FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887976372> ?p ?o ?g. }

• W2887976372 endingPage "45" @default.
• W2887976372 startingPage "34" @default.
• W2887976372 abstract "Despite the state-of-the-art performance for medical image segmentation, deep convolutional neural networks (CNNs) have rarely provided uncertainty estimations regarding their segmentation outputs, e.g., model (epistemic) and image-based (aleatoric) uncertainties. In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks at both pixel level and structure level. We additionally propose a test-time augmentation-based aleatoric uncertainty to analyze the effect of different transformations of the input image on the segmentation output. Test-time augmentation has been previously used to improve segmentation accuracy, yet not been formulated in a consistent mathematical framework. Hence, we also propose a theoretical formulation of test-time augmentation, where a distribution of the prediction is estimated by Monte Carlo simulation with prior distributions of parameters in an image acquisition model that involves image transformations and noise. We compare and combine our proposed aleatoric uncertainty with model uncertainty. Experiments with segmentation of fetal brains and brain tumors from 2D and 3D Magnetic Resonance Images (MRI) showed that 1) the test-time augmentation-based aleatoric uncertainty provides a better uncertainty estimation than calculating the test-time dropout-based model uncertainty alone and helps to reduce overconfident incorrect predictions, and 2) our test-time augmentation outperforms a single-prediction baseline and dropout-based multiple predictions." @default.
• W2887976372 created "2018-08-22" @default.
• W2887976372 creator A5028279799 @default.
• W2887976372 creator A5029722566 @default.
• W2887976372 creator A5035865500 @default.
• W2887976372 creator A5079918230 @default.
• W2887976372 creator A5082106258 @default.
• W2887976372 creator A5090935942 @default.
• W2887976372 date "2019-04-01" @default.
• W2887976372 modified "2023-10-17" @default.
• W2887976372 title "Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks" @default.
• W2887976372 cites W1641498739 @default.
• W2887976372 cites W1683159118 @default.
• W2887976372 cites W1993127575 @default.
• W2887976372 cites W1995151116 @default.
• W2887976372 cites W2101099609 @default.
• W2887976372 cites W2117539524 @default.
• W2887976372 cites W2170854835 @default.
• W2887976372 cites W2301358467 @default.
• W2887976372 cites W2359099468 @default.
• W2887976372 cites W2395611524 @default.
• W2887976372 cites W2581082771 @default.
• W2887976372 cites W2605766009 @default.
• W2887976372 cites W2729876886 @default.
• W2887976372 cites W2751069891 @default.
• W2887976372 cites W2755930428 @default.
• W2887976372 cites W2763160469 @default.
• W2887976372 cites W2784733489 @default.
• W2887976372 cites W2791142503 @default.
• W2887976372 cites W2963785012 @default.
• W2887976372 cites W2971561076 @default.
• W2887976372 cites W4294305479 @default.
• W2887976372 cites W646355753 @default.
• W2887976372 doi "https://doi.org/10.1016/j.neucom.2019.01.103" @default.
• W2887976372 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6783308" @default.
• W2887976372 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31595105" @default.
• W2887976372 hasPublicationYear "2019" @default.
• W2887976372 type Work @default.
• W2887976372 sameAs 2887976372 @default.
• W2887976372 citedByCount "321" @default.
• W2887976372 countsByYear W28879763722019 @default.
• W2887976372 countsByYear W28879763722020 @default.
• W2887976372 countsByYear W28879763722021 @default.
• W2887976372 countsByYear W28879763722022 @default.
• W2887976372 countsByYear W28879763722023 @default.
• W2887976372 crossrefType "journal-article" @default.
• W2887976372 hasAuthorship W2887976372A5028279799 @default.
• W2887976372 hasAuthorship W2887976372A5029722566 @default.
• W2887976372 hasAuthorship W2887976372A5035865500 @default.
• W2887976372 hasAuthorship W2887976372A5079918230 @default.
• W2887976372 hasAuthorship W2887976372A5082106258 @default.
• W2887976372 hasAuthorship W2887976372A5090935942 @default.
• W2887976372 hasBestOaLocation W28879763721 @default.
• W2887976372 hasConcept C105795698 @default.
• W2887976372 hasConcept C115961682 @default.
• W2887976372 hasConcept C119857082 @default.
• W2887976372 hasConcept C124504099 @default.
• W2887976372 hasConcept C153180895 @default.
• W2887976372 hasConcept C154945302 @default.
• W2887976372 hasConcept C19499675 @default.
• W2887976372 hasConcept C2776145597 @default.
• W2887976372 hasConcept C32230216 @default.
• W2887976372 hasConcept C33923547 @default.
• W2887976372 hasConcept C41008148 @default.
• W2887976372 hasConcept C50644808 @default.
• W2887976372 hasConcept C81363708 @default.
• W2887976372 hasConcept C89600930 @default.
• W2887976372 hasConcept C99498987 @default.
• W2887976372 hasConceptScore W2887976372C105795698 @default.
• W2887976372 hasConceptScore W2887976372C115961682 @default.
• W2887976372 hasConceptScore W2887976372C119857082 @default.
• W2887976372 hasConceptScore W2887976372C124504099 @default.
• W2887976372 hasConceptScore W2887976372C153180895 @default.
• W2887976372 hasConceptScore W2887976372C154945302 @default.
• W2887976372 hasConceptScore W2887976372C19499675 @default.
• W2887976372 hasConceptScore W2887976372C2776145597 @default.
• W2887976372 hasConceptScore W2887976372C32230216 @default.
• W2887976372 hasConceptScore W2887976372C33923547 @default.
• W2887976372 hasConceptScore W2887976372C41008148 @default.
• W2887976372 hasConceptScore W2887976372C50644808 @default.
• W2887976372 hasConceptScore W2887976372C81363708 @default.
• W2887976372 hasConceptScore W2887976372C89600930 @default.
• W2887976372 hasConceptScore W2887976372C99498987 @default.
• W2887976372 hasFunder F4320307874 @default.
• W2887976372 hasFunder F4320319990 @default.
• W2887976372 hasFunder F4320320006 @default.
• W2887976372 hasFunder F4320334627 @default.
• W2887976372 hasLocation W28879763721 @default.
• W2887976372 hasLocation W28879763722 @default.
• W2887976372 hasLocation W28879763723 @default.
• W2887976372 hasLocation W28879763724 @default.
• W2887976372 hasLocation W28879763725 @default.
• W2887976372 hasLocation W28879763726 @default.
• W2887976372 hasLocation W28879763727 @default.
• W2887976372 hasLocation W28879763728 @default.
• W2887976372 hasOpenAccess W2887976372 @default.
• W2887976372 hasPrimaryLocation W28879763721 @default.
• W2887976372 hasRelatedWork W1521968289 @default.

• next