FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2263959547> ?p ?o ?g. }

• W2263959547 endingPage "300" @default.
• W2263959547 startingPage "290" @default.
• W2263959547 abstract "Faster and more accurate methods for registration of images are important for research involved in conducting population-based studies that utilize medical imaging, as well as improvements for use in clinical applications. We present a novel computation- and memory-efficient multi-level method on graphics processing units (GPU) for performing registration of two computed tomography (CT) volumetric lung images.We developed a computation- and memory-efficient Diffeomorphic Multi-level B-Spline Transform Composite (DMTC) method to implement nonrigid mass-preserving registration of two CT lung images on GPU. The framework consists of a hierarchy of B-Spline control grids of increasing resolution. A similarity criterion known as the sum of squared tissue volume difference (SSTVD) was adopted to preserve lung tissue mass. The use of SSTVD consists of the calculation of the tissue volume, the Jacobian, and their derivatives, which makes its implementation on GPU challenging due to memory constraints. The use of the DMTC method enabled reduced computation and memory storage of variables with minimal communication between GPU and Central Processing Unit (CPU) due to ability to pre-compute values. The method was assessed on six healthy human subjects.Resultant GPU-generated displacement fields were compared against the previously validated CPU counterpart fields, showing good agreement with an average normalized root mean square error (nRMS) of 0.044±0.015. Runtime and performance speedup are compared between single-threaded CPU, multi-threaded CPU, and GPU algorithms. Best performance speedup occurs at the highest resolution in the GPU implementation for the SSTVD cost and cost gradient computations, with a speedup of 112 times that of the single-threaded CPU version and 11 times over the twelve-threaded version when considering average time per iteration using a Nvidia Tesla K20X GPU.The proposed GPU-based DMTC method outperforms its multi-threaded CPU version in terms of runtime. Total registration time reduced runtime to 2.9min on the GPU version, compared to 12.8min on twelve-threaded CPU version and 112.5min on a single-threaded CPU. Furthermore, the GPU implementation discussed in this work can be adapted for use of other cost functions that require calculation of the first derivatives." @default.
• W2263959547 created "2016-06-24" @default.
• W2263959547 creator A5006854308 @default.
• W2263959547 creator A5015932921 @default.
• W2263959547 creator A5031524081 @default.
• W2263959547 creator A5037389227 @default.
• W2263959547 date "2016-04-01" @default.
• W2263959547 modified "2023-10-17" @default.
• W2263959547 title "Efficient methods for implementation of multi-level nonrigid mass-preserving image registration on GPUs and multi-threaded CPUs" @default.
• W2263959547 cites W1779094783 @default.
• W2263959547 cites W1888801276 @default.
• W2263959547 cites W1963623641 @default.
• W2263959547 cites W1974983861 @default.
• W2263959547 cites W1984205637 @default.
• W2263959547 cites W1995135274 @default.
• W2263959547 cites W2003340824 @default.
• W2263959547 cites W2006003884 @default.
• W2263959547 cites W2008240038 @default.
• W2263959547 cites W2011613824 @default.
• W2263959547 cites W2020133147 @default.
• W2263959547 cites W2023159816 @default.
• W2263959547 cites W2035619816 @default.
• W2263959547 cites W2052314484 @default.
• W2263959547 cites W2054159881 @default.
• W2263959547 cites W2055844022 @default.
• W2263959547 cites W2059681146 @default.
• W2263959547 cites W2088869937 @default.
• W2263959547 cites W2097110160 @default.
• W2263959547 cites W2107360941 @default.
• W2263959547 cites W2107956652 @default.
• W2263959547 cites W2110095731 @default.
• W2263959547 cites W2113576511 @default.
• W2263959547 cites W2115167851 @default.
• W2263959547 cites W2118420236 @default.
• W2263959547 cites W2119139879 @default.
• W2263959547 cites W2119551554 @default.
• W2263959547 cites W2122373806 @default.
• W2263959547 cites W2123533784 @default.
• W2263959547 cites W2130996910 @default.
• W2263959547 cites W2133277680 @default.
• W2263959547 cites W2133584444 @default.
• W2263959547 cites W2137272573 @default.
• W2263959547 cites W2147555557 @default.
• W2263959547 cites W2150703185 @default.
• W2263959547 cites W2155298532 @default.
• W2263959547 cites W2157380596 @default.
• W2263959547 cites W2158167845 @default.
• W2263959547 cites W2166737644 @default.
• W2263959547 cites W2170509487 @default.
• W2263959547 cites W2271761891 @default.
• W2263959547 cites W2611747753 @default.
• W2263959547 cites W4242607144 @default.
• W2263959547 doi "https://doi.org/10.1016/j.cmpb.2015.12.018" @default.
• W2263959547 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/4803628" @default.
• W2263959547 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26776541" @default.
• W2263959547 hasPublicationYear "2016" @default.
• W2263959547 type Work @default.
• W2263959547 sameAs 2263959547 @default.
• W2263959547 citedByCount "21" @default.
• W2263959547 countsByYear W22639595472016 @default.
• W2263959547 countsByYear W22639595472017 @default.
• W2263959547 countsByYear W22639595472018 @default.
• W2263959547 countsByYear W22639595472019 @default.
• W2263959547 countsByYear W22639595472020 @default.
• W2263959547 countsByYear W22639595472021 @default.
• W2263959547 countsByYear W22639595472022 @default.
• W2263959547 countsByYear W22639595472023 @default.
• W2263959547 crossrefType "journal-article" @default.
• W2263959547 hasAuthorship W2263959547A5006854308 @default.
• W2263959547 hasAuthorship W2263959547A5015932921 @default.
• W2263959547 hasAuthorship W2263959547A5031524081 @default.
• W2263959547 hasAuthorship W2263959547A5037389227 @default.
• W2263959547 hasBestOaLocation W22639595472 @default.
• W2263959547 hasConcept C11413529 @default.
• W2263959547 hasConcept C115961682 @default.
• W2263959547 hasConcept C166704113 @default.
• W2263959547 hasConcept C173608175 @default.
• W2263959547 hasConcept C2778119891 @default.
• W2263959547 hasConcept C2779851693 @default.
• W2263959547 hasConcept C31972630 @default.
• W2263959547 hasConcept C41008148 @default.
• W2263959547 hasConcept C45374587 @default.
• W2263959547 hasConcept C459310 @default.
• W2263959547 hasConcept C49154492 @default.
• W2263959547 hasConcept C68339613 @default.
• W2263959547 hasConcept C9390403 @default.
• W2263959547 hasConceptScore W2263959547C11413529 @default.
• W2263959547 hasConceptScore W2263959547C115961682 @default.
• W2263959547 hasConceptScore W2263959547C166704113 @default.
• W2263959547 hasConceptScore W2263959547C173608175 @default.
• W2263959547 hasConceptScore W2263959547C2778119891 @default.
• W2263959547 hasConceptScore W2263959547C2779851693 @default.
• W2263959547 hasConceptScore W2263959547C31972630 @default.
• W2263959547 hasConceptScore W2263959547C41008148 @default.
• W2263959547 hasConceptScore W2263959547C45374587 @default.
• W2263959547 hasConceptScore W2263959547C459310 @default.
• W2263959547 hasConceptScore W2263959547C49154492 @default.
• W2263959547 hasConceptScore W2263959547C68339613 @default.

• next