Automatic cerebellum anatomical parcellation using U-Net with locally constrained optimization
Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Cited by 62 publications
References 40 publications
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, CERES, and CNN. 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 CNN use stochastic algorithms that result in surprisingly high differences between identical analyses for CNN 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.
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, CERES, and CNN. 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 CNN use stochastic algorithms that result in surprisingly high differences between identical analyses for CNN 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.
Multimodal Analysis of Secondary Cerebellar Alterations After Pediatric Traumatic Brain Injury
ImportanceTraumatic 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.ObjectiveTo investigate alterations in subregional cerebellum volume and cerebral white matter microstructure after pediatric TBI and examine subsequent changes in executive function.Design, Setting, and ParticipantsThis 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.ExposureAccidental mild complicated-severe TBI (msTBI) for those in the TBI group. Some controls received a diagnosis of orthopedic injury.Main Outcomes and MeasuresVolume 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.ResultsA 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 RelevanceIn 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.
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-tofemale 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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
Contact Info
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Product
Resources
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.
