Automatic cerebellum anatomical parcellation using U-Net with locally constrained optimization

Sex-steroid hormones relate to cerebellar structure and functional connectivity across adulthood

Aging involves complex biological changes that affect disease susceptibility and aging trajectories. Although females typically live longer than males, they have a higher susceptibility to diseases like Alzheimer's, speculated to be influenced by menopause, and reduced ovarian hormone production. Understanding sex-specific differences is crucial for personalized medical interventions and gender equality in health. Our study aims to elucidate sex differences in regional cerebellar structure and connectivity during normal aging by investigating both structural and functional connectivity variations, with a focus on investigating these differences in the context of sex-steroid hormones. The study included 138 participants (mean age = 57(13.3) years, age range = 35-86 years, 54% women). The cohort was divided into three groups: 38 early middle-aged individuals (EMA) (mean age = 41(4.7) years), 48 late middle-aged individuals (LMA) (mean age = 58(4) years), and 42 older adults (OA) (mean age = 72(6.3) years). All participants underwent MRI scans, and saliva samples were collected for sex-steroid hormone quantification (17β-estradiol (E), progesterone (P), and testosterone (T)). We found less connectivity in females between Lobule I-IV and the cuneus, and greater connectivity in females between Crus I, Crus II, and the precuneus with increased age. Higher 17β-estradiol levels were linked to greater connectivity in Crus I and Crus II cerebellar subregions. Analyzing all participants together, testosterone was associated with both higher and lower connectivity in Lobule I-IV and Crus I, respectively, while higher progesterone levels were linked to lower connectivity in females. Structural differences were observed, with EMA males having larger volumes compared to LMA and OA groups, particularly in the right I-IV, right Crus I, right V, and right VI. EMA females showed higher volumes in the right lobules V and VI. These results highlight the significant role of sex hormones in modulating cerebellar connectivity and structure across adulthood, emphasizing the need to consider sex and hormonal status in neuroimaging studies to better understand age-related cognitive decline and neurological disorders.

Heritability of cerebellar subregion volumes in adolescent and young adult twins

Twin studies have found gross cerebellar volume to be highly heritable. However, whether fine-grained regional volumes within the cerebellum are similarly heritable is still being determined. Anatomical MRI scans from two independent datasets (QTIM: Queensland Twin IMaging, N = 798, mean age 22.1 years; QTAB: Queensland Twin Adolescent Brain, N = 396, mean age 11.3 years) were combined with an optimised and automated cerebellum parcellation algorithm to segment and measure 28 cerebellar regions. We show that the heritability of regional volumetric measures varies widely across the cerebellum (h 2 $$ {h}^2 $$ 47%-91%). Additionally, the good to excellent test-retest reliability for a subsample of QTIM participants suggests that non-genetic variance in cerebellar volumes is due primarily to unique environmental influences rather than measurement error. We also show a consistent pattern of strong associations between the volumes of homologous left and right hemisphere regions. Associations were predominantly driven by genetic effects shared between lobules, with only sparse contributions from environmental effects. These findings are consistent with similar studies of the cerebrum and provide a first approximation of the upper bound of heritability detectable by genome-wide association studies.

Convolutional Neural Network for Fully Automated Cerebellar Volumetry in Children in Comparison to Manual Segmentation and Developmental Trajectory of Cerebellar Volumes

The purpose of this study was to develop a fully automated and reliable volumetry of the cerebellum of children during infancy and childhood using deep learning algorithms in comparison to manual segmentation. In addition, the clinical usefulness of measuring the cerebellar volume is shown. One hundred patients (0 to 16.3 years old) without infratentorial signal abnormalities on conventional MRI were retrospectively selected from our pool of pediatric MRI examinations. Based on a routinely acquired 3D T1-weighted magnetization prepared rapid gradient echo (MPRAGE) sequence, the cerebella were manually segmented using ITK-SNAP. The data set of all 100 cases was divided into four splits (four-fold cross-validation) to train the network (NN) to delineate the boundaries of the cerebellum. First, the accuracy of the newly created neural network was compared with the manual segmentation. Secondly, age-related volume changes were investigated. Our trained NN achieved an excellent Spearman correlation coefficient of 0.99, a Dice Coefficient of 95.0 ± 2.1%, and an intersection over union (IoU) of 90.6 ± 3.8%. Cerebellar volume increased continuously with age, showing an exponentially rapid growth within the first year of life. Using a convolutional neural network, it was possible to achieve reliable, fully automated cerebellar volume measurements in childhood and infancy, even when based on a relatively small cohort. In this preliminary study, age-dependent cerebellar volume changes could be acquired.

Evaluating functional connectivity differences between DBS ON/OFF states in essential tremor

Deep brain stimulation (DBS) targeting the ventral intermediate (Vim) nucleus of the thalamus is an effective treatment for essential tremor (ET). We studied 15 ​ET patients undergoing DBS to a major input/output tract of the Vim, the dentato-rubro-thalamic tract (DRTt), using resting state functional MRI (rsfMRI) to evaluate connectivity differences between DBS ON and OFF and elucidate significant regions most influential in impacting tremor control and/or concomitant gait ataxia. Anatomical/functional 1.5T MRIs were acquired and replicated for each DBS state. Tremor severity and gait ataxia severity were scored with DBS ON at optimal stimulation parameters and immediately upon DBS OFF. Whole brain analysis was performed using dual regression analysis followed by randomized permutation testing for multiple correction comparison. Regions of interest (ROI) analysis was also performed. All 15 patients had tremor improvement between DBS ON/OFF (p ​< ​0.001). Whole brain analysis revealed significant connectivity changes between states in the left pre-central gyrus and left supplemental motor area. Group analysis of ROIs revealed that, with threshold p ​< ​0.05, in DBS ON vs. OFF both tremor duration and tremor improvement were significantly correlated to changes in connectivity. A sub-group analysis of patients with greater ataxia had significantly decreased functional connectivity between multiple ROIs in the cortex and cerebellum when DBS was ON compared to OFF. Stimulation of the DRTt and concordant improvement of tremor resulted in connectivity changes seen in multiple regions outside the motor network; when combined with both structural and electrophysiologic connectivity, this may help to serve as a biomarker to improve DBS targeting and possibly predict outcome.

Volumetric and diffusion MRI abnormalities associated with dysarthria in multiple sclerosis

Up to half of all people with multiple sclerosis experience communication difficulties due to dysarthria, a disorder that impacts the motor aspects of speech production. Dysarthria in multiple sclerosis is linked to cerebellar dysfunction, disease severity and lesion load, but the neuroanatomical substrates of these symptoms remain unclear. In this study, 52 participants with multiple sclerosis and 14 age- and sex-matched healthy controls underwent structural and diffusion MRI, clinical assessment of disease severity and cerebellar dysfunction and a battery of motor speech tasks. Assessments of regional brain volume and white matter integrity, and their relationships with clinical and speech measures, were undertaken. White matter tracts of interest included the interhemispheric sensorimotor tract, cerebello-thalamo-cortical tract and arcuate fasciculus, based on their roles in motor and speech behaviours. Volumetric analyses were targeted to Broca's area, Wernicke's area, the corpus callosum, thalamus and cerebellum. Our results indicated that multiple sclerosis participants scored worse on all motor speech tasks. Fixel-based diffusion MRI analyses showed significant evidence of white matter tract atrophy in each tract of interest. Correlational analyses further indicated that higher speech naturalness-a perceptual measure of dysarthria-and lower reading rate were associated with axonal damage in the interhemispheric sensorimotor tract and left arcuate fasciculus in people with multiple sclerosis. Axonal damage in all tracts of interest also correlated with clinical scales sensitive to cerebellar dysfunction. Participants with multiple sclerosis had lower volumes of the thalamus and corpus callosum compared with controls, although no brain volumetrics correlated with measures of dysarthria. These findings indicate that axonal damage, particularly when measured using diffusion metrics, underpin dysarthria in multiple sclerosis.

