- •Radiomic features based on MRI-FLAIR sequences are effective in predicting MOGAD in ADEM-like presentation patients after subgrouping using age and gender.
- •Inflammatory lesions tend to have a smoother texture and a longer shape(coronal axis) in MOGAD with ADEM-like presentation patients.
- •Support vector machine (SVM) and multilayer perceptron (MLP) models have better performance in this study.
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.
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.
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.
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.
To read this article in full you will need to make a payment
Purchase one-time access:Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
One-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:Subscribe to Multiple Sclerosis and Related Disorders
Already a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
- Clinical and neuroradiological differences of paediatric acute disseminating encephalomyelitis with and without antibodies to the myelin oligodendrocyte glycoprotein.J. Neurol. Neurosurg. Psychiatry. 2015; 86 (- Science Citation Index Expanded (SCI-EXPANDED)): 265-272https://doi.org/10.1136/jnnp-2014-308346 WE
- Children with multiphasic disseminated encephalomyelitis and antibodies to the Myelin Oligodendrocyte Glycoprotein (MOG): extending the spectrum of MOG antibody positive diseases.Mult. Scler. J. 2016; 22 (WE - Science Citation Index Expanded (SCI-EXPANDED)): 1821-1829https://doi.org/10.1177/1352458516631038
- Myelin oligodendrocyte glycoprotein and aquaporin-4 antibodies are highly specific in children with acquired demyelinating syndromes.Dev. Med. Child Neurol. 2018; 60 (958-+WE - Science Citation Index Expanded (SCI-EXPANDED))https://doi.org/10.1111/dmcn.13703
- Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images.Proc. Natl. Acad. Sci. U. S. A. 2015; 112 (WE - Science Citation Index Expanded (SCI-EXPANDED)): E6265-E6273https://doi.org/10.1073/pnas.1505935112
- Radiomic analysis reveals prognostic information in T1-weighted baseline magnetic resonance imaging in patients with glioblastoma.Invest. Radiol. 2017; 52 (WE - Science Citation Index Expanded (SCI-EXPANDED)): 360-366https://doi.org/10.1097/RLI.0000000000000349
- Susceptibility-weighted imaging helps to discriminate pediatric multiple sclerosis from acute disseminated encephalomyelitis.Pediatr. Neurol. 2015; 52 (WE - Science Citation Index Expanded (SCI-EXPANDED)): 36-41https://doi.org/10.1016/j.pediatrneurol.2014.10.014
- International Pediatric Multiple Sclerosis Study Group criteria for pediatric multiple sclerosis and immune-mediated central nervous system demyelinating disorders: revisions to the 2007 definitions.Mult. Scler. J. 2013; 19 (WE - Science Citation Index Expanded (SCI-EXPANDED)): 1261-1267https://doi.org/10.1177/1352458513484547
- Teaching neuroimages: MRI time lag with acute disseminated encephalomyelitis.Neurology. 2012; 78 (WE - Science Citation Index Expanded (SCI-EXPANDED)): E138-E139https://doi.org/10.1212/WNL.0b013e318258305c
- The expanding clinical spectrum of Myelin Oligodendrocyte Glycoprotein (MOG) antibody associated disease in children and adults.Front. Neurol. 2020; 11 (WE - Science Citation Index Expanded (SCI-EXPANDED))https://doi.org/10.3389/fneur.2020.00960
- Repeatability and reproducibility of computed tomography radiomics for pulmonary nodules a multicenter phantom study.Invest. Radiol. 2022; 57 (WE - Science Citation Index Expanded (SCI-EXPANDED)): 242-253https://doi.org/10.1097/RLI.0000000000000834
- Selection of important variables and determination of functional form for continuous predictors in multivariable model building.Stat. Med. 2007; 26 (27th Annual Conference of the International-Society-for-Clinical-Biostatistics)WE - Science Citation Index Expanded (SCI-EXPANDED) WE - Conference Proceedings Citation Index - Science (CPCI-S): 5512-5528https://doi.org/10.1002/sim.3148
- Positive predictive value of myelin oligodendrocyte glycoprotein autoantibody testing.JAMA Neurol. 2021; 78: 741-746https://doi.org/10.1001/jamaneurol.2021.0912
- Myelin Oligodendrocyte Glycoprotein Antibody-Associated Disease (MOGAD): a review of clinical and MRI features, diagnosis, and management.Front. Neurol. 2022; 13https://doi.org/10.3389/fneur.2022.885218
- Acute disseminated encephalomyelitis.Neurology. 2007; 68 (Workshop on Consensus Definitions Proposed for Pediatric Multiple Sclerosis and Related Disorders)WE - Science Citation Index Expanded (SCI-EXPANDED) WE - Conference Proceedings Citation Index - Science (CPCI-S): S23-S36https://doi.org/10.1212/01.wnl.0000259404.51352.7f
- Texture indexes and gray level size zone matrix.Appl. Cell Nucl. Classif. PRIP. 2009; (Published online): 140-145
- Computational radiomics system to decode the radiographic phenotype.Cancer Res. 2017; 77 (WE - Science Citation Index Expanded (SCI-EXPANDED)): E104-E107https://doi.org/10.1158/0008-5472.CAN-17-0339
- Toward computer-assisted triaging of magnetic resonance imaging-guided biopsy in preoperative breast cancer patients.Invest. Radiol. 2021; 56 (WE - Science Citation Index Expanded (SCI-EXPANDED)): 442-449https://doi.org/10.1097/RLI.0000000000000759
- Clinical and neuroimaging characteristics of pediatric acute disseminating encephalomyelitis with and without antibodies to myelin oligodendrocyte glycoprotein.Front. Neurol. 2020; 11 (WE - Science Citation Index Expanded (SCI-EXPANDED))https://doi.org/10.3389/fneur.2020.593287
Published online: December 31, 2022
Accepted: December 30, 2022
Received in revised form: December 26, 2022
Received: September 29, 2022
© 2023 Elsevier B.V. All rights reserved.