A quantitative benchmarking framework for reinforcement learning-based low-dose CT image denoising
Future Technology · 15.08.2026 · 5 (3) · 107-117
DOI: 10.55670/fpll.futech.5.3.10 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Technology, online erschienen am 15.08.2026. Verfasst von Amit Bhupal Pattar und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Low-dose computed tomography (LDCT) reduces radiation exposure but increases noise and structural degradation, which may affect diagnostic reliability. This paper presents a quantitative benchmarking framework to assess reinforcement learning (RL)-based LDCT denoising under standardized, reproducible experimental conditions. The proposed pipeline combines dataset splitting with controlled fragments, percentile preprocessing, classical and deep learning baselines, an RL denoising environment modeled as a Markov Decision Process, and multi-metric statistical validation. Experimental results on multi-level LDCT data show that the proposed RL_stageB model provides the highest overall reconstruction fidelity, which can achieve a mean PSNR 22.732 ± 0.947 dB and SSIM 0.929 ± 0.056, which is higher than strong classical baselines such as bilateral filtering 22.618 dB and Gaussian filtering 22.727 dB, while reducing edge distortion, Edge-L1=0.242. Statistically significant improvements (p
Zitieren
APA
Pattar, A. B., & N, T. S. (2026). A quantitative benchmarking framework for reinforcement learning-based low-dose CT image denoising. Future Technology, 5(3), 107-117. https://doi.org/10.55670/fpll.futech.5.3.10
Vancouver
Pattar AB, N TS. A quantitative benchmarking framework for reinforcement learning-based low-dose CT image denoising. Future Technology. 2026;5(3):107-117. doi:10.55670/fpll.futech.5.3.10
BibTeX
@article{Pattar2026,
author = {Pattar, Amit Bhupal and N, Thimmaraju S},
title = {A quantitative benchmarking framework for reinforcement learning-based low-dose CT image denoising},
journal = {Future Technology},
year = {2026},
volume = {5},
number = {3},
pages = {107--117},
doi = {10.55670/fpll.futech.5.3.10}
}
EUVIMED