Jennifer L. Cuzzocreo

SIMPLE PARADIGM FOR EXTRA-CEREBRAL TISSUE REMOVAL: ALGORITHM AND ANALYSIS

Extraction of the brain-i.e. cerebrum, cerebellum, and brain stem-from T1-weighted structural magnetic resonance images is an important initial step in neuroimage analysis. Although automatic algorithms are available, their inconsistent handling of the cortical mantle often requires manual interaction, thereby reducing their effectiveness. This paper presents a fully automated brain extraction algorithm that incorporates elastic registration, tissue segmentation, and morphological techniques which are combined by a watershed principle, while paying special attention to the preservation of the boundary between the gray matter and the cerebrospinal fluid. The approach was evaluated by comparison to a manual rater, and compared to several other leading algorithms on a publically available data set of brain images using the Dice coefficient and containment index as performance metrics. The qualitative and quantitative impact of this initial step on subsequent cortical surface generation is also presented. Our experiments demonstrate that our approach is quantitatively better than six other leading algorithms (with statistical significance on modern T1-weighted MR data). We also validated the robustness of the algorithm on a very large data set of over one thousand subjects, and showed that it can replace an experienced manual rater as preprocessing for a cortical surface extraction algorithm with statistically insignificant differences in cortical surface position.

Volumetric Neuroimage Analysis Extensions for the MIPAV Software Package

We describe a new collection of publicly available software tools for performing quantitative neuroimage analysis. The tools perform semi-automatic brain extraction, tissue classification, Talairach alignment, and atlas-based measurements within a user-friendly graphical environment. They are implemented as plug-ins for MIPAV, a freely available medical image processing software package from the National Institutes of Health. Because the plug-ins and MIPAV are implemented in Java, both can be utilized on nearly any operating system platform. In addition to the software plug-ins, we have also released a digital version of the Talairach atlas that can be used to perform regional volumetric analyses. Several studies are conducted applying the new tools to simulated and real neuroimaging data sets.

OASIS is Automated Statistical Inference for Segmentation, with applications to multiple sclerosis lesion segmentation in MRI☆

Magnetic resonance imaging (MRI) can be used to detect lesions in the brains of multiple sclerosis (MS) patients and is essential for diagnosing the disease and monitoring its progression. In practice, lesion load is often quantified by either manual or semi-automated segmentation of MRI, which is time-consuming, costly, and associated with large inter- and intra-observer variability. We propose OASIS is Automated Statistical Inference for Segmentation (OASIS), an automated statistical method for segmenting MS lesions in MRI studies. We use logistic regression models incorporating multiple MRI modalities to estimate voxel-level probabilities of lesion presence. Intensity-normalized T1-weighted, T2-weighted, fluid-attenuated inversion recovery and proton density volumes from 131 MRI studies (98 MS subjects, 33 healthy subjects) with manual lesion segmentations were used to train and validate our model. Within this set, OASIS detected lesions with a partial area under the receiver operating characteristic curve for clinically relevant false positive rates of 1% and below of 0.59% (95% CI; [0.50%, 0.67%]) at the voxel level. An experienced MS neuroradiologist compared these segmentations to those produced by LesionTOADS, an image segmentation software that provides segmentation of both lesions and normal brain structures. For lesions, OASIS out-performed LesionTOADS in 74% (95% CI: [65%, 82%]) of cases for the 98 MS subjects. To further validate the method, we applied OASIS to 169 MRI studies acquired at a separate center. The neuroradiologist again compared the OASIS segmentations to those from LesionTOADS. For lesions, OASIS ranked higher than LesionTOADS in 77% (95% CI: [71%, 83%]) of cases. For a randomly selected subset of 50 of these studies, one additional radiologist and one neurologist also scored the images. Within this set, the neuroradiologist ranked OASIS higher than LesionTOADS in 76% (95% CI: [64%, 88%]) of cases, the neurologist 66% (95% CI: [52%, 78%]) and the radiologist 52% (95% CI: [38%, 66%]). OASIS obtains the estimated probability for each voxel to be part of a lesion by weighting each imaging modality with coefficient weights. These coefficients are explicit, obtained using standard model fitting techniques, and can be reused in other imaging studies. This fully automated method allows sensitive and specific detection of lesion presence and may be rapidly applied to large collections of images.

