Automatic segmentation of cerebral white matter hyperintensities using only 3D FLAIR images

Identifying sources of bias when testing three available algorithms for quantifying white matter lesions: BIANCA, LPA and LGA

Brain magnetic resonance imaging frequently reveals white matter lesions (WMLs) in older adults. They are often associated with cognitive impairment and risk of dementia. Given the continuous search for the optimal segmentation algorithm, we broke down this question by exploring whether the output of algorithms frequently used might be biased by the presence of different influencing factors. We studied the impact of age, sex, blood glucose levels, diabetes, systolic blood pressure and hypertension on automatic WML segmentation algorithms. We evaluated three widely used algorithms (BIANCA, LPA and LGA) using the population-based 1000BRAINS cohort (N = 1166, aged 18-87, 523 females, 643 males). We analysed two main aspects. Firstly, we examined whether training data (TD) characteristics influenced WML estimations, assessing the impact of relevant factors in the TD. Secondly, algorithm's output and performance within selected subgroups defined by these factors were assessed. Results revealed that BIANCA's WML estimations are influenced by the characteristics present in the TD. LPA and LGA consistently provided lower WML estimations compared to BIANCA's output when tested on participants under 67 years of age without risk cardiovascular factors. Notably, LPA and LGA showed reduced accuracy for these participants. However, LPA and LGA showed better performance for older participants presenting cardiovascular risk factors. Results suggest that incorporating comprehensive cohort factors like diverse age, sex and participants with and without hypertension in the TD could enhance WML-based analyses and mitigate potential sources of bias. LPA and LGA are a fast and valid option for older participants with cardiovascular risk factors.

Cocaine use is associated with cerebral white matter hyperintensities in HIV disease

BACKGROUND

White matter hyperintensities (WMH), a marker of cerebral small vessel disease and predictor of cognitive decline, are observed at higher rates in persons with HIV (PWH). The use of cocaine, a potent central nervous system stimulant, is disproportionately common in PWH and may contribute to WMH.

METHODS

The sample included of 110 PWH on antiretroviral therapy. Fluid-attenuated inversion recovery (FLAIR) and T1-weighted anatomical MRI scans were collected, along with neuropsychological testing. FLAIR images were processed using the Lesion Segmentation Toolbox. A hierarchical regression model was run to investigate predictors of WMH burden [block 1: demographics; block 2: cerebrovascular disease (CVD) risk; block 3: lesion burden].

RESULTS

The sample was 20% female and 79% African American with a mean age of 45.37. All participants had persistent HIV viral suppression, and the median CD4+ T-cell count was 750. Nearly a third (29%) currently used cocaine regularly, with an average of 23.75 (SD = 20.95) days in the past 90. In the hierarchical linear regression model, cocaine use was a significant predictor of WMH burden (β = .28). WMH burden was significantly correlated with poorer cognitive function (r = -0.27). Finally, higher WMH burden was significantly associated with increased serum concentrations of interferon-γ-inducible protein 10 (IP-10) but lower concentrations of myeloperoxidase (MPO); however, these markers did not differ by COC status.

CONCLUSIONS

WMH burden is associated with poorer cognitive performance in PWH. Cocaine use and CVD risk independently contribute to WMH, and addressing these conditions as part of HIV care may mitigate brain injury underlying neurocognitive impairment.

Segmenting white matter hyperintensities on isotropic three-dimensional Fluid Attenuated Inversion Recovery magnetic resonance images: Assessing deep learning tools on a Norwegian imaging database

An important step in the analysis of magnetic resonance imaging (MRI) data for neuroimaging is the automated segmentation of white matter hyperintensities (WMHs). Fluid Attenuated Inversion Recovery (FLAIR-weighted) is an MRI contrast that is particularly useful to visualize and quantify WMHs, a hallmark of cerebral small vessel disease and Alzheimer's disease (AD). In order to achieve high spatial resolution in each of the three voxel dimensions, clinical MRI protocols are evolving to a three-dimensional (3D) FLAIR-weighted acquisition. The current study details the deployment of deep learning tools to enable automated WMH segmentation and characterization from 3D FLAIR-weighted images acquired as part of a national AD imaging initiative. Based on data from the ongoing Norwegian Disease Dementia Initiation (DDI) multicenter study, two 3D models-one off-the-shelf from the NVIDIA nnU-Net framework and the other internally developed-were trained, validated, and tested. A third cutting-edge Deep Bayesian network model (HyperMapp3r) was implemented without any de-novo tuning to serve as a comparison architecture. The 2.5D in-house developed and 3D nnU-Net models were trained and validated in-house across five national collection sites among 441 participants from the DDI study, of whom 194 were men and whose average age was (64.91 +/- 9.32) years. Both an external dataset with 29 cases from a global collaborator and a held-out subset of the internal data from the 441 participants were used to test all three models. These test sets were evaluated independently. The ground truth human-in-the-loop segmentation was compared against five established WMH performance metrics. The 3D nnU-Net had the highest performance out of the three tested networks, outperforming both the internally developed 2.5D model and the SOTA Deep Bayesian network with an average dice similarity coefficient score of 0.76 +/- 0.16. Our findings demonstrate that WMH segmentation models can achieve high performance when trained exclusively on FLAIR input volumes that are 3D volumetric acquisitions. Single image input models are desirable for ease of deployment, as reflected in the current embedded clinical research project. The 3D nnU-Net had the highest performance, which suggests a way forward for our need to automate WMH segmentation while also evaluating performance metrics during on-going data collection and model retraining.

