Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209439384> ?p ?o ?g. }
- W3209439384 endingPage "102000" @default.
- W3209439384 startingPage "102000" @default.
- W3209439384 abstract "Whole-brain segmentation is a crucial pre-processing step for many neuroimaging analyses pipelines. Accurate and efficient whole-brain segmentations are important for many neuroimage analysis tasks to provide clinically relevant information. Several recently proposed convolutional neural networks (CNN) perform whole brain segmentation using individual 2D slices or 3D patches as inputs due to graphical processing unit (GPU) memory limitations, and use sliding windows to perform whole brain segmentation during inference. However, these approaches lack global and spatial information about the entire brain and lead to compromised efficiency during both training and testing. We introduce a 3D hemisphere-based CNN for automatic whole-brain segmentation of T1-weighted magnetic resonance images of adult brains. First, we trained a localization network to predict bounding boxes for both hemispheres. Then, we trained a segmentation network to segment one hemisphere, and segment the opposing hemisphere by reflecting it across the mid-sagittal plane. Our network shows high performance both in terms of segmentation efficiency and accuracy (0.84 overall Dice similarity and 6.1 mm overall Hausdorff distance) in segmenting 102 brain structures. On multiple independent test datasets, our method demonstrated a competitive performance in the subcortical segmentation task and a high consistency in volumetric measurements of intra-session scans." @default.
- W3209439384 created "2021-11-08" @default.
- W3209439384 creator A5000972836 @default.
- W3209439384 creator A5002709899 @default.
- W3209439384 creator A5011170222 @default.
- W3209439384 creator A5020434567 @default.
- W3209439384 creator A5026662287 @default.
- W3209439384 creator A5028265471 @default.
- W3209439384 creator A5030849116 @default.
- W3209439384 creator A5073216396 @default.
- W3209439384 creator A5077698496 @default.
- W3209439384 date "2022-01-01" @default.
- W3209439384 modified "2023-10-14" @default.
- W3209439384 title "3D hemisphere-based convolutional neural network for whole-brain MRI segmentation" @default.
- W3209439384 cites W1910109443 @default.
- W3209439384 cites W1963163807 @default.
- W3209439384 cites W1983208069 @default.
- W3209439384 cites W1987869189 @default.
- W3209439384 cites W1994947322 @default.
- W3209439384 cites W2002209162 @default.
- W3209439384 cites W2004293194 @default.
- W3209439384 cites W2018077021 @default.
- W3209439384 cites W2024729467 @default.
- W3209439384 cites W2028158228 @default.
- W3209439384 cites W2029924671 @default.
- W3209439384 cites W2030309005 @default.
- W3209439384 cites W2056965030 @default.
- W3209439384 cites W2089975325 @default.
- W3209439384 cites W2115799070 @default.
- W3209439384 cites W2117151480 @default.
- W3209439384 cites W2120731293 @default.
- W3209439384 cites W2123957845 @default.
- W3209439384 cites W2128288198 @default.
- W3209439384 cites W2301358467 @default.
- W3209439384 cites W2321460300 @default.
- W3209439384 cites W2412782625 @default.
- W3209439384 cites W2553219621 @default.
- W3209439384 cites W2567599812 @default.
- W3209439384 cites W2589647984 @default.
- W3209439384 cites W2744275124 @default.
- W3209439384 cites W2760516000 @default.
- W3209439384 cites W2788755901 @default.
- W3209439384 cites W2901434856 @default.
- W3209439384 cites W2901469177 @default.
- W3209439384 cites W2962900979 @default.
- W3209439384 cites W2963105274 @default.
- W3209439384 cites W2963150697 @default.
- W3209439384 cites W2963153291 @default.
- W3209439384 cites W2964302138 @default.
- W3209439384 cites W2980702656 @default.
- W3209439384 cites W2993516307 @default.
- W3209439384 cites W3011390913 @default.
- W3209439384 cites W3033878890 @default.
- W3209439384 cites W3160947785 @default.
- W3209439384 cites W3163803374 @default.
- W3209439384 cites W3206468898 @default.
- W3209439384 cites W4212931019 @default.
- W3209439384 cites W4241074797 @default.
- W3209439384 cites W639708223 @default.
- W3209439384 doi "https://doi.org/10.1016/j.compmedimag.2021.102000" @default.
- W3209439384 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34839147" @default.
- W3209439384 hasPublicationYear "2022" @default.
- W3209439384 type Work @default.
- W3209439384 sameAs 3209439384 @default.
- W3209439384 citedByCount "9" @default.
- W3209439384 countsByYear W32094393842022 @default.
- W3209439384 countsByYear W32094393842023 @default.
- W3209439384 crossrefType "journal-article" @default.
- W3209439384 hasAuthorship W3209439384A5000972836 @default.
- W3209439384 hasAuthorship W3209439384A5002709899 @default.
- W3209439384 hasAuthorship W3209439384A5011170222 @default.
- W3209439384 hasAuthorship W3209439384A5020434567 @default.
- W3209439384 hasAuthorship W3209439384A5026662287 @default.
- W3209439384 hasAuthorship W3209439384A5028265471 @default.
- W3209439384 hasAuthorship W3209439384A5030849116 @default.
- W3209439384 hasAuthorship W3209439384A5073216396 @default.
- W3209439384 hasAuthorship W3209439384A5077698496 @default.
- W3209439384 hasBestOaLocation W32094393841 @default.
- W3209439384 hasConcept C115961682 @default.
- W3209439384 hasConcept C141898687 @default.
- W3209439384 hasConcept C147037132 @default.
- W3209439384 hasConcept C153180895 @default.
- W3209439384 hasConcept C154945302 @default.
- W3209439384 hasConcept C31972630 @default.
- W3209439384 hasConcept C41008148 @default.
- W3209439384 hasConcept C81363708 @default.
- W3209439384 hasConcept C89600930 @default.
- W3209439384 hasConceptScore W3209439384C115961682 @default.
- W3209439384 hasConceptScore W3209439384C141898687 @default.
- W3209439384 hasConceptScore W3209439384C147037132 @default.
- W3209439384 hasConceptScore W3209439384C153180895 @default.
- W3209439384 hasConceptScore W3209439384C154945302 @default.
- W3209439384 hasConceptScore W3209439384C31972630 @default.
- W3209439384 hasConceptScore W3209439384C41008148 @default.
- W3209439384 hasConceptScore W3209439384C81363708 @default.
- W3209439384 hasConceptScore W3209439384C89600930 @default.
- W3209439384 hasLocation W32094393841 @default.
- W3209439384 hasLocation W32094393842 @default.