Alterations in White Matter Fiber Tracts Characterized by Automated Fiber-Tract Quantification and Their Correlations With Cognitive Impairment in Neuromyelitis Optica Spectrum Disorder Patients

Exploring subtypes of multiple sclerosis through unsupervised machine learning of automated fiber quantification

PURPOSE

This study aimed to subtype multiple sclerosis (MS) patients using unsupervised machine learning on white matter (WM) fiber tracts and investigate the implications for cognitive function and disability outcomes.

MATERIALS AND METHODS

We utilized the automated fiber quantification (AFQ) method to extract 18 WM fiber tracts from the imaging data of 103 MS patients in total. Unsupervised machine learning techniques were applied to conduct cluster analysis and identify distinct subtypes. Clinical and diffusion tensor imaging (DTI) metrics were compared among the subtypes, and survival analysis was conducted to examine disability progression and cognitive impairment.

RESULTS

The clustering analysis revealed three distinct subtypes with variations in fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD). Significant differences were observed in clinical and DTI metrics among the subtypes. Subtype 3 showed the fastest disability progression and cognitive decline, while Subtype 2 exhibited a slower rate, and Subtype 1 fell in between.

CONCLUSIONS

Subtyping MS based on WM fiber tracts using unsupervised machine learning identified distinct subtypes with significant cognitive and disability differences. WM abnormalities may serve as biomarkers for predicting disease outcomes, enabling personalized treatment strategies and prognostic predictions for MS patients.

Brain white matter microstructural alterations in patients with systemic lupus erythematosus: an automated fiber quantification study

This study aimed to identify damaged segments of brain white matter fiber tracts in patients with systemic lupus erythematosus (SLE) using diffusion tensor imaging (DTI)-based automated fiber quantification (AFQ), and analyze their relationship with cognitive impairment. Clinical and imaging data for 39 female patients with SLE and for 44 female healthy controls (HCs) were collected. AFQ was used to track whole-brain white matter tracts in each participant, and each tract was segmented into 100 equally spaced nodes. DTI metrics including fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) were calculated at each node. Correlations were also explored between DTI metrics in the damaged segments of white matter fiber tracts and neuropsychological test scores of patients with SLE. Compared with HCs, SLE patients exhibited significantly lower FA values, and significantly higher MD, AD, RD values in many white matter tracts (all P < 0.05, false discovery rate-corrected). FA values in nodes 97-100 of the left inferior fronto-occipital fasciculus (IFOF) positively correlated with the mini-mental state examination score. AFQ enables precise and accurate identification of damage to white matter fiber tracts in brains of patients with SLE. FA values in the left IFOF correlate with cognitive impairment in SLE.

Cross-sectional and longitudinal evaluation of white matter microstructure damage and cognitive correlations by automated fibre quantification in relapsing-remitting multiple sclerosis patients

The purpose of this study was to characterize whole-brain white matter (WM) fibre tracts by automated fibre quantification (AFQ), capture subtle changes cross-sectionally and longitudinally in relapsing-remitting multiple sclerosis (RRMS) patients and explore correlations between these changes and cognitive performance A total of 114 RRMS patients and 71 healthy controls (HCs) were enrolled and follow-up investigations were conducted on 46 RRMS patients. Fractional anisotropy (FA), mean diffusion (MD), axial diffusivity (AD), and radial diffusivity (RD) at each node along the 20 WM fibre tracts identified by AFQ were investigated cross-sectionally and longitudinally in entire and pointwise manners. Partial correlation analyses were performed between the abnormal metrics and cognitive performance. At baseline, compared with HCs, patients with RRMS showed a widespread decrease in FA and increases in MD, AD, and RD among tracts. In the pointwise comparisons, more detailed abnormalities were localized to specific positions. At follow-up, although there was no significant difference in the entire WM fibre tract, there was a reduction in FA in the posterior portion of the right superior longitudinal fasciculus (R_SLF) and elevations in MD and AD in the anterior and posterior portions of the right arcuate fasciculus (R_AF) in the pointwise analysis. Furthermore, the altered metrics were widely correlated with cognitive performance in RRMS patients. RRMS patients exhibited widespread WM microstructure alterations at baseline and alterations in certain regions at follow-up, and the altered metrics were widely correlated with cognitive performance in RRMS patients, which will enhance our understanding of WM microstructure damage and its cognitive correlation in RRMS patients.

