Estimation of Multiple Sclerosis lesion age on magnetic resonance imaging

Sweeney, Elizabeth; Nguyen, Thanh D.; Kuceyeski, Amy; Ryan, Sarah; Zhang, Shun; Zexter, Lily; Wang, Yi; Gauthier, Susan A.

doi:10.1016/j.neuroimage.2020.117451

Cited by 12 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work is planned to address this limitation and provide an estimated age to individual chronic active MS lesions. 36 We selected GA as a comparator because our retrospective data collection started in 2011 when GA was a common first-line therapy. The slight decrease in susceptibility observed in rim lesions of GA-treated cohort may represent a minor effect of GA and/or the natural decay of susceptibility.…”

Section: Discussionmentioning

confidence: 99%

Dimethyl Fumarate Reduces Inflammation in Chronic Active Multiple Sclerosis Lesions

Zinger

Ponath

Sweeney

et al. 2022

Neurol Neuroimmunol Neuroinflamm

Self Cite

View full text Add to dashboard Cite

Background and ObjectivesTo determine the effects of dimethyl fumarate (DMF) and glatiramer acetate on iron content in chronic active lesions in patients with multiple sclerosis (MS) and in human microglia in vitro.MethodsThis was a retrospective observational study of 34 patients with relapsing-remitting MS and clinically isolated syndrome treated with DMF or glatiramer acetate. Patients had lesions with hyperintense rims on quantitative susceptibility mapping, were treated with DMF or glatiramer acetate (GA), and had a minimum of 2 on-treatment scans. Changes in susceptibility in rim lesions were compared among treatment groups in a linear mixed effects model. In a separate in vitro study, induced pluripotent stem cell–derived human microglia were treated with DMF or GA, and treatment-induced changes in iron content and activation state of microglia were compared.ResultsRim lesions in patients treated with DMF had on average a 2.77-unit reduction in susceptibility per year over rim lesions in patients treated with GA (bootstrapped 95% CI −5.87 to −0.01), holding all other variables constant. Moreover, DMF but not GA reduced inflammatory activation and concomitantly iron content in human microglia in vitro.DiscussionTogether, our data indicate that DMF-induced reduction of susceptibility in MS lesions is associated with a decreased activation state in microglial cells. We have demonstrated that a specific disease modifying therapy, DMF, decreases glial activity in chronic active lesions. Susceptibility changes in rim lesions provide an in vivo biomarker for the effect of DMF on microglial activity.Classification of EvidenceThis study provided Class III evidence that DMF is superior to GA in the presence of iron as a marker of inflammation as measured by MRI quantitative susceptibility mapping.

show abstract

Section: Discussionmentioning

confidence: 99%

Dimethyl Fumarate Reduces Inflammation in Chronic Active Multiple Sclerosis Lesions

Zinger

Ponath

Sweeney

et al. 2022

Neurol Neuroimmunol Neuroinflamm

Self Cite

View full text Add to dashboard Cite

show abstract

“…Radiomic features have been shown to be effective in many applications of medical image analysis ( Coroller et al, 2016 , Liu et al, 2016 , Bakas et al, 2017 , Sweeney et al, 2021 ). For QSMRim-Net, radiomic features were calculated over each lesion using the pyradiomics package ( Van Griethuysen et al, 2017 ).…”

Section: Methodsmentioning

confidence: 99%

QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps

Zhang

Nguyen

Zhang

et al. 2022

NeuroImage: Clinical

Self Cite

View full text Add to dashboard Cite

“…Radiomic features have been shown to be effective in many applications of medical image analysis [40][41][42][43]. For QSMRim-Net, radiomic features were calculated over each lesion using the pyradiomics package [44].…”

Section: Radiomic Feature Analysismentioning

confidence: 99%

QSMRim-Net: Imbalance-Aware Learning for Identification of Chronic Active Multiple Sclerosis Lesions on Quantitative Susceptibility Maps

Zhang

Nguyen

Zhang

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background and Purpose: Chronic active multiple sclerosis (MS) lesions are characterized by a paramagnetic rim at the edge of the lesion and are associated with increased disability in patients. Quantitative susceptibility mapping (QSM) is an MRI technique that is sensitive to chronic active lesions, termed rim+ lesions on the QSM. We present QSMRim-Net, a data imbalance-aware deep neural network that fuses lesion-level radiomic and convolutional image features for automated identification of rim+ lesions on QSM. Methods: QSM and T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRI of the brain were collected at 3T for 172 MS patients. Rim+ lesions were manually annotated by two human experts, followed by consensus from a third expert, for a total of 177 rim+ and 3986 rim negative (rim-) lesions. Our automated rim+ detection algorithm, QSMRim-Net, consists of a two-branch feature extraction network and a synthetic minority oversampling network to classify rim+ lesions. The first network branch is for image feature extraction from the QSM and T2-FLAIR, and the second network branch is a fully connected network for QSM lesion-level radiomic feature extraction. The oversampling network is designed to increase classification performance with imbalanced data. Results: On a lesion-level, in a five-fold cross validation framework, the proposed QSMRim-Net detected rim+ lesions with a partial area under the receiver operating characteristic curve (pROC AUC) of 0.760, where clinically relevant false positive rates of less than 0.1 were considered. The method attained an area under the precision recall curve (PR AUC) of 0.704. QSMRim-Net out-performed other state-of-the-art methods applied to the QSM on both pROC AUC and PR AUC. On a subject-level, comparing the predicted rim+ lesion count and the human expert annotated count, QSMRim-Net achieved the lowest mean square error of 0.98 and the highest correlation of 0.89 (95% CI: 0.86, 0.92). Conclusion: This study develops a novel automated deep neural network for rim+ MS lesion identification using T2-FLAIR and QSM images.

show abstract

Estimation of Multiple Sclerosis lesion age on magnetic resonance imaging

Cited by 12 publications

References 44 publications

Dimethyl Fumarate Reduces Inflammation in Chronic Active Multiple Sclerosis Lesions

Dimethyl Fumarate Reduces Inflammation in Chronic Active Multiple Sclerosis Lesions

QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps

QSMRim-Net: Imbalance-Aware Learning for Identification of Chronic Active Multiple Sclerosis Lesions on Quantitative Susceptibility Maps

Contact Info

Product

Resources

About