Structural deviations of the posterior fossa and the cerebellum and their cognitive links in a neurodevelopmental deletion syndrome

High-impact genetic variants associated with neurodevelopmental disorders provide biologically-defined entry points for mechanistic investigation. The 3q29 deletion (3q29Del) is one such variant, conferring a 40-100-fold increased risk for schizophrenia, as well as high risk for autism and intellectual disability. However, the mechanisms leading to neurodevelopmental disability remain largely unknown. Here, we report the first in vivo quantitative neuroimaging study in individuals with 3q29Del (N = 24) and neurotypical controls (N = 1608) using structural MRI. Given prior radiology reports of posterior fossa abnormalities in 3q29Del, we focused our investigation on the cerebellum and its tissue-types and lobules. Additionally, we compared the prevalence of cystic/cyst-like malformations of the posterior fossa between 3q29Del and controls and examined the association between neuroanatomical findings and quantitative traits to probe gene-brain-behavior relationships. 3q29Del participants had smaller cerebellar cortex volumes than controls, before and after correction for intracranial volume (ICV). An anterior-posterior gradient emerged in finer grained lobule-based and voxel-wise analyses. 3q29Del participants also had larger cerebellar white matter volumes than controls following ICV-correction and displayed elevated rates of posterior fossa arachnoid cysts and mega cisterna magna findings independent of cerebellar volume. Cerebellar white matter and subregional gray matter volumes were associated with visual-perception and visual-motor integration skills as well as IQ, while cystic/cyst-like malformations yielded no behavioral link. In summary, we find that abnormal development of cerebellar structures may represent neuroimaging-based biomarkers of cognitive and sensorimotor function in 3q29Del, adding to the growing evidence identifying cerebellar pathology as an intersection point between syndromic and idiopathic forms of neurodevelopmental disabilities.

Sex Differences and Behavioral Associations with Typically Developing Pediatric Regional Cerebellar Gray Matter Volume

The cerebellum contributes to motor and higher-order control throughout neurodevelopment, with marked growth during childhood. Few studies have investigated differential associations of cerebellar morphometry with function in males and females. The present study examines sex differences in regional cerebellar gray matter volume (GMV) and the moderating effect of sex on the relationship between GMV and motor, cognitive, and emotional functions in a large cohort of typically developing (TD) children. Participants included 371 TD children (123 females, age 8-12 years). A convolutional neural network-based approach was employed for cerebellar parcellation. Volumes were harmonized using ComBat to adjust for hardware-induced variations. Regression analyses examined the effect of sex on GMV and whether sex moderated the relationship between GMV and motor, cognitive, and emotional functions. Males showed larger GMV in right lobules I-V, bilateral lobules VI, crus II/VIIb, and VIII, left lobule X, and vermis regions I-V and VIII-X. Greater motor function correlated with less vermis VI-VII GMV in females. Greater cognitive function correlated with greater left lobule VI GMV in females and less left lobule VI GMV in males. Finally, greater internalizing symptoms correlated with greater bilateral lobule IX GMV in females but less in males. These findings reveal sexually dimorphic patterns of cerebellar structure and associations with motor, cognitive, and emotional functions. Males generally show larger GMV than females. Larger GMV was associated with better cognitive functioning for females and better motor/emotional functioning for males.

Altered cerebellar volumes and intrinsic cerebellar networks in patients with transient global amnesia

This study aimed to investigate the differences in cerebellar volumes and intrinsic cerebellar networks between patients with transient global amnesia (TGA) and healthy controls. We retrospectively enrolled patients with TGA and age- and sex-matched healthy controls. We used three-dimensional T1-weighted imaging at the time of TGA diagnosis to obtain cerebellar volumes, and the intrinsic cerebellar network was calculated by applying graph theory based on cerebellar volumes. The nodes were defined as individual cerebellar volumes, and edges as partial correlations, controlling for the effects of age and sex. The cerebellar volumes and intrinsic cerebellar networks were compared between the two groups. We enrolled 44 patients with TGA and 47 healthy controls. The volume of the left cerebellar white matter in patients with TGA was significantly lower than that in healthy controls (1.0328 vs. 1.0753%, p = 0.0094). In addition, there were significant differences in intrinsic cerebellar networks between the two groups. The small-worldness index in patients with TGA was higher than that in the healthy controls (0.951 vs. 0.880, p = 0.038). In the correlation analysis, the volumes of the right cerebellar cortex and lobules VIIIB were significantly correlated with age in patients with TGA (r = -0.323, p = 0.033; r = -0.313, p = 0.038, respectively). Patients with TGA exhibit alterations in cerebellar volumes and intrinsic cerebellar networks compared with healthy controls. These findings may contribute to a better understanding of the pathophysiology of the TGA.

Patterns of subregional cerebellar atrophy across epilepsy syndromes: An ENIGMA-Epilepsy study

OBJECTIVE

The intricate neuroanatomical structure of the cerebellum is of longstanding interest in epilepsy, but has been poorly characterized within the current corticocentric models of this disease. We quantified cross-sectional regional cerebellar lobule volumes using structural magnetic resonance imaging in 1602 adults with epilepsy and 1022 healthy controls across 22 sites from the global ENIGMA-Epilepsy working group.

METHODS

A state-of-the-art deep learning-based approach was employed that parcellates the cerebellum into 28 neuroanatomical subregions. Linear mixed models compared total and regional cerebellar volume in (1) all epilepsies, (2) temporal lobe epilepsy with hippocampal sclerosis (TLE-HS), (3) nonlesional temporal lobe epilepsy, (4) genetic generalized epilepsy, and (5) extratemporal focal epilepsy (ETLE). Relationships were examined for cerebellar volume versus age at seizure onset, duration of epilepsy, phenytoin treatment, and cerebral cortical thickness.

RESULTS

Across all epilepsies, reduced total cerebellar volume was observed (d = .42). Maximum volume loss was observed in the corpus medullare (dmax = .49) and posterior lobe gray matter regions, including bilateral lobules VIIB (dmax = .47), crus I/II (dmax = .39), VIIIA (dmax = .45), and VIIIB (dmax = .40). Earlier age at seizure onset (η ρ max 2  = .05) and longer epilepsy duration (η ρ max 2  = .06) correlated with reduced volume in these regions. Findings were most pronounced in TLE-HS and ETLE, with distinct neuroanatomical profiles observed in the posterior lobe. Phenytoin treatment was associated with reduced posterior lobe volume. Cerebellum volume correlated with cerebral cortical thinning more strongly in the epilepsy cohort than in controls.

SIGNIFICANCE

We provide robust evidence of deep cerebellar and posterior lobe subregional gray matter volume loss in patients with chronic epilepsy. Volume loss was maximal for posterior subregions implicated in nonmotor functions, relative to motor regions of both the anterior and posterior lobe. Associations between cerebral and cerebellar changes, and variability of neuroanatomical profiles across epilepsy syndromes argue for more precise incorporation of cerebellar subregional damage into neurobiological models of epilepsy.

Population-wide cerebellar growth models of children and adolescents

In the past, the cerebellum has been best known for its crucial role in motor function. However, increasingly more findings highlight the importance of cerebellar contributions in cognitive functions and neurodevelopment. Using a total of 7240 neuroimaging scans from 4862 individuals, we describe and provide detailed, openly available models of cerebellar development in childhood and adolescence (age range: 6-17 years), an important time period for brain development and onset of neuropsychiatric disorders. Next to a traditionally used anatomical parcellation of the cerebellum, we generated growth models based on a recently proposed functional parcellation. In both, we find an anterior-posterior growth gradient mirroring the age-related improvements of underlying behavior and function, which is analogous to cerebral maturation patterns and offers evidence for directly related cerebello-cortical developmental trajectories. Finally, we illustrate how the current approach can be used to detect cerebellar abnormalities in clinical samples.

Cerebellar volumes and the intrinsic cerebellar network in patients with obstructive sleep apnea

PURPOSE

This research aimed to explore changes in both cerebellar volume and the intrinsic cerebellar network in patients with obstructive sleep apnea (OSA).

METHODS

Newly diagnosed OSA patients and healthy controls were included in the study. All participants underwent three-dimensional T1-weighted imaging using a 3-T MRI scanner. Cerebellar volumes, both overall and subdivided, were quantified using the ACAPULCO program. The intrinsic cerebellar network was assessed using the BRAPH program, which applied graph theory to the cerebellar volume subdivision. Comparisons were drawn between the patients with OSA and healthy controls.

RESULTS

The study revealed that the 26 patients with OSA exhibited a notably lower total cerebellar volume compared to the 28 healthy controls (8.330 vs. 9.068%, p < 0.001). The volume of the left lobule VIIB was reduced in patients with OSA compared to healthy controls (0.339 vs. 0.407%, p = 0.001). Among patients with OSA, there was a negative correlation between the volume of the left lobule X and apnea-hypopnea index during non-rapid eye movement sleep (r =  - 0.536, p = 0.005). However, no significant differences were observed in the intrinsic cerebellar network between patients and healthy controls.

CONCLUSION

This study established that patients with OSA exhibited decreased total cerebellar volumes and particularly reduced volumes in subdivisions such as the left lobule VIIB compared to healthy controls. These findings suggest potential involvement of the cerebellum in the underlying mechanisms of OSA.

