Comparing two artificial intelligence software packages for normative brain volumetry in memory clinic imaging

Purpose To compare two artificial intelligence software packages performing normative brain volumetry and explore whether they could differently impact dementia diagnostics in a clinical context. Methods Sixty patients (20 Alzheimer’s disease, 20 frontotemporal dementia, 20 mild cognitive impairment) and 20 controls were included retrospectively. One MRI per subject was processed by software packages from two proprietary manufacturers, producing two quantitative reports per subject. Two neuroradiologists assigned forced-choice diagnoses using only the normative volumetry data in these reports. They classified the volumetric profile as “normal,” or “abnormal”, and if “abnormal,” they specified the most likely dementia subtype. Differences between the packages’ clinical impact were assessed by comparing (1) agreement between diagnoses based on software output; (2) diagnostic accuracy, sensitivity, and specificity; and (3) diagnostic confidence. Quantitative outputs were also compared to provide context to any diagnostic differences. Results Diagnostic agreement between packages was moderate, for distinguishing normal and abnormal volumetry (K = .41–.43) and for specific diagnoses (K = .36–.38). However, each package yielded high inter-observer agreement when distinguishing normal and abnormal profiles (K = .73–.82). Accuracy, sensitivity, and specificity were not different between packages. Diagnostic confidence was different between packages for one rater. Whole brain intracranial volume output differed between software packages (10.73%, p < .001), and normative regional data interpreted for diagnosis correlated weakly to moderately (rs = .12–.80). Conclusion Different artificial intelligence software packages for quantitative normative assessment of brain MRI can produce distinct effects at the level of clinical interpretation. Clinics should not assume that different packages are interchangeable, thus recommending internal evaluation of packages before adoption.

Correlating MRI-Based Brain Volumetry and Cognitive Assessment in Down Syndrome Patients

INTRODUCTIONDown syndrome (DS) is the most common genetic cause of intellectual disability. Children and adults with DS show deficits in various aspects of language performance and explicit memory. Here we use magnetic resonance imaging (MRI) on children and adults with DS to characterize changes in the volume of specific brain structures involved in memory and language and their relationship to features of cognitive-behavioral phenotypes.METHODSThirteen children and adults with the DS phenotype and 12 age- and gender-matched healthy controls were analyzed by MRI and underwent a psychological evaluation for language and cognitive abilities.RESULTSThe neuropsychological profile of DS patients showed deficits in different cognition and language domains in correlation with reduced volumes of specific regional and subregional brain structures. Intriguingly, our DS patients showed also a reduced parahippocampal gyrus volume, in contrast with the results found by other researchers.CONCLUSIONSThe memory functions and language skills affected in our DS patients correlate significantly with the reduced volume of specific brain regions, allowing us to understand DS's cognitive-behavioral phenotype. Our results provide an essential basis for early intervention and the design of rehabilitation management protocols.

Correlating MRI-Based Brain Volumetry and Cognitive Assessment in Down Syndrome Patients

INTRODUCTION: Down syndrome (DS) is the most common genetic cause of intellectual disability. Here, we use magnetic resonance imaging (MRI) on children and adults with DS to characterize changes in the volume of specific brain structures involved in memory and language and their relationship to features of cognitive-behavioral phenotypes.METHODS: Thirteen children and adults with the DS phenotype and 12 age- and gender-matched healthy controls were analyzed by MRI and underwent a psychological evaluation for language and cognitive abilities.RESULTS: The neuropsychological profile of DS patients showed deficits in different cognition and language domains in correlation with reduced volumes of specific regional and subregional brain structures.CONCLUSIONS: The memory functions and language skills affected in our DS patients correlate significantly with the reduced volume of specific brain regions, allowing us to understand DS's cognitive-behavioral phenotype. Our results provide an essential basis for early intervention and the design of rehabilitation management protocols.

Inter- and Intra-Scanner Variability of Automated Brain Volumetry on Three Magnetic Resonance Imaging Systems in Alzheimer’s Disease and Controls

Magnetic Resonance Imaging (MRI) has become part of the clinical routine for diagnosing neurodegenerative disorders. Since acquisitions are performed at multiple centers using multiple imaging systems, detailed analysis of brain volumetry differences between MRI systems and scan-rescan acquisitions can provide valuable information to correct for different MRI scanner effects in multi-center longitudinal studies. To this end, five healthy controls and five patients belonging to various stages of the AD continuum underwent brain MRI acquisitions on three different MRI systems (Philips Achieva dStream 1.5T, Philips Ingenia 3T, and GE Discovery MR750w 3T) with harmonized scan parameters. Each participant underwent two subsequent MRI scans per imaging system, repeated on three different MRI systems within 2 h. Brain volumes computed by icobrain dm (v5.0) were analyzed using absolute and percentual volume differences, Dice similarity (DSC) and intraclass correlation coefficients, and coefficients of variation (CV). Harmonized scans obtained with different scanners of the same manufacturer had a measurement error closer to the intra-scanner performance. The gap between intra- and inter-scanner comparisons grew when comparing scans from different manufacturers. This was observed at image level (image contrast, similarity, and geometry) and translated into a higher variability of automated brain volumetry. Mixed effects modeling revealed a significant effect of scanner type on some brain volumes, and of the scanner combination on DSC. The study concluded a good intra- and inter-scanner reproducibility, as illustrated by an average intra-scanner (inter-scanner) CV below 2% (5%) and an excellent overlap of brain structure segmentation (mean DSC &gt; 0.88).

