Corpus Callosum Segmentation Research Articles

Deep Learning-Based Corpus Callosum Segmentation from Brain Images: A Review

Deep Learning-Based Corpus Callosum Segmentation from Brain Images: A Review

Cognitive Impairment in Cerebral Small Vessel Disease Is Associated with Corpus Callosum Microstructure Changes Based on Diffusion MRI.

to evaluate microstructural changes in the corpus callosum (CC) using diffusion MRI (D-MRI) approaches in cSVD patients with different severity of CI and reveal the most sensitive correlations of diffusion metrics with CI. the study included 166 cSVD patients (51.8% women; 60.4 ± 7.6 years) and 44 healthy volunteers (65.9% women; 59.6 ± 6.8 years). All subjects underwent D-MRI (3T) with signal (diffusion tensor and kurtosis) and biophysical (neurite orientation dispersion and density imaging, NODDI, white matter tract integrity, WMTI, multicompartment spherical mean technique, MC-SMT) modeling in three CC segments as well as a neuropsychological assessment. in cSVD patients, microstructural changes were found in all CC segments already at the subjective CI stage, which was found to worsen into mild CI and dementia. More pronounced changes were observed in the forceps minor. Among the signal models FA, MD, MK, RD, and RK, as well as among the biophysical models, MC-SMT (EMD, ETR) and WMTI (AWF) metrics exhibited the largest area under the curve (>0.85), characterizing the loss of microstructural integrity, the severity of potential demyelination, and the proportion of intra-axonal water, respectively. Conclusion: the study reveals the relevance of advanced D-MRI approaches for the assessment of brain tissue changes in cSVD. The identified diffusion biomarkers could be used for the clarification and observation of CI progression.

Significance of Corticospinal, Associative and Inter-Hemispheric Tracts for the Development of Posttraumatic Hemiparesis

Motor disorders are among the most common consequences of severe craniocerebral injury (traumatic brain injury — TBI). Deeper insights into pathophysiological mechanisms of these disorders is important both from a theoretical point of view and in terms of improving neurorehabilitation approaches.The aim of the study was to investigate the correlation of right–sided posttraumatic hemiparesis severity with composite characteristics of fractional anisotropy (FA) in the segments of the corpus callosum (CC), corticospinal tract (CST) and the inferior fronto-occipital fasciculus (IFO) at different stages of traumatic disease (acute, subacute and long-term periods).Material and methods. Cases of 43 patients with TBI were analyzed (28 men and 15 women aged 13 to 59 years, mean age 28±9 years). Forty patients were diagnosed with severe TBI with diffuse axonal damage, three patients had moderate severity TBI. Long-term follow up included continuous clinical and neurological examination with evaluation of patient’s level of consciousness using the CRS-R scale, and the degree of motor deficits in right-sided hemiparesis using a five-point scale. During three post-TBI periods (up to 1 month, from 1 to 6 months, and from 6 to 12 months), patients were examined using diffusion tensor MRI (DTI), tractography and FA. Motor, cortico-spinal tracts and IFO were divided by measurement grid, correlations between FA and scores of right-sided hemiparesis were calculated for each segment.Results. FA correlations (P0.05) with the severity of hemiparesis were established not only for CST motor-specific segments, but also for some CC and IFO segments. In the early period of TBI significant correlations with hemiparesis severity were found not only in the contralateral CST segments, but also in the ipsilateral ones. Significant differences in FA in the related CC and CST segments were found between the groups with good and limited motor recovery: at all stages after TBI, FA was higher in patients with successful recovery.Conclusion. The results of the study provide better insight into pathophysiological mechanisms of post-traumatic motor disorders development, therefore favoring optimization of therapeutic strategies.

