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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Weakly-supervised classification of histopathology slides is acomputationally intensive task, with a typical whole slide image (WSI)containing billions of pixels to process. We propose Discriminative RegionActive Sampling for Multiple Instance Learning (DRAS-MIL), a computationallyefficient slide classification method using attention scores to focus samplingon highly discriminative regions. We apply this to the diagnosis of ovariancancer histological subtypes, which is an essential part of the patient carepathway as different subtypes have different genetic and molecular profiles,treatment options, and patient outcomes. We use a dataset of 714 WSIs acquiredfrom 147 epithelial ovarian cancer patients at Leeds Teaching Hospitals NHSTrust to distinguish the most common subtype, high-grade serous carcinoma, fromthe other four subtypes (low-grade serous, endometrioid, clear cell, andmucinous carcinomas) combined. We demonstrate that DRAS-MIL can achieve similarclassification performance to exhaustive slide analysis, with a 3-foldcross-validated AUC of 0.8679 compared to 0.8781 with standard attention-basedMIL classification. Our approach uses at most 18% as much memory as thestandard approach, while taking 33% of the time when evaluating on a GPU andonly 14% on a CPU alone. Reducing prediction time and memory requirements maybenefit clinical deployment and the democratisation of AI, reducing the extentto which computational hardware limits end-user adoption.

Efficient subtyping of ovarian cancer histopathology whole slide images using active sampling in multiple instance learning