FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022713997> ?p ?o ?g. }

• W3022713997 endingPage "105521" @default.
• W3022713997 startingPage "105521" @default.
• W3022713997 abstract "Abstract Background and objective. Acute stroke lesion segmentation tasks are of great clinical interest as they can help doctors make better informed time-critical treatment decisions. Magnetic resonance imaging (MRI) is time demanding but can provide images that are considered the gold standard for diagnosis. Automated stroke lesion segmentation can provide with an estimate of the location and volume of the lesioned tissue, which can help in the clinical practice to better assess and evaluate the risks of each treatment. Methods. We propose a deep learning methodology for acute and sub-acute stroke lesion segmentation using multimodal MR imaging. We pre-process the data to facilitate learning features based on the symmetry of brain hemispheres. The issue of class imbalance is tackled using small patches with a balanced training patch sampling strategy and a dynamically weighted loss function. Moreover, a combination of whole patch predictions, using a U-Net based CNN architecture, and high degree of overlapping patches reduces the need for additional post-processing. Results. The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Lesion Segmentation challenge (ISLES 2015). These involve the tasks of sub-acute stroke lesion segmentation (SISS) and acute stroke penumbra estimation (SPES) from multiple diffusion, perfusion and anatomical MRI modalities. The performance is compared against state-of-the-art methods with a blind online testing set evaluation on each of the challenges. At the time of submitting this manuscript, our approach is the first method in the online rankings for the SISS (DSC=0.59 ± 0.31) and SPES sub-tasks (DSC=0.84 ± 0.10). When compared with the rest of submitted strategies, we achieve top rank performance with a lower Hausdorff distance. Conclusions. Better segmentation results are obtained by leveraging the anatomy and pathophysiology of acute stroke lesions and using a combined approach to minimize the effects of class imbalance. The same training procedure is used for both tasks, showing the proposed methodology can generalize well enough to deal with different unrelated tasks and imaging modalities without hyper-parameter tuning. In order to promote the reproducibility of our results, a public version of the proposed method has been released to the scientific community." @default.
• W3022713997 created "2020-05-13" @default.
• W3022713997 creator A5027168396 @default.
• W3022713997 creator A5043375263 @default.
• W3022713997 creator A5060062918 @default.
• W3022713997 creator A5064897887 @default.
• W3022713997 creator A5077881500 @default.
• W3022713997 creator A5085592048 @default.
• W3022713997 date "2020-10-01" @default.
• W3022713997 modified "2023-10-18" @default.
• W3022713997 title "Acute and sub-acute stroke lesion segmentation from multimodal MRI" @default.
• W3022713997 cites W1743074346 @default.
• W3022713997 cites W1987869189 @default.
• W3022713997 cites W2097805840 @default.
• W3022713997 cites W2121300729 @default.
• W3022713997 cites W2129869438 @default.
• W3022713997 cites W2147800946 @default.
• W3022713997 cites W2217077692 @default.
• W3022713997 cites W2301358467 @default.
• W3022713997 cites W2484736472 @default.
• W3022713997 cites W2570873234 @default.
• W3022713997 cites W2784209709 @default.
• W3022713997 cites W2791723176 @default.
• W3022713997 cites W2795142235 @default.
• W3022713997 cites W2890354008 @default.
• W3022713997 cites W2963052998 @default.
• W3022713997 cites W2963076262 @default.
• W3022713997 cites W2967486175 @default.
• W3022713997 cites W2977700345 @default.
• W3022713997 cites W2995423635 @default.
• W3022713997 cites W4235770099 @default.
• W3022713997 doi "https://doi.org/10.1016/j.cmpb.2020.105521" @default.
• W3022713997 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32434099" @default.
• W3022713997 hasPublicationYear "2020" @default.
• W3022713997 type Work @default.
• W3022713997 sameAs 3022713997 @default.
• W3022713997 citedByCount "34" @default.
• W3022713997 countsByYear W30227139972021 @default.
• W3022713997 countsByYear W30227139972022 @default.
• W3022713997 countsByYear W30227139972023 @default.
• W3022713997 crossrefType "journal-article" @default.
• W3022713997 hasAuthorship W3022713997A5027168396 @default.
• W3022713997 hasAuthorship W3022713997A5043375263 @default.
• W3022713997 hasAuthorship W3022713997A5060062918 @default.
• W3022713997 hasAuthorship W3022713997A5064897887 @default.
• W3022713997 hasAuthorship W3022713997A5077881500 @default.
• W3022713997 hasAuthorship W3022713997A5085592048 @default.
• W3022713997 hasBestOaLocation W30227139972 @default.
• W3022713997 hasConcept C126322002 @default.
• W3022713997 hasConcept C126838900 @default.
• W3022713997 hasConcept C127413603 @default.
• W3022713997 hasConcept C142724271 @default.
• W3022713997 hasConcept C143409427 @default.
• W3022713997 hasConcept C154945302 @default.
• W3022713997 hasConcept C2776572282 @default.
• W3022713997 hasConcept C2780645631 @default.
• W3022713997 hasConcept C2781156865 @default.
• W3022713997 hasConcept C3020166492 @default.
• W3022713997 hasConcept C41008148 @default.
• W3022713997 hasConcept C71924100 @default.
• W3022713997 hasConcept C78519656 @default.
• W3022713997 hasConcept C89600930 @default.
• W3022713997 hasConcept C99508421 @default.
• W3022713997 hasConceptScore W3022713997C126322002 @default.
• W3022713997 hasConceptScore W3022713997C126838900 @default.
• W3022713997 hasConceptScore W3022713997C127413603 @default.
• W3022713997 hasConceptScore W3022713997C142724271 @default.
• W3022713997 hasConceptScore W3022713997C143409427 @default.
• W3022713997 hasConceptScore W3022713997C154945302 @default.
• W3022713997 hasConceptScore W3022713997C2776572282 @default.
• W3022713997 hasConceptScore W3022713997C2780645631 @default.
• W3022713997 hasConceptScore W3022713997C2781156865 @default.
• W3022713997 hasConceptScore W3022713997C3020166492 @default.
• W3022713997 hasConceptScore W3022713997C41008148 @default.
• W3022713997 hasConceptScore W3022713997C71924100 @default.
• W3022713997 hasConceptScore W3022713997C78519656 @default.
• W3022713997 hasConceptScore W3022713997C89600930 @default.
• W3022713997 hasConceptScore W3022713997C99508421 @default.
• W3022713997 hasLocation W30227139971 @default.
• W3022713997 hasLocation W30227139972 @default.
• W3022713997 hasLocation W30227139973 @default.
• W3022713997 hasOpenAccess W3022713997 @default.
• W3022713997 hasPrimaryLocation W30227139971 @default.
• W3022713997 hasRelatedWork W2006065208 @default.
• W3022713997 hasRelatedWork W2058081075 @default.
• W3022713997 hasRelatedWork W2082520993 @default.
• W3022713997 hasRelatedWork W2084959658 @default.
• W3022713997 hasRelatedWork W2164494555 @default.
• W3022713997 hasRelatedWork W2355091906 @default.
• W3022713997 hasRelatedWork W2381774043 @default.
• W3022713997 hasRelatedWork W2400727047 @default.
• W3022713997 hasRelatedWork W2611590172 @default.
• W3022713997 hasRelatedWork W2425903266 @default.
• W3022713997 hasVolume "194" @default.
• W3022713997 isParatext "false" @default.
• W3022713997 isRetracted "false" @default.
• W3022713997 magId "3022713997" @default.
• W3022713997 workType "article" @default.