Brain ventricle and choroid plexus morphology as predictor of treatment response in major depression: Findings from the EMBARC study

Recent observations suggest a role of the volume of the cerebral ventricle volume, corpus callosum (CC) segment volume, in particular that of the central-anterior part, and choroid plexus (CP) volume for treatment resistance of major depressive disorder (MDD). An increased CP volume has been associated with increased inflammatory activity and changes in the structure of the ventricles and corpus callosum. We attempt to replicate and confirm that these imaging markers are associated with clinical outcome in subjects from the EMBARC study, as implied by a recent pilot study. The EMBARC study is a placebo controlled randomized study comparing sertraline vs. placebo in patients with MDD to identify biological markers of therapy resistance. Association of baseline volumes of the lateral ventricles (LVV), choroid plexus volume (CPV) and volume of segments of the CC with treatment response after 4 weeks treatment was evaluated. 171 subjects (61 male, 110 female) completed the 4 week assessments; gender and age were taken into account for this analyses. As previously reported, no treatment effect of sertraline vs. placebo was observed, therefore the study characterized prognostic markers of response in the pooled population. Change in depression severity was identified by the ratio of the Hamilton-Depression rating scale 17 (HAMD-17) at week 4 divided by the HAMD-17 at baseline (HAMD-17 ratio). Volumes of the lateral ventricles and choroid plexi were positively correlated with the HAMD-17 ratio, indication worse outcome with larger ventricles and choroid plexus volumes, whereas the volume of the central-anterior corpus callosum was negatively correlated with the HAMD-17 ratio. Responders (n = 54) had significantly smaller volumes of the lateral ventricles and CP compared to non-responders (n = 117), whereas the volume of mid-anterior CC was significantly larger compared to non-responders (n = 117), confirming our previous findings. In an exploratory way associations between enlarged LVV and CPV and signs of lipid dysregulation were observed. In conclusion, we confirmed that volumes of lateral ventricles, choroid plexi and the mid-anterior corpus callosum are associated with clinical improvement of depression and may be indicators of metabolic/inflammatory activity.

Corpus Callosum Atrophy in Alcohol-Dependent Men with Memory Disorders and Visual Attention Difficulties.

The earlier research confirm the relationship between structural changes in the corpus callosum and difficulties in attention and memory in the group of patients with alcohol use disorder (AUD). Nevertheless, the image of auditory and visual memory disorders in men with gradual atrophy of the corpus callosum and different alcohol abuse duration, it has not been explained yet. The overriding objective of this study was: (1) to determine whether there are principal and interaction effects of visuospatial and auditory-verbal memory on alcohol consumption and cross-sectional corpus callosum area in men with alcohol use disorder, (2) to assess the impact of callosal changes on the memory and visual attention processes. 97 men with alcohol use disorder were examined. T1-weighted scans were used to carry out corpus callosum segmentation and volumetric measurements. The cognition profile included two domains: attention, memory (visuospatial and auditory-verbal). The results showed that participants with visuospatial memory disorder had inferior education background, and were characterized by a longer duration of alcohol abuse, more severe alcohol use disorder, and greater alcohol consumption per day. Second, alcohol-dependent men with auditory and visual memory disorders had a smaller frontal and posterior part of the corpus callosum areas. Additionally, among the alcohol-dependent men with memory disorders the smaller rostral body of corpus callosum was determined by the longer alcohol abuse duration. On the other hand, the smaller rostral body of corpus callosum was predicted by the older age only in alcohol-dependent men with normal memory. Among all examined individuals were observed a statistically significant relationships among visual attention, visuospatial memory and corpus callosum subregions including in particular genu and isthmus. The smaller corpus callosum cross-sectional area significantly affects visual attention and memory difficulties in alcohol use disorder, especially have differentiated the patients with normal and disordered memory. Longer alcohol abuse duration plays also a significant role in the corpus callosum atrophy in alcohol-dependent men with disordered memory (visuospatial in particular).

A Comprehensive Corpus Callosum Segmentation Tool for Detecting Callosal Abnormalities and Genetic Associations from Multi Contrast MRIs.