Automated Segmentation of Abnormal Tissues in Medical Images

Nowadays, medical image modalities are almost available everywhere. These modalities are bases of diagnosis of various diseases sensitive to specific tissue type. Usually physicians look for abnormalities in these modalities in diagnostic procedures. Count and volume of abnormalities are very important for optimal treatment of patients. Segmentation is a preliminary step for these measurements and also further analysis. Manual segmentation of abnormalities is cumbersome, error prone, and subjective. As a result, automated segmentation of abnormal tissue is a need. In this study, representative techniques for segmentation of abnormal tissues are reviewed. Main focus is on the segmentation of multiple sclerosis lesions, breast cancer masses, lung nodules, and skin lesions. As experimental results demonstrate, the methods based on deep learning techniques perform better than other methods that are usually based on handy feature engineering techniques. Finally, the most common measures to evaluate automated abnormal tissue segmentation methods are reported

Novel Automated Method for the Detection of White Matter Hyperintensities in Brain Multispectral MR Images

BACKGROUND

According to the Standards for Reporting Vascular Changes on Neuroimaging, White Matter Hyperintensities (WMHs) are cerebral white matter lesions that are characterized by abnormal tissues of variable sizes and appear hyperintense in T2-weighted Magnetic Resonance (MR) measurements without cavitation (i.e., their tissue signals differ from those of Cerebrospinal Fluid or CSF). Such abnormal tissue regions are typically observed in the MR images of brains of healthy older adults and are associated with a number of geriatric neurodegenerative diseases. Explanations of the exact causes and mechanisms of these diseases remain inconclusive. Moreover, WMHs are typically identified by visual assessment and manual examination, both of which require considerable time. This brings up a need of developing a method for detecting WMHs more objectively and enabling patients to be treated early. As a consequence, damages on nerve cells can be limited and the severity of patients' conditions can be contained.

AIMS

This paper presents a computer-aided technique for automatically detecting and segmenting anomalies in MR images.

METHODS

The method has two steps: (1) a Band Expansion Process (BEP) to expand the dimensions of brain MR images nonlinearly and (2) anomaly detection algorithms to detect WMHs. Synthesized MR images provided by BrainWeb were used as benchmarks against which the detection performance of the algorithms was determined.

RESULTS

The most notable findings are as follows: Firstly, compared with the other anomaly detection algorithms and the Lesion Segmentation Tool (LST), BEP-anomaly detection is shown to be the most effective in detecting WMHs. Secondly, across all levels of background noise and inhomogeneity, the mean Similarity Index (SI) produced by our proposed algorithm is higher than that produced by LST, indicating that the algorithm is more effective than LST in segmenting WMHs from brain MR images.

CONCLUSION

Experimental results demonstrated a significantly high accuracy of the BEP-K/R-RX method in detection of synthetic brain MS lesion data. In the meantime, it also effectively enhances the detection of brain lesions.

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.

FLAIR-only joint volumetric analysis of brain lesions and atrophy in clinically isolated syndrome (CIS) suggestive of multiple sclerosis

Background

MRI assessment in multiple sclerosis (MS) focuses on the presence of typical white matter (WM) lesions. Neurodegeneration characterised by brain atrophy is recognised in the research field as an important prognostic factor. It is not routinely reported clinically, in part due to difficulty in achieving reproducible measurements. Automated MRI quantification of WM lesions and brain volume could provide important clinical monitoring data. In general, lesion quantification relies on both T1 and FLAIR input images, while tissue volumetry relies on T1. However, T1-weighted scans are not routinely included in the clinical MS protocol, limiting the utility of automated quantification.

Objectives

We address an aspect of this important translational challenge by assessing the performance of FLAIR-only lesion and brain segmentation, against a conventional approach requiring multi-contrast acquisition. We explore whether FLAIR-only grey matter (GM) segmentation yields more variability in performance compared with two-channel segmentation; whether this is related to field strength; and whether the results meet a level of clinical acceptability demonstrated by the ability to reproduce established biological associations.

Methods

We used a multicentre dataset of subjects with a CIS suggestive of MS scanned at 1.5T and 3T in the same week. WM lesions were manually segmented by two raters, ‘manual 1′ guided by consensus reading of CIS-specific lesions and ‘manual 2′ by any WM hyperintensity. An existing brain segmentation method was adapted for FLAIR-only input. Automated segmentation of WM hyperintensity and brain volumes were performed with conventional (T1/T1 + FLAIR) and FLAIR-only methods.

Results

WM lesion volumes were comparable at 1.5T between ‘manual 2′ and FLAIR-only methods and at 3T between ‘manual 2′, T1 + FLAIR and FLAIR-only methods. For cortical GM volume, linear regression measures between conventional and FLAIR-only segmentation were high (1.5T: α = 1.029, R² = 0.997, standard error (SE) = 0.007; 3T: α = 1.019, R² = 0.998, SE = 0.006). Age-associated change in cortical GM volume was a significant covariate in both T1 (p = 0.001) and FLAIR-only (p = 0.005) methods, confirming the expected relationship between age and GM volume for FLAIR-only segmentations.