Smaller total and subregional cerebellar volumes in posttraumatic stress disorder: a mega-analysis by the ENIGMA-PGC PTSD workgroup

Although the cerebellum contributes to higher-order cognitive and emotional functions relevant to posttraumatic stress disorder (PTSD), prior research on cerebellar volume in PTSD is scant, particularly when considering subregions that differentially map on to motor, cognitive, and affective functions. In a sample of 4215 adults (PTSD n = 1642; Control n = 2573) across 40 sites from the ENIGMA-PGC PTSD working group, we employed a new state-of-the-art deep-learning based approach for automatic cerebellar parcellation to obtain volumetric estimates for the total cerebellum and 28 subregions. Linear mixed effects models controlling for age, gender, intracranial volume, and site were used to compare cerebellum volumes in PTSD compared to healthy controls (88% trauma-exposed). PTSD was associated with significant grey and white matter reductions of the cerebellum. Compared to controls, people with PTSD demonstrated smaller total cerebellum volume, as well as reduced volume in subregions primarily within the posterior lobe (lobule VIIB, crus II), vermis (VI, VIII), flocculonodular lobe (lobule X), and corpus medullare (all p-FDR < 0.05). Effects of PTSD on volume were consistent, and generally more robust, when examining symptom severity rather than diagnostic status. These findings implicate regionally specific cerebellar volumetric differences in the pathophysiology of PTSD. The cerebellum appears to play an important role in higher-order cognitive and emotional processes, far beyond its historical association with vestibulomotor function. Further examination of the cerebellum in trauma-related psychopathology will help to clarify how cerebellar structure and function may disrupt cognitive and affective processes at the center of translational models for PTSD.

Examination of Cerebellar Grey-Matter Volume in Children with Neurodevelopmental Disorders: a Coordinated Analysis Using the ACAPULCO Algorithm

Alterations in cerebellar morphology relative to controls have been identified in children with autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), and developmental coordination disorder (DCD). However, it is not clear if common cerebellar regions are affected in each neurodevelopmental disorder and whether cerebellar morphological changes reflect a generic developmental vulnerability, or disorder-specific characteristic. The present study concatenated anatomical MRI scans from five existing cohorts, resulting in data from 252 children between the age of 7 and 12 years (ASD = 58, ADHD = 86, DCD = 22, Controls = 86). The ACAPULCO processing pipeline for cerebellar segmentation was conducted on T1-weighted images. A voxel-wise approach with general linear model was used to compare grey-matter volume of the 27 cerebellar lobules between each clinical group and controls. Our findings revealed that the ADHD group showed lower grey-matter volume in the left Crus I - part of the executive/non-motor portion of the cerebellum, relative to controls (p = 0.02). This no longer remained significant after controlling for medication status. There were no regions of significant differences in volume of the cerebellar lobules in ASD or DCD compared to controls. Future work will conduct harmonisation of behavioural data (cognitive and motor outcomes) across cohorts, enabling more advanced analyses to identify symptom cluster across neurodevelopmental disorders.

Redefining the role of the cerebellum in restless legs syndrome

OBJECTIVES

We aimed to investigate alterations in cerebellar volume and the intrinsic cerebellar network in patients with restless legs syndrome (RLS).

METHODS

We recruited 69 patients with RLS and 50 healthy controls who underwent brain magnetic resonance imaging (MRI), including three-dimensional T1-weighted imaging. The total cerebellar volume and cerebellar volume subdivisions were analyzed through automatic cerebellum anatomical parcellation using U-Net with locally constrained optimization program. The intrinsic cerebellar network was calculated through brain analysis using a graph theory program based on the cerebellar volume subdivisions. The cerebellar volumes and intrinsic cerebellar networks were compared between patients with RLS and healthy controls.

RESULTS

The cerebellar volume and subdivisions in patients with RLS did not show significant differences compared to those in healthy controls. However, significant alterations were observed in the intrinsic cerebellar network of patients with RLS. Increased mean clustering coefficient (0.185 vs. 0.114; p = 0.047) and small-worldness index (0.927 vs. 0.800; p = 0.047) were observed in patients with RLS. Additionally, total cerebellar volume was negatively correlated with the Pittsburgh Sleep Quality Index (r = -0.398; p = 0.020) and Insomnia Severity Index (ISI; r = -0.396; p = 0.011). Negative correlations were additionally observed between the right X lobule volume and the International Restless Legs Syndrome Severity Scale (r = -0.425; p = 0.008) and between the vermis VIII volume and ISI score (r = -0.399; p = 0.011).

CONCLUSION

We demonstrated alterations in the intrinsic cerebellar network in patients with RLS compared with healthy controls, showing increased connectivity with increased segregation in patients with RLS. This suggests a potential role of the cerebellum in RLS pathophysiology.

Cerebellar Volume and Disease Staging in Parkinson's Disease: An ENIGMA-PD Study

BACKGROUND

Increasing evidence points to a pathophysiological role for the cerebellum in Parkinson's disease (PD). However, regional cerebellar changes associated with motor and non-motor functioning remain to be elucidated.

OBJECTIVE

To quantify cross-sectional regional cerebellar lobule volumes using three dimensional T1-weighted anatomical brain magnetic resonance imaging from the global ENIGMA-PD working group.

METHODS

Cerebellar parcellation was performed using a deep learning-based approach from 2487 people with PD and 1212 age and sex-matched controls across 22 sites. Linear mixed effects models compared total and regional cerebellar volume in people with PD at each Hoehn and Yahr (HY) disease stage, to an age- and sex- matched control group. Associations with motor symptom severity and Montreal Cognitive Assessment scores were investigated.

RESULTS

Overall, people with PD had a regionally smaller posterior lobe (dmax  = -0.15). HY stage-specific analyses revealed a larger anterior lobule V bilaterally (dmax  = 0.28) in people with PD in HY stage 1 compared to controls. In contrast, smaller bilateral lobule VII volume in the posterior lobe was observed in HY stages 3, 4, and 5 (dmax  = -0.76), which was incrementally lower with higher disease stage. Within PD, cognitively impaired individuals had lower total cerebellar volume compared to cognitively normal individuals (d = -0.17).

CONCLUSIONS

We provide evidence of a dissociation between anterior "motor" lobe and posterior "non-motor" lobe cerebellar regions in PD. Whereas less severe stages of the disease are associated with larger motor lobe regions, more severe stages of the disease are marked by smaller non-motor regions. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Multimodal Analysis of Secondary Cerebellar Alterations After Pediatric Traumatic Brain Injury

Importance

Traumatic brain injury (TBI) is known to cause widespread neural disruption in the cerebrum. However, less is known about the association of TBI with cerebellar structure and how such changes may alter executive functioning.

Objective

To investigate alterations in subregional cerebellum volume and cerebral white matter microstructure after pediatric TBI and examine subsequent changes in executive function.

Design, Setting, and Participants

This retrospective cohort study combined 12 data sets (collected between 2006 and 2020) from 9 sites in the Enhancing Neuroimaging Genetics Through Meta-Analysis Consortium Pediatric TBI working group in a mega-analysis of cerebellar structure. Participants with TBI or healthy controls (some with orthopedic injury) were recruited from trauma centers, clinics, and institutional trauma registries, some of which were followed longitudinally over a period of 0.7 to 1.9 years. Healthy controls were recruited from the surrounding community. Data analysis occurred from October to December 2022.

Exposure

Accidental mild complicated-severe TBI (msTBI) for those in the TBI group. Some controls received a diagnosis of orthopedic injury.

Main Outcomes and Measures

Volume of 18 cerebellar lobules and vermal regions were estimated from 3-dimensional T1-weighted magnetic resonance imaging (MRI) scans. White matter organization in 28 regions of interest was assessed with diffusion tensor MRI. Executive function was measured by parent-reported scores from the Behavior Rating Inventory of Executive Functioning.

Results

A total of 598 children and adolescents (mean [SD] age, 14.05 [3.06] years; range, 5.45-19.70 years; 386 male participants [64.5%]; 212 female participants [35.5%]) were included in the study, with 314 participants in the msTBI group, and 284 participants in the non-TBI group (133 healthy individuals and 151 orthopedically injured individuals). Significantly smaller total cerebellum volume (d = -0.37; 95% CI, -0.52 to -0.22; P < .001) and subregional cerebellum volumes (eg, corpus medullare; d = -0.43; 95% CI, -0.58 to -0.28; P < .001) were observed in the msTBI group. These alterations were primarily seen in participants in the chronic phase (ie, >6 months postinjury) of injury (total cerebellar volume, d = -0.55; 95% CI, -0.75 to -0.35; P < .001). Smaller cerebellum volumes were associated with higher scores on the Behavior Rating Inventory of Executive Functioning Global Executive Composite score (β = -208.9 mm3; 95% CI, -319.0 to -98.0 mm3; P = .008) and Metacognition Index score (β = -202.5 mm3; 95% CI, -319.0 to -85.0 mm3; P = .02). In a subset of 185 participants with longitudinal data, younger msTBI participants exhibited cerebellum volume reductions (β = 0.0052 mm3; 95% CI, 0.0013 to 0.0090 mm3; P = .01), and older participants slower growth rates. Poorer white matter organization in the first months postinjury was associated with decreases in cerebellum volume over time (β=0.52 mm3; 95% CI, 0.19 to 0.84 mm3; P = .005).

