Multi-stage segmentation of white matter hyperintensity, cortical and lacunar infarcts

Automated neuroradiological support systems for multiple cerebrovascular disease markers - A systematic review and meta-analysis

Cerebrovascular diseases (CVD) can lead to stroke and dementia. Stroke is the second leading cause of death world wide and dementia incidence is increasing by the year. There are several markers of CVD that are visible on brain imaging, including: white matter hyperintensities (WMH), acute and chronic ischaemic stroke lesions (ISL), lacunes, enlarged perivascular spaces (PVS), acute and chronic haemorrhagic lesions, and cerebral microbleeds (CMB). Brain atrophy also occurs in CVD. These markers are important for patient management and intervention, since they indicate elevated risk of future stroke and dementia. We systematically reviewed automated systems designed to support radiologists reporting on these CVD imaging findings. We considered commercially available software and research publications which identify at least two CVD markers. In total, we included 29 commercial products and 13 research publications. Two distinct types of commercial support system were available: those which identify acute stroke lesions (haemorrhagic and ischaemic) from computed tomography (CT) scans, mainly for the purpose of patient triage; and those which measure WMH and atrophy regionally and longitudinally. In research, WMH and ISL were the markers most frequently analysed together, from magnetic resonance imaging (MRI) scans; lacunes and PVS were each targeted only twice and CMB only once. For stroke, commercially available systems largely support the emergency setting, whilst research systems consider also follow-up and routine scans. The systems to quantify WMH and atrophy are focused on neurodegenerative disease support, where these CVD markers are also of significance. There are currently no openly validated systems, commercially, or in research, performing a comprehensive joint analysis of all CVD markers (WMH, ISL, lacunes, PVS, haemorrhagic lesions, CMB, and atrophy).

Executive functions and processing speed in covert cerebral small vessel disease

BACKGROUND AND PURPOSE

Executive dysfunction and slowed processing speed are central cognitive impairments in cerebral small vessel disease (cSVD). It is unclear whether the subcomponents of executive functions become equally affected and whether computerized tests are more sensitive in detecting early cognitive changes over traditional tests. The associations of specific executive abilities (cognitive flexibility, inhibitory control, working memory) and processing speed with white matter hyperintensities (WMHs) and Instrumental Activities of Daily Living (IADL) were examined.

METHODS

In the Helsinki Small Vessel Disease Study, 152 older individuals without stroke or dementia were assessed with brain magnetic resonance imaging and comprehensive neuropsychological evaluation. WMH volumes were obtained with automated segmentation. Executive functions and processing speed measures included established paper-and-pencil tests and the computer-based Flexible Attention Test (FAT), Simon task and Sustained Attention to Response Task.

RESULTS

White matter hyperintensity volume and IADL were associated with multiple cognitive measures across subdomains independently of demographic factors. The highest effect sizes were observed for FAT numbers and number-letter tasks (tablet modifications from the Trail Making Test), FAT visuospatial span, Simon task and semantic verbal fluency. Some of the widely used tests such as Stroop inhibition, phonemic fluency and digit span were not significantly associated with either WMHs or IADL.

CONCLUSION

Processing speed and executive function subcomponents are broadly related to functional abilities and WMH severity in covert cSVD, but the strength of associations within subdomains is heavily dependent on the assessment method. Digital tests providing precise measures of reaction times and response accuracy seem to outperform many of the conventional paper-and-pencil tests.

Subjective vs informant-reported cognitive complaints have differential clinical significance in covert cerebral small vessel disease

Objective

Subjective cognitive complaints are common in patients with cerebral small vessel disease (cSVD), yet their relationship with informant evaluations, objective cognitive functions and severity of brain changes are poorly understood. We studied the associations of subjective and informant reports with findings from comprehensive neuropsychological assessment and brain MRI.

Method

In the Helsinki SVD Study, 152 older adults with varying degrees of white matter hyperintensities (WMH) but without stroke or dementia were classified as having normal cognition or mild cognitive impairment (MCI) based on neuropsychological criteria. The measures also included continuous domain scores for memory and executive functions. Cognitive complaints were evaluated with the subjective and informant versions of the Prospective and Retrospective Memory Questionnaire (PRMQ) and Dysexecutive Questionnaire (DEX); functional abilities with the Amsterdam Instrumental Activities of Daily Living Questionnaire (A-IADL); and depressive symptoms with the Geriatric Depression Scale (GDS-15).

Results

Subjective cognitive complaints correlated significantly with informant reports (r=0.40-0.50, p<0.001). After controlling for demographics, subjective and informant DEX and PRMQ were not related to MCI, memory or executive functions. Instead, subjective DEX and PRMQ significantly associated with GDS-15 and informant DEX and PRMQ with WMH volume and A-IADL.

Conclusions

Neither subjective nor informant-reported cognitive complaints associated with objective cognitive performance. Informant-evaluations were related to functional impairment and more severe WMH, whereas subjective complaints only associated with mild depressive symptoms. These findings suggest that awareness of cognitive impairment may be limited in early-stage cSVD and highlight the value of informant assessments in the identification of patients with functional impairment.

Computer-Aided Extraction of Select MRI Markers of Cerebral Small Vessel Disease: A Systematic Review

Cerebral small vessel disease (CSVD) is a major vascular contributor to cognitive impairment in ageing, including dementias. Imaging remains the most promising method for in vivo studies of CSVD. To replace the subjective and laborious visual rating approaches, emerging studies have applied state-of-the-art artificial intelligence to extract imaging biomarkers of CSVD from MRI scans. We aimed to summarise published computer-aided methods for the examination of three imaging biomarkers of CSVD, namely cerebral microbleeds (CMB), dilated perivascular spaces (PVS), and lacunes of presumed vascular origin. Seventy classical image processing, classical machine learning, and deep learning studies were identified. Transfer learning and weak supervision techniques have been applied to accommodate the limitations in the training data. While good performance metrics were achieved in local datasets, there have not been generalisable pipelines validated in different research and/or clinical cohorts. Future studies could consider pooling data from multiple sources to increase data size and diversity, and evaluating performance using both image processing metrics and associations with clinical measures.

Automatic segmentation of white matter hyperintensities in routine clinical brain MRI by 2D VB-Net: A large-scale study

White matter hyperintensities (WMH) are imaging manifestations frequently observed in various neurological disorders, yet the clinical application of WMH quantification is limited. In this study, we designed a series of dedicated WMH labeling protocols and proposed a convolutional neural network named 2D VB-Net for the segmentation of WMH and other coexisting intracranial lesions based on a large dataset of 1,045 subjects across various demographics and multiple scanners using 2D thick-slice protocols that are more commonly applied in clinical practice. Using our labeling pipeline, the Dice consistency of the WMH regions manually depicted by two observers was 0.878, which formed a solid basis for the development and evaluation of the automatic segmentation system. The proposed algorithm outperformed other state-of-the-art methods (uResNet, 3D V-Net and Visual Geometry Group network) in the segmentation of WMH and other coexisting intracranial lesions and was well validated on datasets with thick-slice magnetic resonance (MR) images and the 2017 medical image computing and computer assisted intervention WMH Segmentation Challenge dataset (with thin-slice MR images), all showing excellent effectiveness. Furthermore, our method can subclassify WMH to display the WMH distributions and is very lightweight. Additionally, in terms of correlation to visual rating scores, our algorithm showed excellent consistency with the manual delineations and was overall better than those from other competing methods. In conclusion, we developed an automatic WMH quantification framework for multiple application scenarios, exhibiting a promising future in clinical practice.

Grey matter atrophy in patients with benign multiple sclerosis

BACKGROUND

Brain atrophy appears during the progression of multiple sclerosis (MS) and is associated with the disability caused by the disease.

METHODS

We investigated global and regional grey matter (GM) and white matter (WM) volumes, WM lesion load, and corpus callosum index (CCI), in benign relapsing-remitting MS (BRRMS, n = 35) with and without any treatment and compared those to aggressive relapsing-remitting MS (ARRMS, n = 46). Structures were analyzed by using an automated MRI quantification tool (cNeuro®).

