EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Low-Dose CT Image Reconstruction Using Uncertainty-Aware Convolution–Attention Networks

Laura Gómez, Daniel Fernández

Frontiers in Applied Physics and Mathematics · 2026-02-20 · 3 (1) · 149-157

DOI: 10.71465/fapm712 ↗

At a glance

Journal article in Frontiers in Applied Physics and Mathematics, published online on 2026-02-20. Written by Laura Gómez and 1 co-authors. The full text is freely available (open access, CC BY 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Reducing radiation dose in computed tomography often leads to increased noise and loss of structural detail. Motivated by hybrid convolution–attention denoising models such as CTLformer, this work investigates an uncertainty-aware reconstruction framework that combines local convolutional filtering with global self-attention. The model incorporates uncertainty estimation to adaptively balance fine-grained texture preservation and noise suppression. Experiments are conducted on two public low-dose CT datasets containing over 45,000 paired normal- and low-dose slices. Comparisons are performed against CNN-based methods (RED-CNN, DnCNN), transformer-based models, and recent hybrid architectures. Quantitative results show average improvements of 0.9–1.3 dB in PSNR and 1.5%–2.4% in SSIM under standard low-dose settings, with reduced variance across anatomical regions.

Cite

APA

Gómez, L., & Fernández, D. (2026). Low-Dose CT Image Reconstruction Using Uncertainty-Aware Convolution–Attention Networks. Frontiers in Applied Physics and Mathematics, 3(1), 149-157. https://doi.org/10.71465/fapm712

Vancouver

Gómez L, Fernández D. Low-Dose CT Image Reconstruction Using Uncertainty-Aware Convolution–Attention Networks. Frontiers in Applied Physics and Mathematics. 2026;3(1):149-157. doi:10.71465/fapm712

BibTeX
@article{Gmez2026,
  author = {Gómez, Laura and Fernández, Daniel},
  title = {Low-Dose CT Image Reconstruction Using Uncertainty-Aware Convolution–Attention Networks},
  journal = {Frontiers in Applied Physics and Mathematics},
  year = {2026},
  volume = {3},
  number = {1},
  pages = {149--157},
  doi = {10.71465/fapm712}
}
Start for free →