Conclusions

FLAIR-only automated segmentation of WM lesions and brain volumes were consistent with results obtained through conventional methods and had the ability to demonstrate biological effects in our study population. Imaging protocol harmonisation and validation with other MS phenotypes could facilitate the integration of automated WM lesion volume and brain atrophy analysis as clinical tools in radiological MS reporting.

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.

BISON: Brain tissue segmentation pipeline using T1 -weighted magnetic resonance images and a random forest classifier

PURPOSE

Tissue segmentation from T₁ -weighted (T1W) MRI is a critical requirement in many neuroscience and clinical applications. However, accurate tissue segmentation is challenging because of the variabilities in tissue intensity profiles caused by differences in scanner models, acquisition protocols, and age. In addition, many methods assume healthy anatomy and fail in the presence of pathology such as white matter hyperintensities (WMHs). We present BISON (Brain tISsue segmentatiON), a new pipeline for tissue segmentation using a random forest classifier and a set of intensity and location priors based on T1W MRI.

METHODS

BISON was developed and cross-validated using multiscanner manual labels of 72 subjects aged 5 to 96 years. We also assessed the test-retest reliability of BISON on two data sets: 20 subjects with scan/rescan MR images and manual segmentations and 90 scans from a single individual. The results were compared against Atropos, a state-of-the-art commonly used tissue classification method from advanced normalization tools (ANTs).

RESULTS

BISON cross-validation dice kappa values against manual segmentations of 72 MRI volumes yielded κ_GM = 0.88, κ_WM = 0.85, κ_CSF = 0.77, outperforming Atropos (κ_GM = 0.79, κ_WM = 0.84, κ_CSF = 0.64), test-retest values on 20 subjects of κ_GM = 0.94, κ_WM = 0.92, κ_CSF = 0.77 outperforming both manual (κ_GM = 0.92, κ_WM = 0.91, κ_CSF =0.74) and Atropos (κ_GM = 0.87, κ_WM = 0.92, κ_CSF = 0.79). Finally, BISON outperformed Atropos, FAST (fast automated segmentation tool) from the FMRIB (Functional Magnetic Resonance Imaging of the Brain) Software Library, and SPM12 (statistical parametric mapping 12) in the presence of WMHs.

CONCLUSION

BISON can provide accurate and robust segmentations in data from various age ranges and scanner models, making it ideal for performing tissue classification in large multicenter and multiscanner databases.

Are multi-contrast magnetic resonance images necessary for segmenting multiple sclerosis brains? A large cohort study based on deep learning

BACKGROUND

Magnetic resonance images with multiple contrasts or sequences are commonly used for segmenting brain tissues, including lesions, in multiple sclerosis (MS). However, acquisition of images with multiple contrasts increases the scan time and complexity of the analysis, possibly introducing factors that could compromise segmentation quality.

OBJECTIVE

To investigate the effect of various combinations of multi-contrast images as input on the segmented volumes of gray (GM) and white matter (WM), cerebrospinal fluid (CSF), and lesions using a deep neural network.

METHODS

U-net, a fully convolutional neural network was used to automatically segment GM, WM, CSF, and lesions in 1000 MS patients. The input to the network consisted of 15 combinations of FLAIR, T1-, T2-, and proton density-weighted images. The Dice similarity coefficient (DSC) was evaluated to assess the segmentation performance. For lesions, true positive rate (TPR) and false positive rate (FPR) were also evaluated. In addition, the effect of lesion size on lesion segmentation was investigated.

RESULTS

Highest DSC was observed for all the tissue volumes, including lesions, when the input was combination of all four image contrasts. All other input combinations that included FLAIR also provided high DSC for all tissue classes. However, the quality of lesion segmentation showed strong dependence on the input images. The DSC and TPR values for inputs with the four contrast combination and FLAIR alone were very similar, but FLAIR showed a moderately higher FPR for lesion size <100 μl. For lesions smaller than 20 μl all image combinations resulted in poor performance. The segmentation quality improved with lesion size.

CONCLUSIONS

Best performance for segmented tissue volumes was obtained with all four image contrasts as the input, and comparable performance was attainable with FLAIR only as the input, albeit with a moderate increase in FPR for small lesions. This implies that acquisition of only FLAIR images provides satisfactory tissue segmentation. Lesion segmentation was poor for very small lesions and improved rapidly with lesion size.

An improved algorithm of white matter hyperintensity detection in elderly adults

•

OASIS-AD is a method for automatic segmentation of white matter hyperintensities in older adults using structural brain MRIs.

•

OASIS-AD is an approach evolved from OASIS, which was developed for automatic lesion segmentation in multiple sclerosis.

•

OASIS-AD is a major refinement of OASIS that takes into account the specific challenges raised by white matter hyperintensities in Alzheimer’s disease.

•

OASIS-AD combines three processing steps: 1) using an eroding procedure on the skull stripped mask; 2) adding a nearest neighbor feature construction approach; and 3) applying a Gaussian filter to refine segmentation results creating a novel process for WMH detection in aging population .

•

OASIS-AD performs better than existing automatic white matter hyperintensity segmentation approaches.

