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

Medical vision-language models enable co-learning and integrating featuresfrom medical imaging and clinical text. However, these models are not easy totrain and the latent representation space can be complex. Here we propose anovel way for pre-training and regularising medical vision-language models. Theproposed method, named Medical vision-language pre-training with Frozenlanguage models and Latent spAce Geometry optimization (M-FLAG), leverages afrozen language model for training stability and efficiency and introduces anovel orthogonality loss to harmonize the latent space geometry. We demonstratethe potential of the pre-trained model on three downstream tasks: medical imageclassification, segmentation, and object detection. Extensive experimentsacross five public datasets demonstrate that M-FLAG significantly outperformsexisting medical vision-language pre-training approaches and reduces the numberof parameters by 78\%. Notably, M-FLAG achieves outstanding performance on thesegmentation task while using only 1\% of the RSNA dataset, even outperformingImageNet pre-trained models that have been fine-tuned using 100\% of the data.

M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization