Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207675193> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3207675193 abstract "Clinical evidence has shown that rib-suppressed chest X-rays (CXRs) can improve the reliability of pulmonary disease diagnosis. However, previous approaches on generating rib-suppressed CXR face challenges in preserving details and eliminating rib residues. We hereby propose a GAN-based disentanglement learning framework called Rib Suppression GAN, or RSGAN, to perform rib suppression by utilizing the anatomical knowledge embedded in unpaired computed tomography (CT) images. In this approach, we employ a residual map to characterize the intensity difference between CXR and the corresponding rib-suppressed result. To predict the residual map in CXR domain, we disentangle the image into structure- and contrast-specific features and transfer the rib structural priors from digitally reconstructed radiographs (DRRs) computed by CT. Furthermore, we employ additional adaptive loss to suppress rib residue and preserve more details. We conduct extensive experiments based on 1,673 CT volumes, and four benchmarking CXR datasets, totaling over 120K images, to demonstrate that (i) our proposed RSGAN achieves superior image quality compared to the state-of-the-art rib suppression methods; (ii) combining CXR with our rib-suppressed result leads to better performance in lung disease classification and tuberculosis area detection." @default.
- W3207675193 created "2021-10-25" @default.
- W3207675193 creator A5023229073 @default.
- W3207675193 creator A5023946220 @default.
- W3207675193 creator A5027455078 @default.
- W3207675193 creator A5028465673 @default.
- W3207675193 date "2021-10-18" @default.
- W3207675193 modified "2023-10-18" @default.
- W3207675193 title "GAN-based disentanglement learning for chest X-ray rib suppression" @default.
- W3207675193 cites W1986649315 @default.
- W3207675193 cites W1992382176 @default.
- W3207675193 cites W2012875423 @default.
- W3207675193 cites W2050464149 @default.
- W3207675193 cites W2087034030 @default.
- W3207675193 cites W2092660105 @default.
- W3207675193 cites W2114175399 @default.
- W3207675193 cites W2137865578 @default.
- W3207675193 cites W2171697262 @default.
- W3207675193 cites W2194775991 @default.
- W3207675193 cites W2515708490 @default.
- W3207675193 cites W2789647448 @default.
- W3207675193 cites W2789713147 @default.
- W3207675193 cites W2909763647 @default.
- W3207675193 cites W2959170286 @default.
- W3207675193 cites W2962785568 @default.
- W3207675193 cites W2962793481 @default.
- W3207675193 cites W2962825119 @default.
- W3207675193 cites W2962837297 @default.
- W3207675193 cites W2963890275 @default.
- W3207675193 cites W2979494820 @default.
- W3207675193 cites W2998954342 @default.
- W3207675193 cites W3015922642 @default.
- W3207675193 cites W3035574324 @default.
- W3207675193 cites W3101156210 @default.
- W3207675193 cites W3131250779 @default.
- W3207675193 cites W3159890710 @default.
- W3207675193 doi "https://doi.org/10.48550/arxiv.2110.09134" @default.
- W3207675193 hasPublicationYear "2021" @default.
- W3207675193 type Work @default.
- W3207675193 sameAs 3207675193 @default.
- W3207675193 citedByCount "1" @default.
- W3207675193 countsByYear W32076751932021 @default.
- W3207675193 crossrefType "posted-content" @default.
- W3207675193 hasAuthorship W3207675193A5023229073 @default.
- W3207675193 hasAuthorship W3207675193A5023946220 @default.
- W3207675193 hasAuthorship W3207675193A5027455078 @default.
- W3207675193 hasAuthorship W3207675193A5028465673 @default.
- W3207675193 hasBestOaLocation W32076751931 @default.
- W3207675193 hasConcept C105702510 @default.
- W3207675193 hasConcept C107673813 @default.
- W3207675193 hasConcept C11413529 @default.
- W3207675193 hasConcept C126838900 @default.
- W3207675193 hasConcept C153180895 @default.
- W3207675193 hasConcept C154945302 @default.
- W3207675193 hasConcept C155512373 @default.
- W3207675193 hasConcept C160306043 @default.
- W3207675193 hasConcept C177769412 @default.
- W3207675193 hasConcept C2989005 @default.
- W3207675193 hasConcept C36454342 @default.
- W3207675193 hasConcept C41008148 @default.
- W3207675193 hasConcept C71924100 @default.
- W3207675193 hasConceptScore W3207675193C105702510 @default.
- W3207675193 hasConceptScore W3207675193C107673813 @default.
- W3207675193 hasConceptScore W3207675193C11413529 @default.
- W3207675193 hasConceptScore W3207675193C126838900 @default.
- W3207675193 hasConceptScore W3207675193C153180895 @default.
- W3207675193 hasConceptScore W3207675193C154945302 @default.
- W3207675193 hasConceptScore W3207675193C155512373 @default.
- W3207675193 hasConceptScore W3207675193C160306043 @default.
- W3207675193 hasConceptScore W3207675193C177769412 @default.
- W3207675193 hasConceptScore W3207675193C2989005 @default.
- W3207675193 hasConceptScore W3207675193C36454342 @default.
- W3207675193 hasConceptScore W3207675193C41008148 @default.
- W3207675193 hasConceptScore W3207675193C71924100 @default.
- W3207675193 hasLocation W32076751931 @default.
- W3207675193 hasOpenAccess W3207675193 @default.
- W3207675193 hasPrimaryLocation W32076751931 @default.
- W3207675193 hasRelatedWork W1983029437 @default.
- W3207675193 hasRelatedWork W2054813188 @default.
- W3207675193 hasRelatedWork W2114980713 @default.
- W3207675193 hasRelatedWork W2149449954 @default.
- W3207675193 hasRelatedWork W2344532017 @default.
- W3207675193 hasRelatedWork W2593428261 @default.
- W3207675193 hasRelatedWork W2799993067 @default.
- W3207675193 hasRelatedWork W3213726327 @default.
- W3207675193 hasRelatedWork W4243827032 @default.
- W3207675193 hasRelatedWork W4301184459 @default.
- W3207675193 isParatext "false" @default.
- W3207675193 isRetracted "false" @default.
- W3207675193 magId "3207675193" @default.
- W3207675193 workType "article" @default.