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

Application of artificial intelligence in medicine brings in highly accuratepredictions achieved by complex models, the reasoning of which is hard tointerpret. Their generalization ability can be reduced because of the lack ofpixel wise annotated images that occurs in frozen section tissue analysis. Topartially overcome this gap, this paper explores the approximate explicitfeature map (aEFM) transform of low-dimensional data into a low-dimensionalsubspace in Hilbert space. There, with a modest increase in computationalcomplexity, linear algorithms yield improved performance and keepinterpretability. They remain amenable to incremental learning that is not atrivial issue for some nonlinear algorithms. We demonstrate proposedmethodology on a very large-scale problem related to intraoperative pixel-wisesemantic segmentation and clustering of adenocarcinoma of a colon in a liver.Compared to the results in the input space, logistic classifier achievedstatistically significant performance improvements in micro balanced accuracyand F1 score in the amounts of 12.04% and 12.58%, respectively. Support vectormachine classifier yielded the increase of 8.04% and 9.41%. For clustering,increases of 0.79% and 0.85% are obtained with ultra large-scale spectralclustering algorithm. Results are supported by a discussion of interpretabilityusing Shapely additive explanation values for predictions of linear classifierin input space and aEFM induced space.

Clustering and classification of low-dimensional data in explicit  feature map domain: intraoperative pixel-wise diagnosis of adenocarcinoma of  a colon in a liver