Aberrant white matter microstructure detected by automatic fiber quantification in pediatric myelin oligodendrocyte glycoprotein antibody-associated disease

BACKGROUND AND OBJECTIVES

Myelin oligodendrocyte glycoprotein antibody-associated diseases (MOGAD) is an idiopathic inflammatory demyelinating disorder in children, for which the precise damage patterns of the white matter (WM) fibers remain unclear. Herein, we utilized diffusion tensor imaging (DTI)-based automated fiber quantification (AFQ) to identify patterns of fiber damage and to investigate the clinical significance of MOGAD-affected fiber tracts.

METHODS

A total of 28 children with MOGAD and 31 healthy controls were included in this study. The AFQ approach was employed to track WM fiber with 100 equidistant nodes defined along each tract for statistical analysis of DTI metrics in both the entire and nodal manner. The feature selection method was used to further screen significantly aberrant DTI metrics of the affected fiber tracts or segments for eight common machine learning (ML) to evaluate their potential in identifying MOGAD. These metrics were then correlated with clinical scales to assess their potential as imaging biomarkers.

RESULTS

In the entire manner, significantly reduced fractional anisotropy (FA) was shown in the left anterior thalamic radiation, arcuate fasciculus, and the posterior and anterior forceps of corpus callosum in MOGAD (all p < 0.05). In the nodal manner, significant DTI metrics alterations were widely observed across 37 segments in 10 fiber tracts (all p < 0.05), mainly characterized by decreased FA and increased radial diffusivity (RD). Among them, 14 DTI metrics in seven fiber tracts were selected as important features to establish ML models, and satisfactory discrimination of MOGAD was obtained in all models (all AUC > 0.85), with the best performance in the logistic regression model (AUC = 0.952). For those features, the FA of left cingulum cingulate and the RD of right inferior frontal-occipital fasciculus were negatively and positively correlated with the expanded disability status scale (r = -0.54, p = 0.014; r = 0.43, p = 0.03), respectively.

CONCLUSION

Pediatric MOGAD exhibits extensive WM fiber tract aberration detected by AFQ. Certain fiber tracts exhibit specific patterns of DTI metrics that hold promising potential as biomarkers.

Exploring resting-state EEG oscillations in patients with Neuromyelitis Optica Spectrum Disorder

BACKGROUND AND OBJECTIVE

Quantitative resting-state electroencephalography (rs-EEG) is a convenient method for characterizing the functional impairments and adaptations of the brain that has been shown to be valuable for assessing many neurological and psychiatric disorders, especially in monitoring disease status and assisting neuromodulation treatment. However, it has not yet been explored in patients with neuromyelitis optica spectrum disorder (NMOSD). This study aimed to investigate the rs-EEG features of NMOSD patients and explore the rs-EEG features related to disease characteristics and complications (such as anxiety, depression, and fatigue).

METHODS

A total of 32 NMOSD patients and 20 healthy controls (HCs) were recruited; their demographic and disease information were collected, and their anxiety, depression, and fatigue symptoms were evaluated. The rs-EEG power spectra of all the participants were obtained. After excluding the participants with low-quality rs-EEG data during processing, statistical analysis was conducted based on the clinical information and rs-EEG data of 29 patients and 19 HCs. The rs-EEG power (the mean spectral energy (MSE) of absolute power and relative power in all frequency bands, as well as the specific power for all electrode sites) of NMOSD patients and HCs was compared. Furthermore, correlation analyses were performed between rs-EEG power and other variables for NMOSD patients (including the disease characteristics and complications).

RESULTS

The distribution of the rs-EEG power spectra in NMOSD patients was similar to that in HCs. The dominant alpha-peaks shifted significantly towards a lower frequency for patients when compared to HCs. The delta and theta power was significantly increased in the NMOSD group compared to that in the HC group. The alpha oscillation power was found to be significantly negatively associated with the degree of anxiety (reflected by the anxiety subscore of hospital anxiety and depression scale (HADS)) and the degree of depression (reflected by the depression subscore of HADS). The gamma oscillation power was revealed to be significantly positively correlated with the fatigue severity scale (FSS) score, while further analysis indicated that the electrode sites of almost the whole brain region showing correlations with fatigue. Regarding the disease variables, no statistically significant rs-EEG features were related to the main disease features in NMOSD patients.