Conclusions and Relevance

In this cohort study of pediatric msTBI, our results demonstrated robust cerebellar volume alterations associated with pediatric TBI, localized to the posterior lobe. Furthermore, longitudinal cerebellum changes were associated with baseline diffusion tensor MRI metrics, suggesting secondary cerebellar atrophy. These results provide further understanding of secondary injury mechanisms and may point to new opportunities for intervention.

Patterns of subregional cerebellar atrophy across epilepsy syndromes: An ENIGMA-Epilepsy study

Objective

The intricate neuroanatomical structure of the cerebellum is of longstanding interest in epilepsy, but has been poorly characterized within the current cortico-centric models of this disease. We quantified cross-sectional regional cerebellar lobule volumes using structural MRI in 1,602 adults with epilepsy and 1,022 healthy controls across twenty-two sites from the global ENIGMA-Epilepsy working group.

Methods

A state-of-the-art deep learning-based approach was employed that parcellates the cerebellum into 28 neuroanatomical subregions. Linear mixed models compared total and regional cerebellar volume in i) all epilepsies; ii) temporal lobe epilepsy with hippocampal sclerosis (TLE-HS); iii) non-lesional temporal lobe epilepsy (TLE-NL); iv) genetic generalised epilepsy; and (v) extra-temporal focal epilepsy (ETLE). Relationships were examined for cerebellar volume versus age at seizure onset, duration of epilepsy, phenytoin treatment, and cerebral cortical thickness.

Results

Across all epilepsies, reduced total cerebellar volume was observed (d=0.42). Maximum volume loss was observed in the corpus medullare (dmax=0.49) and posterior lobe grey matter regions, including bilateral lobules VIIB (dmax= 0.47), Crus I/II (dmax= 0.39), VIIIA (dmax=0.45) and VIIIB (dmax=0.40). Earlier age at seizure onset (ηρ2max=0.05) and longer epilepsy duration (ηρ2max=0.06) correlated with reduced volume in these regions. Findings were most pronounced in TLE-HS and ETLE with distinct neuroanatomical profiles observed in the posterior lobe. Phenytoin treatment was associated with reduced posterior lobe volume. Cerebellum volume correlated with cerebral cortical thinning more strongly in the epilepsy cohort than in controls.

Significance

We provide robust evidence of deep cerebellar and posterior lobe subregional grey matter volume loss in patients with chronic epilepsy. Volume loss was maximal for posterior subregions implicated in non-motor functions, relative to motor regions of both the anterior and posterior lobe. Associations between cerebral and cerebellar changes, and variability of neuroanatomical profiles across epilepsy syndromes argue for more precise incorporation of cerebellum subregions into neurobiological models of epilepsy.

The longitudinal progression of MRI changes in pre-ataxic carriers of SCA3/MJD

BACKGROUND

The natural history of magnetic resonance imaging (MRI) in pre-ataxic stages of spinocerebellar ataxia type 3/Machado-Joseph disease (SCA3/MJD) is not well known. We report cross-sectional and longitudinal data obtained at this stage.

METHODS

Baseline (follow-up) observations included 32 (17) pre-ataxic carriers (SARA < 3) and 20 (12) related controls. The mutation length was used to estimate the time to onset (TimeTo) of gait ataxia. Clinical scales and MRIs were performed at baseline and after a median (IQR) of 30 (7) months. Cerebellar volumetries (ACAPULCO), deep gray-matter (T1-Multiatlas), cortical thickness (FreeSurfer), cervical spinal cord area (SCT) and white matter (DTI-Multiatlas) were assessed. Baseline differences between groups were described; variables that presented a p < 0.1 after Bonferroni correction were assessed longitudinally, using TimeTo and study time. For TimeTo strategy, corrections for age, sex and intracranial volume were done with Z-score progression. A significance level of 5% was adopted.

RESULTS

SCT at C1 level distinguished pre-ataxic carriers from controls. DTI measures of the right inferior cerebellar peduncle (ICP), bilateral middle cerebellar peduncles (MCP) and bilateral medial lemniscus (ML), also distinguished pre-ataxic carriers from controls, and progressed over TimeTo, with effect sizes varying from 0.11 to 0.20, larger than those of the clinical scales. No MRI variable showed progression over study time.

DISCUSSION

DTI parameters of the right ICP, left MCP and right ML were the best biomarkers for the pre-ataxic stage of SCA3/MJD. TimeTo is an interesting timescale, since it captured the longitudinal worsening of these structures.

Cerebellar Volume Reduction in Patients with Isolated REM Sleep Behavior Disorder: Evidence of a Potential Role of the Cerebellum

INTRODUCTION

In this study, we aimed to investigate changes in the total cerebellar volume, subdivisions of the cerebellar volume, and intrinsic cerebellar network in patients with isolated rapid eye movement (REM) sleep behavior disorder (iRBD) compared to healthy controls.

METHODS

We enrolled patients with newly diagnosed iRBD and healthy controls who had no structural lesions according to their brain MRI. All participants underwent three-dimensional T1-weighted imaging. We obtained the total cerebellar volume and subdivisions of the cerebellar volume using the ACAPULCO program and calculated the intrinsic cerebellar network using a BRAPH program based on the subdivisions of the cerebellar volume by applying a graph theory. We compared the cerebellar volumes and intrinsic cerebellar network between the patients with iRBD and healthy controls.

RESULTS

In total, we enrolled 43 patients with iRBD and 47 healthy controls. Total cerebellar volume in patients with iRBD was lower than that in the healthy controls (8.4637 vs. 9.0863%, p = 0.0001). There were significant differences in the subdivisions of cerebellar volume between the groups. The volumes of the right and left lobule VIIB in the patients with iRBD were lower than those in the healthy controls (right, 0.3495 vs. 0.4025%, p = 0.0009; left, 0.3561 vs. 0.4293%, p < 0.0001). However, the other cerebellar volumes, such as the corpus meullare and vermis, were not different between the groups. The intrinsic cerebellar network was not different between the patients with iRBD and healthy controls.

CONCLUSION

We found decreased total cerebellar volumes and subdivisions of the cerebellar volume, particularly in the right and left lobule VIIB, in patients with iRBD compared to healthy controls. The present results suggest that the cerebellum may play a potential role in the pathogenesis of iRBD.

Genetic patterning for child psychopathology is distinct from that for adults and implicates fetal cerebellar development

Childhood psychiatric symptoms are often diffuse but can coalesce into discrete mental illnesses during late adolescence. We leveraged polygenic scores (PGSs) to parse genomic risk for childhood symptoms and to uncover related neurodevelopmental mechanisms with transcriptomic and neuroimaging data. In independent samples (Adolescent Brain Cognitive Development, Generation R) a narrow cross-disorder neurodevelopmental PGS, reflecting risk for attention deficit hyperactivity disorder, autism, depression and Tourette syndrome, predicted psychiatric symptoms through early adolescence with greater sensitivity than broad cross-disorder PGSs reflecting shared risk across eight psychiatric disorders, the disorder-specific PGS individually or two other narrow cross-disorder (Compulsive, Mood-Psychotic) scores. Neurodevelopmental PGS-associated genes were preferentially expressed in the cerebellum, where their expression peaked prenatally. Further, lower gray matter volumes in cerebellum and functionally coupled cortical regions associated with psychiatric symptoms in mid-childhood. These findings demonstrate that the genetic underpinnings of pediatric psychiatric symptoms differ from those of adult illness, and implicate fetal cerebellar developmental processes that endure through childhood.

AUTOMATED VENTRICLE PARCELLATION AND EVAN'S RATIO COMPUTATION IN PRE- AND POST-SURGICAL VENTRICULOMEGALY

Normal pressure hydrocephalus (NPH) is a brain disorder associated with enlarged ventricles and multiple cognitive and motor symptoms. The degree of ventricular enlargement can be measured using magnetic resonance images (MRIs) and characterized quantitatively using the Evan's ratio (ER). Automatic computation of ER is desired to avoid the extra time and variations associated with manual measurements on MRI. Because shunt surgery is often used to treat NPH, it is necessary that this process be robust to image artifacts caused by the shunt and related implants. In this paper, we propose a 3D regions-of-interest aware (ROI-aware) network for segmenting the ventricles. The method achieves state-of-the-art performance on both pre-surgery MRIs and post-surgery MRIs with artifacts. Based on our segmentation results, we also describe an automated approach to compute ER from these results. Experimental results on multiple datasets demonstrate the potential of the proposed method to assist clinicians in the diagnosis and management of NPH.

