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

Transfer learning is a commonly used strategy for medical imageclassification, especially via pretraining on source data and fine-tuning ontarget data. There is currently no consensus on how to choose appropriatesource data, and in the literature we can find both evidence of favoring largenatural image datasets such as ImageNet, and evidence of favoring morespecialized medical datasets. In this paper we perform a systematic study withnine source datasets with natural or medical images, and three target medicaldatasets, all with 2D images. We find that ImageNet is the source leading tothe highest performances, but also that larger datasets are not necessarilybetter. We also study different definitions of data similarity. We show thatcommon intuitions about similarity may be inaccurate, and therefore notsufficient to predict an appropriate source a priori. Finally, we discussseveral steps needed for further research in this field, especially with regardto other types (for example 3D) medical images. Our experiments and pretrainedmodels are available via \url{https://www.github.com/vcheplygina/cats-scans}

Cats, not CAT scans: a study of dataset similarity in transfer learning for 2D medical image classification