scholarly journals Advanced Analysis of Diffusion Tensor Imaging Along With Machine Learning Provides New Sensitive Measures of Tissue Pathology and Intra-Lesion Activity in Multiple Sclerosis

2021 ◽  
Vol 15 ◽  
Author(s):  
Olayinka Oladosu ◽  
Wei-Qiao Liu ◽  
Bruce G. Pike ◽  
Marcus Koch ◽  
Luanne M. Metz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Multiple Sclerosis ◽  
Diffusion Tensor Imaging ◽  
Diffusion Tensor ◽  
Characteristic Curve ◽  
Brain Mri ◽  
Mean Diffusivity ◽  
High Angular Resolution ◽  
Advanced Analysis ◽  
Single Shell

Tissue pathology in multiple sclerosis (MS) is highly complex, requiring multi-dimensional analysis. In this study, our goal was to test the feasibility of obtaining high angular resolution diffusion imaging (HARDI) metrics through single-shell modeling of diffusion tensor imaging (DTI) data, and investigate how advanced measures from single-shell HARDI and DTI tractography perform relative to classical DTI metrics in assessing MS pathology. We examined 52 relapsing-remitting MS patients who had 3T anatomical brain MRI and DTI. Single-shell HARDI modeling yielded 5 sub-voxel-based metrics, totalling 11 diffusion measures including 4 DTI and 2 tractography metrics. Based on machine learning of 3-dimensional regions of interest, we evaluated the importance of the measures through several tissue classification tasks. These included two within-subject comparisons: lesion versus normal appearing white matter (NAWM); and lesion core versus shell. Further, by stratifying patients as having high (above 75%ile) and low (below 25%ile) number of MS lesions, we also performed 2 classifications between subjects for lesions and NAWM respectively. Results showed that in lesion-NAWM analysis, HARDI orientation distribution function (ODF) energy, DTI fractional anisotropy (FA), and HARDI orientation dispersion index were the top three metrics, which together achieved 65.2% accuracy and 0.71 area under the receiver operating characteristic curve (AUROC). In core-shell analysis, DTI mean diffusivity (MD), radial diffusivity, and FA were the top three metrics, and MD dominated the classification, which achieved 59.3% accuracy and 0.59 AUROC alone. Between patients, FA was the leading feature in lesion comparisons, while ODF energy was the best in NAWM separation. Collectively, single-shell modeling of common diffusion data can provide robust orientation measures of lesion and NAWM pathology, and DTI metrics are most sensitive to intra-lesion abnormality. Combined analysis of both advanced and classical diffusion measures may be critical for improved understanding of MS pathology.

scholarly journals Age-Related Variations in Regional White Matter Volumetry and Microstructure During the Post-adolescence Period: A Cross-Sectional Study of a Cohort of 1,713 University Students

2021 ◽  
Vol 15 ◽  
Author(s):  
Ami Tsuchida ◽  
Alexandre Laurent ◽  
Fabrice Crivello ◽  
Laurent Petit ◽  
Antonietta Pepe ◽  
...  
Keyword(s):  
White Matter ◽  
University Students ◽  
Diffusion Tensor ◽  
Brain Mri ◽  
Mean Diffusivity ◽  
High Angular Resolution ◽  
White Matter Volume ◽  
Matter Volume ◽  
Brain White Matter ◽  
Age Related

Human brain white matter undergoes a protracted maturation that continues well into adulthood. Recent advances in diffusion-weighted imaging (DWI) methods allow detailed characterizations of the microstructural architecture of white matter, and they are increasingly utilized to study white matter changes during development and aging. However, relatively little is known about the late maturational changes in the microstructural architecture of white matter during post-adolescence. Here we report on regional changes in white matter volume and microstructure in young adults undergoing university-level education. As part of the MRi-Share multi-modal brain MRI database, multi-shell, high angular resolution DWI data were acquired in a unique sample of 1,713 university students aged 18–26. We assessed the age and sex dependence of diffusion metrics derived from diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI) in the white matter regions as defined in the John Hopkins University (JHU) white matter labels atlas. We demonstrate that while regional white matter volume is relatively stable over the age range of our sample, the white matter microstructural properties show clear age-related variations. Globally, it is characterized by a robust increase in neurite density index (NDI), and to a lesser extent, orientation dispersion index (ODI). These changes are accompanied by a decrease in diffusivity. In contrast, there is minimal age-related variation in fractional anisotropy. There are regional variations in these microstructural changes: some tracts, most notably cingulum bundles, show a strong age-related increase in NDI coupled with decreases in radial and mean diffusivity, while others, mainly cortico-spinal projection tracts, primarily show an ODI increase and axial diffusivity decrease. These age-related variations are not different between males and females, but males show higher NDI and ODI and lower diffusivity than females across many tracts. These findings emphasize the complexity of changes in white matter structure occurring in this critical period of late maturation in early adulthood.

