Cerebrospinal Fluid Flow in Patients with Huntington's Disease.

OBJECTIVE: Investigations of cerebrospinal fluid (CSF) flow aberrations in Huntington's disease (HD) are of growing interest, as impaired CSF flow may contribute to mutant Huntington retention and observed heterogeneous responsiveness to intrathecally administered therapies. METHOD: We assessed net cerebral aqueduct CSF flow and velocity in 29 HD participants (17 premanifest and 12 manifest) and 51 age- and sex matched non-HD control participants using 3-Tesla magnetic resonance imaging methods. Regression models were applied to test hypotheses regarding: (i) net CSF flow and cohort, (ii) net CSF flow and disease severity (CAP-score), and (iii) CSF volume after correcting for age and sex. RESULTS: Group-wise analyses support a decrease in net CSF flow in HD (mean 0.14 ± 0.27 mL/min) relative to control (mean 0.32 ± 0.20 mL/min) participants (p = 0.02), with lowest flow in the manifest HD cohort (mean 0.04 ± 0.25 mL/min). This finding was explained by hyperdynamic CSF movement, manifesting as higher caudal systolic CSF flow velocity and higher diastolic cranial CSF flow velocity across the cardiac cycle, in HD (caudal flow: 0.17 ± 0.07 mL/s, cranial flow: 0.14 ± 0.08 mL/s) compared to control (caudal flow: 0.13 ± 0.06 mL/s, cranial flow: 0.11 ± 0.04 mL/s) participants. A positive correlation between cranial diastolic flow and disease severity was observed (p = 0.02). INTERPRETATIONS: Findings support aqueductal CSF flow dynamics changing with disease severity in HD. These accelerated changes are consistent with changes observed over the typical adult lifespan, and may have relevance to mutant Huntington retention and intrathecally administered therapeutics responsiveness. ANN NEUROL 2023;94:885-894.

Corticostriatal beta oscillation changes associated with cognitive function in Parkinson's disease.

Cognitive impairment is the most frequent non-motor symptom in Parkinson's disease and is associated with deficits in a number of cognitive functions including working memory. However, the pathophysiology of Parkinson's disease cognitive impairment is poorly understood. Beta oscillations have previously been shown to play an important role in cognitive functions including working memory encoding. Decreased dopamine in motor cortico-striato-thalamo-cortical (CSTC) circuits increases the spectral power of beta oscillations and results in Parkinson's disease motor symptoms. Analogous changes in parallel cognitive CSTC circuits involving the caudate and dorsolateral prefrontal cortex (DLPFC) may contribute to Parkinson's disease cognitive impairment. The objective of our study is to evaluate whether changes in beta oscillations in the caudate and DLPFC contribute to cognitive impairment in Parkinson's disease patients. To investigate this, we used local field potential recordings during deep brain stimulation surgery in 15 patients with Parkinson's disease. Local field potentials were recorded from DLPFC and caudate at rest and during a working memory task. We examined changes in beta oscillatory power during the working memory task as well as the relationship of beta oscillatory activity to preoperative cognitive status, as determined from neuropsychological testing results. We additionally conducted exploratory analyses on the relationship between cognitive impairment and task-based changes in spectral power in additional frequency bands. Spectral power of beta oscillations decreased in both DLPFC and caudate during working memory encoding and increased in these structures during feedback. Subjects with cognitive impairment had smaller decreases in caudate and DLPFC beta oscillatory power during encoding. In our exploratory analysis, we found that similar differences occurred in alpha frequencies in caudate and theta and alpha in DLPFC. Our findings suggest that oscillatory power changes in cognitive CSTC circuits may contribute to cognitive symptoms in patients with Parkinson's disease. These findings may inform the future development of novel neuromodulatory treatments for cognitive impairment in Parkinson's disease.

Comprehensive shape analysis of the cortex in Huntington's disease.

The striatum has traditionally been the focus of Huntington's disease research due to the primary insult to this region and its central role in motor symptoms. Beyond the striatum, evidence of cortical alterations caused by Huntington's disease has surfaced. However, findings are not coherent between studies which have used cortical thickness for Huntington's disease since it is the well-established cortical metric of interest in other diseases. In this study, we propose a more comprehensive approach to cortical morphology in Huntington's disease using cortical thickness, sulcal depth, and local gyrification index. Our results show consistency with prior findings in cortical thickness, including its limitations. Our comparison between cortical thickness and local gyrification index underscores the complementary nature of these two measures-cortical thickness detects changes in the sensorimotor and posterior areas while local gyrification index identifies insular differences. Since local gyrification index and cortical thickness measures detect changes in different regions, the two used in tandem could provide a clinically relevant measure of disease progression. Our findings suggest that differences in insular regions may correspond to earlier neurodegeneration and may provide a complementary cortical measure for detection of subtle early cortical changes due to Huntington's disease.