RESULTS

The total brain and cerebral WM volumes were larger in BRRMS than in ARRMS (p = .014, p = .017 respectively). In BRRMS, total brain volumes, regional GM volumes, and CCI were found similar whether or not disease-modifying treatment (DMT) was used. The total (p = .033), as well as subcortical (p = .046) and deep WM (p = .041) lesion load volumes were larger in BRRMS patients without DMT. Cortical GM volumes did not differ between BRRMS and ARRMS, but the volumes of total brain tissue (p = .014) and thalami (p = .003) were larger in patients with BRRMS compared to ARRMS. A positive correlation was found between CCI and whole-brain volume in both BRRMS (r = .73, p < .001) and ARRMS (r = .80, p < .01).

CONCLUSIONS

Thalamic volume is the most prominent measure to differentiate BRRMS and ARRMS. Validation of automated quantification of CCI provides an additional applicable MRI biomarker to detect brain atrophy in MS.

Serum Thioredoxin-80 is associated with age, ApoE4, and neuropathological biomarkers in Alzheimer's disease: a potential early sign of AD

Background

Thioredoxin-80 (Trx80) is a cleavage product from the redox-active protein Thioredoxin-1 and has been previously described as a pro-inflammatory cytokine secreted by immune cells. Previous studies in our group reported that Trx80 levels are depleted in Alzheimer’s disease (AD) brains. However, no studies so far have investigated peripheral Trx80 levels in the context of AD pathology and whether could be associated with the main known AD risk factors and biomarkers.

Methods

Trx80 was measured in serum samples from participants from two different cohorts: the observational memory clinic biobank (GEDOC) (N = 99) with AD CSF biomarker data was available and the population-based lifestyle multidomain intervention trial Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) (N = 47), with neuroimaging data and blood markers of inflammation available. The GEDOC cohort consists of participants diagnosed with subjective cognitive impairment (SCI), mild cognitive impairment (MCI), and AD, whereas the FINGER participants are older adults at-risk of dementia, but without substantial cognitive impairment. One-way ANOVA and multiple comparison tests were used to assess the levels of Trx80 between groups. Linear regression models were used to explore associations of Trx80 with cognition, AD CSF biomarkers (Aβ42, t-tau, p-tau and p-tau/t-tau ratio), inflammatory cytokines, and neuroimaging markers.

Results

In the GEDOC cohort, Trx80 was associated to p-tau/t-tau ratio in the MCI group. In the FINGER cohort, serum Trx80 levels correlated with lower hippocampal volume and higher pro-inflammatory cytokine levels. In both GEDOC and FINGER cohorts, ApoE4 carriers had significantly higher serum Trx80 levels compared to non-ApoE4 carriers. However, Trx80 levels in the brain were further decreased in AD patients with ApoE4 genotype.

Conclusion

We report that serum Trx80 levels are associated to AD disease stage as well as to several risk factors for AD such as age and ApoE4 genotype, which suggests that Trx80 could have potential as serum AD biomarker. Increased serum Trx80 and decreased brain Trx80 levels was particularly seen in ApoE4 carriers. Whether this could contribute to the mechanism by which ApoE4 show increased vulnerability to develop AD would need to be further investigated.

Trial registration

ClinicalTrials.govNCT01041989. Registered on 4 January 2010—retrospectively registered

Supplementary Information

The online version contains supplementary material available at 10.1186/s13195-022-00979-9.

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation

White matter hyperintensities (WMHs) are frequently observed on structural neuroimaging of elderly populations and are associated with cognitive decline and increased risk of dementia. Many existing WMH segmentation algorithms produce suboptimal results in populations with vascular lesions or brain atrophy, or require parameter tuning and are computationally expensive. Additionally, most algorithms do not generate a confidence estimate of segmentation quality, limiting their interpretation. MRI‐based segmentation methods are often sensitive to acquisition protocols, scanners, noise‐level, and image contrast, failing to generalize to other populations and out‐of‐distribution datasets. Given these concerns, we propose a novel Bayesian 3D convolutional neural network with a U‐Net architecture that automatically segments WMH, provides uncertainty estimates of the segmentation output for quality control, and is robust to changes in acquisition protocols. We also provide a second model to differentiate deep and periventricular WMH. Four hundred thirty‐two subjects were recruited to train the CNNs from four multisite imaging studies. A separate test set of 158 subjects was used for evaluation, including an unseen multisite study. We compared our model to two established state‐of‐the‐art techniques (BIANCA and DeepMedic), highlighting its accuracy and efficiency. Our Bayesian 3D U‐Net achieved the highest Dice similarity coefficient of 0.89 ± 0.08 and the lowest modified Hausdorff distance of 2.98 ± 4.40 mm. We further validated our models highlighting their robustness on “clinical adversarial cases” simulating data with low signal‐to‐noise ratio, low resolution, and different contrast (stemming from MRI sequences with different parameters). Our pipeline and models are available at: https://hypermapp3r.readthedocs.io.

Automatic quantification of white matter hyperintensities on T2-weighted fluid attenuated inversion recovery magnetic resonance imaging

White matter hyperintensities (WMH) are areas of increased signal visualized on T2-weighted fluid attenuated inversion recovery (FLAIR) brain magnetic resonance imaging (MRI) sequences. They are typically attributed to small vessel cerebrovascular disease in the context of aging. Among older adults, WMH are associated with risk of cognitive decline and dementia, stroke, and various other health outcomes. There has been increasing interest in incorporating quantitative WMH measurement as outcomes in clinical trials, observational research, and clinical settings. Here, we present a novel, fully automated, unsupervised detection algorithm for WMH segmentation and quantification. The algorithm uses a robust preprocessing pipeline, including brain extraction and a sample-specific mask that incorporates spatial information for automatic false positive reduction, and a half Gaussian mixture model (HGMM). The method was evaluated in 24 participants with varying degrees of WMH (4.9-78.6 cm³) from a community-based study of aging and dementia with dice coefficient, sensitivity, specificity, correlation, and bias relative to the ground truth manual segmentation approach performed by two expert raters. Results were compared with those derived from commonly used available WMH segmentation packages, including SPM lesion probability algorithm (LPA), SPM lesion growing algorithm (LGA), and Brain Intensity AbNormality Classification Algorithm (BIANCA). The HGMM algorithm derived WMH values that had a dice score of 0.87, sensitivity of 0.89, and specificity of 0.99 compared to ground truth. White matter hyperintensity volumes derived with HGMM were strongly correlated with ground truth values (r = 0.97, p = 3.9e-16), with no observable bias (-1.1 [-2.6, 0.44], p-value = 0.16). Our novel algorithm uniquely uses a robust preprocessing pipeline and a half-Gaussian mixture model to segment WMH with high agreement with ground truth for large scale studies of brain aging.

Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images

Robust automated segmentation of white matter hyperintensities (WMHs) in different datasets (domains) is highly challenging due to differences in acquisition (scanner, sequence), population (WMH amount and location) and limited availability of manual segmentations to train supervised algorithms. In this work we explore various domain adaptation techniques such as transfer learning and domain adversarial learning methods, including domain adversarial neural networks and domain unlearning, to improve the generalisability of our recently proposed triplanar ensemble network, which is our baseline model. We used datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For the source domain, we considered a dataset consisting of data acquired from 3 different scanners, while the target domain consisted of 2 datasets. We evaluated the domain adaptation techniques on the target domain datasets, and additionally evaluated the performance on the source domain test dataset for the adversarial techniques. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for fine-tuning in the target domain. On comparing the performance of different techniques on the target dataset, domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.

