Quantitative MRI texture analysis in chronic active multiple sclerosis lesions

Microstructural characterization of multiple sclerosis lesion phenotypes using multiparametric longitudinal analysis

BACKGROUND AND OBJECTIVES

In multiple sclerosis (MS), slowly expanding lesions were shown to be associated with worse disability and prognosis. Their timely detection from cross-sectional data at early disease stages could be clinically relevant to inform treatment planning. Here, we propose to use multiparametric, quantitative MRI to allow a better cross-sectional characterization of lesions with different longitudinal phenotypes.

METHODS

We analysed T1 and T2 relaxometry maps from a longitudinal cohort of MS patients. Lesions were classified as enlarging, shrinking, new or stable based on their longitudinal volumetric change using a newly developed automated technique. Voxelwise deviations were computed as z-scores by comparing individual patient data to T1, T2 and T2/T1 normative values from healthy subjects. We studied the distribution of microstructural properties inside lesions and within perilesional tissue.

RESULTS AND CONCLUSIONS

Stable lesions exhibited the highest T1 and T2 z-scores in lesion tissue, while the lowest values were observed for new lesions. Shrinking lesions presented the highest T1 z-scores in the first perilesional ring while enlarging lesions showed the highest T2 z-scores in the same region. Finally, a classification model was trained to predict the longitudinal lesion type based on microstructural metrics and feature importance was assessed. Z-scores estimated in lesion and perilesional tissue from T1, T2 and T2/T1 quantitative maps carry discriminative and complementary information to classify longitudinal lesion phenotypes, hence suggesting that multiparametric MRI approaches are essential for a better understanding of the pathophysiological mechanisms underlying disease activity in MS lesions.

A generalizable deep voxel-guided morphometry algorithm for the detection of subtle lesion dynamics in multiple sclerosis

Introduction

Multiple sclerosis (MS) is a chronic neurological disorder characterized by the progressive loss of myelin and axonal structures in the central nervous system. Accurate detection and monitoring of MS-related changes in brain structures are crucial for disease management and treatment evaluation. We propose a deep learning algorithm for creating Voxel-Guided Morphometry (VGM) maps from longitudinal MRI brain volumes for analyzing MS disease activity. Our approach focuses on developing a generalizable model that can effectively be applied to unseen datasets.

Methods

Longitudinal MS patient high-resolution 3D T1-weighted follow-up imaging from three different MRI systems were analyzed. We employed a 3D residual U-Net architecture with attention mechanisms. The U-Net serves as the backbone, enabling spatial feature extraction from MRI volumes. Attention mechanisms are integrated to enhance the model's ability to capture relevant information and highlight salient regions. Furthermore, we incorporate image normalization by histogram matching and resampling techniques to improve the networks' ability to generalize to unseen datasets from different MRI systems across imaging centers. This ensures robust performance across diverse data sources.

Results

Numerous experiments were conducted using a dataset of 71 longitudinal MRI brain volumes of MS patients. Our approach demonstrated a significant improvement of 4.3% in mean absolute error (MAE) against the state-of-the-art (SOTA) method. Furthermore, the algorithm's generalizability was evaluated on two unseen datasets (n = 116) with an average improvement of 4.2% in MAE over the SOTA approach.

Discussion

Results confirm that the proposed approach is fast and robust and has the potential for broader clinical applicability.

Independent and reproducible hippocampal radiomics biomarkers for multisite multiple sclerosis and neuromyelitis optica spectrum disorders

OBJECTIVE

To investigate the abnormal radiomics features of the hippocampus in patients with multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD) and to explore the clinical implications of these features.

METHODS

752 participants were recruited in this retrospective multicenter study (7 centers), which included 236 MS, 236 NMOSD, and 280 normal controls (NC). Radiomics features of each side of the hippocampus were extracted, including intensity, shape, texture, and wavelet features (N = 431). To identify the variations in these features, two-sample t-tests were performed between the NMOSD vs. NC, MS vs. NC, and NMOSD vs. MS groups at each site. The statistical results from each site were then integrated through meta-analysis. To investigate the clinical significance of the hippocampal radiomics features, we conducted further analysis to examine the correlations between these features and clinical measures such as Expanded Disability Status Scale (EDSS), Brief Visuospatial Memory Test (BVMT), California Verbal Learning Test (CVLT), and Paced Auditory Serial Addition Task (PASAT).

