FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309635395> ?p ?o ?g. }

• W4309635395 endingPage "22085" @default.
• W4309635395 startingPage "22071" @default.
• W4309635395 abstract "Despite recent advances in the accuracy of brain tumor segmentation, the results still suffer from low reliability and robustness. Uncertainty estimation is an efficient solution to this problem, as it provides a measure of confidence in the segmentation results. The current uncertainty estimation methods based on quantile regression, Bayesian neural network, ensemble, and Monte Carlo dropout are limited by their high computational cost and inconsistency. In order to overcome these challenges, Evidential Deep Learning (EDL) was developed in recent work but primarily for natural image classification and showed inferior segmentation results. In this paper, we proposed a region-based EDL segmentation framework that can generate reliable uncertainty maps and accurate segmentation results, which is robust to noise and image corruption. We used the Theory of Evidence to interpret the output of a neural network as evidence values gathered from input features. Following Subjective Logic, evidence was parameterized as a Dirichlet distribution, and predicted probabilities were treated as subjective opinions. To evaluate the performance of our model on segmentation and uncertainty estimation, we conducted quantitative and qualitative experiments on the BraTS 2020 dataset. The results demonstrated the top performance of the proposed method in quantifying segmentation uncertainty and robustly segmenting tumors. Furthermore, our proposed new framework maintained the advantages of low computational cost and easy implementation and showed the potential for clinical application." @default.
• W4309635395 created "2022-11-28" @default.
• W4309635395 creator A5017326471 @default.
• W4309635395 creator A5017659514 @default.
• W4309635395 creator A5019560977 @default.
• W4309635395 creator A5073429636 @default.
• W4309635395 date "2022-11-17" @default.
• W4309635395 modified "2023-10-11" @default.
• W4309635395 title "Region-based evidential deep learning to quantify uncertainty and improve robustness of brain tumor segmentation" @default.
• W4309635395 cites W1512921847 @default.
• W4309635395 cites W1641498739 @default.
• W4309635395 cites W1901129140 @default.
• W4309635395 cites W1903029394 @default.
• W4309635395 cites W2047229728 @default.
• W4309635395 cites W2103328396 @default.
• W4309635395 cites W2111051539 @default.
• W4309635395 cites W2395611524 @default.
• W4309635395 cites W2613456556 @default.
• W4309635395 cites W2751069891 @default.
• W4309635395 cites W2971561076 @default.
• W4309635395 cites W3015910149 @default.
• W4309635395 cites W3039044273 @default.
• W4309635395 cites W3040617750 @default.
• W4309635395 cites W3098712157 @default.
• W4309635395 cites W3142164167 @default.
• W4309635395 cites W3146464195 @default.
• W4309635395 cites W3183048323 @default.
• W4309635395 cites W4205893333 @default.
• W4309635395 cites W4234587807 @default.
• W4309635395 cites W4246234845 @default.
• W4309635395 cites W4287225447 @default.
• W4309635395 cites W4295916009 @default.
• W4309635395 cites W4312264252 @default.
• W4309635395 cites W4322495747 @default.
• W4309635395 cites W4362458848 @default.
• W4309635395 doi "https://doi.org/10.1007/s00521-022-08016-4" @default.
• W4309635395 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37724130" @default.
• W4309635395 hasPublicationYear "2022" @default.
• W4309635395 type Work @default.
• W4309635395 citedByCount "2" @default.
• W4309635395 countsByYear W43096353952023 @default.
• W4309635395 crossrefType "journal-article" @default.
• W4309635395 hasAuthorship W4309635395A5017326471 @default.
• W4309635395 hasAuthorship W4309635395A5017659514 @default.
• W4309635395 hasAuthorship W4309635395A5019560977 @default.
• W4309635395 hasAuthorship W4309635395A5073429636 @default.
• W4309635395 hasBestOaLocation W43096353951 @default.
• W4309635395 hasConcept C104317684 @default.
• W4309635395 hasConcept C105795698 @default.
• W4309635395 hasConcept C118671147 @default.
• W4309635395 hasConcept C119857082 @default.
• W4309635395 hasConcept C124504099 @default.
• W4309635395 hasConcept C153180895 @default.
• W4309635395 hasConcept C154945302 @default.
• W4309635395 hasConcept C185592680 @default.
• W4309635395 hasConcept C32230216 @default.
• W4309635395 hasConcept C33923547 @default.
• W4309635395 hasConcept C41008148 @default.
• W4309635395 hasConcept C50644808 @default.
• W4309635395 hasConcept C55493867 @default.
• W4309635395 hasConcept C63479239 @default.
• W4309635395 hasConcept C89600930 @default.
• W4309635395 hasConceptScore W4309635395C104317684 @default.
• W4309635395 hasConceptScore W4309635395C105795698 @default.
• W4309635395 hasConceptScore W4309635395C118671147 @default.
• W4309635395 hasConceptScore W4309635395C119857082 @default.
• W4309635395 hasConceptScore W4309635395C124504099 @default.
• W4309635395 hasConceptScore W4309635395C153180895 @default.
• W4309635395 hasConceptScore W4309635395C154945302 @default.
• W4309635395 hasConceptScore W4309635395C185592680 @default.
• W4309635395 hasConceptScore W4309635395C32230216 @default.
• W4309635395 hasConceptScore W4309635395C33923547 @default.
• W4309635395 hasConceptScore W4309635395C41008148 @default.
• W4309635395 hasConceptScore W4309635395C50644808 @default.
• W4309635395 hasConceptScore W4309635395C55493867 @default.
• W4309635395 hasConceptScore W4309635395C63479239 @default.
• W4309635395 hasConceptScore W4309635395C89600930 @default.
• W4309635395 hasFunder F4320306257 @default.
• W4309635395 hasFunder F4320314731 @default.
• W4309635395 hasFunder F4320319992 @default.
• W4309635395 hasFunder F4320320006 @default.
• W4309635395 hasFunder F4320321043 @default.
• W4309635395 hasFunder F4320321705 @default.
• W4309635395 hasFunder F4320332999 @default.
• W4309635395 hasFunder F4320334626 @default.
• W4309635395 hasFunder F4320336039 @default.
• W4309635395 hasIssue "30" @default.
• W4309635395 hasLocation W43096353951 @default.
• W4309635395 hasLocation W43096353952 @default.
• W4309635395 hasLocation W43096353953 @default.
• W4309635395 hasLocation W43096353954 @default.
• W4309635395 hasOpenAccess W4309635395 @default.
• W4309635395 hasPrimaryLocation W43096353951 @default.
• W4309635395 hasRelatedWork W134976887 @default.
• W4309635395 hasRelatedWork W1582206143 @default.
• W4309635395 hasRelatedWork W1840273037 @default.
• W4309635395 hasRelatedWork W2138214894 @default.
• W4309635395 hasRelatedWork W2464972745 @default.

• next