Structural alterations of the midsagittal corpus callosum (midCC) have been associated with a wide range of brain disorders. The midCC is visible on most MRI contrasts and in many acquisitions with a limited field-of-view. Here, we present an automated tool for segmenting and assessing the shape of the midCC from T1w, T2w, and FLAIR images. We train a UNet on images from multiple public datasets to obtain midCC segmentations. A quality control algorithm is also built-in, trained on the midCC shape features. We calculate intraclass correlations (ICC) and average Dice scores in a test-retest dataset to assess segmentation reliability. We test our segmentation on poor quality and partial brain scans. We highlight the biological significance of our extracted features using data from over 40,000 individuals from the UK Biobank; we classify clinically defined shape abnormalities and perform genetic analyses.

Disruption of corpus callosum microstructural integrity by diffusion MRI as a predictor of progression of cerebral microangiopathy

To assess the microstructural integrity of the corpus callosum in patients with cerebral small vessel disease (cSVD) using signal and biophysical diffusion MRI models and to identify the most sensitive markers of disease progression. Diffusion MRI (3 Tesla) was performed in 166 patients (51.8% women; mean age 60.4±7.6) with cSVD and cognitive impairment of varying severity and in 44 healthy volunteers (65.9% women; mean age 59.6±6.8), followed by calculation of signal (diffusion tensor and diffusion kurtosis) and biophysical (WMTI, NODDI, MC-SMT) models, from which profiles of three corpus callosum segments were constructed. The best results were obtained for metrics in the forceps minor and body of the corpus callosum. Among the metrics of the signal models in the forceps minor, fraction anisotropy (FA) and mean diffusion (MD), which characterize the overall loss of microstructural integrity and increase in extra-axonal water, as well as indirect markers of demyelination when considering transverse diffusion parameters (radial diffusion and radial kurtosis), had the larger area under the curve according to the ROC analysis. Among the metrics of the biophysical models in the forceps minor, a larger area under the curve was found in the MC-SMT model for extra-axonal transverse diffusion (ETR), mean diffusion (EMD), and intra-axonal water fraction (INTRA), and in the WMTI model for intra-axonal water fraction (AWF). ETR had high inverse correlations with INTRA and AWF, while INTRA and AWF had high direct intercorrelations. Metrics of signaling (FA, MD, RD, RK) and biophysical patterns (ETR, EMD, INTRA, AWF) in the forceps minor and the corpus callosum body can be considered as indicators of cSVD progression. They indicate disease progression, mainly by an increase in extra-axonal water with the development of demyelination and tissue degeneration in the corpus callosum.

Topology of diffusion changes in corpus callosum in Alzheimer's disease: An exploratory case-control study.

This study aims to assess the integrity of white matter in various segments of the corpus callosum in Alzheimer's disease (AD) by using metrics derived from diffusion tensor imaging (DTI), diffusion kurtosis imaging (DKI) and white matter tract integrity model (WMTI) and compare these findings to healthy controls (HC). The study was approved by the institutional ethics board. 12 AD patients and 12 HC formed the study population. All AD patients were recruited from a tertiary neurology memory clinic. A standardized battery of neuropsychological assessments was administered to the study participants by a trained rater. MRI scans were performed with a Philips Ingenia 3.0T scanner equipped with a 32-channel head coil. The protocol included a T1-weighted sequence, FLAIR and a dMRI acquisition. The dMRI scan included a total of 71 volumes, 8 at b = 0 s/mm2, 15 at b = 1,000 s/mm2 and 48 at b = 2,000 s/mm2. Diffusion data fit was performed using DKI REKINDLE and WMTI models. We detected changes suggesting demyelination and axonal degeneration throughout the corpus callosum of patients with AD, most prominent in the mid-anterior and mid-posterior segments of CC. Axial kurtosis was the most significantly altered metric, being reduced in AD patients in almost all segments of corpus callosum. Reduced axial kurtosis in the CC segments correlated with poor cognition scores in AD patients in the visuospatial, language and attention domains.

