FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2981036610> ?p ?o ?g. }

• W2981036610 endingPage "156977" @default.
• W2981036610 startingPage "156966" @default.
• W2981036610 abstract "Convolutional Neural Networks (CNNs) achieve excellent computer-assisted diagnosis with sufficient annotated training data. However, most medical imaging datasets are small and fragmented. In this context, Generative Adversarial Networks (GANs) can synthesize realistic/diverse additional training images to fill the data lack in the real image distribution; researchers have improved classification by augmenting data with noise-to-image (e.g., random noise samples to diverse pathological images) or image-to-image GANs (e.g., a benign image to a malignant one). Yet, no research has reported results combining noise-to-image and image-to-image GANs for further performance boost. Therefore, to maximize the DA effect with the GAN combinations, we propose a two-step GAN-based DA that generates and refines brain Magnetic Resonance (MR) images with/without tumors separately: (i) Progressive Growing of GANs (PGGANs), multi-stage noise-to-image GAN for high-resolution MR image generation, first generates realistic/diverse 256×256 images; (ii) Multimodal UNsupervised Image-to-image Translation (MUNIT) that combines GANs/Variational AutoEncoders or SimGAN that uses a DA-focused GAN loss, further refines the texture/shape of the PGGAN-generated images similarly to the real ones. We thoroughly investigate CNN-based tumor classification results, also considering the influence of pre-training on ImageNet and discarding weird-looking GAN-generated images. The results show that, when combined with classic DA, our two-step GAN-based DA can significantly outperform the classic DA alone, in tumor detection (i.e., boosting sensitivity 93.67% to 97.48%) and also in other medical imaging tasks." @default.
• W2981036610 created "2019-10-25" @default.
• W2981036610 creator A5018884738 @default.
• W2981036610 creator A5025644766 @default.
• W2981036610 creator A5050229964 @default.
• W2981036610 creator A5056963377 @default.
• W2981036610 creator A5062787398 @default.
• W2981036610 creator A5072874208 @default.
• W2981036610 creator A5073163964 @default.
• W2981036610 creator A5081459146 @default.
• W2981036610 date "2019-01-01" @default.
• W2981036610 modified "2023-10-18" @default.
• W2981036610 title "Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection" @default.
• W2981036610 cites W114517082 @default.
• W2981036610 cites W1641498739 @default.
• W2981036610 cites W1884191083 @default.
• W2981036610 cites W2084413241 @default.
• W2981036610 cites W2117539524 @default.
• W2981036610 cites W2194775991 @default.
• W2981036610 cites W2250322026 @default.
• W2981036610 cites W2572730214 @default.
• W2981036610 cites W2593414223 @default.
• W2981036610 cites W2603777577 @default.
• W2981036610 cites W2770261599 @default.
• W2981036610 cites W2777186991 @default.
• W2981036610 cites W2794022343 @default.
• W2981036610 cites W2806118840 @default.
• W2981036610 cites W2884065486 @default.
• W2981036610 cites W2884547199 @default.
• W2981036610 cites W2889890092 @default.
• W2981036610 cites W2890139949 @default.
• W2981036610 cites W2892053105 @default.
• W2981036610 cites W2893813411 @default.
• W2981036610 cites W2906598409 @default.
• W2981036610 cites W2962793481 @default.
• W2981036610 cites W2962914239 @default.
• W2981036610 cites W2963120721 @default.
• W2981036610 cites W2963709863 @default.
• W2981036610 cites W2963966654 @default.
• W2981036610 cites W2964261464 @default.
• W2981036610 cites W2964334073 @default.
• W2981036610 cites W4288086194 @default.
• W2981036610 doi "https://doi.org/10.1109/access.2019.2947606" @default.
• W2981036610 hasPublicationYear "2019" @default.
• W2981036610 type Work @default.
• W2981036610 sameAs 2981036610 @default.
• W2981036610 citedByCount "133" @default.
• W2981036610 countsByYear W29810366102019 @default.
• W2981036610 countsByYear W29810366102020 @default.
• W2981036610 countsByYear W29810366102021 @default.
• W2981036610 countsByYear W29810366102022 @default.
• W2981036610 countsByYear W29810366102023 @default.
• W2981036610 crossrefType "journal-article" @default.
• W2981036610 hasAuthorship W2981036610A5018884738 @default.
• W2981036610 hasAuthorship W2981036610A5025644766 @default.
• W2981036610 hasAuthorship W2981036610A5050229964 @default.
• W2981036610 hasAuthorship W2981036610A5056963377 @default.
• W2981036610 hasAuthorship W2981036610A5062787398 @default.
• W2981036610 hasAuthorship W2981036610A5072874208 @default.
• W2981036610 hasAuthorship W2981036610A5073163964 @default.
• W2981036610 hasAuthorship W2981036610A5081459146 @default.
• W2981036610 hasBestOaLocation W29810366101 @default.
• W2981036610 hasConcept C115961682 @default.
• W2981036610 hasConcept C151730666 @default.
• W2981036610 hasConcept C153180895 @default.
• W2981036610 hasConcept C154945302 @default.
• W2981036610 hasConcept C2779343474 @default.
• W2981036610 hasConcept C2779757391 @default.
• W2981036610 hasConcept C31972630 @default.
• W2981036610 hasConcept C35772409 @default.
• W2981036610 hasConcept C41008148 @default.
• W2981036610 hasConcept C46686674 @default.
• W2981036610 hasConcept C63099799 @default.
• W2981036610 hasConcept C75294576 @default.
• W2981036610 hasConcept C81363708 @default.
• W2981036610 hasConcept C86803240 @default.
• W2981036610 hasConcept C9417928 @default.
• W2981036610 hasConcept C99498987 @default.
• W2981036610 hasConceptScore W2981036610C115961682 @default.
• W2981036610 hasConceptScore W2981036610C151730666 @default.
• W2981036610 hasConceptScore W2981036610C153180895 @default.
• W2981036610 hasConceptScore W2981036610C154945302 @default.
• W2981036610 hasConceptScore W2981036610C2779343474 @default.
• W2981036610 hasConceptScore W2981036610C2779757391 @default.
• W2981036610 hasConceptScore W2981036610C31972630 @default.
• W2981036610 hasConceptScore W2981036610C35772409 @default.
• W2981036610 hasConceptScore W2981036610C41008148 @default.
• W2981036610 hasConceptScore W2981036610C46686674 @default.
• W2981036610 hasConceptScore W2981036610C63099799 @default.
• W2981036610 hasConceptScore W2981036610C75294576 @default.
• W2981036610 hasConceptScore W2981036610C81363708 @default.
• W2981036610 hasConceptScore W2981036610C86803240 @default.
• W2981036610 hasConceptScore W2981036610C9417928 @default.
• W2981036610 hasConceptScore W2981036610C99498987 @default.
• W2981036610 hasFunder F4320311405 @default.
• W2981036610 hasFunder F4320334764 @default.
• W2981036610 hasLocation W29810366101 @default.
• W2981036610 hasLocation W29810366102 @default.

• next