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

Deep learning has become the mainstream methodological choice for analyzingand interpreting whole-slide digital pathology images (WSIs). It is commonlyassumed that tumor regions carry most predictive information. In this paper, weproposed an unsupervised clustering-based multiple-instance learning, and applyour method to develop deep-learning models for prediction of gene mutationsusing WSIs from three cancer types in The Cancer Genome Atlas (TCGA) studies(CRC, LUAD, and HNSCC). We showed that unsupervised clustering of image patchescould help identify predictive patches, exclude patches lack of predictiveinformation, and therefore improve prediction on gene mutations in all threedifferent cancer types, compared with the WSI based method without selection ofimage patches and models based on only tumor regions. Additionally, ourproposed algorithm outperformed two recently published baseline algorithmsleveraging unsupervised clustering to assist model prediction. Theunsupervised-clustering-based approach for mutation prediction allowsidentification of the spatial regions related to mutation of a specific genevia the resolved probability scores, highlighting the heterogeneity of apredicted genotype in the tumor microenvironment. Finally, our study alsodemonstrated that selection of tumor regions of WSIs is not always the best wayto identify patches for prediction of gene mutations, and other tissue types inthe tumor micro-environment may provide better prediction ability for genemutations than tumor tissues.

Optimize Deep Learning Models for Prediction of Gene Mutations Using Unsupervised Clustering