Anatomical texture patterns identify cerebellar distinctions between essential tremor and Parkinson's disease.

Voxel-based morphometry is an established technique to study focal structural brain differences in neurologic disease. More recently, texture-based analysis methods have enabled a pattern-based assessment of group differences, at the patch level rather than at the voxel level, allowing a more sensitive localization of structural differences between patient populations. In this study, we propose a texture-based approach to identify structural differences between the cerebellum of patients with Parkinson's disease (n = 280) and essential tremor (n = 109). We analyzed anatomical differences of the cerebellum among patients using two features: T1-weighted MRI intensity, and a texture-based similarity feature. Our results show anatomical differences between groups that are localized to the inferior part of the cerebellar cortex. Both the T1-weighted intensity and texture showed differences in lobules VIII and IX, vermis VIII and IX, and middle peduncle, but the texture analysis revealed additional differences in the dentate nucleus, lobules VI and VII, vermis VI and VII. This comparison emphasizes how T1-weighted intensity and texture-based methods can provide a complementary anatomical structure analysis. While texture-based similarity shows high sensitivity for gray matter differences, T1-weighted intensity shows sensitivity for the detection of white matter differences.

Deep learning segmentation of the choroid plexus from structural magnetic resonance imaging (MRI): validation and normative ranges across the adult lifespan.

BACKGROUND: The choroid plexus functions as the blood-cerebrospinal fluid (CSF) barrier, plays an important role in CSF production and circulation, and has gained increased attention in light of the recent elucidation of CSF circulation dysfunction in neurodegenerative conditions. However, methods for routinely quantifying choroid plexus volume are suboptimal and require technical improvements and validation. Here, we propose three deep learning models that can segment the choroid plexus from commonly-acquired anatomical MRI data and report performance metrics and changes across the adult lifespan. METHODS: Fully convolutional neural networks were trained from 3D T1-weighted, 3D T2-weighted, and 2D T2-weighted FLAIR MRI using gold-standard manual segmentations in control and neurodegenerative participants across the lifespan (n = 50; age = 21-85 years). Dice coefficients, 95% Hausdorff distances, and area-under-curve (AUCs) were calculated for each model and compared to segmentations from FreeSurfer using two-tailed Wilcoxon tests (significance criteria: p < 0.05 after false discovery rate multiple comparisons correction). Metrics were regressed against lateral ventricular volume using generalized linear models to assess model performance for varying levels of atrophy. Finally, models were applied to an expanded cohort of adult controls (n = 98; age = 21-89 years) to provide an exemplar of choroid plexus volumetry values across the lifespan. RESULTS: Deep learning results yielded Dice coefficient = 0.72, Hausdorff distance = 1.97 mm, AUC = 0.87 for T1-weighted MRI, Dice coefficient = 0.72, Hausdorff distance = 2.22 mm, AUC = 0.87 for T2-weighted MRI, and Dice coefficient = 0.74, Hausdorff distance = 1.69 mm, AUC = 0.87 for T2-weighted FLAIR MRI; values did not differ significantly between MRI sequences and were statistically improved compared to current commercially-available algorithms (p < 0.001). The intraclass coefficients were 0.95, 0.95, and 0.96 between T1-weighted and T2-weighted FLAIR, T1-weighted and T2-weighted, and T2-weighted and T2-weighted FLAIR models, respectively. Mean lateral ventricle choroid plexus volume across all participants was 3.20 ± 1.4 cm3; a significant, positive relationship (R2 = 0.54-0.60) was observed between participant age and choroid plexus volume for all MRI sequences (p < 0.001). CONCLUSIONS: Findings support comparable performance in choroid plexus delineation between standard, clinically available, non-contrasted anatomical MRI sequences. The software embedding the evaluated models is freely available online and should provide a useful tool for the growing number of studies that desire to quantitatively evaluate choroid plexus structure and function ( https://github.com/hettk/chp_seg ).