AUTOMATED SEGMENTATION OF CORPUS CALLOSUM IN BRAIN MR IMAGES IN ALZHEIMER’S CONDITIONS USING IMPROVED UNET++ MODEL

The Corpus Callosum (CC) is a large white matter bundle that connects the left and right cerebral hemispheres of the human brain. It is susceptible to atrophy as Alzheimer’s disease progresses. The robust segmentation of CC allows quantitative investigation of its structural changes. However, deep learning-based CC segmentation is less explored. In this work, an improved UNet model is proposed for CC segmentation from two-dimensional T1-weighted mid-sagittal brain MRI. For this, mid-sagittal scans (n = 184) from the publicly available Open Access Series of Imaging Studies (OASIS) brain MRI database are used. The images are fed to an improved UNet++ network. The architecture contains a fully convolutional network with two paths, contracting and extracting, that are connected in a U-shape to automatically extract spatial information. Leave one out Cross-Validation (LooCV) method is used to evaluate the robustness of the proposed method. Results show that the proposed approach is able to segment CC from MR images. The proposed method yields the Dice score of 98.43%, and Jaccard index of 98.53%. The improved UNet++ model obtained the highest sensitivity of 99.21% for AD conditions. Further, the performance of the proposed model has been validated against the state-of-the-art methods. Thus, the proposed approach could be useful for the segmentation of MR images in clinical condition.

Neuropsychological and morphometric biomarkers of poor prognosis in patients with mild cognitive impairment

Abstract. Despite a high prevalence of mild cognitive impairment (MCI), there are no accepted algorithms of diff erentiating the syndrome and the prognosis evaluation of later cognitive decline at this time. Objective. To identify biomarkers of poor prognosis in the various MCI types by optimizing neuropsychological examination in combination with MRI morphometry of brain structures. Patients and methods. We examined 45 patients (9 men, 36 women, mean age 72 ± 6.7 years) with MCI according to the modifi ed Petersen’s criteria and the DSM-5 criteria. All patients underwent the MMSE scale, the Detailed Neuropsychological Testing (DNT), which included a Ten Words Test (TWT), a “Double Test” (DT), a visual acuity test, a high-fi eld magnetic resonance imaging (MRI) of the brain with morphometry of cerebral structures (FreeSurfer, FSL). Results. According to the MMSE score, MCI were found in 26 (58%) patients. During the DNT, depending on the state of memory, 14 participants of the study identifi ed a non-amnestic type of MCI (na-MCI), 15 — an amnestic variant with impaired reproduction (ar-MCI), and 16 people — an amnestic type with a primary memory defect (apm-MCI). Volume changes of the anterior corpus callosum segment (CCA) were signifi cantly associated with the Immediate Recall after 4th reading and the Delayed Recall in the general MCI group (rho = 0.58; 0.58; p < 0.05) and the apmMCI group (rho = 0.6; 0.56; p < 0.05). Kruskal–Wallis Test showed that there were signifi cant group diff erences in the volumes of the CCA, right caudate nucleus, left cerebellar hemisphere cortex, posterior corpus callosum segment and left thalamus. At the same time, the fi rst three structures were combined into a set of informative features for differentiating the type of MCI based on the results of Forward stepwise Discriminant Analysis with a 77.3% accurate classifi cation rate (Wilks’s Lambda: 0.35962; approx. F (6.78) = 8.678, p < 0.001). ROC-analysis established the threshold values of the CCA volumes of ≤ 0.05% and the right caudate nucleus volumes of ≤ 0.23% (81.25% sensitivity in both cases; 62.1% and 60.7% specifi city; AUC 0.787 and 0.767; 95% CI 0.639–0.865 and 0.615–0.881; OR 7.1 and 6.7 (95% CI 1.6–30.6 and 1.6–29), associated with a memory defect in persons with MCI, while the ORs are 7.1 and 6.7 (95% CI 1.6–30.6 and 1.6–29), respectively. When both cerebral structures were included in the logit model, 88.6% classifi cation accuracy, 92.6% sensitivity, and 82.4% specifi city of the method were achieved. Conclusion. It has been demonstrated that classifying patients into the various types of MCI based on the data of memory function refl ected by the DNT and supplemented with MRI morphometry of the brain areas may be used as a sensitive and specifi c instrument for determining the category of patients with a high risk of Alzheimer’s disease. A neuropsychological profi le with a defect in primary memory, atrophic changes in anterior segment of the corpus callosum and the right caudate nucleus have been proposed as biomarkers of poor prognosis. Further longitudinal studies are necessary to clarify the proposed biomarkers of poor prognosis information and to detail the mechanisms of the neurodegenerative process.

