Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226200316> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W4226200316 abstract "Application of artificial intelligence in medicine brings in highly accurate predictions achieved by complex models, the reasoning of which is hard to interpret. Their generalization ability can be reduced because of the lack of pixel wise annotated images that occurs in frozen section tissue analysis. To partially overcome this gap, this paper explores the approximate explicit feature map (aEFM) transform of low-dimensional data into a low-dimensional subspace in Hilbert space. There, with a modest increase in computational complexity, linear algorithms yield improved performance and keep interpretability. They remain amenable to incremental learning that is not a trivial issue for some nonlinear algorithms. We demonstrate proposed methodology on a very large-scale problem related to intraoperative pixel-wise semantic segmentation and clustering of adenocarcinoma of a colon in a liver. Compared to the results in the input space, logistic classifier achieved statistically significant performance improvements in micro balanced accuracy and F1 score in the amounts of 12.04% and 12.58%, respectively. Support vector machine 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 spectral clustering algorithm. Results are supported by a discussion of interpretability using Shapely additive explanation values for predictions of linear classifier in input space and aEFM induced space." @default.
- W4226200316 created "2022-05-05" @default.
- W4226200316 creator A5064824381 @default.
- W4226200316 creator A5084500982 @default.
- W4226200316 date "2022-03-07" @default.
- W4226200316 modified "2023-09-25" @default.
- W4226200316 title "Clustering and classification of low-dimensional data in explicit feature map domain: intraoperative pixel-wise diagnosis of adenocarcinoma of a colon in a liver" @default.
- W4226200316 doi "https://doi.org/10.48550/arxiv.2203.03636" @default.
- W4226200316 hasPublicationYear "2022" @default.
- W4226200316 type Work @default.
- W4226200316 citedByCount "0" @default.
- W4226200316 crossrefType "posted-content" @default.
- W4226200316 hasAuthorship W4226200316A5064824381 @default.
- W4226200316 hasAuthorship W4226200316A5084500982 @default.
- W4226200316 hasBestOaLocation W42262003161 @default.
- W4226200316 hasConcept C12267149 @default.
- W4226200316 hasConcept C153180895 @default.
- W4226200316 hasConcept C154945302 @default.
- W4226200316 hasConcept C160633673 @default.
- W4226200316 hasConcept C2781067378 @default.
- W4226200316 hasConcept C41008148 @default.
- W4226200316 hasConcept C73555534 @default.
- W4226200316 hasConcept C83665646 @default.
- W4226200316 hasConcept C89600930 @default.
- W4226200316 hasConcept C95623464 @default.
- W4226200316 hasConceptScore W4226200316C12267149 @default.
- W4226200316 hasConceptScore W4226200316C153180895 @default.
- W4226200316 hasConceptScore W4226200316C154945302 @default.
- W4226200316 hasConceptScore W4226200316C160633673 @default.
- W4226200316 hasConceptScore W4226200316C2781067378 @default.
- W4226200316 hasConceptScore W4226200316C41008148 @default.
- W4226200316 hasConceptScore W4226200316C73555534 @default.
- W4226200316 hasConceptScore W4226200316C83665646 @default.
- W4226200316 hasConceptScore W4226200316C89600930 @default.
- W4226200316 hasConceptScore W4226200316C95623464 @default.
- W4226200316 hasLocation W42262003161 @default.
- W4226200316 hasOpenAccess W4226200316 @default.
- W4226200316 hasPrimaryLocation W42262003161 @default.
- W4226200316 hasRelatedWork W2041636156 @default.
- W4226200316 hasRelatedWork W2120008580 @default.
- W4226200316 hasRelatedWork W2153189372 @default.
- W4226200316 hasRelatedWork W2160451891 @default.
- W4226200316 hasRelatedWork W2348964713 @default.
- W4226200316 hasRelatedWork W2734744645 @default.
- W4226200316 hasRelatedWork W2754350655 @default.
- W4226200316 hasRelatedWork W3043252291 @default.
- W4226200316 hasRelatedWork W4283661982 @default.
- W4226200316 hasRelatedWork W2187500075 @default.
- W4226200316 isParatext "false" @default.
- W4226200316 isRetracted "false" @default.
- W4226200316 workType "article" @default.