Deep learning segmentation of peri-sinus structures from structural magnetic resonance imaging: validation and normative ranges across the adult lifespan.

BACKGROUND: Peri-sinus structures such as arachnoid granulations (AG) and the parasagittal dural (PSD) space have gained much recent attention as sites of cerebral spinal fluid (CSF) egress and neuroimmune surveillance. Neurofluid circulation dysfunction may manifest as morphological changes in these structures, however, automated quantification of these structures is not possible and rather characterization often requires exogenous contrast agents and manual delineation. METHODS: We propose a deep learning architecture to automatically delineate the peri-sinus space (e.g., PSD and intravenous AG structures) using two cascaded 3D fully convolutional neural networks applied to submillimeter 3D T2-weighted non-contrasted MRI images, which can be routinely acquired on all major MRI scanner vendors. The method was evaluated through comparison with gold-standard manual tracing from a neuroradiologist (n = 80; age range = 11-83 years) and subsequently applied in healthy participants (n = 1,872; age range = 5-100 years), using data from the Human Connectome Project, to provide exemplar metrics across the lifespan. Dice-Sørensen and a generalized linear model was used to assess PSD and AG changes across the human lifespan using quadratic restricted splines, incorporating age and sex as covariates. RESULTS: Findings demonstrate that the PSD and AG volumes can be segmented using T2-weighted MRI with a Dice-Sørensen coefficient and accuracy of 80.7 and 74.6, respectively. Across the lifespan, we observed that total PSD volume increases with age with a linear interaction of gender and age equal to 0.9 cm3 per year (p < 0.001). Similar trends were observed in the frontal and parietal, but not occipital, PSD. An increase in AG volume was observed in the third to sixth decades of life, with a linear effect of age equal to 0.64 mm3 per year (p < 0.001) for total AG volume and 0.54 mm3 (p < 0.001) for maximum AG volume. CONCLUSIONS: A tool that can be applied to quantify PSD and AG volumes from commonly acquired T2-weighted MRI scans is reported and exemplar volumetric ranges of these structures are provided, which should provide an exemplar for studies of neurofluid circulation dysfunction. Software and training data are made freely available online ( https://github.com/hettk/spesis ).

Reduced cerebrospinal fluid motion in patients with Parkinson's disease revealed by magnetic resonance imaging with low b-value diffusion weighted imaging.

BACKGROUND: Parkinson's disease is characterized by dopamine-responsive symptoms as well as aggregation of α-synuclein protofibrils. New diagnostic methods assess α-synuclein aggregation characteristics from cerebrospinal fluid (CSF) and recent pathophysiologic mechanisms suggest that CSF circulation disruptions may precipitate α-synuclein retention. Here, diffusion-weighted MRI with low-to-intermediate diffusion-weightings was applied to test the hypothesis that CSF motion is reduced in Parkinson's disease relative to healthy participants. METHODS: Multi-shell diffusion weighted MRI (spatial resolution = 1.8 × 1.8 × 4.0 mm) with low-to-intermediate diffusion weightings (b-values = 0, 50, 100, 200, 300, 700, and 1000 s/mm2) was applied over the approximate kinetic range of suprasellar cistern fluid motion at 3 Tesla in Parkinson's disease (n = 27; age = 66 ± 6.7 years) and non-Parkinson's control (n = 32; age = 68 ± 8.9 years) participants. Wilcoxon rank-sum tests were applied to test the primary hypothesis that the noise floor-corrected decay rate of CSF signal as a function of b-value, which reflects increasing fluid motion, is reduced within the suprasellar cistern of persons with versus without Parkinson's disease and inversely relates to choroid plexus activity assessed from perfusion-weighted MRI (significance-criteria: p < 0.05). RESULTS: Consistent with the primary hypothesis, CSF decay rates were higher in healthy (D = 0.00673 ± 0.00213 mm2/s) relative to Parkinson's disease (D = 0.00517 ± 0.00110 mm2/s) participants. This finding was preserved after controlling for age and sex and was observed in the posterior region of the suprasellar cistern (p < 0.001). An inverse correlation between choroid plexus perfusion and decay rate in the voxels within the suprasellar cistern (Spearman's-r=-0.312; p = 0.019) was observed. CONCLUSIONS: Multi-shell diffusion MRI was applied to identify reduced CSF motion at the level of the suprasellar cistern in adults with versus without Parkinson's disease; the strengths and limitations of this methodology are discussed in the context of the growing literature on CSF flow.

