Semi-supervised low-dose SPECT restoration using sinogram inner-structure aware graph neural network.

Si LiKeming ChenXiangyuan Ma Zengguo Liang

Published in: Physics in medicine and biology (2024)

The proposed framework improves the quality of low-dose SPECT reconstructed images by utilizing sinogram inner-structure and incorporating supplementary unlabeled data, which provides an important tool for dose reduction without sacrificing the image quality.

Keyphrases

low dose
neural network
image quality
high dose
pet ct
computed tomography
convolutional neural network
machine learning
deep learning
electronic health record
optical coherence tomography
big data
dual energy
magnetic resonance imaging
magnetic resonance
data analysis
contrast enhanced