CCsNeT: Automated Corpus Callosum segmentation using fully convolutional network based on U-Net

BackgroundCorpus Callosum (CC) is the most prominent white matter bundle in the human brain that connects the left and right cerebral hemispheres. The present paper proposes a novel method for CC segmentation from 2D T1- weighted mid-sagittal brain MRI. The robust segmentation of CC in the mid-sagittal plane plays a vital role in the quantitative study of CC structural features related to various neurological disorders such as Autism, epilepsy, Alzheimer's disease, and more. MethodologyIn this perspective, the current work proposes a Fully Convolutional Network (FCN), a deep learning architecture-based U-Net model for automated CC segmentation from 2D brain MRI images referred to as CCsNeT. The architecture consists of a 35-layers deep, fully convolutional network with two paths, namely contracting and extracting, connected in a U-shape that automatically extracts spatial information. ResultsThis attempt uses the benchmark brain MRI database comprising ABIDE and OASIS for the experimental investigation. Compared to existing CC segmentation methodologies, the proposed CCsNeT presented improved results achieving Dice Coefficient = 96.74%, and Sensitivity = 97.01% with ABIDE dataset and were further validated against the variants of U-Net model U-Net++, MultiResU-Net, and CE-Net. Further, the performance of CCsNeT has been validated on OASIS and Real-Time Images dataset. ConclusionFinally, the proposed CCsNeT extracts important CC characteristics such as CC area (CCA) and total brain area (TBA) to categorize the considered 2D MRI slices into control and autism spectrum disorder (ASD) groups, thereby minimizing the inter-observer and intra-observer variability.

3d Reconstruction from 2d Corpus Callosum Segmentation

3d Reconstruction from 2d Corpus Callosum Segmentation

Segmental Alterations of the Corpus Callosum in Progressive Supranuclear Palsy: A Multiparametric Magnetic Resonance Imaging Study.

Background: The regional distribution of the widespread cerebral morphological alterations in progressive supranuclear palsy (PSP) is considered to include segmental parts of the corpus callosum (CC).Objective: The study was designed to investigate the regional white matter (WM) of the CC by T1 weighted magnetic resonance imaging (T1w MRI) data combined with diffusion tensor imaging (DTI) data in PSP patients, differentiated in the variants Richardson syndrome and PSP-parkinsonism, and to compare them with Parkinson’s Disease (PD) patients and healthy controls, in order to identify macro- and micro-structural alterations in vivo.Methods: MRI-based WM mapping was used to perform an operator-independent segmentation for the different CC segments in 66 PSP patients vs. 66 PD patients vs. 44 matched healthy controls. The segmentation was followed by both planimetric and texture analysis of the separated CC areas for the comparison of the three groups. Results were complemented by a DTI-based tract-of-interest analysis of the associated callosal tracts.Results: Significant alterations of the parameters entropy and homogeneity compared to controls were observed for PSP as well as for PD for the CC areas I, II, and III. The inhomogeneity in area II in the PSP cohort was the highest and differed significantly from PD. A combined score was defined as a potential marker for the different types of neurodegenerative parkinsonism; receiver operating characteristics (ROC) curves were calculated with areas under the curve values of 0.86 for PSP vs. controls, 0.72 for PD vs. controls, and 0.69 for PSP vs. PD, respectively.Conclusion: The multiparametric MRI texture and DTI analysis demonstrated extensive alterations of the frontal CC in neurodegenerative parkinsonism, whereas regional CC atrophy cannot be regarded as a constant neuroimaging feature of PSP. Specifically, the comparison PSP vs. PD revealed significant alterations in callosal area II. The combination of the texture and the DTI parameters might contribute as a neuroimaging marker for the assessment of the CC in PSP, including the differentiation vs. PD.