Choroid plexus perfusion and bulk cerebrospinal fluid flow across the adult lifespan.

The choroid plexus (ChP) comprises a collection of modified ependymal cells that play an important role in the production of brain cerebrospinal fluid (CSF), and ChP perfusion aberrations have been implicated in a range of cerebrovascular and neurodegenerative disorders. To provide an exemplar for the growing interest in ChP activity, we evaluated ChP perfusion and bulk CSF flow cross-sectionally across the healthy adult lifespan. Participants (n = 77; age range = 21-86 years) were scanned at 3T using T1-weighted, T2-weighted-FLAIR, perfusion-weighted pCASL, and phase contrast MRI to calculate ChP anatomy, perfusion, and aqueductal CSF flow, respectively. Regression models were applied to evaluate aging effects on ChP volume and ChP perfusion in the lateral ventricles, as well as CSF flow. ChP volume (mean ± std = 2.81 ± 1.1 cm3) increased (p < 0.001), ChP perfusion (36.3 ± 8.6 mL/100 g/min) decreased (p = 0.0078), and ChP total blood flow (1.13 ± 0.34 mL/min) increased (p < 0.001) with age. Cranial-to-caudal net CSF flow (0.245 ± 0.20 mL/min) decreased, absolute CSF flow (4.86 ± 2.96 mL/min) increased, and CSF regurgitant fraction (0.87 ± 0.126) increased with age (all: p < 0.001). ChP perfusion was directly related to net cranial-to-caudal CSF flow through the aqueduct (p = 0.033). The implications of these findings are discussed in the context of the growing literature on CSF circulatory dysfunction in neurodegeneration and cerebrovascular disease.

Deep learning segmentation of the choroid plexus from structural magnetic resonance imaging (MRI): validation and normative ranges across the adult lifespan.

Background: The choroid plexus functions as the blood-cerebrospinal fluid barrier, plays an important role in neurofluid production and circulation, and has gained increased attention in light of the recent elucidation of neurofluid circulation dysfunction in neurodegenerative conditions. However, methods for routinely quantifying choroid plexus volume are suboptimal and require technical improvements and validation. Here, we propose three deep learning models that can segment the choroid plexus from commonly-acquired anatomical MRI data and report performance metrics and changes across the adult lifespan. Methods: Fully convolutional neural networks were trained from 3-D T1-weighted, 3-D T2-weighted, and 2-D T2-weighted FLAIR MRI and gold-standard manual segmentations in healthy and neurodegenerative participants across the lifespan (n=50; age=21-85 years). Dice coefficients, 95% Hausdorff distances, and area-under-curve (AUCs) were calculated for each model and compared to segmentations from FreeSurfer using two-tailed Wilcoxon tests (significance criteria: p<0.05 after false discovery rate multiple comparisons correction). Metrics were regressed against lateral ventricular volume using generalized linear models to assess model performance for varying levels of atrophy. Finally, models were applied to an expanded cohort of healthy adults (n=98; age=21-89 years) to provide an exemplar of choroid plexus volumetry values across the lifespan. Results: Deep learning results yielded Dice coefficient=0.72, Hausdorff distance=1.97 mm, AUC=0.87 for T1-weighted MRI, Dice coefficient=0.72, Hausdorff distance=2.22 mm, AUC=0.87 for T2-weighted MRI, and Dice coefficient=0.74, Hausdorff distance=1.69 mm, AUC=0.87 for T2-weighted FLAIR MRI; values did not differ significantly between2 MRI sequences and were statistically improved compared to current commercially-available algorithms (p<0.001). The intraclass coefficients were 0.95, 0.95, and 0.96 between T1-weighted and T2-FLAIR, T1-weighted and T2-weighted, and T2-weighted and T2-FLAIR models, respectively. Mean lateral ventricle choroid plexus volume across all participants was 3.20±1.4 cm3; a significant, positive relationship (R2=0.54; slope=0.047) was observed between participant age and choroid plexus volume for all MRI sequences (p<0.001). Conclusions: Findings support comparable performance in choroid plexus delineation between standard, clinically available, non-contrasted anatomical MRI sequences. The software embedding the evaluated models is freely available online and should provide a useful tool for the growing number of studies that desire to quantitatively evaluate choroid plexus structure and function (https://github.com/hettk/chp_seg).

