FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3047552090> ?p ?o ?g. }

• W3047552090 abstract "Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by separating training and inference. During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image. The hierarchical design has two advantages: First, the memory demand for training on high-resolution images is amortized among subvolumes. Furthermore, anchoring the high-resolution subvolumes to a single low-resolution image ensures anatomical consistency between subvolumes. During inference, our model can directly generate full high-resolution images. We also incorporate an encoder with a similar hierarchical structure into the model to extract features from the images. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation. We also demonstrate clinical applications of the proposed model in data augmentation, image super-resolution and clinical-relevant feature extraction." @default.
• W3047552090 created "2020-08-10" @default.
• W3047552090 creator A5010906829 @default.
• W3047552090 creator A5031717623 @default.
• W3047552090 creator A5068979281 @default.
• W3047552090 creator A5082794781 @default.
• W3047552090 creator A5091082342 @default.
• W3047552090 creator A5091227928 @default.
• W3047552090 date "2020-08-05" @default.
• W3047552090 modified "2023-09-26" @default.
• W3047552090 title "Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN." @default.
• W3047552090 cites W1458229720 @default.
• W3047552090 cites W1901129140 @default.
• W3047552090 cites W1959608418 @default.
• W3047552090 cites W2065984169 @default.
• W3047552090 cites W2082907106 @default.
• W3047552090 cites W2099471712 @default.
• W3047552090 cites W2120851096 @default.
• W3047552090 cites W2163922914 @default.
• W3047552090 cites W2202109488 @default.
• W3047552090 cites W2212660284 @default.
• W3047552090 cites W2412320034 @default.
• W3047552090 cites W2548275288 @default.
• W3047552090 cites W2623975327 @default.
• W3047552090 cites W2624918875 @default.
• W3047552090 cites W2741685120 @default.
• W3047552090 cites W2745006834 @default.
• W3047552090 cites W2753738274 @default.
• W3047552090 cites W2786129249 @default.
• W3047552090 cites W2789318600 @default.
• W3047552090 cites W2791621240 @default.
• W3047552090 cites W2794022343 @default.
• W3047552090 cites W2805715722 @default.
• W3047552090 cites W2807246925 @default.
• W3047552090 cites W2809703834 @default.
• W3047552090 cites W2810645613 @default.
• W3047552090 cites W2884065486 @default.
• W3047552090 cites W2889871190 @default.
• W3047552090 cites W2893749619 @default.
• W3047552090 cites W2907274850 @default.
• W3047552090 cites W2922482433 @default.
• W3047552090 cites W2929753309 @default.
• W3047552090 cites W2949399848 @default.
• W3047552090 cites W2962760235 @default.
• W3047552090 cites W2962793481 @default.
• W3047552090 cites W2962879692 @default.
• W3047552090 cites W2963226019 @default.
• W3047552090 cites W2963373786 @default.
• W3047552090 cites W2963942586 @default.
• W3047552090 cites W2963981733 @default.
• W3047552090 cites W2964127395 @default.
• W3047552090 cites W2964261464 @default.
• W3047552090 cites W2969515180 @default.
• W3047552090 cites W2979297660 @default.
• W3047552090 cites W2979808915 @default.
• W3047552090 cites W2981479880 @default.
• W3047552090 cites W2982316158 @default.
• W3047552090 cites W2982412091 @default.
• W3047552090 cites W2985060393 @default.
• W3047552090 cites W2990807394 @default.
• W3047552090 cites W2994850125 @default.
• W3047552090 cites W2996200424 @default.
• W3047552090 cites W3010798784 @default.
• W3047552090 cites W3013749033 @default.
• W3047552090 cites W3033878890 @default.
• W3047552090 cites W3034697933 @default.
• W3047552090 cites W3103261259 @default.
• W3047552090 cites W3105747145 @default.
• W3047552090 hasPublicationYear "2020" @default.
• W3047552090 type Work @default.
• W3047552090 sameAs 3047552090 @default.
• W3047552090 citedByCount "0" @default.
• W3047552090 crossrefType "posted-content" @default.
• W3047552090 hasAuthorship W3047552090A5010906829 @default.
• W3047552090 hasAuthorship W3047552090A5031717623 @default.
• W3047552090 hasAuthorship W3047552090A5068979281 @default.
• W3047552090 hasAuthorship W3047552090A5082794781 @default.
• W3047552090 hasAuthorship W3047552090A5091082342 @default.
• W3047552090 hasAuthorship W3047552090A5091227928 @default.
• W3047552090 hasConcept C111919701 @default.
• W3047552090 hasConcept C118505674 @default.
• W3047552090 hasConcept C138885662 @default.
• W3047552090 hasConcept C153180895 @default.
• W3047552090 hasConcept C154945302 @default.
• W3047552090 hasConcept C205372480 @default.
• W3047552090 hasConcept C2776214188 @default.
• W3047552090 hasConcept C2776401178 @default.
• W3047552090 hasConcept C2776436953 @default.
• W3047552090 hasConcept C31972630 @default.
• W3047552090 hasConcept C41008148 @default.
• W3047552090 hasConcept C41895202 @default.
• W3047552090 hasConceptScore W3047552090C111919701 @default.
• W3047552090 hasConceptScore W3047552090C118505674 @default.
• W3047552090 hasConceptScore W3047552090C138885662 @default.
• W3047552090 hasConceptScore W3047552090C153180895 @default.
• W3047552090 hasConceptScore W3047552090C154945302 @default.
• W3047552090 hasConceptScore W3047552090C205372480 @default.
• W3047552090 hasConceptScore W3047552090C2776214188 @default.
• W3047552090 hasConceptScore W3047552090C2776401178 @default.
• W3047552090 hasConceptScore W3047552090C2776436953 @default.

• next