A multi-scale ResNet and Swin Transformer fusion network with channel attention predicts PET/CT image quality scores from a new 2,700-image radiologist-labeled dataset and outperforms existing IQA methods.
C-DIIVINE: No-reference image quality assessment based on local magnitude and phase statistics of natural scenes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
MS-IQA: A Multi-Scale Feature Fusion Network for PET/CT Image Quality Assessment
A multi-scale ResNet and Swin Transformer fusion network with channel attention predicts PET/CT image quality scores from a new 2,700-image radiologist-labeled dataset and outperforms existing IQA methods.