Image-domain deep learning denoising for low-dose chest CT on a single 128-slice CT platform: a retrospective image-quality assessment - Takeaways - MDSpire

Image-domain deep learning denoising for low-dose chest CT on a single 128-slice CT platform: a retrospective image-quality assessment

  • By

  • Kaiqing Yao

  • Xue Jiang

  • Liang Lv

  • Yang Li

  • Guangpeng Zhang

  • Zhiyuan Zhang

  • Zhiwei Zhang

  • Xinyou Li

  • Fajin Lv

  • July 14, 2026

Share

  • 1

    A retrospective study evaluated a deep learning denoising algorithm for improving low-dose chest CT image quality on a 128-slice scanner.

  • 2

    The study included 198 patients, divided into low-dose CT and standard-dose CT groups, with image quality assessed using objective and subjective metrics.

  • 3

    LD-AiR significantly reduced image noise and increased signal-to-noise and contrast-to-noise ratios compared to low-dose SAFIRE.

  • 4

    Subjective image quality scores for lung parenchyma and mediastinal soft tissue were significantly higher with LD-AiR than with LD-SAFIRE.

  • 5

    The low-dose CT protocol was associated with approximately 76% lower effective dose compared to the standard-dose CT protocol.

Original Source(s)

Image-domain deep learning denoising for low-dose chest CT on a single 128-slice CT platform: a retrospective image-quality assessment

  • by Kaiqing Yao, Xue Jiang, Liang Lv, Yang Li, Guangpeng Zhang, Zhiyuan Zhang, Zhiwei Zhang, Xinyou Li, Fajin Lv

  • July 14, 2026

Related Content

Proximal Seal After Endovascular Aneurysm Repair: Why Sealing Length Dynamics and Type 2 Endoleak Matter

Quantitative multi-slice spiral CT perfusion parameters as predictors of collateral status and 90-day functional outcome in acute ischemic stroke

Imaging features, diagnosis, and clinical management of hepatic involvement in hereditary hemorrhagic telangiectasia: a case series report and literature review