SDCNN: Self-Supervised Disentangled Convolutional Neural Network for Low-Dose CT Denoising
- 20 November 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
Abstract
Low-dose computed tomography (LDCT) reduces radiation exposure but suffers from high noise, impacting image quality and diagnostic accuracy. Supervised learning has helped address this challenge but requires numerous paired datasets of LDCT and normal-dose CT (NDCT) images, which limits their clinical practice. This article proposes a novel self-supervised disentangled convolutional neural network (SDCNN) that can directly reconstruct high-quality CT images from LDCT data without the need for a clean reference. Unlike other methods that treat noise as a uniform entity, SDCNN disentangles LDCT images into noise-free images, signal-dependent noise, and signal-independent noise, aligning with the intrinsic principles of low-dose noise generation. To enhance the purity of disentanglement, we introduce the concept of combination and re-disentanglement to establish a training framework based on SDCNN. Additionally, we design self-supervised loss functions, including novel anisotropic total variation (TV) and distance loss functions, to improve the efficiency of the denoising process. The signal-guided attention (SGA) module effectively captures the relationship between signal-dependent noise and the signal across both spatial and channel dimensions. Experiments on clinical and animal data demonstrate that the proposed method performed better than all competing state-of-the-art (SOTA) self-supervised algorithms in noise and artifact removal. For example, compared to the self-supervised algorithms, SDCNN improves the multiscale structural similarity (MSSIM), peak signal-to-noise ratio (PSNR), and feature similarity (FSIM) by at least 2.26%, 1.20 dB, 1.23%, whereas, the gradient magnitude similarity deviation (GMSD) is reduced by at least 1.11% on the Mayo clinical data. The code is available at https://github.com/YuhangLiu98/SDCNN .Keywords
Funding Information
- National Key Research and Development Program of China (2022YFE0116700)
- National Natural Science Foundation of China (62171125)
- Natural Science Foundation of Shanxi Province (202303021211148)
This publication has 57 references indexed in Scilit:
- WIA-LD2ND: Wavelet-Based Image Alignment for Self-supervised Low-Dose CT Denoising2024
- Self-supervised deep learning for joint 3D low-dose PET/CT image denoisingComputers in Biology and Medicine, 2023
- A total variation prior unrolling approach for computed tomography reconstructionMedical Physics, 2023
- Cone-beam computed tomography based on truncated adaptive-weight total variationNDT & E International, 2022
- CycleGAN denoising of extreme low-dose cardiac CT using wavelet-assisted noise disentanglementMedical Image Analysis, 2021
- Low‐dose CT reconstruction with Noise2Noise network and testing‐time fine‐tuningMedical Physics, 2021
- Probabilistic self‐learning framework for low‐dose CT denoisingMedical Physics, 2021
- Cycle‐consistent adversarial denoising network for multiphase coronary CT angiographyMedical Physics, 2018
- Few‐view CT reconstruction with group‐sparsity regularizationInternational Journal for Numerical Methods in Biomedical Engineering, 2018
- Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial NetworkJournal of Digital Imaging, 2018