Automated segmentation of the aging brain raises significant challenges because of the prevalence, extent, and heterogeneity of white matter hyperintensities. White matter hyperintensities can be frequently identified in magnetic resonance imaging (MRI) scans of older individuals and among those who have Alzheimer’s disease. We propose OASIS-AD, a method for automatic segmentation of white matter hyperintensities in older adults using structural brain MRIs. OASIS-AD is an approach evolved from OASIS, which was developed for automatic lesion segmentation in multiple sclerosis. OASIS-AD is a major refinement of OASIS that takes into account the specific challenges raised by white matter hyperintensities in Alzheimer’s disease. In particular, OASIS-AD combines three processing steps: 1) using an eroding procedure on the skull stripped mask; 2) adding a nearest neighbor feature construction approach; and 3) applying a Gaussian filter to refine segmentation results, creating a novel process for WMH detection in aging population. We show that OASIS-AD performs better than existing automatic white matter hyperintensity segmentation approaches.

Performance of five automated white matter hyperintensity segmentation methods in a multicenter dataset

White matter hyperintensities (WMHs) are a common manifestation of cerebral small vessel disease, that is increasingly studied with large, pooled multicenter datasets. This data pooling increases statistical power, but poses challenges for automated WMH segmentation. Although there is extensive literature on the evaluation of automated WMH segmentation methods, such evaluations in a multicenter setting are lacking. We performed WMH segmentations in sixty patients scanned on six different magnetic resonance imaging (MRI) scanners (10 patients per scanner) using five freely available and fully-automated WMH segmentation methods (Cascade, kNN-TTP, Lesion-TOADS, LST-LGA and LST-LPA). Different MRI scanner vendors and field strengths were included. We compared these automated WMH segmentations with manual WMH segmentations as a reference. Performance of each method both within and across scanners was assessed using spatial and volumetric correspondence with the reference segmentations by Dice's similarity coefficient (DSC) and intra-class correlation coefficient (ICC) respectively. We found the best performance, both within and across scanners, for kNN-TTP, followed by LST-LPA and LST-LGA, with worse performance for Lesion-TOADS and Cascade. Our findings can serve as a guide for choosing a method and also highlight the importance to further improve and evaluate consistency of methods in a multicenter setting.

Intra-Scanner and Inter-Scanner Reproducibility of Automatic White Matter Hyperintensities Quantification

Objectives: To evaluate white matter hyperintensities (WMH) quantification reproducibility from multiple aspects of view and examine the effects of scan-rescan procedure, types of scanner, imaging protocols, scanner software upgrade, and automatic segmentation tools on WMH quantification results using magnetic resonance imaging (MRI). Methods: Six post-stroke subjects (4 males; mean age = 62.8, range = 58-72 years) were scanned and rescanned with both 3D T1-weighted, 2D and 3D T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) MRI across four different MRI scanners within 12 h. Two automated WMH segmentation and quantification tools were used to measure WMH volume based on each MR scan. Robustness was assessed using the coefficient of variation (CV), Dice similarity coefficient (DSC), and intra-class correlation (ICC). Results: Experimental results show that the best reproducibility was achieved by using 3D T2-FLAIR MRI under intra-scanner setting with CV ranging from 2.69 to 2.97%, while the largest variability resulted from comparing WMH volumes measured based on 2D T2-FLAIR MRI with those of 3D T2-FLAIR MRI, with CV values in the range of 15.62%-29.33%. The WMH quantification variability based on 2D MRIs is larger than 3D MRIs due to their large slice thickness. The DSC of WMH segmentation labels between intra-scanner MRIs ranges from 0.63 to 0.77, while that for inter-scanner MRIs is in the range of 0.63-0.65. In addition to image acquisition, the choice of automatic WMH segmentation tool also has a large impact on WMH quantification. Conclusion: WMH reproducibility is one of the primary issues to be considered in multicenter and longitudinal studies. The study provides solid guidance in assisting multicenter and longitudinal study design to achieve meaningful results with enough power.

The efficiency of the brain connectome is associated with cerebrovascular reactivity in persons with white matter hyperintensities

The purpose of this study was to determine the relationship between the organization of the brain connectome and cerebrovascular reactivity (CVR) in persons with white matter hyperintensities. Diffusion tensor and CVR mapping 3T MRI scans were acquired in 31 participants with white matter hyperintensities. In each participant, the connectome was assessed by reconstructing all white matter tracts with tractography and segmenting the whole brain into multiple regions. Graph theory analysis was performed to quantify how effectively tracts connected brain regions by measuring the global and local efficiency of the connectome. CVR in white matter and gray matter was correlated with the global and local efficiency of the connectome, while adjusting for age, gender, and gray matter volume. For comparison, white matter hyperintensity volume was also correlated with global and local efficiency. White matter CVR was positively correlated with the global efficiency (coefficient: 23.3, p = .005) and local efficiency (coefficient: 2850, p = .004) of the connectome. Gray matter CVR was positively correlated with the global efficiency (coefficient: 21.3, p < .001) and local efficiency (coefficient: 2670, p < .001) of the connectome. White matter hyperintensity volume was negatively correlated with global efficiency (coefficient: -0.0002, p = .003) and local efficiency (coefficient: -0.024, p = .003) of the connectome. The association between CVR and the brain connectome suggests that impaired cerebrovascular function may be part of the pathophysiology of the disruption of the brain connectome in persons with white matter hyperintensities.