Altered Cerebellar Volumes and Intrinsic Cerebellar Network in Juvenile Myoclonic Epilepsy

Objectives. This study is aimed at investigating the alterations in cerebellar volumes and intrinsic cerebellar network in patients with juvenile myoclonic epilepsy (JME) in comparison with healthy controls. Methods. Patients newly diagnosed with JME and healthy controls were enrolled. Three-dimensional T1-weighted imaging was conducted, and no structural lesions were found on brain magnetic resonance imaging. Cerebellar volumes were obtained using the ACAPULCO program, while the intrinsic cerebellar network was evaluated by applying graph theory using the BRAPH program. The nodes were defined as individual cerebellar volumes and edges as partial correlations, controlling for the effects of age and sex. Cerebellar volumes and intrinsic cerebellar networks were compared between the two groups. Results. Forty-five patients with JME and 45 healthy controls were enrolled. Compared with the healthy controls, the patients with JME had significantly lower volumes of the right and left cerebellar white matter (3.33 vs. 3.48%, $p=0.009$ ; 3.35 vs. 3.49%, $p=0.009$ ), corpus medullare (0.99 vs. 1.03%, $p=0.04$ ), and left lobule V (0.19 vs. 0.22%, $p=0.002$ ). The intrinsic cerebellar networks also showed significant differences between the two groups. The small-worldness index in the patients with JME was significantly lower than that in the healthy controls (0.771 vs. 0.919, $p=0.04$ ). Conclusion. The cerebellar volumes and intrinsic cerebellar network demonstrated alterations in the patients with JME when compared with those of the healthy controls. Our study results provide evidence that the cerebellum may play a role in the pathogenesis of JME.

Reduced cerebello-cerebral functional connectivity correlates with disease severity and impaired white matter integrity in Friedreich ataxia

Friedreich ataxia (FRDA) is a rare, inherited neurodegenerative disease characterised in most cases by progressive and debilitating motor dysfunction. Degeneration of cerebellar white matter pathways have been previously reported, alongside indications of cerebello-cerebral functional alterations. In this work, we examine resting-state functional connectivity changes within cerebello-cerebral circuits, and their associations with disease severity (Scale for the Assessment and Rating of Ataxia [SARA]), psychomotor function (speeded and paced finger tapping), and white matter integrity (diffusion tensor imaging) in 35 adults with FRDA and 45 age and sex-matched controls. Voxel-wise seed-based functional connectivity was assessed for three cerebellar cortical regions (anterior lobe, lobules I-V; superior posterior lobe, lobules VI-VIIB; inferior posterior lobe, lobules VIIIA-IX) and two dentate nucleus seeds (dorsal and ventral). Compared to controls, people with FRDA showed significantly reduced connectivity between the anterior cerebellum and bilateral pre/postcentral gyri, and between the superior posterior cerebellum and left dorsolateral PFC. Greater disease severity correlated with lower connectivity in these circuits. Lower anterior cerebellum-motor cortex functional connectivity also correlated with slower speeded finger tapping and less fractional anisotropy in the superior cerebellar peduncles, internal capsule, and precentral white matter in the FRDA cohort. There were no significant between-group differences in inferior posterior cerebellar or dentate nucleus connectivity. This study indicates that altered cerebello-cerebral functional connectivity is associated with functional status and white matter damage in cerebellar efferent pathways in people with FRDA, particularly in motor circuits.

ConvNets for automatic detection of polyglutamine SCAs from brain MRIs: state of the art applications

Polyglutamine spinocerebellar ataxias (polyQ SCAs) are a group of neurodegenerative diseases, clinically and genetically heterogeneous, characterized by loss of balance and motor coordination due to dysfunction of the cerebellum and its connections. The diagnosis of each type of polyQ SCA, alongside with genetic tests, includes medical images analysis, and its automation may help specialists to distinguish between each type. Convolutional neural networks (ConvNets or CNNs) have been recently used for medical image processing, with outstanding results. In this work, we present the main clinical and imaging features of polyglutamine SCAs, and the basics of CNNs. Finally, we review studies that have used this approach to automatically process brain medical images and may be applied to SCAs detection. We conclude by discussing the possible limitations and opportunities of using ConvNets for SCAs diagnose in the future.

Longitudinal Effects of Asymptomatic C9orf72 Carriership on Brain Morphology

OBJECTIVE

We investigated effects of C9orf72 repeat expansion and gene expression on longitudinal cerebral changes before symptom onset.

METHODS

We enrolled 79 asymptomatic family members (AFMs) from 9 families with C9orf72 repeat expansion. Twenty-eight AFMs carried the mutation (C9+). Participants had up to 3 magnetic resonance imaging (MRI) scans, after which we compared motor cortex and motor tracts between C9+ and C9- AFMs using mixed effects models, incorporating kinship to correct for familial relations and lessen effects of other genetic factors. We also compared cortical, subcortical, cerebellar, and connectome structural measurements in a hypothesis-free analysis. We correlated regional C9orf72 expression in donor brains with the pattern of cortical thinning in C9+ AFMs using meta-regression. For comparison, we included 42 C9+ and 439 C9- patients with amyotrophic lateral sclerosis (ALS) in this analysis.

RESULTS

C9+ AFM motor cortex had less gyrification and was thinner than in C9- AFMs, without differences in motor tracts. Whole brain analysis revealed thinner cortex and less gyrification in parietal, occipital, and temporal regions, smaller thalami and right hippocampus, and affected frontotemporal connections. Thinning of bilateral precentral, precuneus, and left superior parietal cortex was faster in C9+ than in C9- AFMs. Higher C9orf72 expression correlated with thinner cortex in both C9+ AFMs and C9+ ALS patients.

INTERPRETATION

In asymptomatic C9orf72 repeat expansion carriers, brain MRI reveals widespread features suggestive of impaired neurodevelopment, along with faster decline of motor and parietal cortex than found in normal aging. C9orf72 expression might play a role in cortical development, and consequently explain the specific brain abnormalities of mutation carriers. ANN NEUROL 2022.

CerebNet: A fast and reliable deep-learning pipeline for detailed cerebellum sub-segmentation

Quantifying the volume of the cerebellum and its lobes is of profound interest in various neurodegenerative and acquired diseases. Especially for the most common spinocerebellar ataxias (SCA), for which the first antisense oligonculeotide-base gene silencing trial has recently started, there is an urgent need for quantitative, sensitive imaging markers at pre-symptomatic stages for stratification and treatment assessment. This work introduces CerebNet, a fully automated, extensively validated, deep learning method for the lobular segmentation of the cerebellum, including the separation of gray and white matter. For training, validation, and testing, T1-weighted images from 30 participants were manually annotated into cerebellar lobules and vermal sub-segments, as well as cerebellar white matter. CerebNet combines FastSurferCNN, a UNet-based 2.5D segmentation network, with extensive data augmentation, e.g. realistic non-linear deformations to increase the anatomical variety, eliminating additional preprocessing steps, such as spatial normalization or bias field correction. CerebNet demonstrates a high accuracy (on average 0.87 Dice and 1.742mm Robust Hausdorff Distance across all structures) outperforming state-of-the-art approaches. Furthermore, it shows high test-retest reliability (average ICC >0.97 on OASIS and Kirby) as well as high sensitivity to disease effects, including the pre-ataxic stage of spinocerebellar ataxia type 3 (SCA3). CerebNet is compatible with FreeSurfer and FastSurfer and can analyze a 3D volume within seconds on a consumer GPU in an end-to-end fashion, thus providing an efficient and validated solution for assessing cerebellum sub-structure volumes. We make CerebNet available as source-code (https://github.com/Deep-MI/FastSurfer).

MRI Clustering Reveals Three ALS Subtypes With Unique Neurodegeneration Patterns

OBJECTIVE

The purpose of this study was to identify subtypes of amyotrophic lateral sclerosis (ALS) by comparing patterns of neurodegeneration using brain magnetic resonance imaging (MRI) and explore their phenotypes.

METHODS

We performed T1-weighted and diffusion tensor imaging in 488 clinically well-characterized patients with ALS and 338 control subjects. Measurements of whole-brain cortical thickness and white matter connectome fractional anisotropy were adjusted for disease-unrelated variation. A probabilistic network-based clustering algorithm was used to divide patients into subgroups of similar neurodegeneration patterns. Clinical characteristics and cognitive profiles were assessed for each subgroup. In total, 512 follow-up scans were used to validate clustering results longitudinally.