Ameliorative role of rolipram, PDE-4 inhibitor, against sodium arsenite-induced vascular dementia in rats

Arsenic exposure to the population leads to serious health problems like neurotoxicity, nephrotoxicity, and cardiovascular abnormality. In the present study, the work has been commenced to discover the prospect of rolipram a phosphodiestrase-4 (PDE-4) inhibitor against sodium arsenite (SA)-induced vascular endothelial dysfunction (EnDF) leading to dementia in rats. Wistar rats were treated with SA (5 mg/kg body weight/day orally) for 44 days for induction of vascular EnDF and dementia. Learning and memory were evaluated using Morris water maze (MWM) test. Vascular EnDF was evaluated using aortic ring preparation. Various biochemical parameters were also evaluated like brain oxidative stress (viz. reduced glutathione and thiobarbituric acid reactive substances level), serum nitrite/nitrate activity, acetylcholinesterase activity, and inflammatory markers (viz. neutrophil infiltration in brain and myeloperoxidase). SA-treated rats showed poor performance in water maze trials indicating attenuated memory and ability to learn with significant rise (p < 0.05) in brain acetylcholinesterase activity, brain oxidative stress, neutrophil count, and significant decrease (p < 0.05) in serum nitrite/nitrate levels and vascular endothelial functions. Rolipram (PDE-4 inhibitor) treatment (0.03 mg/kg and 0.06 mg/kg body weight, intraperitoneally daily for 14 days) significantly improved memory and learning abilities, and restored various biochemical parameters and EnDF. It is concluded that PDE-4 modulator may be considered the prospective target for the treatment of SA-induced vascular EnDF and related dementia.

Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images

White matter hyperintensities (WMHs) have been associated with various cerebrovascular and neurodegenerative diseases. Reliable quantification of WMHs is essential for understanding their clinical impact in normal and pathological populations. Automated segmentation of WMHs is highly challenging due to heterogeneity in WMH characteristics between deep and periventricular white matter, presence of artefacts and differences in the pathology and demographics of populations. In this work, we propose an ensemble triplanar network that combines the predictions from three different planes of brain MR images to provide an accurate WMH segmentation. In the loss functions the network uses anatomical information regarding WMH spatial distribution in loss functions, to improve the efficiency of segmentation and to overcome the contrast variations between deep and periventricular WMHs. We evaluated our method on 5 datasets, of which 3 are part of a publicly available dataset (training data for MICCAI WMH Segmentation Challenge 2017 - MWSC 2017) consisting of subjects from three different cohorts, and we also submitted our method to MWSC 2017 to be evaluated on the unseen test datasets. On evaluating our method separately in deep and periventricular regions, we observed robust and comparable performance in both regions. Our method performed better than most of the existing methods, including FSL BIANCA, and on par with the top ranking deep learning methods of MWSC 2017.

Synergistic associations of cognitive and motor impairments with functional outcome in covert cerebral small vessel disease

BACKGROUND

Cognitive and motor impairments are the key clinical manifestations of cerebral small vessel disease (SVD), but their combined effects on functional outcome have not been elucidated. This study investigated the interactions and mediating effects of cognitive and motor functions on instrumental activities of daily living (IADL) and quality of life in older individuals with various degrees of white matter hyperintensities (WMH).

METHODS

Participants of the Helsinki Small Vessel Disease Study (n = 152) were assessed according to an extensive clinical, physical, neuropsychological and MRI protocol. Volumes of WMH and gray matter (GM) were obtained with automated segmentation.

RESULTS

Cognitive (global cognition, executive functions, processing speed, memory) and motor functions (gait speed, single-leg stance, timed up-and-go) had strong interrelations with each other, and they were significantly associated with IADL, quality of life as well as WMH and GM volumes. A consistent pattern on significant interactions between cognitive and motor functions was found on informant-evaluated IADL, but not on self-evaluated quality of life. The association of WMH volume with IADL was mediated by global cognition, whereas the association of GM volume with IADL was mediated by global cognition and timed up-and-go performance.

CONCLUSION

The results highlight the complex interplay and synergism between motor and cognitive abilities on functional outcome in SVD. The combined effect of motor and cognitive disturbances on IADL is likely to be greater than their individual effects. Patients with both impairments are at disproportionate risk for poor outcome. WMH and brain atrophy contribute to disability through cognitive and motor impairment.

Associations of cognitive reserve and psychological resilience with cognitive functioning in subjects with cerebral white matter hyperintensities

BACKGROUND AND PURPOSE

Cerebral small vessel disease is characterized by progressive white matter hyperintensities (WMH) and cognitive decline. However, variability exists in how individuals maintain cognitive capabilities despite significant neuropathology. The relationships between individual cognitive reserve, psychological resilience and cognitive functioning were examined in subjects with varying degrees of WMH.

METHODS

In the Helsinki Small Vessel Disease Study, 152 subjects (aged 65-75 years) underwent a comprehensive neuropsychological assessment, evaluation of subjective cognitive complaints and brain magnetic resonance imaging with volumetric WMH evaluation. Cognitive reserve was determined by education (years) and the modified Cognitive Reserve Scale (mCRS). Psychological resilience was evaluated with the Resilience Scale 14.

RESULTS

The mCRS total score correlated significantly with years of education (r = 0.23, p < 0.01), but it was not related to age, sex or WMH volume. Together, mCRS score and education were associated with performance in a wide range of cognitive domains including processing speed, executive functions, working memory, verbal memory, visuospatial perception and verbal reasoning. Independently of education, the mCRS score had incremental predictive value on delayed verbal recall and subjective cognitive complaints. Psychological resilience was not significantly related to age, education, sex, WMH severity or cognitive test scores, but it was associated with subjective cognitive complaints.

CONCLUSIONS

Cognitive reserve has strong and consistent associations with cognitive functioning in subjects with WMH. Education is widely associated with objective cognitive functioning, whereas lifetime engagement in cognitively stimulating leisure activities (mCRS) has independent predictive value on memory performance and subjective cognitive complaints. Psychological resilience is strongly associated with subjective, but not objective, cognitive functioning.

Change in CAIDE Dementia Risk Score and Neuroimaging Biomarkers During a 2-Year Multidomain Lifestyle Randomized Controlled Trial: Results of a Post-Hoc Subgroup Analysis

The CAIDE (Cardiovascular Risk Factors, Aging and Dementia) Risk Score is a validated tool estimating dementia risk. It was previously associated with imaging biomarkers. However, associations between dementia risk scores (including CAIDE) and dementia-related biomarkers have not been studied in the context of an intervention. This study investigated associations between change in CAIDE score and change in neuroimaging biomarkers (brain magnetic resonance imaging [MRI] and Pittsburgh Compound B-positron emission tomography [PiB-PET] measures) during the 2-year Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) (post-hoc analyses). FINGER targeted at-risk older adults, aged 60–77 years, from the general population. Participants were randomized to either multidomain intervention (diet, exercise, cognitive training, and vascular risk management) or control group (general health advice). Neuroimaging (MRI and PiB-PET) data from baseline and 2-year visits were used. A toal of 112 participants had repeated brain MRI measures (hippocampal, total gray matter, and white matter lesion volumes, and Alzheimer’s disease signature cortical thickness). Repeated PiB-PET scans were available for 39 participants. Reduction in CAIDE score (indicating lower dementia risk) during the intervention was associated with less decline in hippocampus volume in the intervention group, but not the control group (Randomization group × CAIDE change interaction β coefficient = −0.40, p = .02). Associations for other neuroimaging measures were not significant. The intervention may have benefits on hippocampal volume in individuals who succeed in improving their overall risk level as indicated by a reduction in CAIDE score. This exploratory finding requires further testing and validation in larger studies.

Effects of White Matter Hyperintensities on Verbal Fluency in Healthy Older Adults and MCI/AD

BACKGROUND

White matter hyperintensities (WMHs) are markers for cerebrovascular pathology, which are frequently seen in patients with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Verbal fluency is often impaired especially in AD, but little research has been conducted concerning the specific effects of WMH on verbal fluency in MCI and AD.

OBJECTIVE

Our aim was to examine the relationship between WMH and verbal fluency in healthy old age and pathological aging (MCI/AD) using quantified MRI data.

METHODS

Measures for semantic and phonemic fluency as well as quantified MRI imaging data from a sample of 42 cognitively healthy older adults and 44 patients with MCI/AD (total n = 86) were utilized. Analyses were performed both using the total sample that contained seven left-handed/ambidextrous participants, as well with a sample containing only right-handed participants (n = 79) in order to guard against possible confounding effects regarding language lateralization.

RESULTS

After controlling for age and education and adjusting for multiple correction, WMH in the bilateral frontal and parieto-occipital areas as well as the right temporal area were associated with semantic fluency in cognitively healthy and MCI/AD patients but only in the models containing solely right-handed participants.

CONCLUSION

The results indicate that white matter pathology in both frontal and parieto-occipital cerebral areas may have associations with impaired semantic fluency in right-handed older adults. However, elevated levels of WMH do not seem to be associated with cumulative effects on verbal fluency impairment in patients with MCI or AD. Further studies on the subject are needed.

27-Hydroxycholesterol, cognition, and brain imaging markers in the FINGER randomized controlled trial

BACKGROUND

27-Hydroxycholesterol (27-OH), the main circulating oxysterol in humans and the potential missing link between peripheral hypercholesterolemia and Alzheimer's disease (AD), has not been investigated previously in relation to cognition and neuroimaging markers in the context of preventive interventions.

METHODS

The 2-year Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) included older individuals (60-77 years) at increased risk for dementia but without dementia or substantial cognitive impairment from the general population. Participants were randomized to a multidomain intervention (diet, exercise, cognitive training, and vascular risk management) or control group (general health advice) in a 1:1 ratio. Outcome assessors were masked to group allocation. This FINGER exploratory sub-study included 47 participants with measures of 27-OH, cognition, brain MRI, brain FDG-PET, and PiB-PET. Linear regression models were used to assess the cross-sectional and longitudinal associations between 27-OH, cognition, and neuroimaging markers, considering several potential confounders/intervention effect modifiers.

RESULTS

27-OH reduction during the intervention was associated with improvement in cognition (especially memory). This was not observed in the control group. The intervention reduced 27-OH particularly in individuals with the highest 27-OH levels and younger age. No associations were found between changes in 27-OH levels and neuroimaging markers. However, at baseline, a higher 27-OH was associated with lower total gray matter and hippocampal volume, and lower cognitive scores. These associations were unaffected by total cholesterol levels. While sex seemed to influence associations at baseline, it did not affect longitudinal associations.

CONCLUSION

27-OH appears to be a marker not only for dementia/AD risk, but also for monitoring the effects of preventive interventions on cholesterol metabolism.

TRIAL REGISTRATION

ClinicalTrials.gov , NCT01041989 . Registered on 4 January 2010.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Magnetic resonance imaging manifestations of cerebral small vessel disease: automated quantification and clinical application

The common cerebral small vessel disease (CSVD) neuroimaging features visible on conventional structural magnetic resonance imaging include recent small subcortical infarcts, lacunes, white matter hyperintensities, perivascular spaces, microbleeds, and brain atrophy. The CSVD neuroimaging features have shared and distinct clinical consequences, and the automatic quantification methods for these features are increasingly used in research and clinical settings. This review article explores the recent progress in CSVD neuroimaging feature quantification and provides an overview of the clinical consequences of these CSVD features as well as the possibilities of using these features as endpoints in clinical trials. The added value of CSVD neuroimaging quantification is also discussed for researches focused on the mechanism of CSVD and the prognosis in subjects with CSVD.

Cortical Thickness Estimation in Individuals With Cerebral Small Vessel Disease, Focal Atrophy, and Chronic Stroke Lesions

BACKGROUND

Regional changes to cortical thickness in individuals with neurodegenerative and cerebrovascular diseases (CVD) can be estimated using specialized neuroimaging software. However, the presence of cerebral small vessel disease, focal atrophy, and cortico-subcortical stroke lesions, pose significant challenges that increase the likelihood of misclassification errors and segmentation failures.

PURPOSE

The main goal of this study was to examine a correction procedure developed for enhancing FreeSurfer's (FS's) cortical thickness estimation tool, particularly when applied to the most challenging MRI obtained from participants with chronic stroke and CVD, with varying degrees of neurovascular lesions and brain atrophy.

METHODS

In 155 CVD participants enrolled in the Ontario Neurodegenerative Disease Research Initiative (ONDRI), FS outputs were compared between a fully automated, unmodified procedure and a corrected procedure that accounted for potential sources of error due to atrophy and neurovascular lesions. Quality control (QC) measures were obtained from both procedures. Association between cortical thickness and global cognitive status as assessed by the Montreal Cognitive Assessment (MoCA) score was also investigated from both procedures.

RESULTS

Corrected procedures increased "Acceptable" QC ratings from 18 to 76% for the cortical ribbon and from 38 to 92% for tissue segmentation. Corrected procedures reduced "Fail" ratings from 11 to 0% for the cortical ribbon and 62 to 8% for tissue segmentation. FS-based segmentation of T1-weighted white matter hypointensities were significantly greater in the corrected procedure (5.8 mL vs. 15.9 mL, p < 0.001). The unmodified procedure yielded no significant associations with global cognitive status, whereas the corrected procedure yielded positive associations between MoCA total score and clusters of cortical thickness in the left superior parietal (p = 0.018) and left insula (p = 0.04) regions. Further analyses with the corrected cortical thickness results and MoCA subscores showed a positive association between left superior parietal cortical thickness and Attention (p < 0.001).

CONCLUSION

These findings suggest that correction procedures which account for brain atrophy and neurovascular lesions can significantly improve FS's segmentation results and reduce failure rates, thus maximizing power by preventing the loss of our important study participants. Future work will examine relationships between cortical thickness, cerebral small vessel disease, and cognitive dysfunction due to neurodegenerative disease in the ONDRI study.

Accuracy and reproducibility of automated white matter hyperintensities segmentation with lesion segmentation tool: A European multi-site 3T study

Brain vascular damage accumulate in aging and often manifest as white matter hyperintensities (WMHs) on MRI. Despite increased interest in automated methods to segment WMHs, a gold standard has not been achieved and their longitudinal reproducibility has been poorly investigated. The aim of present work is to evaluate accuracy and reproducibility of two freely available segmentation algorithms. A harmonized MRI protocol was implemented in 3T-scanners across 13 European sites, each scanning five volunteers twice (test-retest) using 2D-FLAIR. Automated segmentation was performed using Lesion segmentation tool algorithms (LST): the Lesion growth algorithm (LGA) in SPM8 and 12 and the Lesion prediction algorithm (LPA). To assess reproducibility, we applied the LST longitudinal pipeline to the LGA and LPA outputs for both the test and retest scans. We evaluated volumetric and spatial accuracy comparing LGA and LPA with manual tracing, and for reproducibility the test versus retest. Median volume difference between automated WMH and manual segmentations (mL) was -0.22[IQR = 0.50] for LGA-SPM8, -0.12[0.57] for LGA-SPM12, -0.09[0.53] for LPA, while the spatial accuracy (Dice Coefficient) was 0.29[0.31], 0.33[0.26] and 0.41[0.23], respectively. The reproducibility analysis showed a median reproducibility error of 20%[IQR = 41] for LGA-SPM8, 14% [31] for LGA-SPM12 and 10% [27] with the LPA cross-sectional pipeline. Applying the LST longitudinal pipeline, the reproducibility errors were considerably reduced (LGA: 0%[IQR = 0], p < 0.001; LPA: 0% [3], p < 0.001) compared to those derived using the cross-sectional algorithms. The DC using the longitudinal pipeline was excellent (median = 1) for LGA [IQR = 0] and LPA [0.02]. LST algorithms showed moderate accuracy and good reproducibility. Therefore, it can be used as a reliable cross-sectional and longitudinal tool in multi-site studies.

Assessment of White Matter Integrity after Pediatric Traumatic Brain Injury

White matter (WM) abnormalities, such as atrophy and hyperintensities (WMH), can be accessed via magnetic resonance imaging (MRI) after pediatric traumatic brain injury (TBI). Several methods are available to classify WM abnormalities (i.e., total WM volumes and WMHs), but automated and manual volumes and clinical ratings have yet to be compared in pediatric TBI. In addition, WM integrity has been associated reliably with processing speed. Consequently, methods of assessing WM integrity should relate to processing speed to have clinical application. This study had two goals: (1) to compare Scheltens rating scale, manual tracing, FreeSurfer, and NeuroQuant® methods of assessing WM abnormalities, and (2) to relate WM methods to processing speed scores. We report findings from the Social Outcomes of Brain Injury in Kids (SOBIK) study, a multi-center study of 60 children with chronic TBI (65% male) from ages 8-13. Scheltens WMH ratings had good to excellent agreement with WMH volumes for both NeuroQuant (ICC = 0.62; r = 0.29, p = 0.005) and manual tracing (ICC = 0.82; r = 0.50, p = 0.000). NeuroQuant WMH volumes did not correlate with manually traced WMH volumes (r = 0.12, p = 0.21) and had poor agreement (ICC = 0.24). NeuroQuant and FreeSurfer total WM volumes correlated (r = 0.38, p = 0.004) and had fair agreement (ICC = 0.52). The WMH assessment methods, both ratings and volumes, were associated with processing speed scores. In contrast, total WM volume was not related to processing speed. Measures of WMH may hold clinical utility for predicting cognitive functioning after pediatric TBI.

