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

This paper introduces the novel concept of few-shot weakly supervisedlearning for pathology Whole Slide Image (WSI) classification, denoted as FSWC.A solution is proposed based on prompt learning and the utilization of a largelanguage model, GPT-4. Since a WSI is too large and needs to be divided intopatches for processing, WSI classification is commonly approached as a MultipleInstance Learning (MIL) problem. In this context, each WSI is considered a bag,and the obtained patches are treated as instances. The objective of FSWC is toclassify both bags and instances with only a limited number of labeled bags.Unlike conventional few-shot learning problems, FSWC poses additionalchallenges due to its weak bag labels within the MIL framework. Drawinginspiration from the recent achievements of vision-language models (V-L models)in downstream few-shot classification tasks, we propose a two-level promptlearning MIL framework tailored for pathology, incorporating language priorknowledge. Specifically, we leverage CLIP to extract instance features for eachpatch, and introduce a prompt-guided pooling strategy to aggregate theseinstance features into a bag feature. Subsequently, we employ a small number oflabeled bags to facilitate few-shot prompt learning based on the bag features.Our approach incorporates the utilization of GPT-4 in a question-and-answermode to obtain language prior knowledge at both the instance and bag levels,which are then integrated into the instance and bag level language prompts.Additionally, a learnable component of the language prompts is trained usingthe available few-shot labeled data. We conduct extensive experiments on threereal WSI datasets encompassing breast cancer, lung cancer, and cervical cancer,demonstrating the notable performance of the proposed method in bag andinstance classification. All codes will be made publicly accessible.

The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification