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

Tissue microarray (TMA) images have been used increasingly often in cancerstudies and the validation of biomarkers. TACOMA---a cutting-edge automaticscoring algorithm for TMA images---is comparable to pathologists in terms ofaccuracy and repeatability. Here we consider how this algorithm may be furtherimproved. Inspired by the recent success of deep learning, we propose toincorporate representations learnable through computation. We explorerepresentations of a group nature through unsupervised learning, e.g.,hierarchical clustering and recursive space partition. Information carried byclustering or spatial partitioning may be more concrete than the labels whenthe data are heterogeneous, or could help when the labels are noisy. The use ofsuch information could be viewed as regularization in model fitting. It ismotivated by major challenges in TMA image scoring---heterogeneity and labelnoise, and the cluster assumption in semi-supervised learning. Using thisinformation on TMA images of breast cancer, we have reduced the error rate ofTACOMA by about 6%. Further simulations on synthetic data provide insights onwhen such representations would likely help. Although we focus on TMAs,learnable representations of this type are expected to be applicable in othersettings.

Incorporating Deep Features in the Analysis of Tissue Microarray Images