RESULTS

Compared with NC, patients with MS exhibited significant differences in 78 radiomics features (P < 0.05/862), with the majority of these being texture features. Patients with NMOSD showed significant differences in 137 radiomics features (P < 0.05/862), most of which were intensity features. The difference between MS and NMOSD patients was observed in 47 radiomics features (P < 0.05/862), mainly texture features. In patients with MS and NMOSD, the most significant features related to the EDSS were intensity and textural features, and the most significant features related to the PASAT were intensity features. Meanwhile, both disease groups observed a weak correlation between radiomics data and BVMT.

CONCLUSION

Variations in the microstructure of the hippocampus can be detected through radiomics, offering a new approach to investigating the abnormal pattern of the hippocampus in MS and NMOSD.

Long-term dynamics of multiple sclerosis iron rim lesions

BACKGROUND

Several studies have pointed out that seemingly chronic multiple sclerosis (MS) lesions may also be in inflammatory states. In pathological studies, up to 40% of chronic MS lesions are characterized as "chronic active" or "smoldering" lesions that are characterized by a rim of iron-laden proinflammatory macrophages/microglial cells at the lesion edge with low-grade continuous myelin breakdown. In vivo, these lesions can be visualized as "iron rim lesions" (IRLs) on susceptibility-weighted imaging (SWI). The aim of this study was to investigate the long-term dynamics of IRLs in vivo for a more detailed evolution of dynamic lesion volume changes occurring over time.

METHODS

We retrospectively identified patients with MS who were followed for at least 36 months (up to 72 months) and underwent at least an annual MRI on the same 3 Tsystem. Using Voxel-Guided Morphometry (VGM) we investigated regional volume changes within lesions and correlated these findings with SWI for the presence of a characteristic hypointense lesion rim. To estimate tissue damage, apparent diffusion coefficient (ADC) values for every lesion at baseline and follow-up MRIs were determined.

RESULTS

Forty-three patients were included in the study. Overall, we identified 302 supratentorial non-confluent MS lesions (52 persistent IRLs, nine transient IRLs, 228 non-IRLs and 13 acute contrast-enhancing lesions). During follow-up, persistent IRLs significantly enlarged, whereas non-IRLs showed a tendency to shrink. At baseline MRI, ADC values were significantly higher in persistent IRLs (1.23 × 10^-3 mm/s²) compared to non-IRLs (1.01 × 10^-3 mm/s²; p < 0.001), but not compared to transient IRLs (1.06 × 10^-3 mm/s²; p = 0.15) and contrast-enhancing lesions (1.15 × 10^-3 mm/s²; p = 1.0). During follow-up, ADC values significantly increased more often in persistent IRLs compared to all other lesion types (p < 0.0001).

CONCLUSIONS

Our long-term data demonstrate that persistent IRLs enlarge during disease duration, whereas non-IRLs show a tendency to shrink. Furthermore, IRLs are associated with sustained tissue damage, supporting the notion that IRLs could represent a new imaging biomarker in MS.

Texture analysis of dorsal striatum in functional neurological (conversion) disorder

In this study, it was aimed to evaluate the dorsal striatum nuclei of patients diagnosed with Functional Neurological Disorder by texture analysis method from magnetic resonance imaging images and to compare them with healthy controls. Study groups consisted of 20 female patients and 20 healthy women. The brains of patients and controls were scanned for high-resolution images with a 1.5T scanner using the sagittal plane and 3D spiral fast spin echo sequence. Using the texture analysis method, mean, standard deviation, minimum, maximum, median, variance, entropy, size %L, size %U, size %M, kurtosis, skewness and homogeneity values of the dorsal striatum nuclei were calculated from the images. The data were compared with comparison tests according to Kolmogorov-Smirnov test results. There was no statistically significant difference between paired regions in terms of texture analysis findings in the cross-sectional images of the participants. In patients, mean, standard deviation, minimum, maximum, median, variance and entropy values for the putamen nucleus, and mean, standard deviation, minimum, maximum, median, variance, entropy and kurtosis values for the caudate nucleus were found significantly higher than controls. Additional receiver operating characteristic curve and logistic regression analyzes were performed. The implications of the results of the study are that there are significant microstructural changes in the dorsal striatum nuclei of patients and their reflection on brain images. Texture analysis is a useful technique to show tissue changes in the dorsal striatum of patients using images. It is highly recommended to use texture analysis to identify and evaluate potentially affected areas of the brain in new studies.