Deep Convolutional Neural Network for Inverse Problems in Imaging

Abstract

In this paper, we propose a novel deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems. Regularized iterative algorithms have emerged as the standard approach to ill-posed inverse problems in the past few decades. These methods produce excellent results, but can be challenging to deploy in practice due to factors including the high computational cost of the forward and adjoint operators and the difficulty of hyper parameter selection. The starting point of our work is the observation that unrolled iterative methods have the form of a CNN (filtering followed by point-wise non-linearity) when the normal operator (H*H, the adjoint of H times H) of the forward model is a convolution. Based on this observation, we propose using direct inversion followed by a CNN to solve normal-convolutional inverse problems. The direct inversion encapsulates the physical model of the system, but leads to artifacts when the problem is ill-posed; the CNN combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure. We demonstrate the performance of the proposed network in sparse-view reconstruction (down to 50 views) on parallel beam X-ray computed tomography in synthetic phantoms as well as in real experimental sinograms. The proposed network outperforms total variation-regularized iterative reconstruction for the more realistic phantoms and requires less than a second to reconstruct a 512 x 512 image on GPU.

References in corpus (9)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• On the difficulty of training Recurrent Neural Networks
• Fully Convolutional Networks for Semantic Segmentation
• Fast Image Recovery Using Variable Splitting and Constrained Optimization
• MatConvNet - Convolutional Neural Networks for MATLAB
• Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis
• Maximal Sparsity with Deep Networks?
• Learning optimal nonlinearities for iterative thresholding algorithms
• On learning optimized reaction diffusion processes for effective image restoration

Cited by in corpus (391)

• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Image reconstruction by domain transform manifold learning
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• MoDL: Model Based Deep Learning Architecture for Inverse Problems
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• Learned Primal-dual Reconstruction
• FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline
• Deep Learning Microscopy
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal
• Solving ill-posed inverse problems using iterative deep neural networks
• Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network
• Convolutional Neural Network Based Metal Artifact Reduction in X-ray Computed Tomography
• Deep learning in nano-photonics: inverse design and beyond
• DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• 3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
• Deep-Learning Inversion of Seismic Data
• CNN-Based Projected Gradient Descent for Consistent Image Reconstruction
• Deep D-bar: Real time Electrical Impedance Tomography Imaging with Deep Neural Networks
• Model based learning for accelerated, limited-view 3D photoacoustic tomography
• DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem
• FISTA-Net: Learning A Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging
• Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning
• Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
• Deep learning approach to Fourier ptychographic microscopy
• Plug and play methods for magnetic resonance imaging (long version)
• Deep-neural-network based sinogram synthesis for sparse-view CT image reconstruction
• DeepEDN: A Deep Learning-based Image Encryption and Decryption Network for Internet of Medical Things
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease
• Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiography
• On the use of deep learning for phase recovery
• Deep Learning Inversion of Electrical Resistivity Data
• InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
• A Review on Deep Learning in Medical Image Reconstruction
• Non-invasive Inference of Thrombus Material Properties with Physics-informed Neural Networks
• MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation
• Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods
• MR image reconstruction using deep density priors
• Deep learning enhanced mobile-phone microscopy
• Computational ghost imaging using deep learning
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
• TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
• Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
• Deep Identity-aware Transfer of Facial Attributes
• Efficient and accurate inversion of multiple scattering with deep learning
• Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models
• The Modern Mathematics of Deep Learning
• Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem
• Diffraction tomography with a deep image prior
• Learning The Invisible: A Hybrid Deep Learning-Shearlet Framework for Limited Angle Computed Tomography
