Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229014737> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4229014737 endingPage "3975" @default.
- W4229014737 startingPage "3966" @default.
- W4229014737 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 using different configurations between 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 sub-volumes. Furthermore, anchoring the high-resolution sub-volumes to a single low-resolution image ensures anatomical consistency between sub-volumes. 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 and clinical-relevant feature extraction." @default.
- W4229014737 created "2022-05-08" @default.
- W4229014737 creator A5010906829 @default.
- W4229014737 creator A5031717623 @default.
- W4229014737 creator A5068979281 @default.
- W4229014737 creator A5082794781 @default.
- W4229014737 creator A5091082342 @default.
- W4229014737 creator A5091227928 @default.
- W4229014737 date "2022-08-01" @default.
- W4229014737 modified "2023-10-13" @default.
- W4229014737 title "Hierarchical Amortized GAN for 3D High Resolution Medical Image Synthesis" @default.
- W4229014737 cites W1458229720 @default.
- W4229014737 cites W2082907106 @default.
- W4229014737 cites W2120851096 @default.
- W4229014737 cites W2791621240 @default.
- W4229014737 cites W2794022343 @default.
- W4229014737 cites W2807246925 @default.
- W4229014737 cites W2810645613 @default.
- W4229014737 cites W2922482433 @default.
- W4229014737 cites W2962793481 @default.
- W4229014737 cites W2963942586 @default.
- W4229014737 cites W2964261464 @default.
- W4229014737 cites W2979297660 @default.
- W4229014737 cites W2979808915 @default.
- W4229014737 cites W3010798784 @default.
- W4229014737 cites W3103261259 @default.
- W4229014737 cites W3105747145 @default.
- W4229014737 cites W3150587331 @default.
- W4229014737 cites W3210071494 @default.
- W4229014737 cites W4214760846 @default.
- W4229014737 cites W4241074797 @default.
- W4229014737 doi "https://doi.org/10.1109/jbhi.2022.3172976" @default.
- W4229014737 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35522642" @default.
- W4229014737 hasPublicationYear "2022" @default.
- W4229014737 type Work @default.
- W4229014737 citedByCount "17" @default.
- W4229014737 countsByYear W42290147372022 @default.
- W4229014737 countsByYear W42290147372023 @default.
- W4229014737 crossrefType "journal-article" @default.
- W4229014737 hasAuthorship W4229014737A5010906829 @default.
- W4229014737 hasAuthorship W4229014737A5031717623 @default.
- W4229014737 hasAuthorship W4229014737A5068979281 @default.
- W4229014737 hasAuthorship W4229014737A5082794781 @default.
- W4229014737 hasAuthorship W4229014737A5091082342 @default.
- W4229014737 hasAuthorship W4229014737A5091227928 @default.
- W4229014737 hasBestOaLocation W42290147371 @default.
- W4229014737 hasConcept C111919701 @default.
- W4229014737 hasConcept C118505674 @default.
- W4229014737 hasConcept C138885662 @default.
- W4229014737 hasConcept C153180895 @default.
- W4229014737 hasConcept C154945302 @default.
- W4229014737 hasConcept C205372480 @default.
- W4229014737 hasConcept C2776214188 @default.
- W4229014737 hasConcept C2776401178 @default.
- W4229014737 hasConcept C31601959 @default.
- W4229014737 hasConcept C31972630 @default.
- W4229014737 hasConcept C41008148 @default.
- W4229014737 hasConcept C41895202 @default.
- W4229014737 hasConcept C52622490 @default.
- W4229014737 hasConceptScore W4229014737C111919701 @default.
- W4229014737 hasConceptScore W4229014737C118505674 @default.
- W4229014737 hasConceptScore W4229014737C138885662 @default.
- W4229014737 hasConceptScore W4229014737C153180895 @default.
- W4229014737 hasConceptScore W4229014737C154945302 @default.
- W4229014737 hasConceptScore W4229014737C205372480 @default.
- W4229014737 hasConceptScore W4229014737C2776214188 @default.
- W4229014737 hasConceptScore W4229014737C2776401178 @default.
- W4229014737 hasConceptScore W4229014737C31601959 @default.
- W4229014737 hasConceptScore W4229014737C31972630 @default.
- W4229014737 hasConceptScore W4229014737C41008148 @default.
- W4229014737 hasConceptScore W4229014737C41895202 @default.
- W4229014737 hasConceptScore W4229014737C52622490 @default.
- W4229014737 hasFunder F4320308109 @default.
- W4229014737 hasFunder F4320332161 @default.
- W4229014737 hasFunder F4320335353 @default.
- W4229014737 hasIssue "8" @default.
- W4229014737 hasLocation W42290147371 @default.
- W4229014737 hasLocation W42290147372 @default.
- W4229014737 hasLocation W42290147373 @default.
- W4229014737 hasLocation W42290147374 @default.
- W4229014737 hasLocation W42290147375 @default.
- W4229014737 hasOpenAccess W4229014737 @default.
- W4229014737 hasPrimaryLocation W42290147371 @default.
- W4229014737 hasRelatedWork W1504288058 @default.
- W4229014737 hasRelatedWork W2017205855 @default.
- W4229014737 hasRelatedWork W2048505601 @default.
- W4229014737 hasRelatedWork W2146076056 @default.
- W4229014737 hasRelatedWork W2167293474 @default.
- W4229014737 hasRelatedWork W2331674254 @default.
- W4229014737 hasRelatedWork W2546942002 @default.
- W4229014737 hasRelatedWork W2811390910 @default.
- W4229014737 hasRelatedWork W2979079341 @default.
- W4229014737 hasRelatedWork W3042897387 @default.
- W4229014737 hasVolume "26" @default.
- W4229014737 isParatext "false" @default.
- W4229014737 isRetracted "false" @default.
- W4229014737 workType "article" @default.