FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2028406867> ?p ?o ?g. }

• W2028406867 endingPage "107" @default.
• W2028406867 startingPage "93" @default.
• W2028406867 abstract "Kernel-based dimensionality reduction is a widely used technique in medical image analysis. To fully unravel the underlying nonlinear manifold the selection of an adequate kernel function and of its free parameters is critical. In practice, however, the kernel function is generally chosen as Gaussian or polynomial and such standard kernels might not always be optimal for a given image dataset or application. In this paper, we present a study on the effect of the kernel functions in nonlinear manifold embedding of medical image data. To this end, we first carry out a literature review on existing advanced kernels developed in the statistics, machine learning, and signal processing communities. In addition, we implement kernel-based formulations of well-known nonlinear dimensional reduction techniques such as Isomap and Locally Linear Embedding, thus obtaining a unified framework for manifold embedding using kernels. Subsequently, we present a method to automatically choose a kernel function and its associated parameters from a pool of kernel candidates, with the aim to generate the most optimal manifold embeddings. Furthermore, we show how the calculated selection measures can be extended to take into account the spatial relationships in images, or used to combine several kernels to further improve the embedding results. Experiments are then carried out on various synthetic and phantom datasets for numerical assessment of the methods. Furthermore, the workflow is applied to real data that include brain manifolds and multispectral images to demonstrate the importance of the kernel selection in the analysis of high-dimensional medical images." @default.
• W2028406867 created "2016-06-24" @default.
• W2028406867 creator A5021986478 @default.
• W2028406867 creator A5044566450 @default.
• W2028406867 creator A5049192404 @default.
• W2028406867 creator A5078391768 @default.
• W2028406867 creator A5087067526 @default.
• W2028406867 date "2015-04-01" @default.
• W2028406867 modified "2023-10-10" @default.
• W2028406867 title "A framework for optimal kernel-based manifold embedding of medical image data" @default.
• W2028406867 cites W1587720067 @default.
• W2028406867 cites W1641498739 @default.
• W2028406867 cites W1965359844 @default.
• W2028406867 cites W1977143580 @default.
• W2028406867 cites W1992354221 @default.
• W2028406867 cites W1993917780 @default.
• W2028406867 cites W1994443280 @default.
• W2028406867 cites W1997780235 @default.
• W2028406867 cites W2001141328 @default.
• W2028406867 cites W2014582301 @default.
• W2028406867 cites W2029706109 @default.
• W2028406867 cites W2042031583 @default.
• W2028406867 cites W2042630303 @default.
• W2028406867 cites W2043508111 @default.
• W2028406867 cites W2045260557 @default.
• W2028406867 cites W2053186076 @default.
• W2028406867 cites W2064390925 @default.
• W2028406867 cites W2082829292 @default.
• W2028406867 cites W2085074697 @default.
• W2028406867 cites W2089443121 @default.
• W2028406867 cites W2093235088 @default.
• W2028406867 cites W2103504761 @default.
• W2028406867 cites W2104343831 @default.
• W2028406867 cites W2107011987 @default.
• W2028406867 cites W2110652811 @default.
• W2028406867 cites W2111340031 @default.
• W2028406867 cites W2113588440 @default.
• W2028406867 cites W2125134203 @default.
• W2028406867 cites W2127180395 @default.
• W2028406867 cites W2127869062 @default.
• W2028406867 cites W2133583786 @default.
• W2028406867 cites W2139212933 @default.
• W2028406867 cites W2140095548 @default.
• W2028406867 cites W2146980616 @default.
• W2028406867 cites W2150534249 @default.
• W2028406867 cites W2157511995 @default.
• W2028406867 cites W2294798173 @default.
• W2028406867 cites W3101749733 @default.
• W2028406867 doi "https://doi.org/10.1016/j.compmedimag.2014.06.001" @default.
• W2028406867 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25008538" @default.
• W2028406867 hasPublicationYear "2015" @default.
• W2028406867 type Work @default.
• W2028406867 sameAs 2028406867 @default.
• W2028406867 citedByCount "13" @default.
• W2028406867 countsByYear W20284068672015 @default.
• W2028406867 countsByYear W20284068672016 @default.
• W2028406867 countsByYear W20284068672017 @default.
• W2028406867 countsByYear W20284068672018 @default.
• W2028406867 countsByYear W20284068672019 @default.
• W2028406867 countsByYear W20284068672023 @default.
• W2028406867 crossrefType "journal-article" @default.
• W2028406867 hasAuthorship W2028406867A5021986478 @default.
• W2028406867 hasAuthorship W2028406867A5044566450 @default.
• W2028406867 hasAuthorship W2028406867A5049192404 @default.
• W2028406867 hasAuthorship W2028406867A5078391768 @default.
• W2028406867 hasAuthorship W2028406867A5087067526 @default.
• W2028406867 hasConcept C11413529 @default.
• W2028406867 hasConcept C114614502 @default.
• W2028406867 hasConcept C122280245 @default.
• W2028406867 hasConcept C12267149 @default.
• W2028406867 hasConcept C127413603 @default.
• W2028406867 hasConcept C151876577 @default.
• W2028406867 hasConcept C153180895 @default.
• W2028406867 hasConcept C154945302 @default.
• W2028406867 hasConcept C182335926 @default.
• W2028406867 hasConcept C2778626561 @default.
• W2028406867 hasConcept C33923547 @default.
• W2028406867 hasConcept C41008148 @default.
• W2028406867 hasConcept C41608201 @default.
• W2028406867 hasConcept C529865628 @default.
• W2028406867 hasConcept C70518039 @default.
• W2028406867 hasConcept C74193536 @default.
• W2028406867 hasConcept C78519656 @default.
• W2028406867 hasConceptScore W2028406867C11413529 @default.
• W2028406867 hasConceptScore W2028406867C114614502 @default.
• W2028406867 hasConceptScore W2028406867C122280245 @default.
• W2028406867 hasConceptScore W2028406867C12267149 @default.
• W2028406867 hasConceptScore W2028406867C127413603 @default.
• W2028406867 hasConceptScore W2028406867C151876577 @default.
• W2028406867 hasConceptScore W2028406867C153180895 @default.
• W2028406867 hasConceptScore W2028406867C154945302 @default.
• W2028406867 hasConceptScore W2028406867C182335926 @default.
• W2028406867 hasConceptScore W2028406867C2778626561 @default.
• W2028406867 hasConceptScore W2028406867C33923547 @default.
• W2028406867 hasConceptScore W2028406867C41008148 @default.
• W2028406867 hasConceptScore W2028406867C41608201 @default.
• W2028406867 hasConceptScore W2028406867C529865628 @default.
• W2028406867 hasConceptScore W2028406867C70518039 @default.

• next