Reliability-Aware CT Image Reconstruction Based on Convolution–Attention Feature Uncertainty
Global Media and Social Sciences Research Journal · 20.02.2026 · 7 (1) · 194-199
DOI: 10.71465/gmssrj165 ↗Kurz gefasst
Fachartikel in der Zeitschrift Global Media and Social Sciences Research Journal, online erschienen am 20.02.2026. Verfasst von Liam O’Connor und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Beyond reconstruction accuracy, reliability assessment is important for clinical adoption of learned CT reconstruction methods. Motivated by convolution–self-attention denoising models such as CTLformer, this work studies reliability-aware CT reconstruction by associating reconstructed images with uncertainty estimates. The model outputs both reconstructed images and pixel-wise uncertainty maps, allowing identification of regions with reduced confidence. Experiments on two clinical CT datasets with 50,000 slices show that uncertainty-aware reconstruction maintains comparable PSNR and SSIM to deterministic baselines while enabling effective detection of reconstruction errors. Regions with high uncertainty correspond closely to metal artifacts and low-dose noise patterns.
Zitieren
APA
O’Connor, L., Martinez, S., & Kim, D. (2026). Reliability-Aware CT Image Reconstruction Based on Convolution–Attention Feature Uncertainty. Global Media and Social Sciences Research Journal, 7(1), 194-199. https://doi.org/10.71465/gmssrj165
Vancouver
O’Connor L, Martinez S, Kim D. Reliability-Aware CT Image Reconstruction Based on Convolution–Attention Feature Uncertainty. Global Media and Social Sciences Research Journal. 2026;7(1):194-199. doi:10.71465/gmssrj165
BibTeX
@article{OConnor2026,
author = {O’Connor, Liam and Martinez, Sophia and Kim, Daniel},
title = {Reliability-Aware CT Image Reconstruction Based on Convolution–Attention Feature Uncertainty},
journal = {Global Media and Social Sciences Research Journal},
year = {2026},
volume = {7},
number = {1},
pages = {194--199},
doi = {10.71465/gmssrj165}
}
EUVIMED