scholarly journals Prediction of the Clinical Severity of Progressive Supranuclear Palsy by Diffusion Tensor Imaging

2019 ◽  
Vol 9 (1) ◽  
pp. 40 ◽  
Author(s):  
Yao-Liang Chen ◽  
Xiang-An Zhao ◽  
Shu-Hang Ng ◽  
Chin-Song Lu ◽  
Yu-Chun Lin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Diffusion Tensor Imaging ◽  
Progressive Supranuclear Palsy ◽  
Rating Scale ◽  
Diffusion Tensor ◽  
Learning Algorithm ◽  
Mean Diffusivity ◽  
Feature Reduction ◽  
Clinical Severity ◽  
Machine Learning Algorithm

Progressive supranuclear palsy (PSP) is characterized by a rapid and progressive clinical course. A timely and objective image-based evaluation of disease severity before standard clinical assessments might increase the diagnostic confidence of the neurologist. We sought to investigate whether features from diffusion tensor imaging of the entire brain with a machine learning algorithm, rather than a few pathogenically involved regions, may predict the clinical severity of PSP. Fifty-three patients who met the diagnostic criteria for probable PSP were subjected to diffusion tensor imaging. Of them, 15 underwent follow-up imaging. Clinical severity was assessed by the neurological examinations. Mean diffusivity and fractional anisotropy maps were spatially co-registered, normalized, and parcellated into 246 brain regions from the human Brainnetome atlas. The predictors of clinical severity from a stepwise linear regression model were determined after feature reduction by the least absolute shrinkage and selection operator. Performance estimates were obtained using bootstrapping, cross-validation, and through application of the model in the patients who underwent repeated imaging. The algorithm confidently predicts the clinical severity of PSP at the individual level (adjusted R2: 0.739 and 0.892, p < 0.001). The machine learning algorithm for selection of diffusion tensor imaging-based features is accurate in predicting motor subscale of unified Parkinson’s disease rating scale and postural instability and gait disturbance of PSP.

Diffusion tensor imaging abnormalities in depressed multiple sclerosis patients

2009 ◽  
Vol 16 (2) ◽  
pp. 189-196 ◽  
Author(s):  
A. Feinstein ◽  
P. O'Connor ◽  
N. Akbar ◽  
L. Moradzadeh ◽  
CJM Scott ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Multiple Sclerosis ◽  
Diffusion Tensor Imaging ◽  
White Matter ◽  
Magnetic Resonance ◽  
Grey Matter ◽  
Diffusion Tensor ◽  
Mean Diffusivity ◽  
Resonance Imaging ◽  
Normal Appearing White Matter

Depression is common in patients with multiple sclerosis, but to date no studies have explored diffusion tensor imaging indices associated with mood change. This study aimed to determine cerebral correlates of depression in multiple sclerosis patients using diffusion tensor imaging. Sixty-two subjects with multiple sclerosis were assessed for depression with the Beck Depression Inventory (BDI-II). All subjects underwent magnetic resonance imaging. Whole brain and regional volumes were calculated for lesions (hyper/hypointense) and normal-appearing white and grey matter. Fractional anisotropy and mean diffusivity were calculated for each brain region. Magnetic resonance imaging comparisons were undertaken between depressed (Beck Depression Inventory ≥19) and non-depressed subjects. Depressed subjects (n = 30) had a higher hypointense lesion volume in the right medial inferior frontal region, a smaller normal-appearing white matter volume in the left superior frontal region, and lower fractional anisotropy and higher mean diffusivity in the left anterior temporal normal-appearing white matter and normal-appearing grey matter regions, respectively. Depressed subjects also had higher mean diffusivity in right inferior frontal hyperintense lesions. Magnetic resonance imaging variables contributed to 43% of the depression variance. We conclude that the presence of more marked diffusion tensor imaging abnormalities in the normal-appearing white matter and normal-appearing grey matter of depressed subjects highlights the importance of more subtle measures of structural brain change in the pathogenesis of depression.

