Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Yichao, Xue, Hengzhi, Teng, YueYang, Guo, Junwen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913036013404160
author Liu, Yichao
Xue, Hengzhi
Teng, YueYang
Guo, Junwen
author_facet Liu, Yichao
Xue, Hengzhi
Teng, YueYang
Guo, Junwen
contents Low-dose computed tomography (LDCT) and positron emission tomography (PET) have emerged as safer alternatives to conventional imaging modalities by significantly reducing radiation exposure. However, current approaches often face a trade$-$off between training stability and computational efficiency. In this study, we propose a novel Hybrid Swin Attention Network (HSANet), which incorporates Efficient Global Attention (EGA) modules and a hybrid upsampling module to address these limitations. The EGA modules enhance both spatial and channel-wise interaction, improving the network's capacity to capture relevant features, while the hybrid upsampling module mitigates the risk of overfitting to noise. We validate the proposed approach using a publicly available LDCT/PET dataset. Experimental results demonstrate that HSANet achieves superior denoising performance compared to state of the art methods, while maintaining a lightweight model size suitable for deployment on GPUs with standard memory configurations. Thus, our approach demonstrates significant potential for practical, real-world clinical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
Liu, Yichao
Xue, Hengzhi
Teng, YueYang
Guo, Junwen
Computer Vision and Pattern Recognition
Low-dose computed tomography (LDCT) and positron emission tomography (PET) have emerged as safer alternatives to conventional imaging modalities by significantly reducing radiation exposure. However, current approaches often face a trade$-$off between training stability and computational efficiency. In this study, we propose a novel Hybrid Swin Attention Network (HSANet), which incorporates Efficient Global Attention (EGA) modules and a hybrid upsampling module to address these limitations. The EGA modules enhance both spatial and channel-wise interaction, improving the network's capacity to capture relevant features, while the hybrid upsampling module mitigates the risk of overfitting to noise. We validate the proposed approach using a publicly available LDCT/PET dataset. Experimental results demonstrate that HSANet achieves superior denoising performance compared to state of the art methods, while maintaining a lightweight model size suitable for deployment on GPUs with standard memory configurations. Thus, our approach demonstrates significant potential for practical, real-world clinical applications.
title Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06591