Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211609> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4387211609 endingPage "194" @default.
- W4387211609 startingPage "184" @default.
- W4387211609 abstract "To obtain high-quality positron emission tomography (PET) images while minimizing radiation exposure, various methods have been proposed for reconstructing standard-dose PET (SPET) images from low-dose PET (LPET) sinograms directly. However, current methods often neglect boundaries during sinogram-to-image reconstruction, resulting in high-frequency distortion in the frequency domain and diminished or fuzzy edges in the reconstructed images. Furthermore, the convolutional architectures, which are commonly used, lack the ability to model long-range non-local interactions, potentially leading to inaccurate representations of global structures. To alleviate these problems, in this paper, we propose a transformer-based model that unites triple domains of sinogram, image, and frequency for direct PET reconstruction, namely TriDo-Former. Specifically, the TriDo-Former consists of two cascaded networks, i.e., a sinogram enhancement transformer (SE-Former) for denoising the input LPET sinograms and a spatial-spectral reconstruction transformer (SSR-Former) for reconstructing SPET images from the denoised sinograms. Different from the vanilla transformer that splits an image into 2D patches, based specifically on the PET imaging mechanism, our SE-Former divides the sinogram into 1D projection view angles to maintain its inner-structure while denoising, preventing the noise in the sinogram from prorogating into the image domain. Moreover, to mitigate high-frequency distortion and improve reconstruction details, we integrate global frequency parsers (GFPs) into SSR-Former. The GFP serves as a learnable frequency filter that globally adjusts the frequency components in the frequency domain, enforcing the network to restore high-frequency details resembling real SPET images. Validations on a clinical dataset demonstrate that our TriDo-Former outperforms the state-of-the-art methods qualitatively and quantitatively." @default.
- W4387211609 created "2023-10-01" @default.
- W4387211609 creator A5000937401 @default.
- W4387211609 creator A5006002666 @default.
- W4387211609 creator A5019644052 @default.
- W4387211609 creator A5031319340 @default.
- W4387211609 creator A5052061493 @default.
- W4387211609 creator A5065143067 @default.
- W4387211609 creator A5065417380 @default.
- W4387211609 creator A5089126739 @default.
- W4387211609 date "2023-01-01" @default.
- W4387211609 modified "2023-10-01" @default.
- W4387211609 title "TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms" @default.
- W4387211609 cites W2122394188 @default.
- W4387211609 cites W2154744699 @default.
- W4387211609 cites W2235069229 @default.
- W4387211609 cites W2385563966 @default.
- W4387211609 cites W2508457857 @default.
- W4387211609 cites W2789588857 @default.
- W4387211609 cites W2798538010 @default.
- W4387211609 cites W2903356598 @default.
- W4387211609 cites W2979695953 @default.
- W4387211609 cites W3007486523 @default.
- W4387211609 cites W3008292561 @default.
- W4387211609 cites W3043997605 @default.
- W4387211609 cites W3092370246 @default.
- W4387211609 cites W3109862379 @default.
- W4387211609 cites W3138516171 @default.
- W4387211609 cites W3204221214 @default.
- W4387211609 cites W4200048078 @default.
- W4387211609 cites W4200341256 @default.
- W4387211609 cites W4210345762 @default.
- W4387211609 cites W4224996716 @default.
- W4387211609 cites W4280622762 @default.
- W4387211609 cites W4285077579 @default.
- W4387211609 cites W4285799895 @default.
- W4387211609 cites W4291415137 @default.
- W4387211609 cites W4381415944 @default.
- W4387211609 doi "https://doi.org/10.1007/978-3-031-43999-5_18" @default.
- W4387211609 hasPublicationYear "2023" @default.
- W4387211609 type Work @default.
- W4387211609 citedByCount "0" @default.
- W4387211609 crossrefType "book-chapter" @default.
- W4387211609 hasAuthorship W4387211609A5000937401 @default.
- W4387211609 hasAuthorship W4387211609A5006002666 @default.
- W4387211609 hasAuthorship W4387211609A5019644052 @default.
- W4387211609 hasAuthorship W4387211609A5031319340 @default.
- W4387211609 hasAuthorship W4387211609A5052061493 @default.
- W4387211609 hasAuthorship W4387211609A5065143067 @default.
- W4387211609 hasAuthorship W4387211609A5065417380 @default.
- W4387211609 hasAuthorship W4387211609A5089126739 @default.
- W4387211609 hasConcept C115961682 @default.
- W4387211609 hasConcept C121332964 @default.
- W4387211609 hasConcept C141379421 @default.
- W4387211609 hasConcept C154945302 @default.
- W4387211609 hasConcept C160633673 @default.
- W4387211609 hasConcept C163294075 @default.
- W4387211609 hasConcept C165801399 @default.
- W4387211609 hasConcept C19118579 @default.
- W4387211609 hasConcept C31972630 @default.
- W4387211609 hasConcept C41008148 @default.
- W4387211609 hasConcept C55020928 @default.
- W4387211609 hasConcept C62520636 @default.
- W4387211609 hasConcept C66322947 @default.
- W4387211609 hasConceptScore W4387211609C115961682 @default.
- W4387211609 hasConceptScore W4387211609C121332964 @default.
- W4387211609 hasConceptScore W4387211609C141379421 @default.
- W4387211609 hasConceptScore W4387211609C154945302 @default.
- W4387211609 hasConceptScore W4387211609C160633673 @default.
- W4387211609 hasConceptScore W4387211609C163294075 @default.
- W4387211609 hasConceptScore W4387211609C165801399 @default.
- W4387211609 hasConceptScore W4387211609C19118579 @default.
- W4387211609 hasConceptScore W4387211609C31972630 @default.
- W4387211609 hasConceptScore W4387211609C41008148 @default.
- W4387211609 hasConceptScore W4387211609C55020928 @default.
- W4387211609 hasConceptScore W4387211609C62520636 @default.
- W4387211609 hasConceptScore W4387211609C66322947 @default.
- W4387211609 hasLocation W43872116091 @default.
- W4387211609 hasOpenAccess W4387211609 @default.
- W4387211609 hasPrimaryLocation W43872116091 @default.
- W4387211609 hasRelatedWork W121273120 @default.
- W4387211609 hasRelatedWork W2002009170 @default.
- W4387211609 hasRelatedWork W2034462085 @default.
- W4387211609 hasRelatedWork W2141888456 @default.
- W4387211609 hasRelatedWork W2337415362 @default.
- W4387211609 hasRelatedWork W2542932817 @default.
- W4387211609 hasRelatedWork W2740820121 @default.
- W4387211609 hasRelatedWork W3159920843 @default.
- W4387211609 hasRelatedWork W317572212 @default.
- W4387211609 hasRelatedWork W4312857205 @default.
- W4387211609 isParatext "false" @default.
- W4387211609 isRetracted "false" @default.
- W4387211609 workType "book-chapter" @default.