FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903841390> ?p ?o ?g. }

• W2903841390 endingPage "408" @default.
• W2903841390 startingPage "403" @default.
• W2903841390 abstract "Plantar pressure image (PPI) recorded in high spatial and temporal resolution is very useful in clinical gait analysis. For functional analysis of PPI, image registration is often performed to maximally correlate source image with a template image. Previous methods estimate the registration parameters by iteratively optimizing different objective functions. These methods are often computational expensive to achieve satisfactory registration accuracy. Can we develop a single PPI registration technique that performs more rapidly than previous methods, and that also maintains adequate PPI correspondence as defined by various (dis)similarity metrics? A cascaded convolutional neural network (CNN) was proposed for the registration of PPIs. Our model was trained to learn a regression from the difference between the template and misaligned images to the registration parameters. The registration performance was evaluated by three different metrics, i.e. the mean squared error (MSE), the exclusive or (XOR), and the mutual information (MI). For comparison, four previous methods were also implemented. These included the principal axes (PA) method, the center of pressure trajectory (COP) method, the MSE method, and the XOR method. Experimental results on a dataset with 71 PPI template-source pairs showed that the proposed CNN-based method could obtain comparable registration accuracy to the MSE and XOR method. With regards to the registration speed, registration durations (mean ± sd in seconds) per image pair were: MSE (30.584 ± 2.171), XOR (24.245 ± 1.596), PA (0.016 ± 0.003), COP (25.614 ± 0.341), and the proposed model (0.054 ± 0.007). Our findings indicate that the proposed registration approach can achieve high accuracy but less computational time. Thus, it is more practical to utilize our pre-trained CNN-based model to develop near-real time applications for plantar pressure images registration." @default.
• W2903841390 created "2018-12-22" @default.
• W2903841390 creator A5035754451 @default.
• W2903841390 creator A5041406343 @default.
• W2903841390 creator A5064860911 @default.
• W2903841390 creator A5069860925 @default.
• W2903841390 creator A5076794753 @default.
• W2903841390 date "2019-02-01" @default.
• W2903841390 modified "2023-10-17" @default.
• W2903841390 title "A convolutional neural network Cascade for plantar pressure images registration" @default.
• W2903841390 cites W1678356000 @default.
• W2903841390 cites W1980378769 @default.
• W2903841390 cites W1982365490 @default.
• W2903841390 cites W1985800432 @default.
• W2903841390 cites W2014503804 @default.
• W2903841390 cites W2021278861 @default.
• W2903841390 cites W2043534529 @default.
• W2903841390 cites W2048180575 @default.
• W2903841390 cites W2050077549 @default.
• W2903841390 cites W2065471242 @default.
• W2903841390 cites W2088886227 @default.
• W2903841390 cites W2127510940 @default.
• W2903841390 cites W2139973231 @default.
• W2903841390 cites W2143732463 @default.
• W2903841390 cites W2149860264 @default.
• W2903841390 cites W2152862207 @default.
• W2903841390 cites W2156875677 @default.
• W2903841390 cites W2171107890 @default.
• W2903841390 cites W2542200242 @default.
• W2903841390 cites W2559117000 @default.
• W2903841390 cites W2601251106 @default.
• W2903841390 cites W639708223 @default.
• W2903841390 doi "https://doi.org/10.1016/j.gaitpost.2018.12.021" @default.
• W2903841390 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30594014" @default.
• W2903841390 hasPublicationYear "2019" @default.
• W2903841390 type Work @default.
• W2903841390 sameAs 2903841390 @default.
• W2903841390 citedByCount "4" @default.
• W2903841390 countsByYear W29038413902020 @default.
• W2903841390 countsByYear W29038413902021 @default.
• W2903841390 countsByYear W29038413902022 @default.
• W2903841390 crossrefType "journal-article" @default.
• W2903841390 hasAuthorship W2903841390A5035754451 @default.
• W2903841390 hasAuthorship W2903841390A5041406343 @default.
• W2903841390 hasAuthorship W2903841390A5064860911 @default.
• W2903841390 hasAuthorship W2903841390A5069860925 @default.
• W2903841390 hasAuthorship W2903841390A5076794753 @default.
• W2903841390 hasConcept C103278499 @default.
• W2903841390 hasConcept C105795698 @default.
• W2903841390 hasConcept C115961682 @default.
• W2903841390 hasConcept C139945424 @default.
• W2903841390 hasConcept C153180895 @default.
• W2903841390 hasConcept C154945302 @default.
• W2903841390 hasConcept C166704113 @default.
• W2903841390 hasConcept C31972630 @default.
• W2903841390 hasConcept C33923547 @default.
• W2903841390 hasConcept C41008148 @default.
• W2903841390 hasConcept C50644808 @default.
• W2903841390 hasConcept C81363708 @default.
• W2903841390 hasConceptScore W2903841390C103278499 @default.
• W2903841390 hasConceptScore W2903841390C105795698 @default.
• W2903841390 hasConceptScore W2903841390C115961682 @default.
• W2903841390 hasConceptScore W2903841390C139945424 @default.
• W2903841390 hasConceptScore W2903841390C153180895 @default.
• W2903841390 hasConceptScore W2903841390C154945302 @default.
• W2903841390 hasConceptScore W2903841390C166704113 @default.
• W2903841390 hasConceptScore W2903841390C31972630 @default.
• W2903841390 hasConceptScore W2903841390C33923547 @default.
• W2903841390 hasConceptScore W2903841390C41008148 @default.
• W2903841390 hasConceptScore W2903841390C50644808 @default.
• W2903841390 hasConceptScore W2903841390C81363708 @default.
• W2903841390 hasFunder F4320321001 @default.
• W2903841390 hasFunder F4320321543 @default.
• W2903841390 hasFunder F4320334897 @default.
• W2903841390 hasLocation W29038413901 @default.
• W2903841390 hasLocation W29038413902 @default.
• W2903841390 hasOpenAccess W2903841390 @default.
• W2903841390 hasPrimaryLocation W29038413901 @default.
• W2903841390 hasRelatedWork W2009466720 @default.
• W2903841390 hasRelatedWork W2011443206 @default.
• W2903841390 hasRelatedWork W2041698670 @default.
• W2903841390 hasRelatedWork W2114100766 @default.
• W2903841390 hasRelatedWork W2125070361 @default.
• W2903841390 hasRelatedWork W2203553948 @default.
• W2903841390 hasRelatedWork W2767651786 @default.
• W2903841390 hasRelatedWork W2912288872 @default.
• W2903841390 hasRelatedWork W3163375306 @default.
• W2903841390 hasRelatedWork W564581980 @default.
• W2903841390 hasVolume "68" @default.
• W2903841390 isParatext "false" @default.
• W2903841390 isRetracted "false" @default.
• W2903841390 magId "2903841390" @default.
• W2903841390 workType "article" @default.