CONCLUSION

The results of this study suggest that the rs-EEG power spectra of NMOSD patients show increased slow oscillations and are potential biomarkers of widespread white matter microstructural damage in NMOSD. Moreover, this study revealed the rs-EEG features associated with anxiety, depression, and fatigue in NMOSD patients, which might help in the evaluation of these complications and the development of neuromodulation treatment. Quantitative rs-EEG analysis may play an important role in the management of NMOSD patients, and future studies are warranted to more comprehensively understand its application value.

In patients with mild disability NMOSD: is the alteration in the cortical morphological or functional network topological properties more significant

Objective

To assess the alteration of individual brain morphological and functional network topological properties and their clinical significance in patients with neuromyelitis optica spectrum disorder (NMOSD).

Materials and methods

Eighteen patients with NMOSD and twenty-two healthy controls (HCs) were included. The clinical assessment of NMOSD patients involved evaluations of disability status, cognitive function, and fatigue impact. For each participant, brain images, including high-resolution T1-weighted images for individual morphological brain networks (MBNs) and resting-state functional MR images for functional brain networks (FBNs) were obtained. Topological properties were calculated and compared for both MBNs and FBNs. Then, partial correlation analysis was performed to investigate the relationships between the altered network properties and clinical variables. Finally, the altered network topological properties were used to classify NMOSD patients from HCs and to analyses time- to-progression of the patients.

Results

The average Expanded Disability Status Scale score of NMOSD patients was 1.05 (range from 0 to 2), indicating mild disability. Compared to HCs, NMOSD patients exhibited a higher normalized characteristic path length (λ) in their MBNs (P = 0.0118, FDR corrected) but showed no significant differences in the global properties of FBNs (p: 0.405-0.488). Network-based statistical analysis revealed that MBNs had more significantly altered connections (P< 0.01, NBS corrected) than FBNs. Altered nodal properties of MBNs were correlated with disease duration or fatigue scores (P< 0.05/6 with Bonferroni correction). Using the altered nodal properties of MBNs, the accuracy of classification of NMOSD patients versus HCs was 96.4%, with a sensitivity of 93.3% and a specificity of 100%. This accuracy was better than that achieved using the altered nodal properties of FBNs. Nodal properties of MBN significantly predicted Expanded Disability Status Scale worsening in patients with NMOSD.

Conclusion

The results indicated that patients with mild disability NMOSD exhibited compensatory increases in local network properties to maintain overall stability. Furthermore, the alterations in the morphological network nodal properties of NMOSD patients not only had better relevance for clinical assessments compared with functional network nodal properties, but also exhibited predictive values of EDSS worsening.

Alterations in white matter fiber tracts and their correlation with flying cadet behavior

An increasing number of studies have shown that flight training alters the human brain structure; however, most studies have focused on gray matter, and the exploration of white matter structure has been largely neglected. This study aimed to investigate the changes in white matter structure induced by flight training and estimate the correlation between such changes and psychomotor and flight performance. Diffusion tensor imaging data were obtained from 25 flying cadets and 24 general college students. Data were collected in 2019 and 2022 and analyzed using automated fiber quantification. This study found no significant changes in the flight group in 2019. However, in 2022, the flight group exhibited significant alterations in the diffusion tensor imaging of the right anterior thalamic radiation, left cingulum cingulate, bilateral superior longitudinal fasciculus, and left arcuate fasciculus. These changes occurred within local nodes of the fiber tracts. In addition, we found that changes in fiber tracts in the 2022 flight group were correlated with the reaction time of the psychomotor test task and flight duration. These findings may help improve flight training programs and provide new ideas for the selection of excellent pilots.

Automated three-dimensional major white matter bundle segmentation using diffusion magnetic resonance imaging

White matter bundle segmentation using diffusion magnetic resonance imaging fiber tractography enables detailed evaluation of individual white matter tracts three-dimensionally, and plays a crucial role in studying human brain anatomy, function, development, and diseases. Manual extraction of streamlines utilizing a combination of the inclusion and exclusion of regions of interest can be considered the current gold standard for extracting white matter bundles from whole-brain tractograms. However, this is a time-consuming and operator-dependent process with limited reproducibility. Several automated approaches using different strategies to reconstruct the white matter tracts have been proposed to address the issues of time, labor, and reproducibility. In this review, we discuss few of the most well-validated approaches that automate white matter bundle segmentation with an end-to-end pipeline, including TRActs Constrained by UnderLying Anatomy (TRACULA), Automated Fiber Quantification, and TractSeg.