Segmentation of corpus callosum based on tensor fuzzy clustering algorithm.

The corpus callosum in the midsagittal plane plays a crucial role in the early diagnosis of diseases. When the anisotropy of the diffusion tensor in the midsagittal plane is calculated, the anisotropy of corpus callosum is close to that of the fornix, which leads to blurred boundary of the segmentation region. To apply a fuzzy clustering algorithm combined with new spatial information to achieve accurate segmentation of the corpus callosum in the midsagittal plane in diffusion tensor images. In this algorithm, a fixed region of interest is selected from the midsagittal plane, and the anisotropic filtering algorithm based on tensor is implemented by replacing the gradient direction of the structural tensor with an eigenvector, thus filtering the diffusion tensor of region of interest. Then, the iterative clustering center based on K-means clustering is used as the initial clustering center of tensor fuzzy clustering algorithm. Taking filtered diffusion tensor as input data and different metrics as similarity measures, the neighborhood diffusion tensor voxel calculation method of Log Euclidean framework is introduced in the membership function calculation, and tensor fuzzy clustering algorithm is proposed. In this study, MGH35 data from the Human Connectome Project (HCP) are tested and the variance, accuracy and specificity of the experimental results are discussed. Segmentation results of three groups of subjects in MGH35 data are reported. The average segmentation accuracy is 97.34%, and the average specificity is 98.43%. When segmenting the corpus callosum of diffusion tensor imaging, our method cannot only effective denoise images, but also achieve high accuracy and specificity.

Extraction and Evaluation of Corpus Callosum from 2D Brain MRI Slice: A Study with Cuckoo Search Algorithm.

The work proposes a computer-based diagnosis method (CBDM) to delineate and assess the corpus callosum (CC) segment from the 2-dimensional (2D) brain magnetic resonance images (MRI). The proposed CBDM consists of two parts: (1) preprocessing and (2) postprocessing sections. The preprocessing tools have a multithreshold technique with the chaotic cuckoo search (CCS) algorithm and a preferred threshold procedure. The postprocessing employs a delineation process for extracting the CC section. The proposed CBDM finally extracts the vital CC parameters, such as total brain area (TBA) and CC area (CCA) to classify the considered 2D MRI slices into the control and autism spectrum disorder (ASD) groups. This attempt considers the benchmark brain MRI database which includes ABIDE and MIDAS for the experimental investigation. The results obtained with ABIDE dataset are further confirmed against the fuzzy C-means driven level set (FCM + LS) and multiphase level set (MLS) technique and the proposed CBDM with Shannon entropy along with active contour (SE + AC) presented improved result in comparison to the existing methodologies. Further, the performance of CBDM is confirmed on MIDAS and clinical dataset. The experimental outcomes approve that the proposed CBDM extracts the CC section from the 2D MR brain images that have higher accuracy compared to alternative techniques.

Longitudinal Evaluation of Cerebellar Signs of H-ABC Tubulinopathy in a Patient and in the taiep Model.

