English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning algorithms utilizing magnetic resonance (MR) images havedemonstrated cutting-edge proficiency in autonomously segmenting multiplesclerosis (MS) lesions. Despite their achievements, these algorithms maystruggle to extend their performance across various sites or scanners, leadingto domain generalization errors. While few-shot or one-shot domain adaptationemerges as a potential solution to mitigate generalization errors, its efficacymight be hindered by the scarcity of labeled data in the target domain. Thispaper seeks to tackle this challenge by integrating one-shot adaptation datawith harmonized training data that incorporates labels. Our approach involvessynthesizing new training data with a contrast akin to that of the test domain,a process we refer to as "contrast harmonization" in MRI. Our experimentsillustrate that the amalgamation of one-shot adaptation data with harmonizedtraining data surpasses the performance of utilizing either data source inisolation. Notably, domain adaptation using exclusively harmonized trainingdata achieved comparable or even superior performance compared to one-shotadaptation. Moreover, all adaptations required only minimal fine-tuning,ranging from 2 to 5 epochs for convergence.

Harmonization-enriched domain adaptation with light fine-tuning for multiple sclerosis lesion segmentation