• Deep Learning Diffuse Optical Tomography
• The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods
• A Deep Learning Reconstruction Framework for Differential Phase-Contrast Computed Tomography with Incomplete Data
• Limited View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning
• Deep-Learning based Inverse Modeling Approaches: A Subsurface Flow Example
• Interpolation and Denoising of Seismic Data using Convolutional Neural Networks
• Deep Null Space Learning for Inverse Problems: Convergence Analysis and Rates
• Self-Supervised Nonlinear Transform-Based Tensor Nuclear Norm for Multi-Dimensional Image Recovery
• Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI with Limited Data
• Regularization by architecture: A deep prior approach for inverse problems
• Solving inverse problems using conditional invertible neural networks
• CNN-Based Image Reconstruction Method for Ultrafast Ultrasound Imaging
• Deep Bayesian Inversion
• Deep variational network for rapid 4D flow MRI reconstruction
• Solving inverse-PDE problems with physics-aware neural networks
• Adversarial Regularizers in Inverse Problems
• Spatial-Angular Attention Network for Light Field Reconstruction
• GAP-net for Snapshot Compressive Imaging
• High-Resolution Limited-Angle Phase Tomography of Dense Layered Objects Using Deep Neural Networks
• Numerical Solution of Inverse Problems by Weak Adversarial Networks
• MoCoNet: Motion Correction in 3D MPRAGE images using a Convolutional Neural Network approach
• PYRO-NN: Python Reconstruction Operators in Neural Networks
• Computationally Efficient Deep Neural Network for Computed Tomography Image Reconstruction
• Untrained networks for compressive lensless photography
• Deep Learning for Passive Synthetic Aperture Radar
• GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks
• All-optical image denoising using a diffractive visual processor
• A Partially Learned Algorithm for Joint Photoacoustic Reconstruction and Segmentation
• Structural engineering from an inverse problems perspective
• Multi-scale Convolutional Neural Networks for Inverse Problems
• Robust Phase Unwrapping via Deep Image Prior for Quantitative Phase Imaging
• SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors
• Learned SPARCOM: Unfolded Deep Super-Resolution Microscopy
• Deep Iterative Reconstruction for Phase Retrieval
• Measuring Robustness in Deep Learning Based Compressive Sensing
• SOM-Net: Unrolling the Subspace-based Optimization for Solving Full-wave Inverse Scattering Problems
• Deep Learning for space-variant deconvolution in galaxy surveys
• Low-Dose CT with Deep Learning Regularization via Proximal Forward Backward Splitting
• DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
• xQSM: Quantitative Susceptibility Mapping with Octave Convolutional and Noise Regularized Neural Networks
• Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography
• Learning MRI Artifact Removal With Unpaired Data
• Image reconstruction algorithms in radio interferometry: from handcrafted to learned regularization denoisers
• Performance Analysis and Dynamic Evolution of Deep Convolutional Neural Network for Nonlinear Inverse Scattering
• Dual-Domain Reconstruction Networks with V-Net and K-Net for fast MRI
• Recent Advances in Imaging Around Corners
• Three-dimensional Generative Adversarial Nets for Unsupervised Metal Artifact Reduction
• WNet: A data-driven dual-domain denoising model for sparse-view computed tomography with a trainable reconstruction layer
• Self-Supervised Deep Active Accelerated MRI
• Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction
• Robust Compressed Sensing MRI with Deep Generative Priors
• LORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Space
• Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties
• Bilevel Optimization, Deep Learning and Fractional Laplacian Regularization with Applications in Tomography
• Photoacoustic image reconstruction via deep learning
• Deep learning reconstruction of digital breast tomosynthesis images for accurate breast density and patient-specific radiation dose estimation
• Biomedical Image Reconstruction: From the Foundations to Deep Neural Networks
• A Helmholtz equation solver using unsupervised learning: Application to transcranial ultrasound
• What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory
• Far-field subwavelength acoustic imaging by deep learning
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• Metal Artifact Reduction in 2D CT Images with Self-supervised Cross-domain Learning
• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Embedded deep learning in ophthalmology: Making ophthalmic imaging smarter
• Exploring Overcomplete Representations for Single Image Deraining using CNNs
• Deep learning-based photoacoustic imaging of vascular network through thick porous media
• Connections between Deep Equilibrium and Sparse Representation Models with Application to Hyperspectral Image Denoising
• PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds
• CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking
• Blending Diverse Physical Priors with Neural Networks
• SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
• An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction
• Deep Unfolding with Normalizing Flow Priors for Inverse Problems
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art
• Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT
• Deep neural network enabled corrective source term approach to hybrid analysis and modeling
• Towards CT-quality Ultrasound Imaging using Deep Learning
• Deep Neural Networks with Trainable Activations and Controlled Lipschitz Constant
• Report on the AAPM deep-learning sparse-view CT (DL-sparse-view CT) Grand Challenge
• Bilevel methods for image reconstruction
• Solving Bayesian Inverse Problems via Variational Autoencoders
• Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting
• Quantitative reconstruction of defects in multi-layered bonded composites using fully convolutional network-based ultrasonic inversion
• Probabilistic Autoencoder
• Deep Encoder-decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-view Data
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• An Unsupervised Reconstruction Method For Low-Dose CT Using Deep Generative Regularization Prior
• A study of why we need to reassess full reference image quality assessment with medical images
• Spectral pre-modulation of training examples enhances the spatial resolution of the Phase Extraction Neural Network (PhENN)
• Deep Learning on Image Denoising: An overview
• Limitations of Deep Learning for Inverse Problems on Digital Hardware
• PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
• LADMM-Net: An Unrolled Deep Network For Spectral Image Fusion From Compressive Data
• Using Conditional Generative Adversarial Networks to Reduce the Effects of Latency in Robotic Telesurgery
• Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning -- A Residual Physics Approach
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning
• Bi-Linear Modeling of Data Manifolds for Dynamic-MRI Recovery
• Quantitative Phase Imaging and Artificial Intelligence: A Review
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction
• Imaging through glass diffusers using densely connected convolutional networks
• Phaseless Microwave Imaging Of Dielectric Cylinders: An Artificial Neural Networks-Based Approach
• Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstruction
• Data driven regularization by projection
• Consolidated Dataset and Metrics for High-Dynamic-Range Image Quality
• Unsupervised Learnable Sinogram Inpainting Network (SIN) for Limited Angle CT reconstruction
• DuDoNet: Dual Domain Network for CT Metal Artifact Reduction
• Physics Assisted Deep Learning for Indoor Imaging using Phaseless Wi-Fi Measurements
• Unified Supervised-Unsupervised (SUPER) Learning for X-ray CT Image Reconstruction
• An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstruction
• Algorithm-driven Advances for Scientific CT Instruments: From Model-based to Deep Learning-based Approaches
• Uncertainty Quantification with Generative Models
• Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
• DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction
• Score-Based Generative Models for PET Image Reconstruction
• Physics-informed Score-based Diffusion Model for Limited-angle Reconstruction of Cardiac Computed Tomography
• Deep Learning-based galaxy image deconvolution
• Deep artifact learning for compressed sensing and parallel MRI
• Deep Learning Interior Tomography for Region-of-Interest Reconstruction
• An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation
• $\Sigma$-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction
• CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
• Two-and-a-half Order Score-based Model for Solving 3D Ill-posed Inverse Problems
• Inversion of Time-Lapse Surface Gravity Data for Detection of 3D CO${}_2$ Plumes via Deep Learning
• k-Space Deep Learning for Accelerated MRI
• Deep Algorithm Unrolling for Blind Image Deblurring
• Momentum-Net: Fast and convergent iterative neural network for inverse problems
• A Trained Regularization Approach Based on Born Iterative Method for Electromagnetic Imaging
• Learned convex regularizers for inverse problems
• Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
• DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Prior
• Quantitative Comparison of Planar Coded Aperture Imaging Reconstruction Methods
• Physics-assisted Generative Adversarial Network for X-Ray Tomography
• Improving Robustness of Deep-Learning-Based Image Reconstruction
• Unsupervised Knowledge-Transfer for Learned Image Reconstruction
• What do AI algorithms actually learn? - On false structures in deep learning
• Approximate k-space models and Deep Learning for fast photoacoustic reconstruction
• Deep learning versus ${\ell }^1$-minimization for compressed sensing photoacoustic tomography
• Application of machine learning regression models to inverse eigenvalue problems
• Bayesian Inference with Generative Adversarial Network Priors
• Medical Imaging Synthesis using Deep Learning and its Clinical Applications: A Review
