Spach Transformer: Spatial and Channel-Wise Transformer Based on Local and Global Self-Attentions for PET Image Denoising

Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely used to improve PET image quality. Though successful and eff...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2024-06, Vol.43 (6), p.2036-2049
Main Authors: Jang, Se-In, Pan, Tinsu, Li, Ye, Heidari, Pedram, Chen, Junyu, Li, Quanzheng, Gong, Kuang
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Biomedical imaging
Convolution
Decoding
Deep learning
Encoders-Decoders
Feature extraction
Humans
Image denoising
Image Processing, Computer-Assisted - methods
Image quality
Image restoration
Imaging, Three-Dimensional - methods
local and global self-attention
low-dose PET
Machine learning
Neural networks
Neural Networks, Computer
Positron emission
Positron emission tomography
Positron-Emission Tomography - methods
Receptive field
Signal to noise ratio
spatial and channel-wise transformer
Transformers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely used to improve PET image quality. Though successful and efficient in local feature extraction, CNN cannot capture long-range dependencies well due to its limited receptive field. Global multi-head self-attention (MSA) is a popular approach to capture long-range information. However, the calculation of global MSA for 3D images has high computational costs. In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs. Experiments based on datasets of different PET tracers, i.e., 18F-FDG, 18F-ACBC, 18F-DCFPyL, and 68Ga-DOTATATE, were conducted to evaluate the proposed framework. Quantitative results show that the proposed Spach Transformer framework outperforms state-of-the-art deep learning architectures.
ISSN:0278-0062
1558-254X
1558-254X
DOI:10.1109/TMI.2023.3336237