A JOINT REGISTRATION AND SEGMENTATION APPROACH TO SKULL STRIPPING

Extraction of the cerebrum, cerebellum, and brain stem from structural magnetic resonances images (MRIs) is an important initial step in neuroimaging. We present an automated algorithm that solves this difficult problem, often referred to as skull stripping, which is novel for its use of registration, segmentation, and morphological operations. Our algorithm is also concerned with an accurate representation of the grey matter boundary, which is a unique feature. We also present results demonstrating the accuracy of this approach

MRI Shows a Region-Specific Pattern of Atrophy in Spinocerebellar Ataxia Type 2

In this study, we used manual delineation of high-resolution magnetic resonance imaging (MRI) to determine the spatial and temporal characteristics of the cerebellar atrophy in spinocerebellar ataxia type 2 (SCA2). Ten subjects with SCA2 were compared to ten controls. The volume of the pons, the total cerebellum, and the individual cerebellar lobules were calculated via manual delineation of structural MRI. SCA2 showed substantial global atrophy of the cerebellum. Furthermore, the degeneration was lobule specific, selectively affecting the anterior lobe, VI, Crus I, Crus II, VIII, uvula, corpus medullare, and pons, while sparing VIIB, tonsil/paraflocculus, flocculus, declive, tuber/folium, pyramis, and nodulus. The temporal characteristics differed in each cerebellar subregion: (1) duration of disease: Crus I, VIIB, VIII, uvula, corpus medullare, pons, and the total cerebellar volume correlated with the duration of disease; (2) age: VI, Crus II, and flocculus correlated with age in control subjects; and (3) clinical scores: VI, Crus I, VIIB, VIII, corpus medullare, pons, and the total cerebellar volume correlated with clinical scores in SCA2. No correlations were found with the age of onset. Our extrapolated volumes at the onset of symptoms suggest that neurodegeneration may be present even during the presymptomatic stages of disease. The spatial and temporal characteristics of the cerebellar degeneration in SCA2 are region specific. Furthermore, our findings suggest the presence of presymptomatic atrophy and a possible developmental component to the mechanisms of pathogenesis underlying SCA2. Our findings further suggest that volumetric analysis may aid in the development of a non-invasive, quantitative biomarker.

Longitudinal multiple sclerosis lesion segmentation: Resource and challenge

Abstract In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time‐points, and test data of fourteen subjects with a mean of 4.4 time‐points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state‐of‐the‐art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: (1) the sharing of a rich data set; (2) collaboration and comparison of the various avenues of research being pursued in the community; and (3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website2 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters. HighlightsPublic lesion data base of 21 training data sets and 61 testing data sets.Fully automated evaluation website.Comparison between 14 state‐of‐the‐art algorithms and 2 manual delineators.

Extreme Deep White Matter Hyperintensity Volumes Are Associated with African American Race

Background: African Americans (AAs) have a higher prevalence of extreme ischemic white matter hyperintensities (WMHs) on magnetic resonance imaging (MRI) than do European Americans (EAs) based on the Cardiovascular Health Study (CHS) score. Ischemic white matter disease, limited to the deep white matter, may be biologically distinct from disease in other regions and may reflect a previously observed trend toward an increased risk of subcortical lacunar infarcts in AAs. We hypothesized that extreme deep WMH volume (DWMV) or periventricular volume (PV) may also have a higher prevalence in AAs. Thus, we studied extreme CHS scores and extreme DWMV and PV in a healthy population enriched for cardiovascular disease risk factors. Methods: We imaged the brains of 593 subjects who were first-degree relatives of probands with early onset coronary disease prior to 60 years of age. WMHs were manually delineated on 3-tesla cranial MRI by a trained radiology reader; the location and volume of lesions were characterized using automated software. DWMV and PV were measured directly with automated software, and the CHS score was determined by a neuroradiologist. Volumes were characterized as being in the upper 25% versus lower 75% of total lesion volume. Volumes in the upper versus the remaining quartiles were examined for AA versus EA race using multiple logistic regression (generalized estimating equations adjusted for family relatedness) and adjusted for major vascular disease risk factors including age ≥55 years versus <55, sex, current smoking, obesity, hypertension, diabetes and low-density lipoprotein >160 mg/dl. Results: Participants were 58% women and 37% AAs, with a mean age of 51.5 ± 11.0 years (range, 29-74 years). AAs had significantly higher odds of having extreme DWMVs (odds ratio, OR, 1.8; 95% confidence interval, CI, 1.2-2.9; p = 0.0076) independently of age, sex, hypertension and all other risk factors. AAs also had significantly higher odds of having extreme CHS scores ≥3 (OR, 1.3; 95% CI, 1.1-3.6; p = 0.025). Extreme PV was not significantly associated with AA race (OR, 1.3; 95% CI, 0.81-2.1; p = 0.26). Conclusions: AAs from families with early-onset cardiovascular disease are more likely to have extreme DWMVs (a subclinical form of cerebrovascular disease) and an extreme CHS score, but not extreme PV, independently of age and other cardiovascular disease risk factors. These findings suggest that this AA population is at an increased risk for DWMV and may be at an increased risk for future subcortical stroke. Longitudinal studies are required to see if DWMV is predictive of symptomatic subcortical strokes in this population.