scholarly journals The neural basis of fatigue in multiple sclerosis

2018 ◽  
Vol 8 (6) ◽  
pp. 492-500 ◽  
Author(s):  
Ana Margarida Novo ◽  
Sonia Batista ◽  
Carolina Alves ◽  
Otília C. d’Almeida ◽  
Inês Brás Marques ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Diffusion Tensor ◽  
Brain Mri ◽  
Mean Diffusivity ◽  
Internal Capsule ◽  
Cerebral Peduncle ◽  
Neural Basis ◽  
Focal Lesions ◽  
External Capsule ◽  
Impact Scale

BackgroundFatigue is a frequent disabling symptom in multiple sclerosis (MS), but its pathophysiology remains incompletely understood. This study aimed to explore the underlying neural basis of fatigue in patients with MS.MethodsWe enrolled 60 consecutive patients with MS and 60 healthy controls (HC) matched on age, sex, and education. Fatigue was assessed using the Portuguese version of the Modified Fatigue Impact Scale (MFIS). All participants underwent 3T brain MRI (conventional and diffusion tensor imaging [DTI] sequences). White matter (WM) focal lesions were identified and T1/T2 lesion volumes were computed. Tract-based spatial statistics were applied for voxel-wise analysis of DTI metrics fractional anisotropy and mean diffusivity (MD) on normal-appearing WM (NAWM). Using Freesurfer software, total and regional volumes of cortical and subcortical gray matter (GM) were calculated.ResultsCompared to HC, patients with MS scored significantly higher on MFIS (33.8 ± 19.7 vs 16.5 ± 15.1, p < 0.001). MFIS scores were not significantly correlated with T1/T2 lesion volumes, total GM volume, or any regional volume of cortical and subcortical GM. Significant correlations were found between global scores of MFIS and MD increase of the NAWM skeleton, including corona radiata, internal capsule, external capsule, corticospinal tract, cingulum, corpus callosum, fornix, superior longitudinal fasciculus, superior fronto-occipital fasciculus, sagittal stratum, posterior thalamic radiation, cerebral peduncle, and uncinate fasciculus.ConclusionsIn this study, fatigue was associated with widespread NAWM damage but not with lesion load or GM atrophy. Functional disconnection, caused by diffuse microstructural WM damage, might be the main neural basis of fatigue in MS.

DTI histogram parameters correlate with the extent of myoinvasion and tumor type in endometrial carcinoma: a preliminary analysis

2019 ◽  
Vol 61 (5) ◽  
pp. 675-684
Author(s):  
Adarsh Ghosh ◽  
Tulika Singh ◽  
Veenu Singla ◽  
Rashmi Bagga ◽  
Radhika Srinivasan ◽  
...  
Keyword(s):  
Diffusion Tensor Imaging ◽  
Endometrial Carcinoma ◽  
Fractional Anisotropy ◽  
Diffusion Tensor ◽  
Characteristic Curve ◽  
Mean Diffusivity ◽  
Area Under The Curve ◽  
Myometrial Invasion ◽  
Tumor Type ◽  
Planar Imaging