Parasagittal dural space hypertrophy and amyloid-ß deposition in Alzheimer's disease.

One of the pathological hallmarks of Alzheimer's and related diseases is the increased accumulation of protein amyloid-ß in the brain parenchyma. As such, recent studies have focused on characterizing protein and related clearance pathways involving perivascular flow of neurofluids, but human studies of these pathways are limited owing to limited methods for evaluating neurofluid circulation non-invasively in vivo. Here, we utilize non-invasive MRI methods to explore surrogate measures of CSF production, bulk flow and egress in the context of independent PET measures of amyloid-ß accumulation in older adults. Participants (N = 23) were scanned at 3.0 T with 3D T2-weighted turbo spin echo, 2D perfusion-weighted pseudo-continuous arterial spin labelling and phase-contrast angiography to quantify parasagittal dural space volume, choroid plexus perfusion and net CSF flow through the aqueduct of Sylvius, respectively. All participants also underwent dynamic PET imaging with amyloid-ß tracer 11C-Pittsburgh Compound B to quantify global cerebral amyloid-ß accumulation. Spearman's correlation analyses revealed a significant relationship between global amyloid-ß accumulation and parasagittal dural space volume (rho = 0.529, P = 0.010), specifically in the frontal (rho = 0.527, P = 0.010) and parietal (rho = 0.616, P = 0.002) subsegments. No relationships were observed between amyloid-ß and choroid plexus perfusion nor net CSF flow. Findings suggest that parasagittal dural space hypertrophy, and its possible role in CSF-mediated clearance, may be closely related to global amyloid-ß accumulation. These findings are discussed in the context of our growing understanding of the physiological mechanisms of amyloid-ß aggregation and clearance via neurofluids.

Reduced suprasellar cistern cerebrospinal fluid motion in patients with Parkinson's disease revealed by magnetic resonance imaging with dynamic cycling of diffusion weightings.

BACKGROUND: Parkinson's disease is characterized by dopamine-responsive symptoms as well as aggregation and accumulation of a-synuclein protofibrils. New diagnostic methods assess a-synuclein aggregation characteristics from cerebrospinal fluid and recent pathophysiologic mechanisms suggest that cerebrospinal fluid circulation disruptions may precipitate a-synuclein retention. Here, we test the hypothesis that cerebrospinal fluid motion at the level of the suprasellar cistern is reduced in Parkinson's disease relative to healthy participants and this reduction relates to choroid plexus perfusion. METHODS: Diffusion weighted imaging (spatial resolution=1.8×1.8×4 mm) magnetic resonance imaging with cycling of diffusion weightings (b-values=0, 50, 100, 200, 300, 700, and 1000 s/mm2) over the approximate kinetic range of suprasellar cistern neurofluid motion was applied at 3-Tesla in Parkinson's disease (n=27; age=66±6.7 years) and healthy (n=32; age=68±8.9 years) participants. Wilcoxon rank-sum tests were applied to test the primary hypothesis that the decay rate of cerebrospinal fluid signal as a function of b-value, which reflects increasing fluid motion, is reduced in persons with versus without Parkinson's disease and inversely relates to choroid plexus activity assessed from perfusion-weighted magnetic resonance imaging (Spearman rank-order correlation; significance-criteria: p<0.05). RESULTS: Consistent with the primary hypothesis, decay rates were higher in healthy (D=0.00328±0.00123mm2/s) relative to Parkinson's disease (D=0.00256±0.0094mm2/s) participants (p=0.016). This finding was preserved after controlling for age and sex. An inverse correlation between choroid plexus perfusion and decay rate (p=0.011) was observed in Parkinson's disease participants. CONCLUSIONS: Cerebrospinal fluid motion at the level of the suprasellar cistern is often reduced in adults with versus without Parkinson's disease and this reduction correlates on average with choroid plexus perfusion.

Parasagittal dural space and cerebrospinal fluid (CSF) flow across the lifespan in healthy adults.