Effect of handedness on fMRI activation in the medial temporal lobe during an auditory verbal memory task.

Several studies have shown marked differences in the neural localization of language functions in the brains of left‐handed individuals when compared with right‐handers. Previous experiments involving functional lateralization have demonstrated cerebral blood flow patterns that differ concordantly with subject handedness while performing language‐related tasks. The effect of handedness on function in specific stages of memory processing, however, is a largely unexplored area. We used a paired‐associates verbal memory task to elicit activation of neural areas related to declarative memory, examining the hypothesis that there are differences in activation in the medial temporal lobe (MTL) between handedness groups. 15 left‐handed and 25 right‐handed healthy adults were matched for all major demographic and neuropsychological variables. Functional and structural imaging data were acquired and analyzed for group differences within MTL subregions. Our results show that activation of the MTL during declarative memory processing varies with handedness. While both groups showed activation in left and right MTL subregions, the left‐handed group showed a statistically significant increase in the left hippocampus and amygdala during both encoding and recall. No increases in activation were found in the right‐handed group. This effect was found in the absence of any differences in performance on the verbal memory task, structural volumetric disparities, or functional asymmetries. This provides evidence of functional differences between left‐handers and right‐handers, which extends to declarative memory processes. Hum Brain Mapp 2009.

Example based lesion segmentation

Automatic and accurate detection of white matter lesions is a significant step toward understanding the progression of many diseases, like Alzheimer’s disease or multiple sclerosis. Multi-modal MR images are often used to segment T2 white matter lesions that can represent regions of demyelination or ischemia. Some automated lesion segmentation methods describe the lesion intensities using generative models, and then classify the lesions with some combination of heuristics and cost minimization. In contrast, we propose a patch-based method, in which lesions are found using examples from an atlas containing multi-modal MR images and corresponding manual delineations of lesions. Patches from subject MR images are matched to patches from the atlas and lesion memberships are found based on patch similarity weights. We experiment on 43 subjects with MS, whose scans show various levels of lesion-load. We demonstrate significant improvement in Dice coefficient and total lesion volume compared to a state of the art model-based lesion segmentation method, indicating more accurate delineation of lesions.

Reconstruction of the human cerebral cortex robust to white matter lesions: Method and validation

Cortical atrophy has been reported in a number of diseases, such as multiple sclerosis and Alzheimers disease, that are also associated with white matter (WM) lesions. However, most cortical reconstruction techniques do not account for these pathologies, thereby requiring additional processing to correct for the effect of WM lesions. In this work, we introduce CRUISE+, an automated process for cortical reconstruction from magnetic resonance brain images with WM lesions. The process extends previously well validated methods to allow for multichannel input images and to accommodate for the presence of WM lesions. We provide new validation data and tools for measuring the accuracy of cortical reconstruction methods on healthy brains as well as brains with multiple sclerosis lesions. Using this data, we validate the accuracy of CRUISE+ and compare it to another state‐of‐the‐art cortical reconstruction tool. Our results demonstrate that CRUISE+ has superior performance in the cortical regions near WM lesions, and similar performance in other regions. Hum Brain Mapp 35:3385–3401, 2014.