Hypomyelination with atrophy of the basal ganglia and cerebellum (H-ABC) is a central neurodegenerative disease due to mutations in the tubulin beta-4A (TUBB4A) gene, characterized by motor development delay, abnormal movements, ataxia, spasticity, dysarthria, and cognitive deficits. Diagnosis is made by integrating clinical data and radiological signs. Differences in MRIs have been reported in patients that carry the same mutation; however, a quantitative study has not been performed so far. Our study aimed to provide a longitudinal analysis of the changes in the cerebellum (Cb), corpus callosum (CC), ventricular system, and striatum in a patient suffering from H-ABC and in the taiep rat. We correlated the MRI signs of the patient with the results of immunofluorescence, gait analysis, segmentation of cerebellum, CC, and ventricular system, performed in the taiep rat. We found that cerebellar and callosal changes, suggesting a potential hypomyelination, worsened with age, in concomitance with the emergence of ataxic gait. We also observed a progressive lateral ventriculomegaly in both patient and taiep, possibly secondary to the atrophy of the white matter. These white matter changes are progressive and can be involved in the clinical deterioration. Hypomyelination with atrophy of the basal ganglia and cerebellum (H-ABC) gives rise to a spectrum of clinical signs whose pathophysiology still needs to be understood.

Pediatrik Popülasyonda Korpus Kallozum Morfometrisinin Değerlendirilmesi, Cinsiyetler Arasında Fark Var Mı?

Aim: Corpus callosum (CC) is a white matter structure and it is the largest interhemispheric commissure that connects the brain hemispheres. The morphology of CC can be affected by congenital and acquired diseases, sex, age, and hand selection. This study aims to investigate morphometric features of CC by age and gender.Material and Methods: Thickness of all corpus callosum segments and length of the long axis of the CC of the healthy pediatric population were measured via magnetic resonance imaging (MRI) from the midsagittal line where the septum pellucidum and massa intermedia can be monitored. A total of 240 participants (120 males and 120 females) were divided into four age groups; 0-2 age group, 3-6 age group, 7-11 age group, and 12-17 age group and thickness of the five segments of the CC (rostrum, genu, body, isthmus, splenium) and anterior-posterior length of the CC were measured. Results: Thicknesses of four segments that included genu, body, isthmus, and splenium (except the rostrum) and length of the long axis of CC increased significantly with age in both genders. However, when we evaluated all participants without gender discrimination, the thickness of all segments of CC and length of the long axis are observed to increase significantly. Conclusion: The obtained data from the healthy pediatric population will help differentiate the abnormal morphometric changes of CC due to congenital and acquired diseases.

Morphometric mapping of the macrostructural abnormalities of midsagittal corpus callosum in Wilson's disease.

Background and PurposeThe corpus callosum (CC) consists of topographically arranged white matter (WM) fibers. Previous studies have indicated the CC to be discretely involved in WD. In this study, we strived to characterize the macrostructural properties of the CC using midsagittal cross-sectional area and thickness profile measurements.Materials and MethodsThis study was performed using archived magnetic resonance imaging (MRI) scans of 14 patients with WD and 14 age- and gender-matched healthy controls. Using an automated software pipeline for morphometric profiling, the midsagittal CC was segmented into five sub-regions (CC1–5) according to the Hofer–Frahm scheme. The mean thickness and area of different CC segments and their clinical and cognitive correlates were identified.ResultsThe mean area was significantly different only in CC2 segment (94.2 ± 25.5 vs. 118.6 ± 19.7 mm2, corrected P < 0.05). The mean thickness was significantly different in CC1 (5.06 ± 1.15 vs. 6.93 ± 0.89 mm, corrected P < 0.05), CC2 (3.73 ± 0.96 vs. 4.87 ± 1.01 mm, corrected P < 0.05), and CC3 segments (3.42 ± 0.84 vs. 3.94 ± 0.72 mm, corrected P < 0.05). The age at onset of neurological symptoms and MMSE score was significantly correlated with the morphometric changes of CC1 and CC2 segments.ConclusionMorphological changes of the CC are discrete in WD. Morphometric loss of CC was associated with an earlier onset of neurological symptoms and cognitive dysfunction in WD.

Tract-specific MRI measures explain learning and recall differences in multiple sclerosis.

