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

Whole-slide images (WSI) in computational pathology have high resolution withgigapixel size, but are generally with sparse regions of interest, which leadsto weak diagnostic relevance and data inefficiency for each area in the slide.Most of the existing methods rely on a multiple instance learning frameworkthat requires densely sampling local patches at high magnification. Thelimitation is evident in the application stage as the heavy computation forextracting patch-level features is inevitable. In this paper, we developRLogist, a benchmarking deep reinforcement learning (DRL) method for fastobservation strategy on WSIs. Imitating the diagnostic logic of humanpathologists, our RL agent learns how to find regions of observation value andobtain representative features across multiple resolution levels, withouthaving to analyze each part of the WSI at the high magnification. We benchmarkour method on two whole-slide level classification tasks, including detectionof metastases in WSIs of lymph node sections, and subtyping of lung cancer.Experimental results demonstrate that RLogist achieves competitiveclassification performance compared to typical multiple instance learningalgorithms, while having a significantly short observation path. In addition,the observation path given by RLogist provides good decision-makinginterpretability, and its ability of reading path navigation can potentially beused by pathologists for educational/assistive purposes. Our code is availableat: \url{https://github.com/tencent-ailab/RLogist}.

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning