analyzed the Human Connectome Project (HCP) database to test this hypothesis. Brain volumetry, cortical thickness, and cortical surface area measures of participants identified as Whites (n = 338) or African Americans (n = 56) were analyzed. Non-parametrical permutation analysis of covariance between these racial identity groups adjusting for age, sex, education, and economic income was implemented. Results indicated volumetric differences in choroid plexus, supratentorial, white matter, and subcortical brain structures. Moreover, differences in cortical thickness and surface area in frontal, parietal, temporal, and occipital brain regions were identified between groups. In this regard, the inclusion of sub-representative minorities in neuroimaging research, such as African American persons, is fundamental for the comprehension of human brain morphometric diversity and to design personalized clinical brain treatments for this population.

Neuroquantification enhances the radiological evaluation of term neonatal hypoxic-ischaemic cerebral injuries.

Background: Injury patterns in hypoxic-ischaemic brain injury (HIBI) are well recognised but there are few studies evaluating cerebral injury using neuroquantification models. Objectives: Quantification of brain volumes in a group of patients with clinically determined cerebral palsy. Method: In this retrospective study, 297 children with cerebral palsy were imaged for suspected HIBI with analysis of various cerebral substrates. Of these, 96 children over the age of 3 years with a clinical diagnosis of cerebral palsy and abnormal MRI findings underwent volumetric analyses using the NeuroQuant® software solution. The spectrum of volumetric changes and the differences between the various subtypes (and individual subgroups) of HIBI were compared. Results: Compared with the available normative NeuroQuant® database, the average intracranial volume was reduced to the 1st percentile in all patient groups (p < 0.001). Statistically significant differences were observed among the types and subgroups of HIBI. Further substrate volume reductions were identified and described involving the thalami, brainstem, hippocampi, putamina and amygdala. The combined volumes of five regions of interest (frontal pole, putamen, hippocampus, brainstem and paracentral lobule) were consistently reduced in the Rolandic basal ganglia-thalamus (RBGT) subtype. Conclusion: This study determined a quantifiable reduction of intracranial volume in all subtypes of HIBI and predictable selective cerebral substrate volume reduction in subtypes and subgroups. In the RBGT subtype, a key combination of five substrate injuries was consistently noted, and thalamic, occipital lobe and brainstem volume reduction was also significant when compared to the watershed subtype. Contribution: This study demonstrates the value of integrating an artificial intelligence programme into the radiologists' armamentarium serving to quantify brain injuries more accurately in HIBI. Going forward this will be an inevitable evolution of daily radiology practice in many fields of medicine, and it would be beneficial for radiologists to embrace these technological innovations.

The Effect of Hearing Loss on Cognitive Function in Subjective Cognitive Decline.

INTRODUCTION: Subjective cognitive decline (SCD) is a self-reported cognitive decline without objective cognitive impairment. The relationship between audiometric hearing loss (HL) and cognitive function has not been reported in SCD. The purpose of this study was to investigate whether HL affects cognition-related indexes in SCD individuals. METHODS: This is a cross-sectional study that used the baseline data of a multicenter cohort study that monitors clinical progression from SCD to dementia. Individuals aged ≥60 years who reported cognitive decline but had no objective cognitive impairment on comprehensive neuropsychological tests were recruited. Participants were grouped into the normal-hearing (NH) and bilateral HL groups. The demographics, clinical characteristics, dementia biomarkers, global cognition, questionnaire scores, neuropsychological test scores, and segmental brain volumes from MRI were compared between the groups. RESULTS: Of a total of 120 participants, one hundred and two had NH (n = 57) or bilateral HL (n = 45). There were no group differences in the demographic and clinical data except the age. The biomarkers, global cognition, and questionnaire scores were not different between the groups. The HL group performed worse (the z-score of -0.06) in the Stroop Color Word Test than the NH group (0.27) (p = 0.025). Brain volumetric analysis revealed that the HL group had reduced gray matter volumes in four brain subregions: left temporal pole, left caudal middle frontal gyrus, left hippocampus, and right isthmus of the cingulate gyrus. CONCLUSION: In SCD, HL exerted an adverse effect on cognitive function, primarily frontal executive function tested in the Stroop task. HL was also related to gray matter volume reductions in brain subregions, although causality needs further investigation. This study may provide evidence for a potential link between hearing and cognition in SCD, an emerging clinical entity.

Information-processing speed in mildly disabled relapsing-remitting multiple sclerosis patients correlates with volumetry of optic chiasma and subcortical grey matter nuclei.

INTRODUCTION: Multiple sclerosis (MS) is an inflammatory demyelinating disease leading not only to physical disability but also to cognitive dysfunction. The aim of our study was to test cognitive functions of MS patients with mild relapsing-remitting form and to find out the relationship between cognitive functions and brain volumetry. METHODS: 52 patients (RRMSp) and 23 age-related healthy participants (CON) were enrolled. Mild disability was defined by mean EDSS 2.4 (≤ 4.0), and by median of disease duration 5.2 years. Cognitive status was tested using Single Digit Modality Test (SDMT). Brain volumetry was processed in FreeSurfer 2.0.0. RESULTS: RRMSp patients showed significantly lower SDMT score than CON. SDMT results correlated positively with volume of thalamus, putamen and nc. caudate, and negatively with optic chiasma volume. Compared with CON, RRMSp presented with significantly lower volume in left and right nc. accumbent, cuneus and insular GM, right putamen, total brain cortical grey matter (GM), white matters hypointensities, and 3rd ventricular widths. CONCLUSION: To our best knowledge, this is the first study that presents results showing a correlation of lower SDMT with higher optic chiasma volume, due to its subclinical chronic demyelination. We confirmed that GM atrophy is involved in cognitive functions in MS (Tab. 3, Fig. 2, Ref. 73).