FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950883963> ?p ?o ?g. }

• W2950883963 abstract "Deep learning approaches have shown promising performance for compressed sensing-based Magnetic Resonance Imaging. While deep neural networks trained with mean squared error (MSE) loss functions can achieve high peak signal to noise ratio, the reconstructed images are often blurry and lack sharp details, especially for higher undersampling rates. Recently, adversarial and perceptual loss functions have been shown to achieve more visually appealing results. However, it remains an open question how to (1) optimally combine these loss functions with the MSE loss function and (2) evaluate such a perceptual enhancement. In this work, we propose a hybrid method, in which a visual refinement component is learnt on top of an MSE loss-based reconstruction network. In addition, we introduce a semantic interpretability score, measuring the visibility of the region of interest in both ground truth and reconstructed images, which allows us to objectively quantify the usefulness of the image quality for image post-processing and analysis. Applied on a large cardiac MRI dataset simulated with 8-fold undersampling, we demonstrate significant improvements ($p<0.01$) over the state-of-the-art in both a human observer study and the semantic interpretability score." @default.
• W2950883963 created "2019-06-27" @default.
• W2950883963 creator A5006461848 @default.
• W2950883963 creator A5018511955 @default.
• W2950883963 creator A5030367033 @default.
• W2950883963 creator A5032499810 @default.
• W2950883963 creator A5037038047 @default.
• W2950883963 creator A5038400548 @default.
• W2950883963 creator A5039512035 @default.
• W2950883963 creator A5047234552 @default.
• W2950883963 creator A5052451660 @default.
• W2950883963 creator A5062702770 @default.
• W2950883963 creator A5073429636 @default.
• W2950883963 creator A5087093169 @default.
• W2950883963 date "2018-06-28" @default.
• W2950883963 modified "2023-09-27" @default.
• W2950883963 title "Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction" @default.
• W2950883963 cites W1901129140 @default.
• W2950883963 cites W2099471712 @default.
• W2950883963 cites W2168668658 @default.
• W2950883963 cites W2331128040 @default.
• W2950883963 cites W2432004435 @default.
• W2950883963 cites W2527819024 @default.
• W2950883963 cites W2552808051 @default.
• W2950883963 cites W2594014149 @default.
• W2950883963 cites W2631883531 @default.
• W2950883963 cites W2778924750 @default.
• W2950883963 cites W2962835968 @default.
• W2950883963 cites W2963073614 @default.
• W2950883963 cites W2963174698 @default.
• W2950883963 cites W2963186101 @default.
• W2950883963 cites W2963470893 @default.
• W2950883963 cites W2963504252 @default.
• W2950883963 cites W2964121744 @default.
• W2950883963 hasPublicationYear "2018" @default.
• W2950883963 type Work @default.
• W2950883963 sameAs 2950883963 @default.
• W2950883963 citedByCount "0" @default.
• W2950883963 crossrefType "posted-content" @default.
• W2950883963 hasAuthorship W2950883963A5006461848 @default.
• W2950883963 hasAuthorship W2950883963A5018511955 @default.
• W2950883963 hasAuthorship W2950883963A5030367033 @default.
• W2950883963 hasAuthorship W2950883963A5032499810 @default.
• W2950883963 hasAuthorship W2950883963A5037038047 @default.
• W2950883963 hasAuthorship W2950883963A5038400548 @default.
• W2950883963 hasAuthorship W2950883963A5039512035 @default.
• W2950883963 hasAuthorship W2950883963A5047234552 @default.
• W2950883963 hasAuthorship W2950883963A5052451660 @default.
• W2950883963 hasAuthorship W2950883963A5062702770 @default.
• W2950883963 hasAuthorship W2950883963A5073429636 @default.
• W2950883963 hasAuthorship W2950883963A5087093169 @default.
• W2950883963 hasConcept C105795698 @default.
• W2950883963 hasConcept C108583219 @default.
• W2950883963 hasConcept C124851039 @default.
• W2950883963 hasConcept C136536468 @default.
• W2950883963 hasConcept C139945424 @default.
• W2950883963 hasConcept C141379421 @default.
• W2950883963 hasConcept C146849305 @default.
• W2950883963 hasConcept C153180895 @default.
• W2950883963 hasConcept C154945302 @default.
• W2950883963 hasConcept C2781067378 @default.
• W2950883963 hasConcept C31972630 @default.
• W2950883963 hasConcept C33923547 @default.
• W2950883963 hasConcept C41008148 @default.
• W2950883963 hasConcept C50644808 @default.
• W2950883963 hasConceptScore W2950883963C105795698 @default.
• W2950883963 hasConceptScore W2950883963C108583219 @default.
• W2950883963 hasConceptScore W2950883963C124851039 @default.
• W2950883963 hasConceptScore W2950883963C136536468 @default.
• W2950883963 hasConceptScore W2950883963C139945424 @default.
• W2950883963 hasConceptScore W2950883963C141379421 @default.
• W2950883963 hasConceptScore W2950883963C146849305 @default.
• W2950883963 hasConceptScore W2950883963C153180895 @default.
• W2950883963 hasConceptScore W2950883963C154945302 @default.
• W2950883963 hasConceptScore W2950883963C2781067378 @default.
• W2950883963 hasConceptScore W2950883963C31972630 @default.
• W2950883963 hasConceptScore W2950883963C33923547 @default.
• W2950883963 hasConceptScore W2950883963C41008148 @default.
• W2950883963 hasConceptScore W2950883963C50644808 @default.
• W2950883963 hasLocation W29508839631 @default.
• W2950883963 hasOpenAccess W2950883963 @default.
• W2950883963 hasPrimaryLocation W29508839631 @default.
• W2950883963 hasRelatedWork W2580080206 @default.
• W2950883963 hasRelatedWork W2806009642 @default.
• W2950883963 hasRelatedWork W2809834193 @default.
• W2950883963 hasRelatedWork W2890459603 @default.
• W2950883963 hasRelatedWork W2905530235 @default.
• W2950883963 hasRelatedWork W2942729634 @default.
• W2950883963 hasRelatedWork W2951359900 @default.
• W2950883963 hasRelatedWork W2963713691 @default.
• W2950883963 hasRelatedWork W2963737915 @default.
• W2950883963 hasRelatedWork W2974811010 @default.
• W2950883963 hasRelatedWork W3035335920 @default.
• W2950883963 hasRelatedWork W3036889868 @default.
• W2950883963 hasRelatedWork W3043012353 @default.
• W2950883963 hasRelatedWork W3113205501 @default.
• W2950883963 hasRelatedWork W3130500085 @default.
• W2950883963 hasRelatedWork W3134850653 @default.
• W2950883963 hasRelatedWork W3144612861 @default.
• W2950883963 hasRelatedWork W3172468630 @default.

• next