White Matter Hyperintensities and Cognitive Impairment in Healthy and Pathological Aging: A Quantified Brain MRI Study

BACKGROUND

Brain changes involving the white matter (WM), often an indication of cerebrovascular pathology, are frequently seen in patients with mild cognitive impairment (MCI) and Alzheimer disease (AD). Few studies have examined possible cognitive domain- or group-specific cognitive effects of WM pathology in old age, MCI, and AD.

OBJECTIVE

Our purpose was to examine the relationship between WM hyperintensities (WMH), a typical marker for WM pathology, and cognitive functioning in healthy old age and pathological aging using quantified MRI data.

METHODS

We utilized multidomain neuropsychological data and quantified MRI data from a sample of 42 cognitively healthy older adults and 44 patients with MCI/AD (total n = 86).

RESULTS

After controlling for age and education, WMH in the temporal and parieto-occipital lobes was associated with impairments in processing speed and parieto-occipital pathology with verbal memory impairment in the whole sample. Additionally, temporal WMH was associated with impaired processing speed in the patient group specifically.

CONCLUSIONS

WM pathology is strongly associated with impaired processing speed, and our results indicate that these impairments arise from WMH in the temporal and parieto-occipital regions. In MCI and AD patients with temporal WMH, processing speed impairments are especially prominent. The results of this study increase our knowledge of cognitive repercussions stemming from temporal and/or parieto-occipital WM pathology in healthy and pathological aging.

Thalamic Atrophy Predicts 5-Year Disability Progression in Multiple Sclerosis

Purpose: Thalamus is among the first brain regions to become atrophic in multiple sclerosis (MS). We studied whether thalamic atrophy predicts disability progression at 5 years in a cohort of Finnish MS patients.

Methods: Global and regional brain volumes were measured from 24 newly diagnosed relapsing MS (RMS) patients 6 months after initiation of therapy and from 36 secondary progressive MS (SPMS) patients. The patients were divided into groups based on baseline whole brain parenchymal (BP) and thalamic atrophy. Standard scores (z scores) were computed by comparing individual brain volumes with healthy controls. A z score cutoff of −1.96 was applied to separate atrophic from normal brain volumes. The Expanded Disability Status Scale (EDSS), brain magnetic resonance imaging (MRI) findings, and relapses were assessed at baseline and at 2 years and EDSS progression at 5 years.

Results: Baseline thalamus volume predicted disability in 5 years in a logistic regression model (p = 0.031). At 5 years, EDSS was same or better in 12 of 18 patients with no brain atrophy at baseline but only in 5 of 18 patients with isolated thalamic atrophy [odds ratio (OR) (95% CI) = 5.2 (1.25, 21.57)]. The patients with isolated thalamic atrophy had more escalations of disease-modifying therapies during follow-up.

Conclusion: Patients with thalamic atrophy at baseline were at a higher risk for 5-year EDSS increase than patients with no identified brain atrophy. Brain volume measurement at a single time point could help predict disability progression in MS and complement clinical and routine MRI evaluation in therapeutic decision-making.

Automated White Matter Hyperintensity Segmentation Using Bayesian Model Selection: Assessment and Correlations with Cognitive Change

Accurate, automated white matter hyperintensity (WMH) segmentations are needed for large-scale studies to understand contributions of WMH to neurological diseases. We evaluated Bayesian Model Selection (BaMoS), a hierarchical fully-unsupervised model selection framework for WMH segmentation. We compared BaMoS segmentations to semi-automated segmentations, and assessed whether they predicted longitudinal cognitive change in control, early Mild Cognitive Impairment (EMCI), late Mild Cognitive Impairment (LMCI), subjective/significant memory concern (SMC) and Alzheimer's (AD) participants. Data were downloaded from the Alzheimer's disease Neuroimaging Initiative (ADNI). Magnetic resonance images from 30 control and 30 AD participants were selected to incorporate multiple scanners, and were semi-automatically segmented by 4 raters and BaMoS. Segmentations were assessed using volume correlation, Dice score, and other spatial metrics. Linear mixed-effect models were fitted to 180 control, 107 SMC, 320 EMCI, 171 LMCI and 151 AD participants separately in each group, with the outcomes being cognitive change (e.g. mini-mental state examination; MMSE), and BaMoS WMH, age, sex, race and education used as predictors. There was a high level of agreement between BaMoS' WMH segmentation volumes and a consensus of rater segmentations, with a median Dice score of 0.74 and correlation coefficient of 0.96. BaMoS WMH predicted cognitive change in: control, EMCI, and SMC groups using MMSE; LMCI using clinical dementia rating scale; and EMCI using Alzheimer's disease assessment scale-cognitive subscale (p < 0.05, all tests). BaMoS compares well to semi-automated segmentation, is robust to different WMH loads and scanners, and can generate volumes which predict decline. BaMoS can be applicable to further large-scale studies.

Evaluating 2-[18F]FDG-PET in differential diagnosis of dementia using a data-driven decision model

•

Addition of 2-[¹⁸F]FDG-PET to common diagnostic tests improved the accuracy for DLB and FTD.

•

Two new 2-[¹⁸F]FDG-PET biomarkers demonstrated specific disease patterns for DLB and FTD.

•

Different combinations of diagnostic tests were valuable for each subtype of dementia.

2-[¹⁸F]fluoro-2-deoxy-d-glucose positron emission tomography (2-[¹⁸F]FDG-PET) has an emerging supportive role in dementia diagnostic as distinctive metabolic patterns are specific for Alzheimer's disease (AD), dementia with Lewy bodies (DLB) and frontotemporal dementia (FTD). Previous studies have demonstrated that a data-driven decision model based on the disease state index (DSI) classifier supports clinicians in the differential diagnosis of dementia by using different combinations of diagnostic tests and biomarkers. Until now, this model has not included 2-[¹⁸F]FDG-PET data.

The objective of the study was to evaluate 2-[¹⁸F]FDG-PET biomarkers combined with commonly used diagnostic tests in the differential diagnosis of dementia using the DSI classifier.

We included data from 259 subjects diagnosed with AD, DLB, FTD, vascular dementia (VaD), and subjective cognitive decline from two independent study cohorts. We also evaluated three 2-[¹⁸F]FDG-PET biomarkers (anterior vs. posterior index (API-PET), occipital vs. temporal index, and cingulate island sign) to improve the classification accuracy for both FTD and DLB.

We found that the addition of 2-[¹⁸F]FDG-PET biomarkers to cognitive tests, CSF and MRI biomarkers considerably improved the classification accuracy for all pairwise comparisons of DLB (balanced accuracies: DLB vs. AD from 64% to 77%; DLB vs. FTD from 71% to 92%; and DLB vs. VaD from 71% to 84%). The two 2-[¹⁸F]FDG-PET biomarkers, API-PET and occipital vs. temporal index, improved the accuracy for FTD and DLB, especially as compared to AD. Moreover, different combinations of diagnostic tests were valuable to differentiate specific subtypes of dementia.

In conclusion, this study demonstrated that the addition of 2-[¹⁸F]FDG-PET to commonly used diagnostic tests provided complementary information that may help clinicians in diagnosing patients, particularly for differentiating between patients with FTD, DLB, and AD.

Selection of memory clinic patients for CSF biomarker assessment can be restricted to a quarter of cases by using computerized decision support, without compromising diagnostic accuracy

INTRODUCTION

An accurate and timely diagnosis for Alzheimer's disease (AD) is important, both for care and research. The current diagnostic criteria allow the use of CSF biomarkers to provide pathophysiological support for the diagnosis of AD. How these criteria should be operationalized by clinicians is unclear. Tools that guide in selecting patients in which CSF biomarkers have clinical utility are needed. We evaluated computerized decision support to select patients for CSF biomarker determination.

