Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313897977> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4313897977 endingPage "100092" @default.
- W4313897977 startingPage "100092" @default.
- W4313897977 abstract "Cerebrovascular disease is one of the world's leading causes of death. Blood vessel segmentation is a primary stage in diagnosing. Although a few deep neural networks have been suggested to automate volumetric brain blood vessel segmentation, few studies have considered the relevance of the evaluation metrics to diagnosing cerebrovascular disease due to the complicated nature of this task. This study aimed to understand if brain vasculature segmentation using a convolutional neural network (CNN) could meet radiologists' requirements for disease diagnosis. We employed a deeply supervised attention-gated 3D U-Net trained based on the Focal Tversky loss function to extract brain vasculatures from volumetric magnetic resonance angiography (MRA) images. Here we show that our training procedure led to biologically relevant results despite not scoring well using the Dice score, a common metric for algorithm evaluation. We achieved Dice (±SD) = 0.71 ± 0.02 and two radiologists confirmed and validated that our method successfully captured the major blood vessel branches of the circle of Willis (CoW) having biological importance, including internal carotid artery (ICA), middle cerebral artery (MCA), anterior cerebral artery (ACA), and posterior cerebral artery (PCA). Adding radiologists' expert opinions, we could fill this gap that using only the current common evaluation metrics, such as the Dice coefficient, is not enough for brain vessel segmentation assessment. These results suggest the additional value for computational approaches that are designed with end-user stakeholders in mind." @default.
- W4313897977 created "2023-01-10" @default.
- W4313897977 creator A5006885747 @default.
- W4313897977 creator A5022903711 @default.
- W4313897977 creator A5065995488 @default.
- W4313897977 creator A5066924235 @default.
- W4313897977 creator A5074195085 @default.
- W4313897977 creator A5078852705 @default.
- W4313897977 creator A5090666078 @default.
- W4313897977 date "2023-01-01" @default.
- W4313897977 modified "2023-10-18" @default.
- W4313897977 title "Model utility of a deep learning-based segmentation is not Dice coefficient dependent: A case study in volumetric brain blood vessel segmentation" @default.
- W4313897977 cites W2026616100 @default.
- W4313897977 cites W2550848904 @default.
- W4313897977 cites W2808302424 @default.
- W4313897977 cites W2888358068 @default.
- W4313897977 cites W2920218276 @default.
- W4313897977 cites W2936503027 @default.
- W4313897977 cites W2946711149 @default.
- W4313897977 cites W2949153442 @default.
- W4313897977 cites W2963351448 @default.
- W4313897977 cites W2967844572 @default.
- W4313897977 cites W2994958466 @default.
- W4313897977 cites W3004894558 @default.
- W4313897977 cites W3007268491 @default.
- W4313897977 cites W3012387312 @default.
- W4313897977 cites W3092226997 @default.
- W4313897977 cites W3117058671 @default.
- W4313897977 cites W3164956625 @default.
- W4313897977 cites W3204934826 @default.
- W4313897977 doi "https://doi.org/10.1016/j.ibmed.2023.100092" @default.
- W4313897977 hasPublicationYear "2023" @default.
- W4313897977 type Work @default.
- W4313897977 citedByCount "0" @default.
- W4313897977 crossrefType "journal-article" @default.
- W4313897977 hasAuthorship W4313897977A5006885747 @default.
- W4313897977 hasAuthorship W4313897977A5022903711 @default.
- W4313897977 hasAuthorship W4313897977A5065995488 @default.
- W4313897977 hasAuthorship W4313897977A5066924235 @default.
- W4313897977 hasAuthorship W4313897977A5074195085 @default.
- W4313897977 hasAuthorship W4313897977A5078852705 @default.
- W4313897977 hasAuthorship W4313897977A5090666078 @default.
- W4313897977 hasBestOaLocation W43138979771 @default.
- W4313897977 hasConcept C108583219 @default.
- W4313897977 hasConcept C124504099 @default.
- W4313897977 hasConcept C126838900 @default.
- W4313897977 hasConcept C143409427 @default.
- W4313897977 hasConcept C153180895 @default.
- W4313897977 hasConcept C154945302 @default.
- W4313897977 hasConcept C163892561 @default.
- W4313897977 hasConcept C22029948 @default.
- W4313897977 hasConcept C2524010 @default.
- W4313897977 hasConcept C33923547 @default.
- W4313897977 hasConcept C41008148 @default.
- W4313897977 hasConcept C71924100 @default.
- W4313897977 hasConcept C81363708 @default.
- W4313897977 hasConcept C89600930 @default.
- W4313897977 hasConceptScore W4313897977C108583219 @default.
- W4313897977 hasConceptScore W4313897977C124504099 @default.
- W4313897977 hasConceptScore W4313897977C126838900 @default.
- W4313897977 hasConceptScore W4313897977C143409427 @default.
- W4313897977 hasConceptScore W4313897977C153180895 @default.
- W4313897977 hasConceptScore W4313897977C154945302 @default.
- W4313897977 hasConceptScore W4313897977C163892561 @default.
- W4313897977 hasConceptScore W4313897977C22029948 @default.
- W4313897977 hasConceptScore W4313897977C2524010 @default.
- W4313897977 hasConceptScore W4313897977C33923547 @default.
- W4313897977 hasConceptScore W4313897977C41008148 @default.
- W4313897977 hasConceptScore W4313897977C71924100 @default.
- W4313897977 hasConceptScore W4313897977C81363708 @default.
- W4313897977 hasConceptScore W4313897977C89600930 @default.
- W4313897977 hasLocation W43138979771 @default.
- W4313897977 hasOpenAccess W4313897977 @default.
- W4313897977 hasPrimaryLocation W43138979771 @default.
- W4313897977 hasRelatedWork W2807114581 @default.
- W4313897977 hasRelatedWork W2920218276 @default.
- W4313897977 hasRelatedWork W2948809999 @default.
- W4313897977 hasRelatedWork W2969790209 @default.
- W4313897977 hasRelatedWork W3006135495 @default.
- W4313897977 hasRelatedWork W3118494652 @default.
- W4313897977 hasRelatedWork W4200528772 @default.
- W4313897977 hasRelatedWork W4297786172 @default.
- W4313897977 hasRelatedWork W4360850309 @default.
- W4313897977 hasRelatedWork W4365788530 @default.
- W4313897977 hasVolume "7" @default.
- W4313897977 isParatext "false" @default.
- W4313897977 isRetracted "false" @default.
- W4313897977 workType "article" @default.