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

The conventional pretraining-and-finetuning paradigm, while effective forcommon diseases with ample data, faces challenges in diagnosing data-scarceoccupational diseases like pneumoconiosis. Recently, large language models(LLMs) have exhibits unprecedented ability when conducting multiple tasks indialogue, bringing opportunities to diagnosis. A common strategy might involveusing adapter layers for vision-language alignment and diagnosis in a dialogicmanner. Yet, this approach often requires optimization of extensive learnableparameters in the text branch and the dialogue head, potentially diminishingthe LLMs' efficacy, especially with limited training data. In our work, weinnovate by eliminating the text branch and substituting the dialogue head witha classification head. This approach presents a more effective method forharnessing LLMs in diagnosis with fewer learnable parameters. Furthermore, tobalance the retention of detailed image information with progression towardsaccurate diagnosis, we introduce the contextual multi-token engine. This engineis specialized in adaptively generating diagnostic tokens. Additionally, wepropose the information emitter module, which unidirectionally emitsinformation from image tokens to diagnosis tokens. Comprehensive experimentsvalidate the superiority of our methods and the effectiveness of proposedmodules. Our codes can be found athttps://github.com/CodeMonsterPHD/PneumoLLM/tree/main.

PneumoLLM: Harnessing the Power of Large Language Model for Pneumoconiosis Diagnosis