RESULTS

The clustering algorithm divided patients with ALS into 3 subgroups of 187, 163, and 138 patients. All subgroups displayed involvement of the precentral gyrus and are characterized, respectively, by (1) pure motor involvement (pure motor cluster [PM]), (2) orbitofrontal and temporal involvement (frontotemporal cluster [FT]), and (3) involvement of the posterior cingulate cortex, parietal white matter, temporal operculum, and cerebellum (cingulate-parietal-temporal cluster [CPT]). These subgroups had significantly distinct clinical profiles regarding male-to-female ratio, age at symptom onset, and frequency of bulbar symptom onset. FT and CPT revealed higher rates of cognitive impairment on the Edinburgh cognitive and behavioral ALS screen (ECAS). Longitudinally, clustering remained stable: at 90.4% of their follow-up visits, patients clustered in the same subgroup as their baseline visit.

INTERPRETATION

ALS can manifest itself in 3 main patterns of cerebral neurodegeneration, each associated with distinct clinical characteristics and cognitive profiles. Besides the pure motor and frontotemporal dementia (FTD)-like variants of ALS, a new neuroimaging phenotype has emerged, characterized by posterior cingulate, parietal, temporal, and cerebellar involvement. ANN NEUROL 2022;92:1030-1045.

Cardiac MRI segmentation of the atria based on UU-NET

Background and objective

In today's society, people's work pressure, coupled with irregular diet, lack of exercise and other bad lifestyle, resulting in frequent cardiovascular diseases. Medical imaging has made great progress in modern society, among which the role of MRI in cardiovascular field is self-evident. Based on this research background, how to process cardiac MRI quickly and accurately by computer has been extensively discussed. By comparing and analyzing several traditional image segmentation and deep learning image segmentation, this paper proposes the left and right atria segmentation algorithm of cardiac MRI based on UU-NET network.

Methods

In this paper, an atrial segmentation algorithm for cardiac MRI images in UU-NET network is proposed. Firstly, U-shaped upper and lower sampling modules are constructed by using residual theory, which are used as encoders and decoders of the model. Then, the modules are interconnected to form multiple paths from input to output to increase the information transmission capacity of the model.

Results

The segmentation method based on UU-NET network has achieved good results proposed in this paper, compared with the current mainstream image segmentation algorithm results have been improved to a certain extent. Through the analysis of the experimental results, the image segmentation algorithm based on UU-NET network on the data set, its performance in the verification set and online set is higher than other grid models. The DSC in the verification set is 96.7%, and the DSC in the online set is 96.7%, which is nearly one percentage point higher than the deconvolution neural network model. The hausdorff distance (HD) is 1.2 mm. Compared with other deep learning models, it is significantly improved (about 3 mm error is reduced), and the time is 0.4 min.

Conclusion

The segmentation algorithm based on UU-NET improves the segmentation accuracy obviously compared with other segmentation models. Our technique will be able to help diagnose and treat cardiac complications.

A multifaceted gradient in human cerebellum of structural and functional development

The organization of the basic tissue and functional properties of the cerebellum across development is unknown. Combining several large datasets, we demonstrate in the human cerebellum a static tissue gradient in adults that mirrors a similar growth-rate gradient across development. Quantitative tissue metrics corroborate unique densities of certain lipids and proteins among lobules, and cerebellar structural development closely follows cerebellar functional properties through childhood.

Cerebellar Contributions to Motor and Cognitive Control in Multiple Sclerosis✰✰✰

OBJECTIVE

To evaluate relationships between specific cerebellar regions and common clinical measures of motor and cognitive function in persons with multiple sclerosis (PwMS).

DESIGN

Cross-sectional.

SETTING

Laboratory.

PARTICIPANTS

Twenty-nine PwMS and 28 age- and sex-matched controls without multiple sclerosis (MS) (N=57).

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURES

Both diffusion and lobule magnetic resonance imaging analyses and common clinical measures of motor and cognitive function were used to examine structure-function relationships in the cerebellum.

RESULTS

PwMS demonstrate significantly worse motor and cognitive function than controls, including weaker strength, slower walking, and poorer performance on the Symbol Digit Modalities Test, but demonstrate no differences in cerebellar volume. However, PwMS demonstrate significantly worse diffusivity (mean diffusivity: P=.0003; axial diffusivity: P=.0015; radial diffusivity: P=.0005; fractional anisotropy: P=.016) of the superior cerebellar peduncle, the primary output of the cerebellum. Increased volume of the motor lobules (I-V, VIII) was significantly related to better motor (P<.022) and cognitive (P=.046) performance, and increased volume of the cognitive lobules (VI-VII) was also related to better motor (P<.032) and cognitive (P=.008) performance, supporting the role of the cerebellum in both motor and cognitive functioning.

CONCLUSIONS

These data highlight the contributions of the cerebellum to both motor and cognitive function in PwMS. Using novel neuroimaging techniques to examine structure-function relationships in PwMS improves our understanding of individualized differences in this heterogeneous group and may provide an avenue for targeted, individualized rehabilitation aimed at improving cerebellar dysfunction in MS.

A Fast and Memory-Efficient Brain MRI Segmentation Framework for Clinical Applications

Current segmentation tools of brain MRI provide quantitative structural information for diagnosing neurological disorders. However, their clinical application is generally limited due to high memory usage and time consumption. Although 3D CNN-based segmentation methods have recently achieved the state-of-the-art and come up with timely available results, they heavily require high memory GPUs. In this paper, we customize a memory-efficient (GPU) brain structure segmentation framework, named FLBS, based on nnU-nets which enables our framework to adapt its architecture based on memory constraints dynamically. To further reduce the need for memory, we also reduce multi-label brain segmentation to the fusion of sequential single-label segmentations. In the first step, single label patches are extracted from the T1w and segmentation maps by locating the approximate area of each structure on the MNI305 template, including the safety margin. These considerations not only decrease the hardware usage but also maintains comparable computational time. Moreover, the target brain structures are customizable based on the specific clinical applications. We evaluate the performance in terms of Dice coefficient, runtime, and GPU requirement on OASIS-3 and CoRR-BNU1 datasets. The validation results show our comparable accuracies with state-of-the-arts and confirm the generalizability on unseen datasets while significantly reducing GPU requirements and maintaining runtime duration. Our framework is also executable on a budget GPU with a minimum requirement of 4G RAM. Clinical Relevance- We develop a memory-efficient deep Brain MRI segmentation tool that significantly reduces the hardware requirement of MRI segmentation while maintaining comparable accuracy and time. These advantages make FLBS suitable for widespread use in clinical applications especially for clinics with a limited budget. We plan to release the framework as a part of a free clinical brain imaging analysis tool. The code for this framework is publicly available.

Convolutional Neural Networks for Segmenting Cerebellar Fissures from Magnetic Resonance Imaging

The human cerebellum plays an important role in coordination tasks. Diseases such as spinocerebellar ataxias tend to cause severe damage to the cerebellum, leading patients to a progressive loss of motor coordination. The detection of such damages can help specialists to approximate the state of the disease, as well as to perform statistical analysis, in order to propose treatment therapies for the patients. Manual segmentation of such patterns from magnetic resonance imaging is a very difficult and time-consuming task, and is not a viable solution if the number of images to process is relatively large. In recent years, deep learning techniques such as convolutional neural networks (CNNs or convnets) have experienced an increased development, and many researchers have used them to automatically segment medical images. In this research, we propose the use of convolutional neural networks for automatically segmenting the cerebellar fissures from brain magnetic resonance imaging. Three models are presented, based on the same CNN architecture, for obtaining three different binary masks: fissures, cerebellum with fissures, and cerebellum without fissures. The models perform well in terms of precision and efficiency. Evaluation results show that convnets can be trained for such purposes, and could be considered as additional tools in the diagnosis and characterization of neurodegenerative diseases.

Evaluating the impact of MR image harmonization on thalamus deep network segmentation

Medical image segmentation is one of the core tasks of medical image analysis. Automatic segmentation of brain magnetic resonance images (MRIs) can be used to visualize and track changes of the brain's anatomical structures that may occur due to normal aging or disease. Machine learning techniques are widely used in automatic structure segmentation. However, the contrast variation between the training and testing data makes it difficult for segmentation algorithms to generate consistent results. To address this problem, an image-to-image translation technique called MR image harmonization can be used to match the contrast between different data sets. It is important for the harmonization to transform image intensity while maintaining the underlying anatomy. In this paper, we present a 3D U-Net algorithm to segment the thalamus from multiple MR image modalities and investigate the impact of harmonization on the segmentation algorithm. Manual delineations of thalamic nuclei on two data sets are available. However, we aim to analyze the thalamus in another large data set where ground truth labels are lacking. We trained two segmentation networks, one with unharmonized images and the other with harmonized images, on one data set with manual labels, and compared their performances on the other data set with manual labels. These two data groups were diagnosed with two brain disorders and were acquired with similar imaging protocols. The harmonization target is the large data set without manual labels, which also has a different imaging protocol. The networks trained on unharmonized and harmonized data showed no significant difference when evaluating on the other data set; demonstrating that image harmonization can maintain the anatomy and does not affect the segmentation task. The two networks were evaluated on the harmonization target data set and the network trained on harmonized data showed significant improvement over the network trained on unharmonized data. Therefore, the network trained on harmonized data provides the potential to process large amounts of data from other sites, even in the absence of site-specific training data.