Novel Volumetric and Surface-Based Magnetic Resonance Indices of the Aging Brain – Does Male and Female Brain Age in the Same Way?

Introduction: Novel post-processing methods allow not only for assessment of brain volumetry or cortical thickness based on magnetic resonance imaging (MRI) but also for more detailed analysis of cortical shape and complexity using parameters such as sulcal depth, gyrification index, or fractal dimension. The aim of this study was to analyze changes in brain volumetry and other cortical indices during aging in men and women.Material and Methods: Material consisted of 697 healthy volunteers (aged 38–80 years; M/F, 264/443) who underwent brain MRI using a 1.5-T scanner. Voxel-based volumetry of total gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) was performed followed by assessment of cortical parameters [cortical thickness (CT), sulcal depth (SD), gyrification index (GI), and fractal dimension (FD)] in 150 atlas locations using surface-based morphometry with a region-based approach. All parameters were compared among seven age groups (grouped every 5 years) separately for men and women. Additionally, percentile curves for men and women were provided for total volumes of GM, WM, and CSF.Results: In men and women, a decrease in GM and WM volumes and an increase in CSF volume seem to progress slowly since the age of 45. In men, significant GM and WM loss as well as CSF increase start above 55 years of age, while in women, significant GM loss starts above 50 and significant WM loss as well as CSF increase above 60. CT was found to significantly decrease with aging in 39% of locations in women and in 36% of locations in men, SD was found to increase in 13.5% of locations in women and in 1.3% of locations in men, GI was decreased in 3.4% of locations in women and in 2.0% of locations in men, and FD was changed in 2.7% of locations in women compared to 2.0% in men.Conclusions: Male and female brains start aging at the similar age of 45. Compared to men, in women, the cortex is affected earlier and in the more complex pattern regarding not only cortical loss but also other alterations within the cortical shape, with relatively longer sparing of WM volume.

RELATIONSHIP BETWEEN COGNITIVE RESERVE, MOTOR RESERVE AND THALAMUS VOLUMETRY IN OLDER ADULTS

With the increasing worldwide population, an ongoing escalation in mild cognitive impairment and dementia is predicted. Motor reserve – the cumulative physical activity experience gained throughout life, as well as cognitive reserve – the brain’s ability to overcome a pathology, such as neurodegenerative disorders, - has been identified as protective factors in cognitive decline. Thus, this study aimed to investigate the relationship between cognitive reserve, motor reserve, and brain volumetry in older adults. 44 older adults (M = 70, SD = 5.18, 77.3% female) with no self-reported significant neurological, ongoing oncological etc. disorders that might limit their participation in the study were involved in the study. All participants underwent a thorough life-style and psychological assessment, as well as structural brain MRI analysis. Overall, our study indicated the significance of a combination of lifestyle factors in predicting thalamic volume. The results of this study indicate that life-long participation in physical, intellectual, and social activities could be beneficial for preserving the volume of thalamus, which is among the first to decline due to aging.

Cerebellar White Matter Abnormalities in Patients with Charcot-Marie-Tooth disease

Charcot-Marie-Tooth disease (CMT) is a genetically heterogeneous hereditary peripheral neuropathy. Brain volumetry and diffusion tensor imaging (DTI) were performed in CMT patients with PMP22 duplication, MFN2, GJB1, or NEFL mutations to investigate for structural changes of the cerebellum.Volume in cerebellar white matter (WM) was significantly reduced in CMT patients with NEFL mutations. Abnormal DTI findings ​​were observed in the superior, middle, and inferior cerebellar peduncles predominantly in NEFL mutations, and partly in GJB1 mutations. Cerebellar ataxia was more prevalent in the NEFL mutation (72.7%) than GJB1 mutation (9.1%), but not observed in other genotypic subtypes, which indicates that structural cerebellar abnormalities were associated with the presence of cerebellar ataxia. However, NEFL and GJB1 mutations did not affect cerebellar gray matter (GM), and neither cerebellar GM nor WM abnormalities were observed in PMP22 duplication or MFN2 mutations. We found structural evidence of cerebellar WM abnormalities in CMT patients with NEFL and GJB1 mutations and the association between cerebellar WM involvement and cerebellar ataxia in these genetic subtypes, especially in the NEFL subgroup. Therefore, we suggest that neuroimaging such as MRI volumetry or DTI in CMT patients could play an important role in detecting abnormalities of the cerebellar WM.