Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379660342> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4379660342 endingPage "782" @default.
- W4379660342 startingPage "771" @default.
- W4379660342 abstract "Self-supervised image denoising techniques emerged as convenient methods that allow training denoising models without requiring ground-truth noise-free data. Existing methods usually optimize loss metrics that are calculated from multiple noisy realizations of similar images, e.g., from neighboring tomographic slices. However, those approaches fail to utilize the multiple contrasts that are routinely acquired in medical imaging modalities like MRI or dual-energy CT. In this work, we propose the new self-supervised training scheme Noise2Contrast that combines information from multiple measured image contrasts to train a denoising model. We stack denoising with domain-transfer operators to utilize the independent noise realizations of different image contrasts to derive a self-supervised loss. The trained denoising operator achieves convincing quantitative and qualitative results, outperforming state-of-the-art self-supervised methods by 4.7–11.0%/4.8–7.3% (PSNR/SSIM) on brain MRI data and by 43.6–50.5%/57.1–77.1% (PSNR/SSIM) on dual-energy CT X-ray microscopy data with respect to the noisy baseline. Our experiments on different real measured data sets indicate that Noise2Contrast training generalizes to other multi-contrast imaging modalities." @default.
- W4379660342 created "2023-06-08" @default.
- W4379660342 creator A5009773791 @default.
- W4379660342 creator A5011796999 @default.
- W4379660342 creator A5025633906 @default.
- W4379660342 creator A5029146495 @default.
- W4379660342 creator A5032499810 @default.
- W4379660342 creator A5037663527 @default.
- W4379660342 creator A5040049345 @default.
- W4379660342 creator A5049539538 @default.
- W4379660342 creator A5061411458 @default.
- W4379660342 creator A5068070921 @default.
- W4379660342 creator A5083618878 @default.
- W4379660342 creator A5087291004 @default.
- W4379660342 creator A5020455437 @default.
- W4379660342 date "2023-01-01" @default.
- W4379660342 modified "2023-10-18" @default.
- W4379660342 title "Noise2Contrast: Multi-contrast Fusion Enables Self-supervised Tomographic Image Denoising" @default.
- W4379660342 cites W1901129140 @default.
- W4379660342 cites W2061027870 @default.
- W4379660342 cites W2069045463 @default.
- W4379660342 cites W2902857081 @default.
- W4379660342 cites W3026174455 @default.
- W4379660342 cites W3125908253 @default.
- W4379660342 cites W3186987339 @default.
- W4379660342 cites W3191864036 @default.
- W4379660342 cites W4225786145 @default.
- W4379660342 cites W4280565701 @default.
- W4379660342 cites W4281730462 @default.
- W4379660342 cites W4284894230 @default.
- W4379660342 cites W4306879673 @default.
- W4379660342 cites W4312896951 @default.
- W4379660342 doi "https://doi.org/10.1007/978-3-031-34048-2_59" @default.
- W4379660342 hasPublicationYear "2023" @default.
- W4379660342 type Work @default.
- W4379660342 citedByCount "0" @default.
- W4379660342 crossrefType "book-chapter" @default.
- W4379660342 hasAuthorship W4379660342A5009773791 @default.
- W4379660342 hasAuthorship W4379660342A5011796999 @default.
- W4379660342 hasAuthorship W4379660342A5020455437 @default.
- W4379660342 hasAuthorship W4379660342A5025633906 @default.
- W4379660342 hasAuthorship W4379660342A5029146495 @default.
- W4379660342 hasAuthorship W4379660342A5032499810 @default.
- W4379660342 hasAuthorship W4379660342A5037663527 @default.
- W4379660342 hasAuthorship W4379660342A5040049345 @default.
- W4379660342 hasAuthorship W4379660342A5049539538 @default.
- W4379660342 hasAuthorship W4379660342A5061411458 @default.
- W4379660342 hasAuthorship W4379660342A5068070921 @default.
- W4379660342 hasAuthorship W4379660342A5083618878 @default.
- W4379660342 hasAuthorship W4379660342A5087291004 @default.
- W4379660342 hasConcept C105795698 @default.
- W4379660342 hasConcept C115961682 @default.
- W4379660342 hasConcept C146849305 @default.
- W4379660342 hasConcept C153180895 @default.
- W4379660342 hasConcept C154945302 @default.
- W4379660342 hasConcept C163294075 @default.
- W4379660342 hasConcept C186370098 @default.
- W4379660342 hasConcept C2776502983 @default.
- W4379660342 hasConcept C31972630 @default.
- W4379660342 hasConcept C33923547 @default.
- W4379660342 hasConcept C41008148 @default.
- W4379660342 hasConcept C99498987 @default.
- W4379660342 hasConceptScore W4379660342C105795698 @default.
- W4379660342 hasConceptScore W4379660342C115961682 @default.
- W4379660342 hasConceptScore W4379660342C146849305 @default.
- W4379660342 hasConceptScore W4379660342C153180895 @default.
- W4379660342 hasConceptScore W4379660342C154945302 @default.
- W4379660342 hasConceptScore W4379660342C163294075 @default.
- W4379660342 hasConceptScore W4379660342C186370098 @default.
- W4379660342 hasConceptScore W4379660342C2776502983 @default.
- W4379660342 hasConceptScore W4379660342C31972630 @default.
- W4379660342 hasConceptScore W4379660342C33923547 @default.
- W4379660342 hasConceptScore W4379660342C41008148 @default.
- W4379660342 hasConceptScore W4379660342C99498987 @default.
- W4379660342 hasLocation W43796603421 @default.
- W4379660342 hasOpenAccess W4379660342 @default.
- W4379660342 hasPrimaryLocation W43796603421 @default.
- W4379660342 hasRelatedWork W1632903234 @default.
- W4379660342 hasRelatedWork W1969449762 @default.
- W4379660342 hasRelatedWork W1977373830 @default.
- W4379660342 hasRelatedWork W1987421842 @default.
- W4379660342 hasRelatedWork W2005185696 @default.
- W4379660342 hasRelatedWork W2035413902 @default.
- W4379660342 hasRelatedWork W2121179941 @default.
- W4379660342 hasRelatedWork W2144748970 @default.
- W4379660342 hasRelatedWork W2716174519 @default.
- W4379660342 hasRelatedWork W3004045746 @default.
- W4379660342 isParatext "false" @default.
- W4379660342 isRetracted "false" @default.
- W4379660342 workType "book-chapter" @default.