• Vector Magnetic Current Imaging of an 8 nm Process Node Chip and 3D Current Distributions Using the Quantum Diamond Microscope
• Deep Learning for Biomedical Image Reconstruction: A Survey
• Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction
• Inverse problems on low-dimensional manifolds
• Consensus Neural Network for Medical Imaging Denoising with Only Noisy Training Samples
• End-to-end reconstruction meets data-driven regularization for inverse problems
• Y-Net: A Hybrid Deep Learning Reconstruction Framework for Photoacoustic Imaging in vivo
• WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
• Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
• PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction
• Dual Network Architecture for Few-view CT -- Trained on ImageNet Data and Transferred for Medical Imaging
• Conditional Injective Flows for Bayesian Imaging
• Machine Learning for Improved Current Density Reconstruction from 2D Vector Magnetic Images
• Signal retrieval with measurement system knowledge using variational generative model
• Investigating the Use of Traveltime and Reflection Tomography for Deep Learning-Based Sound-Speed Estimation in Ultrasound Computed Tomography
• Efficient Physics-Based Learned Reconstruction Methods for Real-Time 3D Near-Field MIMO Radar Imaging
• Universal Deep Beamformer for Variable Rate Ultrasound Imaging
• Interval Neural Networks: Uncertainty Scores
• Fidelity Imposed Network Edit (FINE) for Solving Ill-Posed Image Reconstruction
• End-to-end Memory-Efficient Reconstruction for Cone Beam CT
• Semi-Blind Source Separation with Learned Constraints
• Unrolled Optimization with Deep Learning-based Priors for Phaseless Inverse Scattering Problems
• Efficient and Generic 1D Dilated Convolution Layer for Deep Learning
• Deep Learning Techniques for Inverse Problems in Imaging
• A Compound Gaussian Least Squares Algorithm and Unrolled Network for Linear Inverse Problems
• Theoretical Interpretation of Learned Step Size in Deep-Unfolded Gradient Descent
• Learned Interferometric Imaging for the SPIDER Instrument
• Improving image quality of sparse-view lung tumor CT images with U-Net
• On the Contractivity of Plug-and-Play Operators
• Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learning
• An unsupervised deep learning framework for medical image denoising
• LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT
• Learned Cone-Beam CT Reconstruction Using Neural Ordinary Differential Equations
• Plug-and-Play Algorithms for Video Snapshot Compressive Imaging
• Reciprocal Translation between SAR and Optical Remote Sensing Images with Cascaded-Residual Adversarial Networks
• Noise-robust latent vector reconstruction in ptychography using deep generative models
• A Dataset-free Deep learning Method for Low-Dose CT Image Reconstruction
• LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CT
• Learned SVD: solving inverse problems via hybrid autoencoding
• Deep Learning Reconstruction for 9-View Dual Energy CT Baggage Scanner
• Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction
• ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
• Deep synthesis regularization of inverse problems
• A Multimodal Deep Network for the Reconstruction of T2W MR Images
• Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery
• InverseNet: Solving Inverse Problems with Splitting Networks
• Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learning
• Investigating the robustness of a learning-based method for quantitative phase retrieval from propagation-based x-ray phase contrast measurements under laboratory conditions
• Improving Automated Hemorrhage Detection in Sparse-view Computed Tomography via Deep Convolutional Neural Network based Artifact Reduction
• Sparse-View Spectral CT Reconstruction Using Deep Learning
• Invertible residual networks in the context of regularization theory for linear inverse problems
• NETT Regularization for Compressed Sensing Photoacoustic Tomography
• MRI Reconstruction with Regularized 3D Diffusion Model (R3DM)
• Posterior Estimation Using Deep Learning: A Simulation Study of Compartmental Modeling in Dynamic PET
• Convex Regularization Behind Neural Reconstruction
• Experimental design for MRI by greedy policy search
• Towards smart optical focusing: Deep learning-empowered wavefront shaping in nonstationary scattering media
• Sinogram interpolation for sparse-view micro-CT with deep learning neural network
• 3D Deep Learning Enables Fast Imaging of Spines through Scattering Media by Temporal Focusing Microscopy
• Visual Physics: Discovering Physical Laws from Videos
• Limited View Tomographic Reconstruction Using a Deep Recurrent Framework with Residual Dense Spatial-Channel Attention Network and Sinogram Consistency
• A Lightweight Structure Aimed to Utilize Spatial Correlation for Sparse-View CT Reconstruction
• Hybrid Self-Attention NEAT: A novel evolutionary approach to improve the NEAT algorithm
• Contrastive Learning for Local and Global Learning MRI Reconstruction
• PgNN: Physics-guided Neural Network for Fourier Ptychographic Microscopy
• Deep Shape from Polarization
