Mitigating catastrophic forgetting in Multiple sclerosis lesion segmentation using elastic weight consolidation

Multiple sclerosis (MS) lesion segmentation is crucial for monitoring disease progression. Deep learning methods have shown promising results but suffer from domain shift problems when evaluated in data from different protocols or scanners. Transfer learning (TL) achieves successful domain adaptatio...

Full description

Bibliographic Details

Published in:	NeuroImage: Clinical
Main Authors:	Luisana Álvarez, Sergi Valverde, Àlex Rovira, Xavier Lladó
Format:	Article
Language:	English
Published:	Elsevier 2025-01-01
Subjects:	Multiple sclerosis Lesion segmentation Continuous learning Transfer learning Catastrophic forgetting
Online Access:	http://www.sciencedirect.com/science/article/pii/S2213158225000658