Axial Self-Similarity based modular Noise2Noise for progressive LDCT denoising without ground truth
Medical & Biological Engineering & Computing · 2026-04 · 64 (4) · 1589-1608
DOI: 10.1007/s11517-026-03565-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 02.04.2026. Verfasst von Kousik Sarkar und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Indian Institute of Technology (ISM), Dhanbad, Jharkhand, 826004, India. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit nennt 45 Literaturangaben.
Abstract (Originalsprache)
Low-dose computed tomography (LDCT) has emerged as an alternative to standard-dose computed tomography (SDCT) to reduce radiation exposure. However, this dose reduction comes at the cost of increased noise and artifacts, which can compromise diagnostic accuracy. Although deep learning–based denoising methods have shown promising performance in LDCT denoising, their reliance on paired noisy-clean or noisy-noisy datasets limits practical applicability. Additionally, deep denoisers trained via end-to-end mapping on paired data typically produce a single denoised output with a fixed noise reduction level. In clinical practice, LDCT is often acquired at variable dose levels, and fixed-level denoising may not adapt well to such variability. In this study, we present a modular self-supervised denoising method by building upon the Noise2Noise principle. Axial self-similarity among neighboring slices within a CT volume has been exploited to relax the need for paired noisy-clean or noisy-noisy data. In particular, a self-supervised loss that incorporates inter-slice congruence and neighboring slice consistency is developed to enable effective learning directly from a single LDCT scan. Furthermore, an end-to-process training scheme is employed through the modular cascading of multiple identical denoising module. Each cascade refines the output of the previous stage, resulting in denoised outputs at multiple noise reduction levels across stages. Experiments on two publicly available LDCT datasets demonstrate the effectiveness of our method in reducing noise while preserving structural details, highlighting its clinical potential.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science and Engineering, Indian Institute of Technology (ISM), Dhanbad, Jharkhand, 826004, India.
- Department of Computer Science and Engineering, Indian Institute of Technology (ISM), Dhanbad, Jharkhand, 826004, India. soumen@iitism.ac.in.
Zitieren
APA
Sarkar, K., & Bag, S. (2026). Axial Self-Similarity based modular Noise2Noise for progressive LDCT denoising without ground truth. Medical & Biological Engineering & Computing, 64(4), 1589-1608. https://doi.org/10.1007/s11517-026-03565-5
Vancouver
Sarkar K, Bag S. Axial Self-Similarity based modular Noise2Noise for progressive LDCT denoising without ground truth. Medical & Biological Engineering & Computing. 2026;64(4):1589-1608. doi:10.1007/s11517-026-03565-5
BibTeX
@article{Sarkar2026,
author = {Sarkar, Kousik and Bag, Soumen},
title = {Axial Self-Similarity based modular Noise2Noise for progressive LDCT denoising without ground truth},
journal = {Medical & Biological Engineering & Computing},
year = {2026},
volume = {64},
number = {4},
pages = {1589--1608},
doi = {10.1007/s11517-026-03565-5}
}
EUVIMED