Multi-atlas based detection and localization (MADL) for location-dependent quantification of white matter hyperintensities

The extent and spatial location of white matter hyperintensities (WMH) on brain MRI may be relevant to the development of cognitive decline in older persons. Here, we introduce a new method, known as the Multi-atlas based Detection and Localization (MADL), to evaluate WMH on fluid-attenuated inversion recovery (FLAIR) data. This method simultaneously parcellates the whole brain into 143 structures and labels hyperintense areas within each WM structure. First, a multi-atlas library was established with FLAIR data of normal elderly brains; and then a multi-atlas fusion algorithm was developed by which voxels with locally abnormal intensities were detected as WMH. At the same time, brain segmentation maps were generated from the multi-atlas fusion process to determine the anatomical location of WMH. Areas identified using the MADL method agreed well with manual delineation, with an interclass correlation of 0.97 and similarity index (SI) between 0.55 and 0.72, depending on the total WMH load. Performance was compared to other state-of-the-art WMH detection methods, such as BIANCA and LST. MADL-based analyses of WMH in an older population revealed a significant association between age and WMH load in deep WM but not subcortical WM. The findings also suggested increased WMH load in selective brain regions in subjects with mild cognitive impairment compared to controls, including the inferior deep WM and occipital subcortical WM. The proposed MADL approach may facilitate location-dependent characterization of WMH in older individuals with memory impairment.

•

We proposed a multi-atlas based method for simultaneous detection and location of WMH on FLAIR images.

•

The method generates whole-brain segmentation for location-dependent WMH analysis.

•

The method showed reasonably high detection accuracy in comparison with other methods.

•

Results revealed a selective association between deep brain WMH and subject age.

•

Results suggested increased WMH in the inferior white matter in MCI patients.

Impact of white matter hyperintensities on surrounding white matter tracts

PURPOSE

It is unclear how white matter hyperintensities disrupt surrounding white matter tracts. The aim of this tractography study was to determine the spatial relationship between diffusion characteristics along white matter tracts and the distance from white matter hyperintensities.

METHODS

Diffusion tensor 3-T MRI scans were acquired in 29 participants with white matter hyperintensities. In each subject, tractography by the fiber assignment by continuous tracking method was used to segment corticospinal tracts. Mean diffusivity, radial diffusivity, axial diffusivity, and fractional anisotropy were measured along corticospinal tracts in relation to white matter hyperintensities. Diffusion characteristics along tracts were correlated with distance from white matter hyperintensities and were also compared between tracts traversing and not traversing white matter hyperintensities.

RESULTS

In tracts not traversing through white matter hyperintensities, increasing distance from white matter hyperintensities was associated with decreased mean diffusivity (p = 0.002) and increased fractional anisotropy (p = 0.006). In tracts traversing white matter hyperintensities, compared to tracts not traversing white matter hyperintensites, the mean diffusivity was higher at 6-8 voxels, axial diffusivity higher at 4-8 voxels, and radial diffusivity higher at 7 voxels away from white matter hyperintensities (all p < 0.006).

CONCLUSION

White matter hyperintensities are associated with two patterns of altered diffusion characteristics in the surrounding white matter tract network. Diffusion characteristics along white matter tracts improve further away from white matter hyperintensities suggestive of a local penumbra pattern. Also, altered diffusion extends further along tracts traversing white matter hyperintensities suggestive of a Wallerian-type degenerative pattern.

Validation of T1w-based segmentations of white matter hyperintensity volumes in large-scale datasets of aging

INTRODUCTION

Fluid-attenuated Inversion Recovery (FLAIR) and dual T2w and proton density (PD) magnetic resonance images (MRIs) are considered to be the optimum sequences for detecting white matter hyperintensities (WMHs) in aging and Alzheimer's disease populations. However, many existing large multisite studies forgo their acquisition in favor of other MRI sequences due to economic and time constraints.

METHODS

In this article, we have investigated whether FLAIR and T2w/PD sequences are necessary to detect WMHs in Alzheimer's and aging studies, compared to using only T1w images. Using a previously validated automated tool based on a Random Forests classifier, WMHs were segmented for the baseline visits of subjects from ADC, ADNI1, and ADNI2/GO studies with and without T2w/PD and FLAIR information. The obtained WMH loads (WMHLs) in different lobes were then correlated with manually segmented WMHLs, each other, age, cognitive, and clinical measures to assess the strength of the correlations with and without using T2w/PD and FLAIR information.

RESULTS

The WMHLs obtained from T1w-Only segmentations correlated with the manual WMHLs (ADNI1: r = .743, p < .001, ADNI2/GO: r = .904, p < .001), segmentations obtained from T1w + T2w + PD for ADNI1 (r = .888, p < .001) and T1w + FLAIR for ADNI2/GO (r = .969, p < .001), age (ADNI1: r = .391, p < .001, ADNI2/GO: r = .466, p < .001), and ADAS13 (ADNI1: r = .227, p < .001, ADNI2/GO: r = .190, p < 0.001), and NPI (ADNI1: r = .290, p < .001, ADNI2/GO: r = 0.144, p < .001), controlling for age.

CONCLUSION

Our results suggest that while T2w/PD and FLAIR provide more accurate estimates of the true WMHLs, T1w-Only segmentations can still provide estimates that hold strong correlations with the actual WMHLs, age, and performance on various cognitive/clinical scales, giving added value to datasets where T2w/PD or FLAIR are not available.

Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer's Disease

Segmentation and volumetric quantification of white matter hyperintensities (WMHs) is essential in assessment and monitoring of the vascular burden in aging and Alzheimer's disease (AD), especially when considering their effect on cognition. Manually segmenting WMHs in large cohorts is technically unfeasible due to time and accuracy concerns. Automated tools that can detect WMHs robustly and with high accuracy are needed. Here, we present and validate a fully automatic technique for segmentation and volumetric quantification of WMHs in aging and AD. The proposed technique combines intensity and location features frommultiplemagnetic resonance imaging contrasts and manually labeled training data with a linear classifier to perform fast and robust segmentations. It provides both a continuous subject specific WMH map reflecting different levels of tissue damage and binary segmentations. Themethodwas used to detectWMHs in 80 elderly/AD brains (ADC data set) as well as 40 healthy subjects at risk of AD (PREVENT-AD data set). Robustness across different scanners was validated using ten subjects from ADNI2/GO study. Voxel-wise and volumetric agreements were evaluated using Dice similarity index (SI) and intra-class correlation (ICC), yielding ICC=0.96 , SI = 0.62±0.16 for ADC data set and ICC=0.78 , SI=0.51±0.15 for PREVENT-AD data set. The proposed method was robust in the independent sample yielding SI=0.64±0.17 with ICC=0.93 for ADNI2/GO subjects. The proposed method provides fast, accurate, and robust segmentations on previously unseen data from different models of scanners, making it ideal to study WMHs in large scale multi-site studies.

Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

Performance comparison of 10 different classification techniques in segmenting white matter hyperintensities in aging

INTRODUCTION

White matter hyperintensities (WMHs) are areas of abnormal signal on magnetic resonance images (MRIs) that characterize various types of histopathological lesions. The load and location of WMHs are important clinical measures that may indicate the presence of small vessel disease in aging and Alzheimer's disease (AD) patients. Manually segmenting WMHs is time consuming and prone to inter-rater and intra-rater variabilities. Automated tools that can accurately and robustly detect these lesions can be used to measure the vascular burden in individuals with AD or the elderly population in general. Many WMH segmentation techniques use a classifier in combination with a set of intensity and location features to segment WMHs, however, the optimal choice of classifier is unknown.

METHODS

We compare 10 different linear and nonlinear classification techniques to identify WMHs from MRI data. Each classifier is trained and optimized based on a set of features obtained from co-registered MR images containing spatial location and intensity information. We further assess the performance of the classifiers using different combinations of MRI contrast information. The performances of the different classifiers were compared on three heterogeneous multi-site datasets, including images acquired with different scanners and different scan-parameters. These included data from the ADC study from University of California Davis, the NACC database and the ADNI study. The classifiers (naïve Bayes, logistic regression, decision trees, random forests, support vector machines, k-nearest neighbors, bagging, and boosting) were evaluated using a variety of voxel-wise and volumetric similarity measures such as Dice Kappa similarity index (SI), Intra-Class Correlation (ICC), and sensitivity as well as computational burden and processing times. These investigations enable meaningful comparisons between the performances of different classifiers to determine the most suitable classifiers for segmentation of WMHs. In the spirit of open-source science, we also make available a fully automated tool for segmentation of WMHs with pre-trained classifiers for all these techniques.

RESULTS

Random Forests yielded the best performance among all classifiers with mean Dice Kappa (SI) of 0.66±0.17 and ICC=0.99 for the ADC dataset (using T1w, T2w, PD, and FLAIR scans), SI=0.72±0.10, ICC=0.93 for the NACC dataset (using T1w and FLAIR scans), SI=0.66±0.23, ICC=0.94 for ADNI1 dataset (using T1w, T2w, and PD scans) and SI=0.72±0.19, ICC=0.96 for ADNI2/GO dataset (using T1w and FLAIR scans). Not using the T2w/PD information did not change the performance of the Random Forest classifier (SI=0.66±0.17, ICC=0.99). However, not using FLAIR information in the ADC dataset significantly decreased the Dice Kappa, but the volumetric correlation did not drastically change (SI=0.47±0.21, ICC=0.95).

CONCLUSION

Our investigations showed that with appropriate features, most off-the-shelf classifiers are able to accurately detect WMHs in presence of FLAIR scan information, while Random Forests had the best performance across all datasets. However, we observed that the performances of most linear classifiers and some nonlinear classifiers drastically decline in absence of FLAIR information, with Random Forest still retaining the best performance.

