Noise2Inverse: Self-supervised deep convolutional denoising for tomography

Abstract

Recovering a high-quality image from noisy indirect measurements is an important problem with many applications. For such inverse problems, supervised deep convolutional neural network (CNN)-based denoising methods have shown strong results, but the success of these supervised methods critically depends on the availability of a high-quality training dataset of similar measurements. For image denoising, methods are available that enable training without a separate training dataset by assuming that the noise in two different pixels is uncorrelated. However, this assumption does not hold for inverse problems, resulting in artifacts in the denoised images produced by existing methods. Here, we propose Noise2Inverse, a deep CNN-based denoising method for linear image reconstruction algorithms that does not require any additional clean or noisy data. Training a CNN-based denoiser is enabled by exploiting the noise model to compute multiple statistically independent reconstructions. We develop a theoretical framework which shows that such training indeed obtains a denoising CNN, assuming the measured noise is element-wise independent and zero-mean. On simulated CT datasets, Noise2Inverse demonstrates an improvement in peak signal-to-noise ratio and structural similarity index compared to state-of-the-art image denoising methods and conventional reconstruction methods, such as Total-Variation Minimization. We also demonstrate that the method is able to significantly reduce noise in challenging real-world experimental datasets.

This paper appears in: IEEE Transactions on Computational Imaging On page(s): 1320-1335 Print ISSN: 2333-9403 Online ISSN: 2333-9403 Digital Object Identifier: 10.1109/TCI.2020.3019647

References in corpus (11)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• scikit-image: Image processing in Python
• Learned Primal-dual Reconstruction
• Deep Image Prior
• A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
• Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data
• RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
• Efficient and accurate inversion of multiple scattering with deep learning
• A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography
• Regularization by architecture: A deep prior approach for inverse problems

Cited by in corpus (14)

• Systematic Review on Learning-based Spectral CT
• A study of why we need to reassess full reference image quality assessment with medical images
• Algorithm-driven Advances for Scientific CT Instruments: From Model-based to Deep Learning-based Approaches
• Clinical Micro-CT Empowered by Interior Tomography, Robotic Scanning, and Deep Learning
• Self-Supervised Training For Low Dose CT Reconstruction
• Transfer Learning Application of Self-supervised Learning in ARPES
• End-to-end Memory-Efficient Reconstruction for Cone Beam CT
• A Dataset-free Deep learning Method for Low-Dose CT Image Reconstruction
• A tomographic workflow to enable deep learning for X-ray based foreign object detection
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction
• Dynamic laboratory X-ray phase-contrast microtomography with structure-based prior regularisation
• Fully Unsupervised Dynamic MRI Reconstruction via Diffeo-Temporal Equivariance
• Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Data
• TomoSelfDEQ: Self-Supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction