FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380894241> ?p ?o ?g. }

• W4380894241 endingPage "102873" @default.
• W4380894241 startingPage "102873" @default.
• W4380894241 abstract "Abdominal multi-organ segmentation in multi-sequence magnetic resonance images (MRI) is of great significance in many clinical scenarios, e.g., MRI-oriented pre-operative treatment planning. Labeling multiple organs on a single MR sequence is a time-consuming and labor-intensive task, let alone manual labeling on multiple MR sequences. Training a model by one sequence and generalizing it to other domains is one way to reduce the burden of manual annotation, but the existence of domain gap often leads to poor generalization performance of such methods. Image translation-based unsupervised domain adaptation (UDA) is a common way to address this domain gap issue. However, existing methods focus less on keeping anatomical consistency and are limited by one-to-one domain adaptation, leading to low efficiency for adapting a model to multiple target domains. This work proposes a unified framework called OMUDA for one-to-multiple unsupervised domain-adaptive segmentation, where disentanglement between content and style is used to efficiently translate a source domain image into multiple target domains. Moreover, generator refactoring and style constraint are conducted in OMUDA for better maintaining cross-modality structural consistency and reducing domain aliasing. The average Dice Similarity Coefficients (DSCs) of OMUDA for multiple sequences and organs on the in-house test set, the AMOS22 dataset and the CHAOS dataset are 85.51%, 82.66% and 91.38%, respectively, which are slightly lower than those of CycleGAN(85.66% and 83.40%) in the first two data sets and slightly higher than CycleGAN(91.36%) in the last dataset. But compared with CycleGAN, OMUDA reduces floating-point calculations by about 87 percent in the training phase and about 30 percent in the inference stage respectively. The quantitative results in both segmentation performance and training efficiency demonstrate the usability of OMUDA in some practical scenes, such as the initial phase of product development." @default.
• W4380894241 created "2023-06-17" @default.
• W4380894241 creator A5000116428 @default.
• W4380894241 creator A5000340215 @default.
• W4380894241 creator A5005517804 @default.
• W4380894241 creator A5029722566 @default.
• W4380894241 creator A5037288936 @default.
• W4380894241 creator A5054191914 @default.
• W4380894241 creator A5066553616 @default.
• W4380894241 creator A5082033856 @default.
• W4380894241 creator A5086347026 @default.
• W4380894241 creator A5089811847 @default.
• W4380894241 date "2023-08-01" @default.
• W4380894241 modified "2023-09-27" @default.
• W4380894241 title "A novel one-to-multiple unsupervised domain adaptation framework for abdominal organ segmentation" @default.
• W4380894241 cites W1983592655 @default.
• W4380894241 cites W2321272510 @default.
• W4380894241 cites W2554204699 @default.
• W4380894241 cites W2601258016 @default.
• W4380894241 cites W2603777577 @default.
• W4380894241 cites W2791680898 @default.
• W4380894241 cites W2952056941 @default.
• W4380894241 cites W2962793481 @default.
• W4380894241 cites W2963198662 @default.
• W4380894241 cites W2963767194 @default.
• W4380894241 cites W2963890275 @default.
• W4380894241 cites W2978111064 @default.
• W4380894241 cites W2981392058 @default.
• W4380894241 cites W3002569343 @default.
• W4380894241 cites W3003384866 @default.
• W4380894241 cites W3006040295 @default.
• W4380894241 cites W3027849539 @default.
• W4380894241 cites W3034600949 @default.
• W4380894241 cites W3125213214 @default.
• W4380894241 cites W3162505601 @default.
• W4380894241 cites W3182200686 @default.
• W4380894241 cites W4298110661 @default.
• W4380894241 doi "https://doi.org/10.1016/j.media.2023.102873" @default.
• W4380894241 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37421932" @default.
• W4380894241 hasPublicationYear "2023" @default.
• W4380894241 type Work @default.
• W4380894241 citedByCount "0" @default.
• W4380894241 crossrefType "journal-article" @default.
• W4380894241 hasAuthorship W4380894241A5000116428 @default.
• W4380894241 hasAuthorship W4380894241A5000340215 @default.
• W4380894241 hasAuthorship W4380894241A5005517804 @default.
• W4380894241 hasAuthorship W4380894241A5029722566 @default.
• W4380894241 hasAuthorship W4380894241A5037288936 @default.
• W4380894241 hasAuthorship W4380894241A5054191914 @default.
• W4380894241 hasAuthorship W4380894241A5066553616 @default.
• W4380894241 hasAuthorship W4380894241A5082033856 @default.
• W4380894241 hasAuthorship W4380894241A5086347026 @default.
• W4380894241 hasAuthorship W4380894241A5089811847 @default.
• W4380894241 hasConcept C103278499 @default.
• W4380894241 hasConcept C115961682 @default.
• W4380894241 hasConcept C134306372 @default.
• W4380894241 hasConcept C153180895 @default.
• W4380894241 hasConcept C154945302 @default.
• W4380894241 hasConcept C2776436953 @default.
• W4380894241 hasConcept C33923547 @default.
• W4380894241 hasConcept C36503486 @default.
• W4380894241 hasConcept C41008148 @default.
• W4380894241 hasConcept C89600930 @default.
• W4380894241 hasConceptScore W4380894241C103278499 @default.
• W4380894241 hasConceptScore W4380894241C115961682 @default.
• W4380894241 hasConceptScore W4380894241C134306372 @default.
• W4380894241 hasConceptScore W4380894241C153180895 @default.
• W4380894241 hasConceptScore W4380894241C154945302 @default.
• W4380894241 hasConceptScore W4380894241C2776436953 @default.
• W4380894241 hasConceptScore W4380894241C33923547 @default.
• W4380894241 hasConceptScore W4380894241C36503486 @default.
• W4380894241 hasConceptScore W4380894241C41008148 @default.
• W4380894241 hasConceptScore W4380894241C89600930 @default.
• W4380894241 hasLocation W43808942411 @default.
• W4380894241 hasLocation W43808942412 @default.
• W4380894241 hasOpenAccess W4380894241 @default.
• W4380894241 hasPrimaryLocation W43808942411 @default.
• W4380894241 hasRelatedWork W2033914206 @default.
• W4380894241 hasRelatedWork W2046077695 @default.
• W4380894241 hasRelatedWork W2061997307 @default.
• W4380894241 hasRelatedWork W2146076056 @default.
• W4380894241 hasRelatedWork W2163831990 @default.
• W4380894241 hasRelatedWork W2353865532 @default.
• W4380894241 hasRelatedWork W2358941527 @default.
• W4380894241 hasRelatedWork W3003836766 @default.
• W4380894241 hasRelatedWork W4213400667 @default.
• W4380894241 hasRelatedWork W4287367810 @default.
• W4380894241 hasVolume "88" @default.
• W4380894241 isParatext "false" @default.
• W4380894241 isRetracted "false" @default.
• W4380894241 workType "article" @default.