FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286541699> ?p ?o ?g. }

• W4286541699 endingPage "167" @default.
• W4286541699 startingPage "151" @default.
• W4286541699 abstract "Brain extraction is an indispensable step in neuro-imaging with a direct impact on downstream analyses. Most such methods have been developed for non-pathologically affected brains, and hence tend to suffer in performance when applied on brains with pathologies, e.g., gliomas, multiple sclerosis, traumatic brain injuries. Deep Learning (DL) methodologies for healthcare have shown promising results, but their clinical translation has been limited, primarily due to these methods suffering from i) high computational cost, and ii) specific hardware requirements, e.g., DL acceleration cards. In this study, we explore the potential of mathematical optimizations, towards making DL methods amenable to application in low resource environments. We focus on both the qualitative and quantitative evaluation of such optimizations on an existing DL brain extraction method, designed for pathologically-affected brains and agnostic to the input modality. We conduct direct optimizations and quantization of the trained model (i.e., prior to inference on new data). Our results yield substantial gains, in terms of speedup, latency, throughput, and reduction in memory usage, while the segmentation performance of the initial and the optimized models remains stable, i.e., as quantified by both the Dice Similarity Coefficient and the Hausdorff Distance. These findings support post-training optimizations as a promising approach for enabling the execution of advanced DL methodologies on plain commercial-grade CPUs, and hence contributing to their translation in limited- and low- resource clinical environments." @default.
• W4286541699 created "2022-07-22" @default.
• W4286541699 creator A5000052866 @default.
• W4286541699 creator A5028649744 @default.
• W4286541699 creator A5040273551 @default.
• W4286541699 creator A5041549836 @default.
• W4286541699 creator A5043497448 @default.
• W4286541699 creator A5049617352 @default.
• W4286541699 creator A5064222905 @default.
• W4286541699 creator A5068309305 @default.
• W4286541699 creator A5074115355 @default.
• W4286541699 date "2022-01-01" @default.
• W4286541699 modified "2023-09-27" @default.
• W4286541699 title "Optimization of Deep Learning Based Brain Extraction in MRI for Low Resource Environments" @default.
• W4286541699 cites W110887467 @default.
• W4286541699 cites W1641498739 @default.
• W4286541699 cites W1901129140 @default.
• W4286541699 cites W2071881327 @default.
• W4286541699 cites W2083927153 @default.
• W4286541699 cites W2106235379 @default.
• W4286541699 cites W2117340355 @default.
• W4286541699 cites W2118987707 @default.
• W4286541699 cites W2121014637 @default.
• W4286541699 cites W2127890285 @default.
• W4286541699 cites W2132513126 @default.
• W4286541699 cites W2157848968 @default.
• W4286541699 cites W2194775991 @default.
• W4286541699 cites W2301358467 @default.
• W4286541699 cites W2464708700 @default.
• W4286541699 cites W2517954747 @default.
• W4286541699 cites W2611631440 @default.
• W4286541699 cites W2751069891 @default.
• W4286541699 cites W2783923767 @default.
• W4286541699 cites W2788833028 @default.
• W4286541699 cites W2793236705 @default.
• W4286541699 cites W2810700317 @default.
• W4286541699 cites W2912281309 @default.
• W4286541699 cites W2914199948 @default.
• W4286541699 cites W2968446587 @default.
• W4286541699 cites W2982036758 @default.
• W4286541699 cites W2998218113 @default.
• W4286541699 cites W3010939994 @default.
• W4286541699 cites W3012393256 @default.
• W4286541699 cites W3026062881 @default.
• W4286541699 cites W3026200185 @default.
• W4286541699 cites W3028293663 @default.
• W4286541699 cites W3037636883 @default.
• W4286541699 cites W3040690877 @default.
• W4286541699 cites W3105432754 @default.
• W4286541699 cites W3108835732 @default.
• W4286541699 cites W3112701542 @default.
• W4286541699 cites W3125468979 @default.
• W4286541699 doi "https://doi.org/10.1007/978-3-031-08999-2_12" @default.
• W4286541699 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36331281" @default.
• W4286541699 hasPublicationYear "2022" @default.
• W4286541699 type Work @default.
• W4286541699 citedByCount "2" @default.
• W4286541699 countsByYear W42865416992023 @default.
• W4286541699 crossrefType "book-chapter" @default.
• W4286541699 hasAuthorship W4286541699A5000052866 @default.
• W4286541699 hasAuthorship W4286541699A5028649744 @default.
• W4286541699 hasAuthorship W4286541699A5040273551 @default.
• W4286541699 hasAuthorship W4286541699A5041549836 @default.
• W4286541699 hasAuthorship W4286541699A5043497448 @default.
• W4286541699 hasAuthorship W4286541699A5049617352 @default.
• W4286541699 hasAuthorship W4286541699A5064222905 @default.
• W4286541699 hasAuthorship W4286541699A5068309305 @default.
• W4286541699 hasAuthorship W4286541699A5074115355 @default.
• W4286541699 hasBestOaLocation W42865416992 @default.
• W4286541699 hasConcept C108583219 @default.
• W4286541699 hasConcept C119857082 @default.
• W4286541699 hasConcept C13164978 @default.
• W4286541699 hasConcept C149635348 @default.
• W4286541699 hasConcept C153180895 @default.
• W4286541699 hasConcept C154945302 @default.
• W4286541699 hasConcept C173608175 @default.
• W4286541699 hasConcept C2776214188 @default.
• W4286541699 hasConcept C2781357197 @default.
• W4286541699 hasConcept C41008148 @default.
• W4286541699 hasConcept C42935608 @default.
• W4286541699 hasConcept C68339613 @default.
• W4286541699 hasConcept C89600930 @default.
• W4286541699 hasConceptScore W4286541699C108583219 @default.
• W4286541699 hasConceptScore W4286541699C119857082 @default.
• W4286541699 hasConceptScore W4286541699C13164978 @default.
• W4286541699 hasConceptScore W4286541699C149635348 @default.
• W4286541699 hasConceptScore W4286541699C153180895 @default.
• W4286541699 hasConceptScore W4286541699C154945302 @default.
• W4286541699 hasConceptScore W4286541699C173608175 @default.
• W4286541699 hasConceptScore W4286541699C2776214188 @default.
• W4286541699 hasConceptScore W4286541699C2781357197 @default.
• W4286541699 hasConceptScore W4286541699C41008148 @default.
• W4286541699 hasConceptScore W4286541699C42935608 @default.
• W4286541699 hasConceptScore W4286541699C68339613 @default.
• W4286541699 hasConceptScore W4286541699C89600930 @default.
• W4286541699 hasLocation W42865416991 @default.
• W4286541699 hasLocation W42865416992 @default.
• W4286541699 hasLocation W42865416993 @default.

• next