Cerebellar Volumes and Sensorimotor Behavior in Autism Spectrum Disorder

Background

Sensorimotor issues are common in autism spectrum disorder (ASD), though their neural bases are not well understood. The cerebellum is vital to sensorimotor control and reduced cerebellar volumes in ASD have been documented. Our study examined the extent to which cerebellar volumes are associated with multiple sensorimotor behaviors in ASD.

Materials and Methods

Fifty-eight participants with ASD and 34 typically developing (TD) controls (8-30 years) completed a structural MRI scan and precision grip testing, oculomotor testing, or both. Force variability during precision gripping as well as absolute error and trial-to-trial error variability of visually guided saccades were examined. Volumes of cerebellar lobules, vermis, and white matter were quantified. The relationships between each cerebellar region of interest (ROI) and force variability, saccade error, and saccade error variability were examined.

Results

Relative to TD controls, individuals with ASD showed increased force variability. Individuals with ASD showed a reduced volume of cerebellar vermis VI-VII relative to TD controls. Relative to TD females, females with ASD showed a reduced volume of bilateral cerebellar Crus II/lobule VIIB. Increased volume of Crus I was associated with increased force variability. Increased volume of vermal lobules VI-VII was associated with reduced saccade error for TD controls but not individuals with ASD. Increased right lobule VIII and cerebellar white matter volumes as well as reduced right lobule VI and right lobule X volumes were associated with greater ASD symptom severity. Reduced volumes of right Crus II/lobule VIIB were associated with greater ASD symptom severity in only males, while reduced volumes of right Crus I were associated with more severe restricted and repetitive behaviors only in females.

Conclusion

Our finding that increased force variability in ASD is associated with greater cerebellar Crus I volumes indicates that disruption of sensory feedback processing supported by Crus I may contribute to skeletomotor differences in ASD. Results showing that volumes of vermal lobules VI-VII are associated with saccade precision in TD but not ASD implicates atypical organization of the brain systems supporting oculomotor control in ASD. Associations between volumes of cerebellar subregions and ASD symptom severity suggest cerebellar pathological processes may contribute to multiple developmental challenges in ASD.

Artificial intelligence with deep learning in nuclear medicine and radiology

The use of deep learning in medical imaging has increased rapidly over the past few years, finding applications throughout the entire radiology pipeline, from improved scanner performance to automatic disease detection and diagnosis. These advancements have resulted in a wide variety of deep learning approaches being developed, solving unique challenges for various imaging modalities. This paper provides a review on these developments from a technical point of view, categorizing the different methodologies and summarizing their implementation. We provide an introduction to the design of neural networks and their training procedure, after which we take an extended look at their uses in medical imaging. We cover the different sections of the radiology pipeline, highlighting some influential works and discussing the merits and limitations of deep learning approaches compared to other traditional methods. As such, this review is intended to provide a broad yet concise overview for the interested reader, facilitating adoption and interdisciplinary research of deep learning in the field of medical imaging.

Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory

In magnetic resonance (MR) imaging, a lack of standardization in acquisition often causes pulse sequence-based contrast variations in MR images from site to site, which impedes consistent measurements in automatic analyses. In this paper, we propose an unsupervised MR image harmonization approach, CALAMITI (Contrast Anatomy Learning and Analysis for MR Intensity Translation and Integration), which aims to alleviate contrast variations in multi-site MR imaging. Designed using information bottleneck theory, CALAMITI learns a globally disentangled latent space containing both anatomical and contrast information, which permits harmonization. In contrast to supervised harmonization methods, our approach does not need a sample population to be imaged across sites. Unlike traditional unsupervised harmonization approaches which often suffer from geometry shifts, CALAMITI better preserves anatomy by design. The proposed method is also able to adapt to a new testing site with a straightforward fine-tuning process. Experiments on MR images acquired from ten sites show that CALAMITI achieves superior performance compared with other harmonization approaches.

Automated segmentation of deep brain nuclei using convolutional neural networks and susceptibility weighted imaging

The advent of susceptibility-sensitive MRI techniques, such as susceptibility weighted imaging (SWI), has enabled accurate in vivo visualization and quantification of iron deposition within the human brain. Although previous approaches have been introduced to segment iron-rich brain regions, such as the substantia nigra, subthalamic nucleus, red nucleus, and dentate nucleus, these methods are largely unavailable and manual annotation remains the most used approach to label these regions. Furthermore, given their recent success in outperforming other segmentation approaches, convolutional neural networks (CNN) promise better performances. The aim of this study was thus to evaluate state-of-the-art CNN architectures for the labeling of deep brain nuclei from SW images. We implemented five CNN architectures and considered ensembles of these models. Furthermore, a multi-atlas segmentation model was included to provide a comparison not based on CNN. We evaluated two prediction strategies: individual prediction, where a model is trained independently for each region, and combined prediction, which simultaneously predicts multiple closely located regions. In the training dataset, all models performed with high accuracy with Dice coefficients ranging from 0.80 to 0.95. The regional SWI intensities and volumes from the models' labels were strongly correlated with those obtained from manual labels. Performances were reduced on the external dataset, but were higher or comparable to the intrarater reliability and most models achieved significantly better results compared to multi-atlas segmentation. CNNs can accurately capture the individual variability of deep brain nuclei and represent a highly useful tool for their segmentation from SW images.

Unique Morphometric Features of the Cerebellum and Cerebellocerebral Structural Correlation Between Autism Spectrum Disorder and Schizophrenia

Background

Although cerebellar morphological involvement has been increasingly recognized in autism spectrum disorder (ASD) and schizophrenia (SZ), the extent to which there are morphological differences between them has not been definitively quantified. Furthermore, although previous studies have demonstrated increased anatomical cerebellocerebral correlations in both conditions, differences between their associations have not been well characterized.

Methods

We compared cerebellar volume between males with ASD (n = 31), males with SZ (n = 28), and typically developing males (n = 49). A total of 31 cerebellar subregions were investigated with the cerebellum segmented into their constituent lobules, in gray matter (GM) and white matter (WM) separately. Additionally, structural correlations with the contralateral cerebrum were analyzed for each cerebellar lobule.

Results

We found significantly larger WM volume in the bilateral lobules VI and Crus I in the ASD group than in other groups. While WM or GM volumes of these right lobules had positive associations with ASD symptoms, there was a negative association between GM volume of the right Crus I and SZ symptoms. We further observed, in the ASD group specifically, significant correlations between WM of the right lobule VI and WM of the left frontal pole (r = 0.67) and between GM of the right lobule VI and the left caudate (r = 0.60).

Conclusions

Our findings support evidence that cerebellar morphology is involved in ASD and SZ with different mechanisms. Furthermore, this study showed that these biological differences require consideration when determining diagnostic criteria and treatment for these disorders.

Neuroanatomical norms in the UK Biobank: The impact of allometric scaling, sex, and age

Few neuroimaging studies are sufficiently large to adequately describe population‐wide variations. This study's primary aim was to generate neuroanatomical norms and individual markers that consider age, sex, and brain size, from 629 cerebral measures in the UK Biobank (N = 40,028). The secondary aim was to examine the effects and interactions of sex, age, and brain allometry—the nonlinear scaling relationship between a region and brain size (e.g., total brain volume)—across cerebral measures. Allometry was a common property of brain volumes, thicknesses, and surface areas (83%) and was largely stable across age and sex. Sex differences occurred in 67% of cerebral measures (median |β| = .13): 37% of regions were larger in males and 30% in females. Brain measures (49%) generally decreased with age, although aging effects varied across regions and sexes. While models with an allometric or linear covariate adjustment for brain size yielded similar significant effects, omitting brain allometry influenced reported sex differences in variance. Finally, we contribute to the reproducibility of research on sex differences in the brain by replicating previous studies examining cerebral sex differences. This large‐scale study advances our understanding of age, sex, and brain allometry's impact on brain structure and provides data for future UK Biobank studies to identify the cerebral regions that covary with specific phenotypes, independently of sex, age, and brain size.

Brain Structural Signature of RFC1-Related Disorder

BACKGROUND

The cerebellar ataxia, neuropathy, and vestibular areflexia syndrome was initially described in the early 1990s as a late-onset slowly progressive condition. Its underlying genetic cause was recently mapped to the RFC1 gene, and additional reports have expanded on the phenotypic manifestations related to RFC1, although little is known about the pattern and extent of structural brain abnormalities in this condition.

