Window-Level is a Strong Denoising Surrogate

TL;DR

This paper introduces a novel self-supervised learning method called SSWL-IDN that effectively denoises low-dose CT images by predicting window-leveled equivalents, reducing the need for large reference datasets.

Contribution

The paper presents a new self-supervised approach for CT denoising that is task-relevant, simple, and effective, leveraging window-level prediction within a VAE framework.

Findings

Effective denoising at 5% dose level

Works across abdomen and chest CT images

Reduces reliance on large reference datasets

Abstract

CT image quality is heavily reliant on radiation dose, which causes a trade-off between radiation dose and image quality that affects the subsequent image-based diagnostic performance. However, high radiation can be harmful to both patients and operators. Several (deep learning-based) approaches have been attempted to denoise low dose images. However, those approaches require access to large training sets, specifically the full dose CT images for reference, which can often be difficult to obtain. Self-supervised learning is an emerging alternative for lowering the reference data requirement facilitating unsupervised learning. Currently available self-supervised CT denoising works are either dependent on foreign domain or pretexts are not very task-relevant. To tackle the aforementioned challenges, we propose a novel self-supervised learning approach, namely Self-Supervised Window-Leveling for Image DeNoising (SSWL-IDN), leveraging an innovative, task-relevant, simple, yet effective surrogate -- prediction of the window-leveled equivalent. SSWL-IDN leverages residual learning and a hybrid loss combining perceptual loss and MSE, all incorporated in a VAE framework. Our extensive (in- and cross-domain) experimentation demonstrates the effectiveness of SSWL-IDN in aggressive denoising of CT (abdomen and chest) images acquired at 5\% dose level only.