Background Myoinvasion and tumor-type determines surgical planning in endometrial carcinoma. Purpose To evaluate whole tumor diffusion tensor imaging histogram texture parameters in evaluating myoinvasion and tumor type in endometrial carcinoma. Material and Methods Twenty-seven patients with endometrial carcinoma underwent diffusion tensor imaging on a 1.5-T MRI system using echo-planar imaging sequence with 0 and 700 s/mm2 b values. Whole tumor histogram parameters were obtained from fractional anisotropy, mean diffusivity maps. Mann–Whitney U test and receiver operating characteristic curve analyses were used Results The mean fractional anisotropy of tumors with no myoinvasion was significantly higher than tumors which underwent myoinvasion, suggesting higher anisotropy in tumors which did not invade the myometrium. Voxel-wise heterogeneity in distribution of fractional anisotropy and mean diffusivity was seen in the form of higher uniformity and lower entropy of tumors with superficial <50% myoinvasion versus >50% myoinvasion. Uniformity, entropy, and energy of voxel-wise fractional anisotropy distribution gave an area under the curve of 0.827, 0.821, and 0.796, respectively, in predicting the presence of deep myometrial invasion while energy, entropy, and uniformity of mean diffusivity distribution in tumor gave an area under the curve of 0.84, 0.815, and 0.809 respectively. Tumor type was predicted with an area under the curve of 0.747, 0.759, and 0.765 for the uniformity, energy, and entropy of voxel-wise fractional anisotropy distribution. A logistic regression combining all the important histogram parameters obtained 94% and 88% sensitivity and 88% and 80% specificity in predicting deep myoinvasion and tumor type, respectively. Conclusion Diffusion tensor histogram analysis can better characterize endometrial carcinomas and can be used as a quantitative marker of tumor behavior.

scholarly journals Relationship between timed 25-foot walk and diffusion tensor imaging in multiple sclerosis

2016 ◽  
Vol 2 ◽  
pp. 205521731665536 ◽  
Author(s):  
Sylvia Klineova ◽  
Rebecca Farber ◽  
Catarina Saiote ◽  
Colleen Farrell ◽  
Bradley N Delman ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Multiple Sclerosis ◽  
Diffusion Tensor Imaging ◽  
Magnetic Resonance ◽  
Diffusion Tensor ◽  
Mean Diffusivity ◽  
Resonance Imaging ◽  
Corticospinal Tracts ◽  
Multiple Sclerosis Patients ◽  
And Diffusion

Objective/Background The majority of multiple sclerosis patients experience impaired walking ability, which impacts quality of life. Timed 25-foot walk is commonly used to gauge gait impairment but results can be broadly variable. Objective biological markers that correlate closely with patients’ disability are needed. Diffusion tensor imaging, quantifying fiber tract integrity, might provide such information. In this project we analyzed relationships between timed 25-foot walk, conventional and diffusion tensor imaging magnetic resonance imaging markers. Design/Methods A cohort of gait impaired multiple sclerosis patients underwent brain and cervical spinal cord magnetic resonance imaging. Diffusion tensor imaging mean diffusivity and fractional anisotropy were measured on the brain corticospinal tracts and spinal restricted field of vision at C2/3. We analyzed relationships between baseline timed 25-foot walk, conventional and diffusion tensor imaging magnetic resonance imaging markers. Results Multivariate linear regression analysis showed a statistically significant association between several magnetic resonance imaging and diffusion tensor imaging metrics and timed 25-foot walk: brain mean diffusivity corticospinal tracts (p = 0.004), brain corticospinal tracts axial and radial diffusivity (P = 0.004 and 0.02), grey matter volume (p = 0.05), white matter volume (p = 0.03) and normalized brain volume (P = 0.01). The linear regression model containing mean diffusivity corticospinal tracts and controlled for gait assistance was the best fit model (p = 0.004). Conclusions Our results suggest an association between diffusion tensor imaging metrics and gait impairment, evidenced by brain mean diffusivity corticospinal tracts and timed 25-foot walk.

scholarly journals Diffusion tensor imaging of the normal-appearing deep gray matter in primary and secondary progressive multiple sclerosis

2019 ◽  
Vol 61 (1) ◽  
pp. 85-92
Author(s):  
Ramona Woitek ◽  
Fritz Leutmezer ◽  
Assunta Dal-Bianco ◽  
Julia Furtner ◽  
Gregor Kasprian ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Diffusion Tensor Imaging ◽  
Substantia Nigra ◽  
Gray Matter ◽  
Diffusion Tensor ◽  
Mean Diffusivity ◽  
Progressive Multiple Sclerosis ◽  
Secondary Progressive Multiple Sclerosis ◽  
Secondary Progressive ◽  
Deep Gray Matter