Correlating quantitative tractography at 3T MRI and cognitive tests in healthy older adults

This study used diffusion tensor imaging tractography at 3 T MRI to relate cognitive function to white matter tracts in the brain. Brain T2 fluid attenuated inversion recovery-weighted and diffusion tensor 3 T MRI scans were acquired in thirty-three healthy participants without mild cognitive impairment or dementia. They completed a battery of neuropsychological tests including the Montreal Cognitive Assessment, Stroop test, Trail Making Test B, Wechsler Memory Scale-III Longest span forward, Wechsler Memory Scale-III Longest span backward, Mattis Dementia Rating Scale, California Verbal Learning Test Version II Long Delay Free Recall, and Letter Number Sequencing. Tractography was generated by the Fiber Assignment by Continuous Tracking method. The corpus callosum, cingulum, long association fibers, corticospinal/bulbar tracts, thalamic projection fibers, superior cerebellar peduncle, middle cerebellar peduncle and inferior cerebellar peduncle were manually segmented. The fractional anisotropy (FA) and mean diffusivity (MD) of these tracts were quantified. We studied the association between cognitive test scores and the MD and FA of tracts while controlling for age and total white matter hyperintensities volume. Worse scores on the Stroop test was associated with decreased FA of the corpus callosum, corticospinal/bulbar tract, and thalamic projection tracts. Scores on the other cognitive tests were not associated with either the FA or MD of measured tracts. In healthy persons the Stroop test appears to be a better predictor of the microstructural integrity of white matter tracts measured by DTI tractography than other cognitive tests.

Tractography at 3T MRI of Corpus Callosum Tracts Crossing White Matter Hyperintensities

BACKGROUND AND PURPOSE

The impact of white matter hyperintensities on the diffusion characteristics of crossing tracts is unclear. This study used quantitative tractography at 3T MR imaging to compare, in the same individuals, the diffusion characteristics of corpus callosum tracts that crossed white matter hyperintensities with the diffusion characteristics of corpus callosum tracts that did not pass through white matter hyperintensities.

MATERIALS AND METHODS

Brain T2 fluid-attenuated inversion recovery-weighted and diffusion tensor 3T MR imaging scans were acquired in 24 individuals with white matter hyperintensities. Tractography data were generated by the Fiber Assignment by Continuous Tracking method. White matter hyperintensities and corpus callosum tracts were manually segmented. In the corpus callosum, the fractional anisotropy, radial diffusivity, and mean diffusivity of tracts crossing white matter hyperintensities were compared with the fractional anisotropy, radial diffusivity, and mean diffusivity of tracts that did not cross white matter hyperintensities. The cingulum, long association fibers, corticospinal/bulbar tracts, and thalamic projection fibers were included for comparison.

RESULTS

Within the corpus callosum, tracts that crossed white matter hyperintensities had decreased fractional anisotropy compared with tracts that did not pass through white matter hyperintensities (P = .002). Within the cingulum, tracts that crossed white matter hyperintensities had increased radial diffusivity compared with tracts that did not pass through white matter hyperintensities (P = .001).

CONCLUSIONS

In the corpus callosum and cingulum, tracts had worse diffusion characteristics when they crossed white matter hyperintensities. These results support a role for white matter hyperintensities in the disruption of crossing tracts.

Correlation of 3D FLAIR and Dopamine Transporter Imaging in Patients With Parkinsonism

OBJECTIVE

The purpose of this study is to evaluate direct in vivo visualization of nigrosome-1 in substantia nigra (SN) with 3D FLAIR imaging and its diagnostic value in predicting the intactness of presynaptic dopaminergic function of the nigrostriatal pathway.

MATERIALS AND METHODS

Forty-five patients showing parkinsonism who underwent both 3D FLAIR and dopamine transporter (DAT) imaging were recruited. In total, 90 SNs were reviewed on axial 3D FLAIR images. We regarded oval or linear hyperintensities on the posterolateral side of SN as intact nigrosome-1. Two neuroradiologists independently evaluated the appearance of nigrosome-1, and disagreements were settled by consensus. Kappa values for interrater agreement were calculated. Diagnostic performances of the appearance of nigrosome-1 for predicting presynaptic dopaminergic function on DAT imaging and Parkinson disease (PD) were calculated.

RESULTS

The diagnostic performances of a loss of nigrosome-1 on 3D FLAIR images were sensitivity of 85.7%, specificity of 85.4%, positive predictive value (PPV) of 83.7%, and negative predictive value (NPV) of 87.2% for predicting impaired presynaptic dopaminergic function on DAT imaging, and sensitivity of 94.7%, specificity of 76.9%, PPV of 85.7%, and NPV of 90.9% for predicting PD. When only oval hyperintensity was considered as intact nigrosome-1, its sensitivity and NPV were increased up to 95.2% and 91.7%, respectively, for predicting impaired presynaptic dopaminergic function on DAT imaging, and both increased to 100% for predicting PD. Interobserver agreement for the appearance of nigrosome-1 on 3D FLAIR images was substantial (κ = 0.625).

CONCLUSION

Nigrosome-1 could be visualized on 3D FLAIR images, and its loss can be used to predict presynaptic dopaminergic function and to diagnose PD with high accuracy.

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.

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.

Cognitive Function and 3-Tesla Magnetic Resonance Imaging Tractography of White Matter Hyperintensities in Elderly Persons

BACKGROUND/AIMS

This study used 3-Tesla magnetic resonance imaging (MRI) tractography to determine if there was an association between tracts crossing white matter hyperintensities (WMH) and cognitive function in elderly persons.

METHODS

Brain T2-weighted fluid-attenuated inversion recovery (FLAIR) and diffusion tensor MRI scans were acquired in participants above the age of 60 years. Twenty-six persons had WMH identified on T2 FLAIR scans. They completed a battery of neuropsychological tests and were classified as normal controls (n = 15) or with Alzheimer's dementia (n = 11). Tractography was generated by the Fiber Assignment by Continuous Tracking method. All tracts that crossed WMH were segmented. The average fractional anisotropy and average mean diffusivity of these tracts were quantified. We studied the association between cognitive test scores with the average mean diffusivity and average fractional anisotropy of tracts while controlling for age, total WMH volume and diagnosis.

