FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002401> ?p ?o ?g. }

• W4386002401 endingPage "107768" @default.
• W4386002401 startingPage "107768" @default.
• W4386002401 abstract "Unsupervised domain adaptation (UDA) is a powerful approach in tackling domain discrepancies and reducing the burden of laborious and error-prone pixel-level annotations for instance segmentation. However, the domain adaptation strategies utilized in previous instance segmentation models pool all the labeled/detected instances together to train the instance-level GAN discriminator, which neglects the differences among multiple instance categories. Such pooling prevents UDA instance segmentation models from learning categorical correspondence between source and target domains for accurate instance classification; To tackle this challenge, we propose an Instance Segmentation CycleGAN (ISC-GAN) algorithm for UDA multiclass-instance segmentation. We conduct extensive experiments on the multiclass nuclei recognition task to transfer knowledge from hematoxylin and eosin to immunohistochemistry stained pathology images. Specifically, we fuse CycleGAN with Mask R-CNN to learn categorical correspondence with image-level domain adaptation and virtual supervision. Moreover, we utilize Curriculum Learning to separate the learning process into two steps: 1) learning segmentation only on labeled source data, and 2) learning target domain segmentation with paired virtual labels generated by ISC-GAN. The performance was further improved through experiments with other strategies, including Shared Weights, Knowledge Distillation, and Expanded Source Data. Comparing to the baseline model or the three UDA instance detection and segmentation models, ISC-GAN illustrates the state-of-the-art performance, with 39.1% average precision and 49.4% average recall. The source codes of ISC-GAN are available at https://github.com/sdw95927/InstanceSegmentation-CycleGAN. ISC-GAN adapted knowledge from hematoxylin and eosin to immunohistochemistry stained pathology images, suggesting the potential for reducing the need for large annotated pathological image datasets in deep learning and computer vision tasks." @default.
• W4386002401 created "2023-08-20" @default.
• W4386002401 creator A5002454159 @default.
• W4386002401 creator A5009964025 @default.
• W4386002401 creator A5029148706 @default.
• W4386002401 creator A5030693092 @default.
• W4386002401 creator A5052709439 @default.
• W4386002401 creator A5068615078 @default.
• W4386002401 creator A5082372978 @default.
• W4386002401 date "2023-11-01" @default.
• W4386002401 modified "2023-10-17" @default.
• W4386002401 title "Unsupervised domain adaptation for nuclei segmentation: Adapting from hematoxylin & eosin stained slides to immunohistochemistry stained slides using a curriculum approach" @default.
• W4386002401 cites W2041280778 @default.
• W4386002401 cites W2133059825 @default.
• W4386002401 cites W2556232360 @default.
• W4386002401 cites W2786808285 @default.
• W4386002401 cites W2952846726 @default.
• W4386002401 cites W2964152246 @default.
• W4386002401 cites W2981841914 @default.
• W4386002401 cites W2998794254 @default.
• W4386002401 cites W3085410595 @default.
• W4386002401 cites W3111140902 @default.
• W4386002401 cites W4213328656 @default.
• W4386002401 cites W4223503656 @default.
• W4386002401 cites W4361285006 @default.
• W4386002401 doi "https://doi.org/10.1016/j.cmpb.2023.107768" @default.
• W4386002401 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37619429" @default.
• W4386002401 hasPublicationYear "2023" @default.
• W4386002401 type Work @default.
• W4386002401 citedByCount "0" @default.
• W4386002401 crossrefType "journal-article" @default.
• W4386002401 hasAuthorship W4386002401A5002454159 @default.
• W4386002401 hasAuthorship W4386002401A5009964025 @default.
• W4386002401 hasAuthorship W4386002401A5029148706 @default.
• W4386002401 hasAuthorship W4386002401A5030693092 @default.
• W4386002401 hasAuthorship W4386002401A5052709439 @default.
• W4386002401 hasAuthorship W4386002401A5068615078 @default.
• W4386002401 hasAuthorship W4386002401A5082372978 @default.
• W4386002401 hasConcept C134306372 @default.
• W4386002401 hasConcept C153180895 @default.
• W4386002401 hasConcept C154945302 @default.
• W4386002401 hasConcept C33923547 @default.
• W4386002401 hasConcept C36503486 @default.
• W4386002401 hasConcept C41008148 @default.
• W4386002401 hasConcept C89600930 @default.
• W4386002401 hasConceptScore W4386002401C134306372 @default.
• W4386002401 hasConceptScore W4386002401C153180895 @default.
• W4386002401 hasConceptScore W4386002401C154945302 @default.
• W4386002401 hasConceptScore W4386002401C33923547 @default.
• W4386002401 hasConceptScore W4386002401C36503486 @default.
• W4386002401 hasConceptScore W4386002401C41008148 @default.
• W4386002401 hasConceptScore W4386002401C89600930 @default.
• W4386002401 hasFunder F4320308129 @default.
• W4386002401 hasFunder F4320332161 @default.
• W4386002401 hasLocation W43860024011 @default.
• W4386002401 hasLocation W43860024012 @default.
• W4386002401 hasOpenAccess W4386002401 @default.
• W4386002401 hasPrimaryLocation W43860024011 @default.
• W4386002401 hasRelatedWork W2033914206 @default.
• W4386002401 hasRelatedWork W2042327336 @default.
• W4386002401 hasRelatedWork W2350741829 @default.
• W4386002401 hasRelatedWork W2358668433 @default.
• W4386002401 hasRelatedWork W2376932109 @default.
• W4386002401 hasRelatedWork W2382290278 @default.
• W4386002401 hasRelatedWork W2390279801 @default.
• W4386002401 hasRelatedWork W2748952813 @default.
• W4386002401 hasRelatedWork W2899084033 @default.
• W4386002401 hasRelatedWork W4221146251 @default.
• W4386002401 hasVolume "241" @default.
• W4386002401 isParatext "false" @default.
• W4386002401 isRetracted "false" @default.
• W4386002401 workType "article" @default.