OBJECTIVE

The aim is to characterize the structural signature of brain damage in RFC1-related disorder, correlating the findings with clinical symptoms and normal brain RFC1 expression.

METHODS

We recruited 22 individuals with molecular confirmation of RFC1 expansions and submitted them to high-resolution 3T magnetic resonance imaging scans. We performed multimodal analyses to assess separately cerebral and cerebellar abnormalities within gray and white matter (WM). The results were compared with a group of 22 age- and sex-matched controls.

RESULTS

The mean age and disease duration of patients were 62.8 and 10.9 years, respectively. Ataxia, sensory neuronopathy, and vestibular areflexia were the most frequent manifestations, but parkinsonism and pyramidal signs were also noticed. We found that RFC1-related disorder is characterized by widespread and relatively symmetric cerebellar and basal ganglia atrophy. There is brainstem volumetric reduction along all its segments. Cerebral WM is also involved-mostly the corpus callosum and deep tracts, but cerebral cortical damage is rather restricted.

CONCLUSION

This study adds new relevant insights into the pathophysiological mechanisms of RFC1-related disorder. It should no longer be considered a purely cerebellar and sensory pathway disorder. Basal ganglia and deep cerebral WM are additional targets of damage. © 2021 International Parkinson and Movement Disorder Society.

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

Since its renaissance, deep learning has been widely used in various medical imaging tasks and has achieved remarkable success in many medical imaging applications, thereby propelling us into the so-called artificial intelligence (AI) era. It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. However, medical imaging presents unique challenges that confront deep learning approaches. In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues. We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. Then, we present several case studies that are commonly found in clinical practice, including digital pathology and chest, brain, cardiovascular, and abdominal imaging. Rather than presenting an exhaustive literature survey, we instead describe some prominent research highlights related to these case study applications. We conclude with a discussion and presentation of promising future directions.

Anatomical texture patterns identify cerebellar distinctions between essential tremor and Parkinson's disease

Voxel-based morphometry is an established technique to study focal structural brain differences in neurologic disease. More recently, texture-based analysis methods have enabled a pattern-based assessment of group differences, at the patch level rather than at the voxel level, allowing a more sensitive localization of structural differences between patient populations. In this study, we propose a texture-based approach to identify structural differences between the cerebellum of patients with Parkinson's disease (n = 280) and essential tremor (n = 109). We analyzed anatomical differences of the cerebellum among patients using two features: T1-weighted MRI intensity, and a texture-based similarity feature. Our results show anatomical differences between groups that are localized to the inferior part of the cerebellar cortex. Both the T1-weighted intensity and texture showed differences in lobules VIII and IX, vermis VIII and IX, and middle peduncle, but the texture analysis revealed additional differences in the dentate nucleus, lobules VI and VII, vermis VI and VII. This comparison emphasizes how T1-weighted intensity and texture-based methods can provide a complementary anatomical structure analysis. While texture-based similarity shows high sensitivity for gray matter differences, T1-weighted intensity shows sensitivity for the detection of white matter differences.

MRI subcortical segmentation in neurodegeneration with cascaded 3D CNNs

The subcortical structures of the brain are relevant for many neurodegenerative diseases like Huntington's disease (HD). Quantitative segmentation of these structures from magnetic resonance images (MRIs) has been studied in clinical and neuroimaging research. Recently, convolutional neural networks (CNNs) have been successfully used for many medical image analysis tasks, including subcortical segmentation. In this work, we propose a 2-stage cascaded 3D subcortical segmentation framework, with the same 3D CNN architecture for both stages. Attention gates, residual blocks and output adding are used in our proposed 3D CNN. In the first stage, we apply our model to downsampled images to output a coarse segmentation. Next, we crop the extended subcortical region from the original image based on this coarse segmentation, and we input the cropped region to the second CNN to obtain the final segmentation. Left and right pairs of thalamus, caudate, pallidum and putamen are considered in our segmentation. We use the Dice coefficient as our metric and evaluate our method on two datasets: the publicly available IBSR dataset and a subset of the PREDICT-HD database, which includes healthy controls and HD subjects. We train our models on only healthy control subjects and test on both healthy controls and HD subjects to examine model generalizability. Compared with the state-of-the-art methods, our method has the highest mean Dice score on all considered subcortical structures (except the thalamus on IBSR), with more pronounced improvement for HD subjects. This suggests that our method may have better ability to segment MRIs of subjects with neurodegenerative disease.

Replicability, Repeatability, and Long-term Reproducibility of Cerebellar Morphometry

To identify robust and reproducible methods of cerebellar morphometry that can be used in future large-scale structural MRI studies, we investigated the replicability, repeatability, and long-term reproducibility of three fully automated software tools: FreeSurfer, CEREbellum Segmentation (CERES), and automatic cerebellum anatomical parcellation using U-Net with locally constrained optimization (ACAPULCO). Replicability was defined as computational replicability, determined by comparing two analyses of the same high-resolution MRI data set performed with identical analysis software and computer hardware. Repeatability was determined by comparing the analyses of two MRI scans of the same participant taken during two independent MRI sessions on the same day for the Kirby-21 study. Long-term reproducibility was assessed by analyzing two MRI scans of the same participant in the longitudinal OASIS-2 study. We determined percent difference, the image intraclass correlation coefficient, the coefficient of variation, and the intraclass correlation coefficient between two analyses. Our results show that CERES and ACAPULCO use stochastic algorithms that result in surprisingly high differences between identical analyses for ACAPULCO and small differences for CERES. Changes between two consecutive scans from the Kirby-21 study were less than ± 5% in most cases for FreeSurfer and CERES (i.e., demonstrating high repeatability). As expected, long-term reproducibility was lower than repeatability for all software tools. In summary, CERES is an accurate, as demonstrated before, and reproducible tool for fully automated segmentation and parcellation of the cerebellum. We conclude with recommendations for the assessment of replicability, repeatability, and long-term reproducibility in future studies on cerebellar structure.

A Review of Publicly Available Automatic Brain Segmentation Methodologies, Machine Learning Models, Recent Advancements, and Their Comparison

BACKGROUND

The noninvasive study of the structure and functions of the brain using neuroimaging techniques is increasingly being used for its clinical and research perspective. The morphological and volumetric changes in several regions and structures of brains are associated with the prognosis of neurological disorders such as Alzheimer's disease, epilepsy, schizophrenia, etc. and the early identification of such changes can have huge clinical significance. The accurate segmentation of three-dimensional brain magnetic resonance images into tissue types (i.e., grey matter, white matter, cerebrospinal fluid) and brain structures, thus, has huge importance as they can act as early biomarkers. The manual segmentation though considered the "gold standard" is time-consuming, subjective, and not suitable for bigger neuroimaging studies. Several automatic segmentation tools and algorithms have been developed over the years; the machine learning models particularly those using deep convolutional neural network (CNN) architecture are increasingly being applied to improve the accuracy of automatic methods.

PURPOSE

The purpose of the study is to understand the current and emerging state of automatic segmentation tools, their comparison, machine learning models, their reliability, and shortcomings with an intent to focus on the development of improved methods and algorithms.

METHODS

The study focuses on the review of publicly available neuroimaging tools, their comparison, and emerging machine learning models particularly those based on CNN architecture developed and published during the last five years.

CONCLUSION

Several software tools developed by various research groups and made publicly available for automatic segmentation of the brain show variability in their results in several comparison studies and have not attained the level of reliability required for clinical studies. The machine learning models particularly three dimensional fully convolutional network models can provide a robust and efficient alternative with relation to publicly available tools but perform poorly on unseen datasets. The challenges related to training, computation cost, reproducibility, and validation across distinct scanning modalities for machine learning models need to be addressed.

Longitudinal analysis of regional cerebellum volumes during normal aging

Some cross-sectional studies suggest reduced cerebellar volumes with aging, but there have been few longitudinal studies of age changes in cerebellar subregions in cognitively healthy older adults. In this work, 2,023 magnetic resonance (MR) images of 822 cognitively normal participants from the Baltimore Longitudinal Study of Aging (BLSA) were analyzed. Participants ranged in age from 50 to 95 years (mean 70.7 years) at the baseline assessment. Follow-up intervals were 1-9 years (mean 3.7 years) for participants with two or more visits. We used a recently developed cerebellum parcellation algorithm based on convolutional neural networks to divide the cerebellum into 28 subregions. Linear mixed effects models were applied to the volume of each cerebellar subregion to investigate cross-sectional and longitudinal age effects, as well as effects of sex and their interactions, after adjusting for intracranial volume. Our findings suggest spatially varying atrophy patterns across the cerebellum with respect to age and sex both cross-sectionally and longitudinally.