FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136804573> ?p ?o ?g. }

• W3136804573 endingPage "1037" @default.
• W3136804573 startingPage "1030" @default.
• W3136804573 abstract "In acute stroke patients with large vessel occlusions, it would be helpful to be able to predict the difference in the size and location of the final infarct based on the outcome of reperfusion therapy. Our aim was to demonstrate the value of deep learning-based tissue at risk and ischemic core estimation. We trained deep learning models using a baseline MR image in 3 multicenter trials.Patients with acute ischemic stroke from 3 multicenter trials were identified and grouped into minimal (≤20%), partial (20%-80%), and major (≥80%) reperfusion status based on 4- to 24-hour follow-up MR imaging if available or into unknown status if not. Attention-gated convolutional neural networks were trained with admission imaging as input and the final infarct as ground truth. We explored 3 approaches: 1) separate: train 2 independent models with patients with minimal and major reperfusion; 2) pretraining: develop a single model using patients with partial and unknown reperfusion, then fine-tune it to create 2 separate models for minimal and major reperfusion; and 3) thresholding: use the current clinical method relying on apparent diffusion coefficient and time-to-maximum of the residue function maps. Models were evaluated using area under the curve, the Dice score coefficient, and lesion volume difference.Two hundred thirty-seven patients were included (minimal, major, partial, and unknown reperfusion: n = 52, 80, 57, and 48, respectively). The pretraining approach achieved the highest median Dice score coefficient (tissue at risk = 0.60, interquartile range, 0.43-0.70; core = 0.57, interquartile range, 0.30-0.69). This was higher than the separate approach (tissue at risk = 0.55; interquartile range, 0.41-0.69; P = .01; core = 0.49; interquartile range, 0.35-0.66; P = .04) or thresholding (tissue at risk = 0.56; interquartile range, 0.42-0.65; P = .008; core = 0.46; interquartile range, 0.16-0.54; P < .001).Deep learning models with fine-tuning lead to better performance for predicting tissue at risk and ischemic core, outperforming conventional thresholding methods." @default.
• W3136804573 created "2021-03-29" @default.
• W3136804573 creator A5000895141 @default.
• W3136804573 creator A5009588075 @default.
• W3136804573 creator A5015032920 @default.
• W3136804573 creator A5021957840 @default.
• W3136804573 creator A5035343735 @default.
• W3136804573 creator A5036153527 @default.
• W3136804573 creator A5051620273 @default.
• W3136804573 creator A5065577825 @default.
• W3136804573 creator A5079031814 @default.
• W3136804573 creator A5082029341 @default.
• W3136804573 date "2021-03-25" @default.
• W3136804573 modified "2023-10-18" @default.
• W3136804573 title "Tissue at Risk and Ischemic Core Estimation Using Deep Learning in Acute Stroke" @default.
• W3136804573 cites W1901129140 @default.
• W3136804573 cites W1973913902 @default.
• W3136804573 cites W1990814258 @default.
• W3136804573 cites W1995981953 @default.
• W3136804573 cites W2006558385 @default.
• W3136804573 cites W2119542322 @default.
• W3136804573 cites W2126896722 @default.
• W3136804573 cites W2130121805 @default.
• W3136804573 cites W2139621750 @default.
• W3136804573 cites W2144831962 @default.
• W3136804573 cites W2152705022 @default.
• W3136804573 cites W2156896333 @default.
• W3136804573 cites W2166645498 @default.
• W3136804573 cites W2180684088 @default.
• W3136804573 cites W2220129321 @default.
• W3136804573 cites W2272223753 @default.
• W3136804573 cites W2346062110 @default.
• W3136804573 cites W2533998335 @default.
• W3136804573 cites W2592430879 @default.
• W3136804573 cites W2600981297 @default.
• W3136804573 cites W2777652322 @default.
• W3136804573 cites W2787867590 @default.
• W3136804573 cites W2800452457 @default.
• W3136804573 cites W2891010780 @default.
• W3136804573 cites W2896817483 @default.
• W3136804573 cites W2902080736 @default.
• W3136804573 cites W2902558766 @default.
• W3136804573 cites W2944491145 @default.
• W3136804573 cites W2945717944 @default.
• W3136804573 cites W2980755248 @default.
• W3136804573 cites W2998393945 @default.
• W3136804573 cites W3010687358 @default.
• W3136804573 doi "https://doi.org/10.3174/ajnr.a7081" @default.
• W3136804573 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8191664" @default.
• W3136804573 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33766823" @default.
• W3136804573 hasPublicationYear "2021" @default.
• W3136804573 type Work @default.
• W3136804573 sameAs 3136804573 @default.
• W3136804573 citedByCount "18" @default.
• W3136804573 countsByYear W31368045732021 @default.
• W3136804573 countsByYear W31368045732022 @default.
• W3136804573 countsByYear W31368045732023 @default.
• W3136804573 crossrefType "journal-article" @default.
• W3136804573 hasAuthorship W3136804573A5000895141 @default.
• W3136804573 hasAuthorship W3136804573A5009588075 @default.
• W3136804573 hasAuthorship W3136804573A5015032920 @default.
• W3136804573 hasAuthorship W3136804573A5021957840 @default.
• W3136804573 hasAuthorship W3136804573A5035343735 @default.
• W3136804573 hasAuthorship W3136804573A5036153527 @default.
• W3136804573 hasAuthorship W3136804573A5051620273 @default.
• W3136804573 hasAuthorship W3136804573A5065577825 @default.
• W3136804573 hasAuthorship W3136804573A5079031814 @default.
• W3136804573 hasAuthorship W3136804573A5082029341 @default.
• W3136804573 hasBestOaLocation W31368045731 @default.
• W3136804573 hasConcept C115961682 @default.
• W3136804573 hasConcept C119060515 @default.
• W3136804573 hasConcept C124504099 @default.
• W3136804573 hasConcept C126322002 @default.
• W3136804573 hasConcept C126838900 @default.
• W3136804573 hasConcept C127413603 @default.
• W3136804573 hasConcept C141071460 @default.
• W3136804573 hasConcept C143409427 @default.
• W3136804573 hasConcept C154945302 @default.
• W3136804573 hasConcept C163892561 @default.
• W3136804573 hasConcept C164705383 @default.
• W3136804573 hasConcept C2776572282 @default.
• W3136804573 hasConcept C2779581417 @default.
• W3136804573 hasConcept C2780387585 @default.
• W3136804573 hasConcept C2780645631 @default.
• W3136804573 hasConcept C2989005 @default.
• W3136804573 hasConcept C3020166492 @default.
• W3136804573 hasConcept C41008148 @default.
• W3136804573 hasConcept C500558357 @default.
• W3136804573 hasConcept C535046627 @default.
• W3136804573 hasConcept C541997718 @default.
• W3136804573 hasConcept C70816921 @default.
• W3136804573 hasConcept C71924100 @default.
• W3136804573 hasConcept C78519656 @default.
• W3136804573 hasConcept C81363708 @default.
• W3136804573 hasConceptScore W3136804573C115961682 @default.
• W3136804573 hasConceptScore W3136804573C119060515 @default.
• W3136804573 hasConceptScore W3136804573C124504099 @default.
• W3136804573 hasConceptScore W3136804573C126322002 @default.

• next