Background Despite strongly overlapping patterns of clinical and histopathologic findings in primary and secondary progressive multiple sclerosis, differences concerning motor symptoms, central nervous system inflammation, atrophy, and demyelination that cannot be accounted for by lesion load alone remain to be elucidated. Purpose To evaluate the normal-appearing deep gray matter in patients with primary and secondary progressive multiple sclerosis, diffusion tensor imaging was used in this study. Material and Methods In 14 multiple sclerosis patients with primary and secondary progressive multiple sclerosis, axial echo-planar single-shot diffusion tensor imaging sequences with 32 diffusion-encoding directions and axial FLAIR sequences were acquired on a 3T system using an eight-channel SENSE head coil. FLAIR hyperintense multiple sclerosis lesions were outlined semi-automatically and normal-appearing deep gray matter was outlined manually (caudate nucleus, globus pallidus, putamen, thalamus, substantia nigra, and red nucleus). Fractional anisotropy and mean diffusivity values within the normal-appearing deep gray matter for the two groups were compared. Results Interhemispheric differences in mean diffusivity values (but not in fractional anisotropy), were significantly higher in primary progressive multiple sclerosis than in secondary progressive multiple sclerosis for the substantia nigra ( P = 0.04) and the putamen ( P = 0.021). Volumes, mean diffusivity, or fractional anisotropy of the remaining normal-appearing deep gray matter did not differ significantly. Conclusion This study showed a higher interhemispheric difference in the mean diffusivity in the substantia nigra and putamen in patients with primary progressive multiple sclerosis than in those with secondary progressive multiple sclerosis. These changes may represent edema, as well as axonal and myelin loss that can affect the normal-appearing deep gray matter of the two hemispheres differently and may point to differences in the laterality of motor symptoms.

Disconnection as a mechanism for social cognition impairment in multiple sclerosis

Neurology ◽  
2017 ◽  
Vol 89 (1) ◽  
pp. 38-45 ◽  
Author(s):  
Sonia Batista ◽  
Carolina Alves ◽  
Otília C. d’Almeida ◽  
Ana Afonso ◽  
Ricardo Félix-Morais ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Social Cognition ◽  
White Matter ◽  
Corpus Callosum ◽  
Diffusion Tensor ◽  
Brain Mri ◽  
Mean Diffusivity ◽  
Uncinate Fasciculus ◽  
Neural Basis ◽  
Cognition Impairment

Objective:To assess the contribution of microstructural normal-appearing white matter (NAWM) damage to social cognition impairment, specifically in the theory of mind (ToM), in multiple sclerosis (MS).Methods:We enrolled consecutively 60 patients with MS and 60 healthy controls (HC) matched on age, sex, and education level. All participants underwent ToM testing (Eyes Test, Videos Test) and 3T brain MRI including conventional and diffusion tensor imaging sequences. Tract-based spatial statistics (TBSS) were applied for whole-brain voxel-wise analysis of fractional anisotropy (FA) and mean diffusivity (MD) on NAWM.Results:Patients with MS performed worse on both tasks of ToM compared to HC (Eyes Test 58.7 ± 13.8 vs 81.9 ± 10.4, p < 0.001, Hedges g −1.886; Videos Test 75.3 ± 9.3 vs 88.1 ± 7.1, p < 0.001, Hedges g −1.537). Performance on ToM tests was correlated with higher values of FA and lower values of MD across widespread white matter tracts. The largest effects (≥90% of voxels with statistical significance) for the Eyes Test were body and genu of corpus callosum, fornix, tapetum, uncinate fasciculus, and left inferior cerebellar peduncle, and for the Videos Test genu and splenium of corpus callosum, fornix, uncinate fasciculus, left tapetum, and right superior fronto-occipital fasciculus.Conclusions:These results indicate that a diffuse pattern of NAWM damage in MS contributes to social cognition impairment in the ToM domain, probably due to a mechanism of disconnection within the social brain network. Gray matter pathology is also expected to have an important role; thus further research is required to clarify the neural basis of social cognition impairment in MS.

