Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999292493> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2999292493 abstract "Magnetic Resonance Images (MRIs) are extremely used in the medical field to detect and better understand diseases. In order to fasten automatic processing of scans and enhance medical research, this project focuses on automatically segmenting targeted parts of MRIs and generating new MRI datasets from random noise. More specifically, a Deep Neural Network architecture called U-net is used to segment bones and cartilages of Knee MRIs, and several Generative Adversarial Networks (GANs) are compared and tuned to create new realistic and high quality brain MRIs that can be used as training set for more advanced models. Three main architectures are described: Deep Convolution GAN (DCGAN), Super Resolution Residual GAN (SRResGAN) and Progressive GAN (ProGAN), and five loss functions are tested: the Original loss, LSGAN, WGAN, WGAN_GP and DRAGAN. Moreover, a quantitative benchmark is carried out thanks to evaluation measures using Principal Component Analysis. The results show that U-net can achieve state-of-the-art performance in segmenting bones and cartilages in Knee MRIs (Accuracy of more than 99.5%). Moreover, the three GAN architectures can successfully generate realistic brain MRIs even if some models have difficulties to converge. The main insights to stabilize the networks are using one-sided smoothing labels, regularization with gradient penalty in the loss function (like in WGAN_GP or DRAGAN), adding a minibatch similarity layer in the Discriminator and a long training time." @default.
- W2999292493 created "2020-01-23" @default.
- W2999292493 creator A5090916367 @default.
- W2999292493 date "2020-01-10" @default.
- W2999292493 modified "2023-09-27" @default.
- W2999292493 title "Segmentation and Generation of Magnetic Resonance Images by Deep Neural Networks" @default.
- W2999292493 cites W1901129140 @default.
- W2999292493 cites W2038952578 @default.
- W2999292493 cites W2099471712 @default.
- W2999292493 cites W2112796928 @default.
- W2999292493 cites W2121222027 @default.
- W2999292493 cites W2124260444 @default.
- W2999292493 cites W2163605009 @default.
- W2999292493 cites W2194775991 @default.
- W2999292493 cites W2739748921 @default.
- W2999292493 cites W2747543643 @default.
- W2999292493 cites W2775288145 @default.
- W2999292493 cites W2786204509 @default.
- W2999292493 cites W2787223504 @default.
- W2999292493 cites W2904319976 @default.
- W2999292493 cites W2928133111 @default.
- W2999292493 cites W2952978770 @default.
- W2999292493 cites W2962760235 @default.
- W2999292493 cites W2962770929 @default.
- W2999292493 cites W2962835968 @default.
- W2999292493 cites W2962879692 @default.
- W2999292493 cites W2963073614 @default.
- W2999292493 cites W2963470893 @default.
- W2999292493 cites W2963684088 @default.
- W2999292493 cites W2993303538 @default.
- W2999292493 hasPublicationYear "2020" @default.
- W2999292493 type Work @default.
- W2999292493 sameAs 2999292493 @default.
- W2999292493 citedByCount "0" @default.
- W2999292493 crossrefType "posted-content" @default.
- W2999292493 hasAuthorship W2999292493A5090916367 @default.
- W2999292493 hasConcept C108583219 @default.
- W2999292493 hasConcept C153180895 @default.
- W2999292493 hasConcept C154945302 @default.
- W2999292493 hasConcept C185798385 @default.
- W2999292493 hasConcept C205649164 @default.
- W2999292493 hasConcept C2779803651 @default.
- W2999292493 hasConcept C31972630 @default.
- W2999292493 hasConcept C3770464 @default.
- W2999292493 hasConcept C41008148 @default.
- W2999292493 hasConcept C45347329 @default.
- W2999292493 hasConcept C50644808 @default.
- W2999292493 hasConcept C58640448 @default.
- W2999292493 hasConcept C76155785 @default.
- W2999292493 hasConcept C81363708 @default.
- W2999292493 hasConcept C89600930 @default.
- W2999292493 hasConcept C94915269 @default.
- W2999292493 hasConceptScore W2999292493C108583219 @default.
- W2999292493 hasConceptScore W2999292493C153180895 @default.
- W2999292493 hasConceptScore W2999292493C154945302 @default.
- W2999292493 hasConceptScore W2999292493C185798385 @default.
- W2999292493 hasConceptScore W2999292493C205649164 @default.
- W2999292493 hasConceptScore W2999292493C2779803651 @default.
- W2999292493 hasConceptScore W2999292493C31972630 @default.
- W2999292493 hasConceptScore W2999292493C3770464 @default.
- W2999292493 hasConceptScore W2999292493C41008148 @default.
- W2999292493 hasConceptScore W2999292493C45347329 @default.
- W2999292493 hasConceptScore W2999292493C50644808 @default.
- W2999292493 hasConceptScore W2999292493C58640448 @default.
- W2999292493 hasConceptScore W2999292493C76155785 @default.
- W2999292493 hasConceptScore W2999292493C81363708 @default.
- W2999292493 hasConceptScore W2999292493C89600930 @default.
- W2999292493 hasConceptScore W2999292493C94915269 @default.
- W2999292493 hasLocation W29992924931 @default.
- W2999292493 hasOpenAccess W2999292493 @default.
- W2999292493 hasPrimaryLocation W29992924931 @default.
- W2999292493 hasRelatedWork W2524644797 @default.
- W2999292493 hasRelatedWork W2729876886 @default.
- W2999292493 hasRelatedWork W2737861363 @default.
- W2999292493 hasRelatedWork W2753963274 @default.
- W2999292493 hasRelatedWork W2762531514 @default.
- W2999292493 hasRelatedWork W2788509011 @default.
- W2999292493 hasRelatedWork W2795209768 @default.
- W2999292493 hasRelatedWork W2897914647 @default.
- W2999292493 hasRelatedWork W2899113323 @default.
- W2999292493 hasRelatedWork W2904322775 @default.
- W2999292493 hasRelatedWork W2928045706 @default.
- W2999292493 hasRelatedWork W2945275406 @default.
- W2999292493 hasRelatedWork W2949286170 @default.
- W2999292493 hasRelatedWork W2951830443 @default.
- W2999292493 hasRelatedWork W2993184403 @default.
- W2999292493 hasRelatedWork W3008264294 @default.
- W2999292493 hasRelatedWork W3013085919 @default.
- W2999292493 hasRelatedWork W3092093474 @default.
- W2999292493 hasRelatedWork W3097855346 @default.
- W2999292493 hasRelatedWork W3195952673 @default.
- W2999292493 isParatext "false" @default.
- W2999292493 isRetracted "false" @default.
- W2999292493 magId "2999292493" @default.
- W2999292493 workType "article" @default.