BACKGROUND: Recent studies have suggested alternative cerebrospinal fluid (CSF) clearance pathways for brain parenchymal metabolic waste products. One fundamental but relatively under-explored component of these pathways is the anatomic region surrounding the superior sagittal sinus, which has been shown to have relevance to trans-arachnoid molecular passage. This so-called parasagittal dural (PSD) space may play a physiologically significant role as a distal intracranial component of the human glymphatic circuit, yet fundamental gaps persist in our knowledge of how this space changes with normal aging and intracranial bulk fluid transport. METHODS: We re-parameterized MRI methods to assess CSF circulation in humans using high resolution imaging of the PSD space and phase contrast measures of flow through the cerebral aqueduct to test the hypotheses that volumetric measures of PSD space (1) are directly related to CSF flow (mL/s) through the cerebral aqueduct, and (2) increase with age. Multi-modal 3-Tesla MRI was applied in healthy participants (n = 62; age range = 20-83 years) across the adult lifespan whereby phase contrast assessments of CSF flow through the aqueduct were paired with non-contrasted T1-weighted and T2-weighted MRI for PSD volumetry. PSD volume was extracted using a recently validated neural networks algorithm. Non-parametric regression models were applied to evaluate how PSD volume related to tissue volume and age cross-sectionally, and separately how PSD volume related to CSF flow (significance criteria: two-sided p < 0.05). RESULTS: A significant PSD volume enlargement in relation to normal aging (p < 0.001, Spearman's-[Formula: see text] = 0.6), CSF volume (p < 0.001, Spearman's-[Formula: see text] = 0.6) and maximum CSF flow through the aqueduct of Sylvius (anterograde and retrograde, p < 0.001) were observed. The elevation in PSD volume was not significantly related to gray or white matter tissue volumes. Findings are consistent with PSD volume increasing with age and bulk CSF flow. CONCLUSIONS: Findings highlight the feasibility of quantifying PSD volume non-invasively in vivo in humans using machine learning and non-contrast MRI. Additionally, findings demonstrate that PSD volume increases with age and relates to CSF volume and bi-directional flow. Values reported should provide useful normative ranges for how PSD volume adjusts with age, which will serve as a necessary pre-requisite for comparisons to persons with neurodegenerative disorders.

Multi-scale graph-based grading for Alzheimer's disease prediction.

The prediction of subjects with mild cognitive impairment (MCI) who will progress to Alzheimer's disease (AD) is clinically relevant, and may above all have a significant impact on accelerating the development of new treatments. In this paper, we present a new MRI-based biomarker that enables us to accurately predict conversion of MCI subjects to AD. In order to better capture the AD signature, we introduce two main contributions. First, we present a new graph-based grading framework to combine inter-subject similarity features and intra-subject variability features. This framework involves patch-based grading of anatomical structures and graph-based modeling of structure alteration relationships. Second, we propose an innovative multiscale brain analysis to capture alterations caused by AD at different anatomical levels. Based on a cascade of classifiers, this multiscale approach enables the analysis of alterations of whole brain structures and hippocampus subfields at the same time. During our experiments using the ADNI-1 dataset, the proposed multiscale graph-based grading method obtained an area under the curve (AUC) of 81% to predict conversion of MCI subjects to AD within three years. Moreover, when combined with cognitive scores, the proposed method obtained 85% of AUC. These results are competitive in comparison to state-of-the-art methods evaluated on the same dataset.

TENSOR-BASED GRADING: A NOVEL PATCH-BASED GRADING APPROACH FOR THE ANALYSIS OF DEFORMATION FIELDS IN HUNTINGTON'S DISEASE.

The improvements in magnetic resonance imaging have led to the development of numerous techniques to better detect structural alterations caused by neurodegenerative diseases. Among these, the patch-based grading framework has been proposed to model local patterns of anatomical changes. This approach is attractive because of its low computational cost and its competitive performance. Other studies have proposed to analyze the deformations of brain structures using tensor-based morphometry, which is a highly interpretable approach. In this work, we propose to combine the advantages of these two approaches by extending the patch-based grading framework with a new tensor-based grading method that enables us to model patterns of local deformation using a log-Euclidean metric. We evaluate our new method in a study of the putamen for the classification of patients with pre-manifest Huntington's disease and healthy controls. Our experiments show a substantial increase in classification accuracy (87.5 ± 0.5 vs. 81.3 ± 0.6) compared to the existing patch-based grading methods, and a good complement to putamen volume, which is a primary imaging-based marker for the study of Huntington's disease.

Patch-Based Abnormality Maps for Improved Deep Learning-Based Classification of Huntington's Disease.