Cognitive difficulties are common and a key concern for people with multiple sclerosis. Advancing knowledge of the role of white matter pathology in multiple sclerosis-related cognitive impairment is essential as both occur early in the disease with implications for early intervention. Consequently, this cross-sectional study asked whether quantifying the relationships between lesions and specific white matter structures could better explain co-existing cognitive differences than whole brain imaging measures. Forty participants with relapse-onset multiple sclerosis underwent cognitive testing and MRI at 3 Tesla. They were classified as cognitively impaired (n = 24) or unimpaired (n = 16) and differed across verbal fluency, learning and recall tasks corrected for intelligence and education (corrected P-values = 0.007–0.04). The relationships between lesions and white matter were characterized across six measures: conventional voxel-based T2 lesion load, whole brain tractogram load (lesioned volume/whole tractogram volume), whole bundle volume, bundle load (lesioned volume/whole bundle volume), Tractometry (diffusion-tensor and high angular resolution diffusion measures sampled from all bundle streamlines) and lesionometry (diffusion measures sampled from streamlines traversing lesions only). The tract-specific measures were extracted from corpus callosum segments (genu and isthmus), striato-prefrontal and -parietal pathways, and the superior longitudinal fasciculi (sections I, II and III). White matter measure-task associations demonstrating at least moderate evidence against the null hypothesis (Bayes Factor threshold < 0.2) were examined using independent t-tests and covariate analyses (significance level P < 0.05). Tract-specific measures were significant predictors (all P-values < 0.05) of task-specific clinical scores and diminished the significant effect of group as a categorical predictor in Story Recall (isthmus bundle load), Figure Recall (right striato-parietal lesionometry) and Design Learning (left superior longitudinal fasciculus III volume). Lesion load explained the difference in List Learning, whereas Letter Fluency was not associated with any of the imaging measures. Overall, tract-specific measures outperformed the global lesion and tractogram load measures. Variation in regional lesion burden translated to group differences in tract-specific measures, which in turn, attenuated differences in individual cognitive tasks. The structural differences converged in temporo-parietal regions with particular influence on tasks requiring visuospatial-constructional processing. We highlight that measures quantifying the relationships between tract-specific structure and multiple sclerosis lesions uncovered associations with cognition masked by overall tract volumes and global lesion and tractogram loads. These tract-specific white matter quantifications show promise for elucidating the relationships between neuropathology and cognition in multiple sclerosis.

Deep Learning Corpus Callosum Segmentation as a Neurodegenerative Marker in Multiple Sclerosis.

Corpus callosum atrophy is a sensitive biomarker of multiple sclerosis (MS) neurodegeneration but typically requires manual 2D or volumetric 3D-based segmentations. We developed a supervised machine learning algorithm, DeepnCCA, for corpus callosum segmentation and relate callosal morphology to clinical disability using conventional MRI scans collected in clinical routine. In a prospective study of 553 MS patients with 704 acquisitions, 200 unique 2D T2 -weighted MRI scans were delineated to develop, train, and validate DeepnCCA. Comparative FreeSurfer segmentations were obtained in 504 3D T1 -weighted scans. Both FreeSurfer and DeepnCCA outputs were correlated with clinical disability. Using principal component analysis of the DeepnCCA output, the morphological changes were explored in relation to clinical disease burden. DeepnCCA and manual segmentations had high similarity (Dice coefficients 98.1 .11%, 89.3 .76%, for intracranial and corpus callosum area, respectively through 10-fold cross-validation). DeepnCCA had numerically stronger correlations with cognitive and physical disability as compared to FreeSurfer: Expanded disability status scale (EDSS) ±6 months (r = -.22 P = .002; r = -.17, P = .013), future EDSS (r = -.26, P<.001; r = -.17, P = .012), and future symbol digit modalities test (r = .26, P = .001; r = .24, P = .003). The corpus callosum became thinner with increasing cognitive and physical disability. Increasing physical disability, additionally, significantly correlated with a more angled corpus callosum. DeepnCCA (https://github.com/plattenmichael/DeepnCCA/) is an openly available tool that can provide fast and accurate corpus callosum measurements applicable to large MS cohorts, potentially suitable for monitoring disease progression and therapy response.