• Machine Friendly Machine Learning: Interpretation of Computed Tomography Without Image Reconstruction
• Efficient B-mode Ultrasound Image Reconstruction from Sub-sampled RF Data using Deep Learning
• Momentum-Net for Low-Dose CT Image Reconstruction
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction
• Random mesh projectors for inverse problems
• Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction
• Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems
• Deep-learning Image Reconstruction for Real-time Photoacoustic System
• Self-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks
• Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging
• Extreme Few-view CT Reconstruction using Deep Inference
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
• DIVA: Deep Unfolded Network from Quantum Interactive Patches for Image Restoration
• Feasibility-based Fixed Point Networks
• NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network
• Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography
• Enhancing Brain Source Reconstruction by Initializing 3D Neural Networks with Physical Inverse Solutions
• Bayesian Reasoning with Trained Neural Networks
• LAMA-Net: A Convergent Network Architecture for Dual-Domain Reconstruction
• Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram
• Compressive-Sensing Data Reconstruction for Structural Health Monitoring: A Machine-Learning Approach
• Deep Learning Techniques for Compressive Sensing-Based Reconstruction and Inference -- A Ubiquitous Systems Perspective
• Unsupervised Spatial-spectral Network Learning for Hyperspectral Compressive Snapshot Reconstruction
• Snapshot Interferometric 3D Imaging by Compressive Sensing and Deep Learning
• Deep learning based low-dose synchrotron radiation CT reconstruction
• Deep Unfolding of a Proximal Interior Point Method for Image Restoration
• AI-Enabled Ultra-Low-Dose CT Reconstruction
• 3D U-NetR: Low Dose Computed Tomography Reconstruction via Deep Learning and 3 Dimensional Convolutions
• Chest X-Ray Bone Suppression for Improving Classification of Tuberculosis-Consistent Findings
• A novel combination of theoretical analysis and data-driven method for reconstruction of structural defects
• Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements
• Unsupervised Learning From Incomplete Measurements for Inverse Problems
• Learning Apparent Diffusion Coefficient Maps from Accelerated Radial k-Space Diffusion-Weighted MRI in Mice using a Deep CNN-Transformer Model
• From Nano to Macro: Overview of the IEEE Bio Image and Signal Processing Technical Committee
• LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT
• Adaptive convolutional neural networks for k-space data interpolation in fast magnetic resonance imaging
• Dynamic imaging using a deep generative SToRM (Gen-SToRM) model
• Solving inverse problems via auto-encoders
• Learning a Probabilistic Strategy for Computational Imaging Sensor Selection
• Representation and reconstruction of covariance operators in linear inverse problems
• Equivariant Imaging: Learning Beyond the Range Space
• Adaptive Local Neighborhood-based Neural Networks for MR Image Reconstruction from Undersampled Data
• On the randomised stability constant for inverse problems
• Differentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal
• Applications of Deep Learning for Ill-Posed Inverse Problems Within Optical Tomography
• Inversion of Integral Models: a Neural Network Approach
• A Fast Deep Learning Approach for Beam Orientation Optimization for Prostate Cancer IMRT Treatments
• Deep Decomposition Learning for Inverse Imaging Problems
• Inverse Aerodynamic Design of Gas Turbine Blades using Probabilistic Machine Learning
• Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
• Deep-learning inversion: a next generation seismic velocity-model building method
• Learning to Reconstruct Crack Profiles for Eddy Current Nondestructive Testing
• MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction
• Data-Driven Theory-guided Learning of Partial Differential Equations using SimultaNeous Basis Function Approximation and Parameter Estimation (SNAPE)
• IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI
• Magnetic Resonance Parameter Mapping using Self-supervised Deep Learning with Model Reinforcement
• Scaling Up Bayesian Uncertainty Quantification for Inverse Problems using Deep Neural Networks
• Machine Learning aided k-t SENSE for fast reconstruction of highly accelerated PCMR data
• Learning the geometry of wave-based imaging
• Stabilizing Deep Tomographic Reconstruction
• Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies
• Joint ptycho-tomography with deep generative priors
• A two-stage approach for beam hardening artifact reduction in low-dose dental CBCT
• Equivariant neural networks for inverse problems
• Deep learning using a biophysical model for Robust and Accelerated Reconstruction (RoAR) of quantitative and artifact-free R2* images
• Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation
• Seeing through a Black Box: Toward High-Quality Terahertz TomographicImaging via Multi-Scale Spatio-Spectral Image Fusion
