Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning.

Jason UwaezePonnada A NarayanaArash KamaliVladimir BravermanMichael A Jacobs Alireza Akhbardeh

Published in: Diagnostics (Basel, Switzerland) (2024)

NLDR methods, Isomap and LLE, are viable options for the identification of active MS lesions on non-contrast images, and potentially could be used as a clinical decision tool.

Keyphrases

machine learning
multiple sclerosis
deep learning
artificial intelligence
big data
mass spectrometry
magnetic resonance
convolutional neural network
white matter
ms ms
optical coherence tomography
decision making
contrast enhanced
computed tomography
magnetic resonance imaging