RESULTS

An increased mean diffusivity of tracts crossing WMH was associated with worse performance on the Wechsler Memory Scale-III Longest Span Forward (p = 0.02). There was no association between the fractional anisotropy of tracts and performance on cognitive testing.

CONCLUSION

The mean diffusivity of tracts crossing WMH measured by tractography is a novel correlate of performance on the Wechsler Memory Scale-III Longest Span Forward in elderly persons.

The Technical and Clinical Features of 3D-FLAIR in Neuroimaging

In clinical MR neuroimaging, 3D fluid-attenuated inversion recovery (3D-FLAIR) with a variable-flip-angle turbo spin echo sequence is becoming popular. There are more than 100 reports regarding 3D-FLAIR in the PubMed database. In this article, the technical and clinical features of 3D-FLAIR for neuroimaging are reviewed and summarized. 3D-FLAIR allows thinner slices with multi-planar reformation capability, a higher flow sensitivity, high sensitivity to subtle T1 changes in fluid, images without cerebrospinal fluid (CSF) inflow artifacts, and a 3D dataset compatible with computer-aided analysis. In addition, 3D-FLAIR can be obtained within a clinically reasonable scan time. It is important for radiologists to be familiar with the features of 3D-FLAIR and to provide useful information for patients.

Automatic segmentation and volumetric quantification of white matter hyperintensities on fluid-attenuated inversion recovery images using the extreme value distribution

INTRODUCTION

This study aims to develop an automatic segmentation framework on the basis of extreme value distribution (EVD) for the detection and volumetric quantification of white matter hyperintensities (WMHs) on fluid-attenuated inversion recovery (FLAIR) images.

METHODS

Two EVD-based segmentation methods, namely the Gumbel and Fréchet segmentation, were developed to detect WMHs on FLAIR (slice thickness = 5 mm; TR/TE/TI = 11,000/120/2,800 ms; flip angle = 90°) images. Another automatic segmentation method using a trimmed likelihood estimator (TLE) was implemented for comparison with our proposed segmentation framework. The performances of the three automatic segmentation methods were evaluated by comparing with the manual segmentation method.

RESULTS

The Dice similarity coefficients (DSCs) of the two EVD-based segmentation methods were larger than those of the TLE-based segmentation method (Gumbel, 0.823 ± 0.063; Fréchet, 0.843 ± 0.057; TLE, 0.817 ± 0.068), demonstrating that the EVD-based segmentation outperformed the TLE-based segmentation. The Fréchet segmentation obtained larger DSCs on patients with moderate to severe lesion loads and a comparable performance on patients with mild lesion loads, indicating that the Fréchet segmentation was superior to the Gumbel segmentation. The Gumbel segmentation underestimated the lesion volumes of all patients, whereas the Fréchet and TLE-based segmentation methods obtained overestimated lesion volumes (Manual, 13.71 ± 14.02 cc; Gumbel, 12.73 ± 13.21 cc; Fréchet, 13.88 ± 13.96 cc; TLE, 13.54 ± 12.27 cc). Moreover, the EVD-based segmentation was demonstrated to be comparable to other state-of-the-art methods on a publicly available dataset.

CONCLUSION

The proposed EVD-based segmentation framework is a promising, effective, and convenient tool for volumetric quantification and further study of WMHs in aging and dementia.

Automated White Matter Hyperintensity Detection in Multiple Sclerosis Using 3D T2 FLAIR

White matter hyperintensities (WMH) seen on T2WI are a hallmark of multiple sclerosis (MS) as it indicates inflammation associated with the disease. Automatic detection of the WMH can be valuable in diagnosing and monitoring of treatment effectiveness. T2 fluid attenuated inversion recovery (FLAIR) MR images provided good contrast between the lesions and other tissue; however the signal intensity of gray matter tissue was close to the lesions in FLAIR images that may cause more false positives in the segment result. We developed and evaluated a tool for automated WMH detection only using high resolution 3D T2 fluid attenuated inversion recovery (FLAIR) MR images. We use a high spatial frequency suppression method to reduce the gray matter area signal intensity. We evaluate our method in 26 MS patients and 26 age matched health controls. The data from the automated algorithm showed good agreement with that from the manual segmentation. The linear correlation between these two approaches in comparing WMH volumes was found to be Y = 1.04X + 1.74  (R (2) = 0.96). The automated algorithm estimates the number, volume, and category of WMH.

SELF-SUPERVISED MRI TISSUE SEGMENTATION BY DISCRIMINATIVE CLUSTERING

The study of brain lesions can benefit from a clear identification of transitions between healthy and pathological tissues, through the analysis of brain imaging data. Current signal processing methods, able to address these issues, often rely on strong prior information. In this article, a new method for tissue segmentation is proposed. It is based on a discriminative strategy, in a self-supervised machine learning approach. This method avoids the use of prior information, which makes it very versatile, and able to cope with different tissue types. It also returns tissue probabilities for each voxel, crucial for a good characterization of the evolution of brain lesions. Simulated as well as real benchmark data were used to validate the accuracy of the method and compare it against other segmentation algorithms.

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.