Neighbor2Inverse: Self-Supervised Denoising for Low-Dose Region-of-Interest Phase Contrast CT

2026-05-01

AI Summary

This work addresses the challenge of significant noise amplification in low-dose phase-contrast computed tomography (CT) imaging, where existing supervised denoising methods are hindered by the scarcity of paired high- and low-dose training data. The authors propose a self-supervised denoising framework that extends the Neighbor2Neighbor paradigm to the inverse problem of CT reconstruction. By subsampling a single projection to generate two structurally consistent yet noise-independent views, the method enables direct training of a convolutional neural network in the image domain without requiring ground-truth labels. Evaluated on region-of-interest phase-contrast CT, the approach substantially improves contrast-to-noise ratio and spatial resolution, outperforming both conventional analytical methods and current self-supervised techniques. Furthermore, it demonstrates strong generalization capability in simulated low-dose clinical CT scenarios.

Abstract

Propagation-based X-ray phase-contrast imaging (PBI) enables high-contrast visualization of lung structures and holds strong medical potential. However, safe translation to the clinic will require a substantial radiation dose reduction, which inevitably increases image noise. Supervised convolutional-neural-network-based denoising can restore image quality but depends on paired low- and high-dose datasets, which are rarely available in practice. Self-supervised methods avoid this limitation, yet most are not well adapted to the inverse problem of PBI computed tomography (CT). We introduce Neighbor2Inverse, a self-supervised denoising framework designed for low-dose PBI-CT that generalizes to clinical CT. Building on the Neighbor2Neighbor principle, each noisy projection is subsampled into two variants that preserve structural information but contain independent noise realizations. These are reconstructed separately, and the resulting pairs are used to train a denoising network directly in the image domain. We benchmark the proposed method against established analytical and self-supervised denoising approaches. In region-of-interest PBI CT experiments, Neighbor2Inverse achieves superior noise suppression while preserving fine structural details, as demonstrated by improved contrast-to-noise ratio, spatial resolution, and composite image quality metrics. Competitive performance is also observed on clinical CT data under simulated low-dose conditions. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Code, data, and interactive figures are available at https://github.com/J-3TO/Neighbor2Inverse.

Problem

• phase-contrast CT
• low-dose imaging
• self-supervised denoising
• inverse problem
• region-of-interest

Innovation

• self-supervised denoising
• phase-contrast CT
• Neighbor2Inverse
• low-dose imaging
• image reconstruction