Susceptibility-weighted imaging helps to discriminate pediatric multiple sclerosis from acute disseminated encephalomyelitis

Differentiation of MOGAD in ADEM-like presentation children based on FLAIR MRI features

OBJECTIVE

The differences in magnetic resonance imaging (MRI) between children with classic acute disseminated encephalomyelitis (ADEM) and myelinal oligodendrocyte glycoprotein antibody associated disease (MOGAD) with ADEM-like presentation are controversial. The purpose of this study was to investigate whether the radiological characteristics of the MRI-FLAIR sequence can predict MOGAD in children with ADEM-like presentation and to further explore its imaging differences.

METHODS

We extracted 1041 radiomics features from MRI-FLAIR lesions. Then we used the redundancy analysis (Spearman correlation coefficient), significance test (student test or Mann-Whitney U test), least absolute contraction and selection operator (LASSO) to select potential predictors from the feature groups. The selected potential predictors and MOG antibody test results were used to fit the machine learning model for classification. Combined with feature selection and machine learning classifiers, the optimal model for each subgroup was derived. The resulting models have been evaluated using the receiver operator characteristic curve (ROC) at the lesion level and the model performance was evaluated at the case level using decision curve analysis.

RESULTS

We retrospectively reviewed and re-diagnosed 70 ADEM-like presentation cases in our center from April 2015 to January 2020. Including 49 cases with classic ADEM and 21 cases with MOGAD. 30(43%) were female, with a median age of 5.3 years. On the four subgroups by age and gender, the area under the curve (AUC) of the optimal models were 89%, 90%, 98%, and 99%, and the MOGAD detection rates (Specificity) were 83%, 83%, 92%, and 75%, respectively.

CONCLUSIONS

The machine learning model trained on radiomics features of MR-FLAIR images can effectively predict patients' MOGAD. This study provides a fast, objective, and quantifiable method for MOGAD diagnosis.

Utility of paramagnetic rim lesions on 1.5-T susceptibility phase imaging for the diagnosis of pediatric multiple sclerosis

BACKGROUND

Studies have suggested that paramagnetic rim lesions on 7-tesla (T) and 3-T susceptibility-based brain MRI are specific features of multiple sclerosis (MS) lesions in adults.

OBJECTIVE

The aim of this study was to investigate whether the presence of paramagnetic rim lesions on 1.5-T phase images can help discriminate pediatric patients with MS from those with other demyelinating diseases.

MATERIALS AND METHODS

In this retrospective study we reviewed brain MRIs performed on 1.5-T scanners that included susceptibility-weighted imaging (SWI) sequences with phase images in children younger than 18 years diagnosed with MS and other acquired demyelinating syndromes. In each case, five white matter lesions were selected using T2/fluid-attenuated inversion recovery images for further paramagnetic rim evaluation on SWI. Two researchers performed independent assessments of the presence of paramagnetic rim lesions. Discrepancies between them were settled by consensus, with input from a senior neuroradiologist.

RESULTS

We included 13 children diagnosed with MS and 16 children diagnosed with non-MS demyelinating diseases and analyzed a total of 132 focal white matter lesions. Seventy-one percent of the lesions in the MS group had paramagnetic rims, while none of the lesions in the non-MS group had rims. All but one of the children with MS had at least one lesion with a paramagnetic rim. The presence of one lesion with a paramagnetic rim on 1.5-T phase-contrast images resulted in 70% sensitivity and 100% specificity for MS.

CONCLUSION

Paramagnetic rim lesions detected on 1.5-T phase-contrast MR images can help discriminate MS from other acquired demyelinating syndromes in the pediatric population.

Current Advances in Pediatric Onset Multiple Sclerosis

Multiple sclerosis (MS) is an autoimmune inflammatory disease affecting the central nervous system leading to demyelination. MS in the pediatric population is rare, but has been shown to lead to significant disability over the duration of the disease. As we have learned more about pediatric MS, there has been a development of improved diagnostic criteria leading to earlier diagnosis, earlier initiation of disease-modifying therapies (DMT), and an increasing number of DMT used in the treatment of pediatric MS. Over time, treatment with DMT has trended towards the initiation of higher efficacy treatment at time of diagnosis to help prevent further disease progression and accrual of disability over time, and there is evidence in current literature that supports this change in treatment patterns. In this review, we discuss the current knowledge in diagnosis, treatment, and clinical outcomes in pediatric MS.

Pediatric Multiple Sclerosis: Distinguishing Clinical and MR Imaging Features

This article presents an overview of evolving diagnostic criteria of pediatric multiple sclerosis and related disorders, emphasizing distinguishing clinical and neuroimaging features that should be considered for differential diagnosis in childhood and adolescence. New data on the integrity of brain tissue in children with MS provided by advanced MR imaging techniques are addressed as well.

Susceptibility-Based Neuroimaging: Standard Methods, Clinical Applications, and Future Directions

The evaluation of neuropathologies using MRI methods that leverage tissue susceptibility have become standard practice, especially to detect blood products or mineralization. Additionally, emerging MRI techniques have the ability to provide new information based on tissue susceptibility properties in a robust and quantitative manner. This paper discusses these advanced susceptibility imaging techniques and their clinical applications.

MRI to Discriminate Pediatric MS from ADEM

Investigators from Washington University School of Medicine and University of Florida College of Medicine, report that susceptibility-weight imaging (SWI) may be useful in differentiating initial presentation of pediatric multiple sclerosis (MS) from acute disseminated encephalomyelitis (ADEM).