Deep learning techniques have demonstrated state-of-the-art performances in many medical imaging applications. These methods can efficiently learn specific patterns. An alternative approach to deep learning is patch-based grading methods, which aim to detect local similarities and differences between groups of subjects. This latter approach usually requires less training data compared to deep learning techniques. In this work, we propose two major contributions: first, we combine patch-based and deep learning methods. Second, we propose to extend the patch-based grading method to a new patch-based abnormality metric. Our method enables us to detect localized structural abnormalities in a test image by comparison to a template library consisting of images from a variety of healthy controls. We evaluate our method by comparing classification performance using different sets of features and models. Our experiments show that our novel patch-based abnormality metric increases deep learning performance from 91.3% to 95.8% of accuracy compared to standard deep learning approaches based on the MRI intensity.

Author Correction: Multimodal hippocampal subfield grading for Alzheimer's disease classification.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Multimodal Hippocampal Subfield Grading For Alzheimer's Disease Classification.

Numerous studies have proposed biomarkers based on magnetic resonance imaging (MRI) to detect and predict the risk of evolution toward Alzheimer's disease (AD). Most of these methods have focused on the hippocampus, which is known to be one of the earliest structures impacted by the disease. To date, patch-based grading approaches provide among the best biomarkers based on the hippocampus. However, this structure is complex and is divided into different subfields, not equally impacted by AD. Former in-vivo imaging studies mainly investigated structural alterations of these subfields using volumetric measurements and microstructural modifications with mean diffusivity measurements. The aim of our work is to improve the current classification performances based on the hippocampus with a new multimodal patch-based framework combining structural and diffusivity MRI. The combination of these two MRI modalities enables the capture of subtle structural and microstructural alterations. Moreover, we propose to study the efficiency of this new framework applied to the hippocampal subfields. To this end, we compare the classification accuracy provided by the different hippocampal subfields using volume, mean diffusivity, and our novel multimodal patch-based grading framework combining structural and diffusion MRI. The experiments conducted in this work show that our new multimodal patch-based method applied to the whole hippocampus provides the most discriminating biomarker for advanced AD detection while our new framework applied into subiculum obtains the best results for AD prediction, improving by two percentage points the accuracy compared to the whole hippocampus.

Multiple Sclerosis Lesion Segmentation with Tiramisu and 2.5D Stacked Slices.

In this paper, we present a fully convolutional densely connected network (Tiramisu) for multiple sclerosis (MS) lesion segmentation. Different from existing methods, we use stacked slices from all three anatomical planes to achieve a 2.5D method. Individual slices from a given orientation provide global context along the plane and the stack of adjacent slices adds local context. By taking stacked data from three orientations, the network has access to more samples for training and can make more accurate segmentation by combining information of different forms. The conducted experiments demonstrated the competitive performance of our method. For an ablation study, we simulated lesions on healthy controls to generate images with ground truth lesion masks. This experiment confirmed that the use of 2.5D patches, stacked data and the Tiramisu model improve the MS lesion segmentation performance. In addition, we evaluated our approach on the Longitudinal MS Lesion Segmentation Challenge. The overall score of 93.1 places the L 2-loss variant of our method in the first position on the leaderboard, while the focal-loss variant has obtained the best Dice coefficient and lesion-wise true positive rate with 69.3% and 60.2%, respectively.

Adaptive fusion of texture-based grading for Alzheimer's disease classification.

Alzheimer's disease is a neurodegenerative process leading to irreversible mental dysfunctions. To date, diagnosis is established after incurable brain structure alterations. The development of new biomarkers is crucial to perform an early detection of this disease. With the recent improvement of magnetic resonance imaging, numerous methods were proposed to improve computer-aided detection. Among these methods, patch-based grading framework demonstrated state-of-the-art performance. Usually, methods based on this framework use intensity or grey matter maps. However, it has been shown that texture filters improve classification performance in many cases. The aim of this work is to improve performance of patch-based grading framework with the development of a novel texture-based grading method. In this paper, we study the potential of multi-directional texture maps extracted with 3D Gabor filters to improve patch-based grading method. We also proposed a novel patch-based fusion scheme to efficiently combine multiple grading maps. To validate our approach, we study the optimal set of filters and compare the proposed method with different fusion schemes. In addition, we also compare our new texture-based grading biomarker with state-of-the-art methods. Experiments show an improvement of AD detection and prediction accuracy. Moreover, our method obtains competitive performance with 91.3% of accuracy and 94.6% of area under a curve for AD detection.