MIMoSA: An Automated Method for Intermodal Segmentation Analysis of Multiple Sclerosis Brain Lesions.

Alessandra M ValcarcelKristin A LinnSimon N VandekarTheodore D SatterthwaiteJohn MuschelliPeter A CalabresiDzung L PhamMelissa Lynne MartinRussell T Shinohara

Published in: Journal of neuroimaging : official journal of the American Society of Neuroimaging (2018)

MIMoSA resulted in statistically significant improvements in lesion segmentation performance compared with LesionTOADS and OASIS, and performed competitively in an additional validation study.

Keyphrases

multiple sclerosis
convolutional neural network
deep learning
white matter
resting state
functional connectivity
cerebral ischemia
machine learning