FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165289342> ?p ?o ?g. }

• W3165289342 endingPage "106197" @default.
• W3165289342 startingPage "106197" @default.
• W3165289342 abstract "• The computational cost is reduced compared with classical “coarse-fine” registration stage by adopting the resampling algorithm in the coarse registration stage. • A patch embedding segmentation approach based on conditional random field (CRF) model potentially improves the segmentation performance of the hippocampus. • Furthermore, considering the label map rich in prior information is not fully used, the segmentation results are refined based on SPBM method. • Compared with state-of-the-art methods, our proposed method can obtain more accurate hippocampus segmentation results. Accurate and automatic segmentation of the hippocampus plays a vital role in the diagnosis and treatment of nervous system diseases. However, due to the anatomical variability of different subjects, the registered atlas images are not always perfectly aligned with the target image. This makes the segmentation of the hippocampus still face great challenges. In this paper, we propose a robust discriminative label fusion method under the multi-atlas framework. It is a patch embedding label fusion method based on conditional random field (CRF) model that integrates the metric learning and the graph cuts by an integrated formulation. Unlike most current label fusion methods with fixed (non-learning) distance metrics, a novel distance metric learning is presented to enhance discriminative observation and embed it into the unary potential function. In particular, Bayesian inference is utilized to extend a classic distance metric learning, in which large margin constraints are instead of pairwise constraints to obtain a more robust distance metric. And the pairwise homogeneity is fully considered in the spatial prior term based on classification labels and voxel intensity. The resulting integrated formulation is globally minimized by the efficient graph cuts algorithm. Further, sparse patch based method is utilized to polish the obtained segmentation results in label space. The proposed method is evaluated on IABA dataset and ADNI dataset for hippocampus segmentation. The Dice scores achieved by our method are 87.2 % , 87.8 % , 88.2 % and 88.9 % on left and right hippocampus on both two datasets, while the best Dice scores obtained by other methods are 86.0 % , 86.9 % , 86.8 % and 88.0 % on IABA dataset and ADNI dataset respectively. Experiments show that our approach achieves higher accuracy than state-of-the-art methods. We hope the proposed model can be transferred to combine with other promising distance measurement algorithms." @default.
• W3165289342 created "2021-06-07" @default.
• W3165289342 creator A5010081691 @default.
• W3165289342 creator A5023851282 @default.
• W3165289342 creator A5028235866 @default.
• W3165289342 creator A5035534911 @default.
• W3165289342 creator A5040327019 @default.
• W3165289342 creator A5073292890 @default.
• W3165289342 date "2021-09-01" @default.
• W3165289342 modified "2023-10-16" @default.
• W3165289342 title "A robust discriminative multi-atlas label fusion method for hippocampus segmentation from MR image" @default.
• W3165289342 cites W2010587020 @default.
• W3165289342 cites W2014105136 @default.
• W3165289342 cites W2018662705 @default.
• W3165289342 cites W2032377318 @default.
• W3165289342 cites W2047896044 @default.
• W3165289342 cites W2078524519 @default.
• W3165289342 cites W2103857226 @default.
• W3165289342 cites W2114740909 @default.
• W3165289342 cites W2119300483 @default.
• W3165289342 cites W2129812935 @default.
• W3165289342 cites W2143973889 @default.
• W3165289342 cites W2148157540 @default.
• W3165289342 cites W2148347694 @default.
• W3165289342 cites W2413700323 @default.
• W3165289342 cites W2520010025 @default.
• W3165289342 cites W2555500380 @default.
• W3165289342 cites W2583043129 @default.
• W3165289342 cites W2611552378 @default.
• W3165289342 cites W2762363380 @default.
• W3165289342 cites W2771234593 @default.
• W3165289342 cites W2811631974 @default.
• W3165289342 cites W2888098356 @default.
• W3165289342 cites W2899478482 @default.
• W3165289342 cites W2904419476 @default.
• W3165289342 cites W2914973951 @default.
• W3165289342 cites W2919080049 @default.
• W3165289342 cites W2922050091 @default.
• W3165289342 cites W2944879639 @default.
• W3165289342 cites W2956959608 @default.
• W3165289342 cites W2960986212 @default.
• W3165289342 cites W2975244163 @default.
• W3165289342 cites W2983426645 @default.
• W3165289342 cites W2983483640 @default.
• W3165289342 doi "https://doi.org/10.1016/j.cmpb.2021.106197" @default.
• W3165289342 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34102562" @default.
• W3165289342 hasPublicationYear "2021" @default.
• W3165289342 type Work @default.
• W3165289342 sameAs 3165289342 @default.
• W3165289342 citedByCount "2" @default.
• W3165289342 countsByYear W31652893422022 @default.
• W3165289342 countsByYear W31652893422023 @default.
• W3165289342 crossrefType "journal-article" @default.
• W3165289342 hasAuthorship W3165289342A5010081691 @default.
• W3165289342 hasAuthorship W3165289342A5023851282 @default.
• W3165289342 hasAuthorship W3165289342A5028235866 @default.
• W3165289342 hasAuthorship W3165289342A5035534911 @default.
• W3165289342 hasAuthorship W3165289342A5040327019 @default.
• W3165289342 hasAuthorship W3165289342A5073292890 @default.
• W3165289342 hasConcept C105702510 @default.
• W3165289342 hasConcept C138885662 @default.
• W3165289342 hasConcept C153180895 @default.
• W3165289342 hasConcept C154945302 @default.
• W3165289342 hasConcept C158525013 @default.
• W3165289342 hasConcept C2776673561 @default.
• W3165289342 hasConcept C31972630 @default.
• W3165289342 hasConcept C41008148 @default.
• W3165289342 hasConcept C41895202 @default.
• W3165289342 hasConcept C71924100 @default.
• W3165289342 hasConcept C89600930 @default.
• W3165289342 hasConcept C97931131 @default.
• W3165289342 hasConceptScore W3165289342C105702510 @default.
• W3165289342 hasConceptScore W3165289342C138885662 @default.
• W3165289342 hasConceptScore W3165289342C153180895 @default.
• W3165289342 hasConceptScore W3165289342C154945302 @default.
• W3165289342 hasConceptScore W3165289342C158525013 @default.
• W3165289342 hasConceptScore W3165289342C2776673561 @default.
• W3165289342 hasConceptScore W3165289342C31972630 @default.
• W3165289342 hasConceptScore W3165289342C41008148 @default.
• W3165289342 hasConceptScore W3165289342C41895202 @default.
• W3165289342 hasConceptScore W3165289342C71924100 @default.
• W3165289342 hasConceptScore W3165289342C89600930 @default.
• W3165289342 hasConceptScore W3165289342C97931131 @default.
• W3165289342 hasFunder F4320321001 @default.
• W3165289342 hasFunder F4320321392 @default.
• W3165289342 hasFunder F4320324173 @default.
• W3165289342 hasLocation W31652893421 @default.
• W3165289342 hasOpenAccess W3165289342 @default.
• W3165289342 hasPrimaryLocation W31652893421 @default.
• W3165289342 hasRelatedWork W1669643531 @default.
• W3165289342 hasRelatedWork W2005437358 @default.
• W3165289342 hasRelatedWork W2024160000 @default.
• W3165289342 hasRelatedWork W2061273563 @default.
• W3165289342 hasRelatedWork W2285052147 @default.
• W3165289342 hasRelatedWork W2517104666 @default.
• W3165289342 hasRelatedWork W2729514902 @default.
• W3165289342 hasRelatedWork W2773500201 @default.
• W3165289342 hasRelatedWork W4287995534 @default.

• next