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

Healthcare clinics regularly encounter dynamic data that changes due tovariations in patient populations, treatment policies, medical devices, andemerging disease patterns. Deep learning models can suffer from catastrophicforgetting when fine-tuned in such scenarios, causing poor performance onpreviously learned tasks. Continual learning allows learning on new taskswithout performance drop on previous tasks. In this work, we investigate theperformance of continual learning models on four different medical imagingscenarios involving ten classification datasets from diverse modalities,clinical specialties, and hospitals. We implement various continual learningapproaches and evaluate their performance in these scenarios. Our resultsdemonstrate that a single model can sequentially learn new tasks from differentspecialties and achieve comparable performance to naive methods. These findingsindicate the feasibility of recycling or sharing models across the same ordifferent medical specialties, offering another step towards the development ofgeneral-purpose medical imaging AI that can be shared across institutions.

Class-Incremental Continual Learning for General Purpose Healthcare Models