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

Determining lymphoma subtypes is a crucial step for better patients treatmenttargeting to potentially increase their survival chances. In this context, theexisting gold standard diagnosis method, which is based on gene expressiontechnology, is highly expensive and time-consuming making difficult itsaccessibility. Although alternative diagnosis methods based on IHC(immunohistochemistry) technologies exist (recommended by the WHO), they stillsuffer from similar limitations and are less accurate. WSI (Whole Slide Image)analysis by deep learning models showed promising new directions for cancerdiagnosis that would be cheaper and faster than existing alternative methods.In this work, we propose a vision transformer-based framework fordistinguishing DLBCL (Diffuse Large B-Cell Lymphoma) cancer subtypes fromhigh-resolution WSIs. To this end, we propose a multi-modal architecture totrain a classifier model from various WSI modalities. We then exploit thismodel through a knowledge distillation mechanism for efficiently driving thelearning of a mono-modal classifier. Our experimental study conducted on adataset of 157 patients shows the promising performance of our mono-modalclassification model, outperforming six recent methods from thestate-of-the-art dedicated for cancer classification. Moreover, the power-lawcurve, estimated on our experimental data, suggest that with more training datafrom a reasonable number of additional patients, our model has the potential toachieve diagnostic accuracy comparable to that of IHC technologies.

A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models