METHODS

We included 535 subjects (139 controls, 286 Alzheimer's disease dementia, 82 frontotemporal dementia and 28 vascular dementia) from three clinical cohorts. Positive (AD like) and negative (normal) CSF biomarker profiles were simulated to estimate whether knowledge of CSF biomarkers would impact (confidence in) diagnosis. We applied these simulated CSF values and combined them with demographic, neuropsychology and MRI data to initiate CSF testing (computerized decision support approach). We compared proportion of CSF measurements and patients diagnosed with sufficient confidence (probability of correct class ≥0.80) based on an algorithm with scenarios without CSF (only neuropsychology, MRI and APOE), CSF according to the appropriate use criteria (AUC) and CSF for all patients.

RESULTS

The computerized decision support approach recommended CSF testing in 140 (26%) patients, which yielded a diagnosis with sufficient confidence in 379 (71%) of all patients. This approach was more efficient than CSF in none (0% CSF, 308 (58%) diagnosed), CSF selected based on AUC (295 (55%) CSF, 350 (65%) diagnosed) or CSF in all (100% CSF, 348 (65%) diagnosed).

CONCLUSIONS

We used a computerized decision support with simulated CSF results in controls and patients with different types of dementia. This approach can support clinicians in making a balanced decision in ordering additional biomarker testing. Computer-supported prediction restricts CSF testing to only 26% of cases, without compromising diagnostic accuracy.

Brain volumes and cortical thickness on MRI in the Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER)

Background

The Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) was a multicenter randomized controlled trial that reported beneficial effects on cognition for a 2-year multimodal intervention (diet, exercise, cognitive training, vascular risk monitoring) versus control (general health advice). This study reports exploratory analyses of brain MRI measures.

Methods

FINGER targeted 1260 older individuals from the general Finnish population. Participants were 60–77 years old, at increased risk for dementia but without dementia/substantial cognitive impairment. Brain MRI scans were available for 132 participants (68 intervention, 64 control) at baseline and 112 participants (59 intervention, 53 control) at 2 years. MRI measures included regional brain volumes, cortical thickness, and white matter lesion (WML) volume. Cognition was assessed at baseline and 1- and 2-year visits using a comprehensive neuropsychological test battery. We investigated the (1) differences between the intervention and control groups in change in MRI outcomes (FreeSurfer 5.3) and (2) post hoc sub-group analyses of intervention effects on cognition in participants with more versus less pronounced structural brain changes at baseline (mixed-effects regression models, Stata 12).

Results

No significant differences between the intervention and control groups were found on the changes in MRI measures. Beneficial intervention effects on processing speed were more pronounced in individuals with higher baseline cortical thickness in Alzheimer’s disease signature areas (composite measure of entorhinal, inferior and middle temporal, and fusiform regions). The randomization group × time × cortical thickness interaction coefficient was 0.198 (p = 0.021). A similar trend was observed for higher hippocampal volume (group × time × hippocampus volume interaction coefficient 0.1149, p = 0.085).

Conclusions

The FINGER MRI exploratory sub-study did not show significant differences between the intervention and control groups on changes in regional brain volumes, regional cortical thicknesses, or WML volume after 2 years in at-risk elderly without substantial impairment. The cognitive benefits on processing speed of the FINGER intervention may be more pronounced in individuals with fewer structural brain changes on MRI at baseline. This suggests that preventive strategies may be more effective if started early, before the occurrence of more pronounced structural brain changes.

Trial registration

ClinicalTrials.gov, NCT01041989. Registered January 5, 2010.

Thalamic Atrophy Without Whole Brain Atrophy Is Associated With Absence of 2-Year NEDA in Multiple Sclerosis

Purpose: To study which brain volume measures best differentiate early relapsing MS (RMS) and secondary progressive MS (SPMS) patients and correlate with disability and cognition. To test whether isolated thalamic atrophy at study baseline correlates with NEDA (no evidence of disease activity) at 2 years.

Methods: Total and regional brain volumes were measured from 24 newly diagnosed RMS patients 6 months after initiation of therapy and 2 years thereafter, and in 36 SPMS patients. Volumes were measured by SIENAX and cNeuro. The patients were divided into subgroups based on whole brain parenchyma (BP) and thalamic atrophy at baseline. Standard scores (z-scores) were computed by comparing individual brain volumes against healthy controls. A z-score cut-off of −1.96 was applied to separate atrophic from normal brain volumes. The Expanded Disability Status Scale (EDSS) and Symbol Digit Modalities Test (SDMT) were assessed at baseline and at 2 years. Differences in achieving NEDA-3, NEDA-4, EDSS progression, and SDMT change were analyzed between patients with no thalamic or BP atrophy and in patients with isolated thalamic atrophy at baseline.

Results: At baseline, 7 SPMS and 12 RMS patients had no brain atrophy, 8 SPMS and 10 RMS patients had isolated thalamic atrophy and 2 RMS and 20 SPMS patients had both BP and thalamic atrophy. NEDA-3 was reached in 11/19 patients with no brain atrophy but only in 2/16 patients with isolated thalamic atrophy (p = 0.012). NEDA-4 was reached in 7/19 patients with no brain atrophy and in 1/16 of the patients with isolated thalamic atrophy (p = 0.047). At 2 years, EDSS was same or better in 16/19 patients with no brain atrophy but only in 5/17 patients with isolated thalamic atrophy (p = 0.002). There was no significant difference in the EDSS, relapses or SDMT between patients with isolated thalamic atrophy and no atrophy at baseline.

Conclusion: Patients with isolated thalamic atrophy were at a higher risk for not reaching 2-year NEDA-3 and for EDSS increase than patients with no identified brain atrophy. The groups were clinically indistinguishable. A single measurement of thalamic and whole brain atrophy could help identify patients needing most effective therapies from early on.

MRI-based evaluation of structural degeneration in the ageing brain: Pathophysiology and assessment

Advances in MRI technology have significantly contributed to our ability to understand the process of brain ageing, allowing us to track and assess changes that occur during normal ageing and neurological conditions. This paper focuses on reviewing structural changes of the ageing brain that are commonly seen using MRI, summarizing the pathophysiology, prevalence, and neuroanatomical distribution of changes including atrophy, lacunes, white matter lesions, and dilated perivascular spaces. We also review the clinically accessible methodology for assessing these MRI-based changes, covering visual rating scales, as well computer-aided and fully automated methods. Subsequently, we consider novel assessment methods designed to evaluate changes across the whole brain, and finally discuss new directions in this field of research.

Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network

BACKGROUND AND OBJECTIVE

White matter lesions are non-static brain lesions that have a prevalence rate up to 98% in the elderly population. Because they may be associated with several brain diseases, it is important that they are detected as soon as possible. Magnetic Resonance Imaging (MRI) provides three-dimensional data with the possibility to detect and emphasize contrast differences in soft tissues, providing rich information about the human soft tissue anatomy. However, the amount of data provided for these images is far too much for manual analysis/interpretation, representing a difficult and time-consuming task for specialists. This work presents a computational methodology capable of detecting regions of white matter lesions of the brain in MRI of FLAIR modality. The techniques highlighted in this methodology are SLIC0 clustering for candidate segmentation and convolutional neural networks for candidate classification.

METHODS

The methodology proposed here consists of four steps: (1) images acquisition, (2) images preprocessing, (3) candidates segmentation and (4) candidates classification.

RESULTS

The methodology was applied on 91 magnetic resonance images provided by DASA, and achieved an accuracy of 98.73%, specificity of 98.77% and sensitivity of 78.79% with 0.005 of false positives, without any false positives reduction technique, in detection of white matter lesion regions.

CONCLUSIONS

It is demonstrated the feasibility of the analysis of brain MRI using SLIC0 and convolutional neural network techniques to achieve success in detection of white matter lesions regions.

Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin

Lacunes of presumed vascular origin (lacunes) are associated with an increased risk of stroke, gait impairment, and dementia and are a primary imaging feature of the small vessel disease. Quantification of lacunes may be of great importance to elucidate the mechanisms behind neuro-degenerative disorders and is recommended as part of study standards for small vessel disease research. However, due to the different appearance of lacunes in various brain regions and the existence of other similar-looking structures, such as perivascular spaces, manual annotation is a difficult, elaborative and subjective task, which can potentially be greatly improved by reliable and consistent computer-aided detection (CAD) routines. In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN). We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.

Reproducibility and variability of quantitative magnetic resonance imaging markers in cerebral small vessel disease

Brain imaging is essential for the diagnosis and characterization of cerebral small vessel disease. Several magnetic resonance imaging markers have therefore emerged, providing new information on the diagnosis, progression, and mechanisms of small vessel disease. Yet, the reproducibility of these small vessel disease markers has received little attention despite being widely used in cross-sectional and longitudinal studies. This review focuses on the main small vessel disease-related markers on magnetic resonance imaging including: white matter hyperintensities, lacunes, dilated perivascular spaces, microbleeds, and brain volume. The aim is to summarize, for each marker, what is currently known about: (1) its reproducibility in studies with a scan-rescan procedure either in single or multicenter settings; (2) the acquisition-related sources of variability; and, (3) the techniques used to minimize this variability. Based on the results, we discuss technical and other challenges that need to be overcome in order for these markers to be reliably used as outcome measures in future clinical trials. We also highlight the key points that need to be considered when designing multicenter magnetic resonance imaging studies of small vessel disease.

BIANCA (Brain Intensity AbNormality Classification Algorithm): A new tool for automated segmentation of white matter hyperintensities

Reliable quantification of white matter hyperintensities of presumed vascular origin (WMHs) is increasingly needed, given the presence of these MRI findings in patients with several neurological and vascular disorders, as well as in elderly healthy subjects. We present BIANCA (Brain Intensity AbNormality Classification Algorithm), a fully automated, supervised method for WMH detection, based on the k-nearest neighbour (k-NN) algorithm. Relative to previous k-NN based segmentation methods, BIANCA offers different options for weighting the spatial information, local spatial intensity averaging, and different options for the choice of the number and location of the training points. BIANCA is multimodal and highly flexible so that the user can adapt the tool to their protocol and specific needs. We optimised and validated BIANCA on two datasets with different MRI protocols and patient populations (a "predominantly neurodegenerative" and a "predominantly vascular" cohort). BIANCA was first optimised on a subset of images for each dataset in terms of overlap and volumetric agreement with a manually segmented WMH mask. The correlation between the volumes extracted with BIANCA (using the optimised set of options), the volumes extracted from the manual masks and visual ratings showed that BIANCA is a valid alternative to manual segmentation. The optimised set of options was then applied to the whole cohorts and the resulting WMH volume estimates showed good correlations with visual ratings and with age. Finally, we performed a reproducibility test, to evaluate the robustness of BIANCA, and compared BIANCA performance against existing methods. Our findings suggest that BIANCA, which will be freely available as part of the FSL package, is a reliable method for automated WMH segmentation in large cross-sectional cohort studies.

Segmentation of perivascular spaces in 7T MR image using auto-context model with orientation-normalized features

Quantitative study of perivascular spaces (PVSs) in brain magnetic resonance (MR) images is important for understanding the brain lymphatic system and its relationship with neurological diseases. One of the major challenges is the accurate extraction of PVSs that have very thin tubular structures with various directions in three-dimensional (3D) MR images. In this paper, we propose a learning-based PVS segmentation method to address this challenge. Specifically, we first determine a region of interest (ROI) by using the anatomical brain structure and the vesselness information derived from eigenvalues of image derivatives. Then, in the ROI, we extract a number of randomized Haar features which are normalized with respect to the principal directions of the underlying image derivatives. The classifier is trained by the random forest model that can effectively learn both discriminative features and classifier parameters to maximize the information gain. Finally, a sequential learning strategy is used to further enforce various contextual patterns around the thin tubular structures into the classifier. For evaluation, we apply our proposed method to the 7T brain MR images scanned from 17 healthy subjects aged from 25 to 37. The performance is measured by voxel-wise segmentation accuracy, cluster-wise classification accuracy, and similarity of geometric properties, such as volume, length, and diameter distributions between the predicted and the true PVSs. Moreover, the accuracies are also evaluated on the simulation images with motion artifacts and lacunes to demonstrate the potential of our method in segmenting PVSs from elderly and patient populations. The experimental results show that our proposed method outperforms all existing PVS segmentation methods.

Differential diagnosis of neurodegenerative diseases using structural MRI data

Different neurodegenerative diseases can cause memory disorders and other cognitive impairments. The early detection and the stratification of patients according to the underlying disease are essential for an efficient approach to this healthcare challenge. This emphasizes the importance of differential diagnostics. Most studies compare patients and controls, or Alzheimer's disease with one other type of dementia. Such a bilateral comparison does not resemble clinical practice, where a clinician is faced with a number of different possible types of dementia.

Here we studied which features in structural magnetic resonance imaging (MRI) scans could best distinguish four types of dementia, Alzheimer's disease, frontotemporal dementia, vascular dementia, and dementia with Lewy bodies, and control subjects. We extracted an extensive set of features quantifying volumetric and morphometric characteristics from T1 images, and vascular characteristics from FLAIR images. Classification was performed using a multi-class classifier based on Disease State Index methodology. The classifier provided continuous probability indices for each disease to support clinical decision making.

A dataset of 504 individuals was used for evaluation. The cross-validated classification accuracy was 70.6% and balanced accuracy was 69.1% for the five disease groups using only automatically determined MRI features. Vascular dementia patients could be detected with high sensitivity (96%) using features from FLAIR images. Controls (sensitivity 82%) and Alzheimer's disease patients (sensitivity 74%) could be accurately classified using T1-based features, whereas the most difficult group was the dementia with Lewy bodies (sensitivity 32%). These results were notable better than the classification accuracies obtained with visual MRI ratings (accuracy 44.6%, balanced accuracy 51.6%). Different quantification methods provided complementary information, and consequently, the best results were obtained by utilizing several quantification methods.

The results prove that automatic quantification methods and computerized decision support methods are feasible for clinical practice and provide comprehensive information that may help clinicians in the diagnosis making.

•

Differential diagnostics of dementias was studied using structural MRI data.

•

504 patients with both T1 and FLAIR MRIs from five patient classes were evaluated.

•

Different fully automatic quantification methods were compared and combined.

•

Classification accuracy of 70.6% was obtained for 5-class classification problem.

•

Combination of several quantification methods was needed for optimal accuracy.

Automatic Detection of White Matter Hyperintensities in Healthy Aging and Pathology Using Magnetic Resonance Imaging: A Review

White matter hyperintensities (WMH) are commonly seen in the brain of healthy elderly subjects and patients with several neurological and vascular disorders. A truly reliable and fully automated method for quantitative assessment of WMH on magnetic resonance imaging (MRI) has not yet been identified. In this paper, we review and compare the large number of automated approaches proposed for segmentation of WMH in the elderly and in patients with vascular risk factors. We conclude that, in order to avoid artifacts and exclude the several sources of bias that may influence the analysis, an optimal method should comprise a careful preprocessing of the images, be based on multimodal, complementary data, take into account spatial information about the lesions and correct for false positives. All these features should not exclude computational leanness and adaptability to available data.

Bayesian model selection for pathological neuroimaging data applied to white matter lesion segmentation

In neuroimaging studies, pathologies can present themselves as abnormal intensity patterns. Thus, solutions for detecting abnormal intensities are currently under investigation. As each patient is unique, an unbiased and biologically plausible model of pathological data would have to be able to adapt to the subject's individual presentation. Such a model would provide the means for a better understanding of the underlying biological processes and improve one's ability to define pathologically meaningful imaging biomarkers. With this aim in mind, this work proposes a hierarchical fully unsupervised model selection framework for neuroimaging data which enables the distinction between different types of abnormal image patterns without pathological a priori knowledge. Its application on simulated and clinical data demonstrated the ability to detect abnormal intensity clusters, resulting in a competitive to improved behavior in white matter lesion segmentation when compared to three other freely-available automated methods.

