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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recent contrastive learning methods achieved state-of-the-art in low labelregimes. However, the training requires large batch sizes and heavyaugmentations to create multiple views of an image. With non-contrastivemethods, the negatives are implicitly incorporated in the loss, allowingdifferent images and modalities as pairs. Although the meta-information (i.e.,age, sex) in medical imaging is abundant, the annotations are noisy and proneto class imbalance. In this work, we exploited already existing temporalinformation (different visits from a patient) in a longitudinal opticalcoherence tomography (OCT) dataset using temporally informed non-contrastiveloss (TINC) without increasing complexity and need for negative pairs.Moreover, our novel pair-forming scheme can avoid heavy augmentations andimplicitly incorporates the temporal information in the pairs. Finally, theserepresentations learned from the pretraining are more successful in predictingdisease progression where the temporal information is crucial for thedownstream task. More specifically, our model outperforms existing models inpredicting the risk of conversion within a time frame from intermediateage-related macular degeneration (AMD) to the late wet-AMD stage.

TINC: Temporally Informed Non-Contrastive Learning for Disease Progression Modeling in Retinal OCT Volumes