scholarly journals Diffusion Tensor Imaging Abnormalities in Cognitively Impaired Multiple Sclerosis Patients

2010 ◽  
Vol 37 (5) ◽  
pp. 608-614 ◽  
Author(s):  
Nadine Akbar ◽  
Nancy J. Lobaugh ◽  
Paul O'Connor ◽  
Linda Moradzadeh ◽  
Christopher J. M. Scott ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Cognitive Impairment ◽  
Diffusion Tensor Imaging ◽  
Diffusion Tensor ◽  
Neuropsychological Testing ◽  
Mean Diffusivity ◽  
Brain Parenchyma ◽  
Hyperintense Lesion ◽  
Normal Appearing White Matter ◽  
Multiple Sclerosis Patients

Background:Cognitive impairment can add to the burden of disease in patients with multiple sclerosis (MS). The aim of this study was to assess the relative importance of diffusion tensor imaging (DTI) indices derived from normal appearing white matter (NAWM) and grey matter (NAGM) in determining cognitive dysfunction in MS patients.Methods:Sixty two MS patients [51 female, mean age= 41 (sd=9.6) years, median expanded disability status scale (EDSS)=2.5] meeting modified McDonald criteria for MS underwent neuropsychological testing using the Neuropsychological Screening Battery for MS (NSBMS) and magnetic resonance imaging (MRI, 1.5T GE) that included DTI sequences. Total T1 hypointense and T2 hyperintense lesion volumes were obtained using semi-automated software. Lesion volumes were subtracted from whole-brain parenchyma to obtain measures of NAWM and NAGM. Fractional anisotropy (FA) of NAWM and mean diffusivity (MD) of NAGM were obtained.Results:Cognitive impairment was present in 11 patients (18%). These patients had higher EDSS scores, were less educated, and were more likely to have secondary progressive MS. They also had higher hypointense (p=0.001) and hyperintense (p=0.004) lesion volumes, greater NAWM atrophy (p=0.007), lower FA of total NAWM (p=0.003), and higher MD of total NAGM (p=0.015). Using a logistic regression analysis, and after controlling for demographic and disease-related differences between groups, FA of NAWM emerged as a significant predictor of cognitive impairment adding to the variance derived from lesion and atrophy data.Conclusion:This study underlies the important role of normal-appearing brain tissue in the pathogenesis of MS-related cognitive impairment.

scholarly journals Machine Learning for the Classification of Alzheimer’s Disease and Its Prodromal Stage Using Brain Diffusion Tensor Imaging Data: A Systematic Review

Processes ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1071
Author(s):  
Lucia Billeci ◽  
Asia Badolato ◽  
Lorenzo Bachi ◽  
Alessandro Tonacci
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Diffusion Tensor Imaging ◽  
Magnetic Resonance ◽  
Diffusion Tensor ◽  
Classification Problem ◽  
Computer Algorithms ◽  
Imaging Data

Alzheimer’s disease is notoriously the most common cause of dementia in the elderly, affecting an increasing number of people. Although widespread, its causes and progression modalities are complex and still not fully understood. Through neuroimaging techniques, such as diffusion Magnetic Resonance (MR), more sophisticated and specific studies of the disease can be performed, offering a valuable tool for both its diagnosis and early detection. However, processing large quantities of medical images is not an easy task, and researchers have turned their attention towards machine learning, a set of computer algorithms that automatically adapt their output towards the intended goal. In this paper, a systematic review of recent machine learning applications on diffusion tensor imaging studies of Alzheimer’s disease is presented, highlighting the fundamental aspects of each work and reporting their performance score. A few examined studies also include mild cognitive impairment in the classification problem, while others combine diffusion data with other sources, like structural magnetic resonance imaging (MRI) (multimodal analysis). The findings of the retrieved works suggest a promising role for machine learning in evaluating effective classification features, like fractional anisotropy, and in possibly performing on different image modalities with higher accuracy.

Sign in / Sign up

Export Citation Format

Share Document