Cortical thickness estimation in longitudinal stroke studies: A comparison of 3 measurement methods

There is considerable controversy about the causes of cognitive decline after stroke, with evidence for both the absence and coexistence of Alzheimer pathology. A reduction in cortical thickness has been shown to be an important biomarker for the progression of many neurodegenerative diseases, including Alzheimer's disease (AD). However, brain volume changes following stroke are not well described. Cortical thickness estimation presents an ideal way to detect regional and global post-stroke brain atrophy. In this study, we imaged a group of patients in the first month after stroke and at 3 months. We compared three methods of estimating cortical thickness on unmasked images: one surface-based (FreeSurfer) and two voxel-based methods (a Laplacian method and a registration method, DiRecT). We used three benchmarks for our analyses: accuracy of segmentation (especially peri-lesional performance), reproducibility, and biological validity. We found important differences between these methods in cortical thickness values and performance in high curvature areas and peri-lesional regions, but similar reproducibility metrics. FreeSurfer had less reliance on manual boundary correction than the other two methods, while reproducibility was highest in the Laplacian method. A discussion of the caveats for each method and recommendations for use in a stroke population is included. We conclude that both surface- and voxel-based methods are valid for estimating cortical thickness in stroke populations.

White matter hyperintensities segmentation: a new semi-automated method

White matter hyperintensities (WMH) are brain areas of increased signal on T2-weighted or fluid-attenuated inverse recovery magnetic resonance imaging (MRI) scans. In this study we present a new semi-automated method to measure WMH load that is based on the segmentation of the intensity histogram of fluid-attenuated inversion recovery images. Thirty patients with mild cognitive impairment with variable WMH load were enrolled. The semi-automated WMH segmentation included removal of non-brain tissue, spatial normalization, removal of cerebellum and brain stem, spatial filtering, thresholding to segment probable WMH, manual editing for correction of false positives and negatives, generation of WMH map, and volumetric estimation of the WMH load. Accuracy was quantitatively evaluated by comparing semi-automated and manual WMH segmentations performed by two independent raters. Differences between the two procedures were assessed using Student’s t-tests and similarity was evaluated using linear regression model and Dice similarity coefficient (DSC). The volumes of the manual and semi-automated segmentations did not statistically differ (t-value = -1.79, DF = 29, p = 0.839 for rater 1; t-value = 1.113, DF = 29, p = 0.2749 for rater 2), were highly correlated [R² = 0.921, F_(1,29) = 155.54, p < 0.0001 for rater 1; R² = 0.935, F_(1,29) = 402.709, p < 0.0001 for rater 2] and showed a very strong spatial similarity (mean DSC = 0.78, for rater 1 and 0.77 for rater 2). In conclusion, our semi-automated method to measure the load of WMH is highly reliable and could represent a good tool that could be easily implemented in routinely neuroimaging analyses to map clinical consequences of WMH.

Abnormalities of cortical thickness, subcortical shapes, and white matter integrity in subcortical vascular cognitive impairment

Subcortical vascular cognitive impairment (sVCI) is caused by lacunar infarcts or extensive and/or diffuse lesions in the white matter that may disrupt the white matter circuitry connecting cortical and subcortical regions and result in the degeneration of neurons in these regions. This study used structural magnetic resonance imaging (MRI) and high angular resolution diffusion imaging (HARDI) techniques to examine cortical thickness, subcortical shapes, and white matter integrity in mild vascular cognitive impairment no dementia (VCIND Mild) and moderate-to-severe VCI (MSVCI). Our study found that compared to controls (n = 25), VCIND Mild (n = 25), and MSVCI (n = 30) showed thinner cortex predominantly in the frontal cortex. The cortex in MSVCI was thinner in the parietal and lateral temporal cortices than that in VCIND Mild. Moreover, compared to controls, VCIND Mild and MSVCI showed smaller shapes (i.e., volume reduction) in the thalamus, putamen, and globus pallidus and ventricular enlargement. Finally, compared to controls, VCIND Mild, and MSVCI showed an increased mean diffusivity in the white matter, while decreased generalized fractional anisotropy was only found in the MSVCI subjects. The major axonal bundles involved in the white matter abnormalities were mainly toward the frontal regions, including the internal capsule/corona radiata, uncinate fasciculus, and anterior section of the inferior fronto-occipital fasciculus, and were anatomically connected to the affected cortical and subcortical structures. Our findings suggest that abnormalities in cortical, subcortical, and white matter morphology in sVCI occur in anatomically connected structures, and that abnormalities progress along a similar trajectory from the mild to moderate and severe conditions.

Longitudinal quantitative analysis of the tuber-to-brain proportion in patients with tuberous sclerosis

OBJECT

In patients with tuberous sclerosis complex (TSC), the tuber-to-brain proportion (TBP) is a marker of seizure severity and cognitive function. However, few studies have quantified the TBP. Furthermore, authors of these studies have measured the TBP at only a single time point, despite the fact that tuber cells were found to express proliferation markers, suggesting that they may be dynamic lesions. Authors of the present study used a semi-automated tuber segmentation program to determine whether the TBP changes over time.

METHODS

Axial FLAIR MR images were retrospectively identified for patients with TSC who had undergone imaging at the authors' institution between February 1998 and June 2009. Using FireVoxel software, the TBP was measured for each patient at a minimum interval of 2 years.

RESULTS

Twelve patients meeting the study inclusion criteria were identified. The mean TBP was 1.88% (range 0.38%-3.70%). Eight patients demonstrated minimal changes and 3 patients demonstrated small increases in TBP. The remaining patient exhibited a decrease of 1.00%, which correlated with a visible decrease in the size of 2 cerebellar lesions.

CONCLUSIONS

Semi-automated brain segmentation is a valuable tool in the longitudinal study of tubers. A subset of patients with TSC, particularly those with cerebellar lesions, may exhibit changes in the TBP over time.

Towards the automatic computational assessment of enlarged perivascular spaces on brain magnetic resonance images: a systematic review

Enlarged perivascular spaces (EPVS), visible in brain MRI, are an important marker of small vessel disease and neuroinflammation. We systematically evaluated the literature up to June 2012 on possible methods for their computational assessment and analyzed confounds with lacunes and small white matter hyperintensities. We found six studies that assessed/identified EPVS computationally by seven different methods, and four studies that described techniques to automatically segment similar structures and are potentially suitable for EPVS segmentation. T2-weighted MRI was the only sequence that identified all EPVS, but FLAIR and T1-weighted images were useful in their differentiation. Inconsistency within the literature regarding their diameter and terminology, and overlap in shape, intensity, location, and size with lacunes, conspires against their differentiation and the accuracy and reproducibility of any computational segmentation technique. The most promising approach will need to combine various MR sequences and consider all these features for accurate EPVS determination.

Automated detection of white matter signal abnormality using T2 relaxometry: application to brain segmentation on term MRI in very preterm infants

Hyperintense white matter signal abnormalities, also called diffuse excessive high signal intensity (DEHSI), are observed in up to 80% of very preterm infants on T2-weighted MRI scans at term-equivalent age. DEHSI may represent a developmental stage or diffuse microstructural white matter abnormalities. Automated quantitative assessment of DEHSI severity may help resolve this debate and improve neonatal brain tissue segmentation. For T2-weighted sequence without fluid attenuation, the signal intensity distribution of DEHSI greatly overlaps with that of cerebrospinal fluid (CSF) making its detection difficult. Furthermore, signal intensities of T2-weighted images are susceptible to magnetic field inhomogeneity. Increased signal intensities caused by field inhomogeneity may be confused with DEHSI. To overcome these challenges, we propose an algorithm to detect DEHSI using T2 relaxometry, whose reflection of the rapid changes in free water content provides improved distinction between CSF and DEHSI over that of conventional T2-weighted imaging. Moreover, the parametric transverse relaxation time T2 is invulnerable to magnetic field inhomogeneity. We conducted computer simulations to select an optimal detection parameter and to validate the proposed method. We also demonstrated that brain tissue segmentation is further enhanced by incorporating DEHSI detection for both simulated preterm infant brain images and in vivo in very preterm infants imaged at term-equivalent age.