• Current Advances in Computational Lung Ultrasound Imaging: A Review
• Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction
• Learned SIRT for Cone Beam Computed Tomography Reconstruction
• Deep learning based dictionary learning and tomographic image reconstruction
• Learning-based Motion Artifact Removal Networks (LEARN) for Quantitative $R_2^{\ast }$ Mapping
• A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods
• Regularization of Inverse Problems: Deep Equilibrium Models versus Bilevel Learning
• Improved low-count quantitative PET reconstruction with an iterative neural network
• Learning Schatten--von Neumann Operators
• Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction
• Stability Bounds for the Unfolded Forward-Backward Algorithm
• Fisher information flow in artificial neural networks
• Assessment of Deep-Learning Methods for the Enhancement of Experimental Low Dose Dental CBCT Volumes
• Low Photon Budget Phase Retrieval with Perceptual Loss Trained Deep Neural Networks
• Dynamic Imaging using Deep Bi-linear Unsupervised Regularization (DEBLUR)
• Bayesian Convolutional Neural Networks for Compressed Sensing Restoration
• Improving Generalization of Sequence Encoder-Decoder Networks for Inverse Imaging of Cardiac Transmembrane Potential
• Spectrally Consistent UNet for High Fidelity Image Transformations
• Stability of Scattering Decoder For Nonlinear Diffractive Imaging
• MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
• Deep Learning-based Low-dose Tomography Reconstruction with Hybrid-dose Measurements
• Learning Priors in High-frequency Domain for Inverse Imaging Reconstruction
• SUPER Learning: A Supervised-Unsupervised Framework for Low-Dose CT Image Reconstruction
• A hierarchical approach to deep learning and its application to tomographic reconstruction
• Distribution Conditional Denoising: A Flexible Discriminative Image Denoiser
• Reconstructing unseen modalities and pathology with an efficient Recurrent Inference Machine
• Estimating Adsorption Isotherm Parameters in Chromatography via a Virtual Injection Promoting Feed-forward Neural Network
• UVTomo-GAN: An adversarial learning based approach for unknown view X-ray tomographic reconstruction
• Core shell NaErF4 at NaYF4 upconversion nanoparticles qualify a NIR speckle wavemeter by a visible CCD
• Structurally Adaptive Multi-Derivative Regularization for Image Recovery from Sparse Fourier Samples
• Intelligent Metasurface Imager and Recognizer
• AHP-Net: adaptive-hyper-parameter deep learning based image reconstruction method for multilevel low-dose CT
• High-quality Low-dose CT Reconstruction Using Convolutional Neural Networks with Spatial and Channel Squeeze and Excitation
• AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry
• A Lightweight Solution of Industrial Computed Tomography with Convolutional Neural Network
• Experimental digital Gabor hologram rendering by a model-trained convolutional neural network
• Deep Inertia $L_p$ Half-Quadratic Splitting Unrolling Network for Sparse View CT Reconstruction
• Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Data
• Do CNNs solve the CT inverse problem?
• Error Control and Loss Functions for the Deep Learning Inversion of Borehole Resistivity Measurements
• DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems
• Unsupervised Adaptive Neural Network Regularization for Accelerated Radial Cine MRI
• Sparse View Tomographic Reconstruction of Elongated Objects using Learned Primal-Dual Networks
• Equivariant plug-and-play image reconstruction
• Model-Aware Regularization For Learning Approaches To Inverse Problems
• A model-guided deep network for limited-angle computed tomography
• A Residual Solver and Its Unfolding Neural Network for Total Variation Regularized Models
• Two-layer Residual Sparsifying Transform Learning for Image Reconstruction
• Compressive Sampling for Array Cameras
• Reconstruction for Diverging-Wave Imaging Using Deep Convolutional Neural Networks
• An Adversarial Learning Based Approach for Unknown View Tomographic Reconstruction
• Scalable Double Regularization for 3D Nano-CT Reconstruction
• An Online Deep Learning Approach Toward the Prediction of Power System Stresses Using Voltage Phasors
• A cascaded dual-domain deep learning reconstruction method for sparsely spaced multidetector helical CT
• High speed and reconfigurable optronic neural network with digital nonlinear activation
• Unsupervised Hyperspectral Mixed Noise Removal Via Spatial-Spectral Constrained Deep Image Prior
• Inverse Problem of Nonlinear Schrödinger Equation as Learning of Convolutional Neural Network
• Deep Learning for the Approximation of a Shape Functional
• Robust lEarned Shrinkage-Thresholding (REST): Robust unrolling for sparse recover
• Learning convex regularizers satisfying the variational source condition for inverse problems
• Fast Super-resolution 3D SAR Imaging Using an Unfolded Deep Network
• Manifold learning-based feature extraction for structural defect reconstruction
• Physics-based Learned Design: Optimized Coded-Illumination for Quantitative Phase Imaging