Deep learning for photoacoustic tomography from sparse data
From MaRDI portal
convolutional neural networksdeep learningimage reconstructioninverse problemsphotoacoustic tomographysparse data
Inverse problems for integral equations (45Q05) Neural nets and related approaches to inference from stochastic processes (62M45) Numerical methods for inverse problems for integral equations (65R32) Learning and adaptive systems in artificial intelligence (68T05) Biomedical imaging and signal processing (92C55) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Abstract: The development of fast and accurate image reconstruction algorithms is a central aspect of computed tomography. In this paper, we investigate this issue for the sparse data problem in photoacoustic tomography (PAT). We develop a direct and highly efficient reconstruction algorithm based on deep learning. In our approach image reconstruction is performed with a deep convolutional neural network (CNN), whose weights are adjusted prior to the actual image reconstruction based on a set of training data. The proposed reconstruction approach can be interpreted as a network that uses the PAT filtered backprojection algorithm for the first layer, followed by the U-net architecture for the remaining layers. Actual image reconstruction with deep learning consists in one evaluation of the trained CNN, which does not require time consuming solution of the forward and adjoint problems. At the same time, our numerical results demonstrate that the proposed deep learning approach reconstructs images with a quality comparable to state of the art iterative approaches for PAT from sparse data.
Recommendations
- Computed tomography reconstruction using deep image prior and learned reconstruction methods
- A Galerkin least squares approach for photoacoustic tomography
- Efficient regularization with wavelet sparsity constraints in photoacoustic tomography
- Single-stage reconstruction algorithm for quantitative photoacoustic tomography
- Iterative methods for photoacoustic tomography in attenuating acoustic media
Cites work
- A direct method for photoacoustic tomography with inhomogeneous sound speed
- A Galerkin least squares approach for photoacoustic tomography
- A mollification approach for inverting the spherical mean Radon transform
- A novel compressed sensing scheme for photoacoustic tomography
- A series solution and a fast algorithm for the inversion of the spherical mean Radon transform
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Analysis of bounded variation penalty methods for ill-posed problems
- Analysis of Iterative Methods in Photoacoustic Tomography with Variable Sound Speed
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Deep learning
- Determining a Function from Its Mean Values Over a Family of Spheres
- Efficient regularization with wavelet sparsity constraints in photoacoustic tomography
- Explicit inversion formulae for the spherical mean Radon transform
- Fourier reconstruction in optoacoustic imaging using truncated regularized inverse k -space interpolation
- Inversion of circular means and the wave equation on convex planar domains
- Inversion of Spherical Means and the Wave Equation in Even Dimensions
- Iterative Methods for Total Variation Denoising
- Mathematics of photoacoustic and thermoacoustic tomography
- Natural language processing (almost) from scratch
- On steepest-descent-Kaczmarz methods for regularizing systems of nonlinear ill-posed equations
- On the adjoint operator in photoacoustic tomography
- Operator learning approach for the limited view problem in photoacoustic tomography
- Pattern recognition and machine learning.
- Reconstruction and time reversal in thermoacoustic tomography in acoustically homogeneous and inhomogeneous media
- Sampling Conditions for the Circular Radon Transform
- Sparsity in inverse geophysical problems
- Temporal back-projection algorithms for photoacoustic tomography with integrating line detectors
- The mathematics of computerized tomography
- Thermoacoustic tomography with variable sound speed
- Uniqueness of reconstruction and an inversion procedure for thermoacoustic and photoacoustic tomography with variable sound speed
- Universal inversion formulas for recovering a function from spherical means
- Variational methods in imaging
Cited in
(28)- Image decomposition algorithm for dual-energy computed tomography via fully convolutional network
- Big in Japan: regularizing networks for solving inverse problems
- Networks for nonlinear diffusion problems in imaging
- A data and knowledge driven approach for SPECT using convolutional neural networks and iterative algorithms
- Learning to scan: a deep reinforcement learning approach for personalized scanning in CT imaging
- Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
- On the randomised stability constant for inverse problems
- LU-Net: combining LSTM and U-Net for sinogram synthesis in sparse-view SPECT reconstruction
- A review on deep learning in medical image reconstruction
- Data-consistent neural networks for solving nonlinear inverse problems
- A Galerkin least squares approach for photoacoustic tomography
- NETT: solving inverse problems with deep neural networks
- A Data-Driven Iteratively Regularized Landweber Iteration
- Numerical solution of inverse problems by weak adversarial networks
- Biomedical image reconstruction: from the foundations to deep neural networks
- On learned operator correction in inverse problems
- Compressed sensing photoacoustic tomography reduces to compressed sensing for undersampled Fourier measurements
- Unsupervised knowledge-transfer for learned image reconstruction
- Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
- Sampling type method combined with deep learning for inverse scattering with one incident wave
- Learn an index operator by CNN for solving diffusive optical tomography: a deep direct sampling method
- Utilizing Variational Autoencoders in the Bayesian Inverse Problem of Photoacoustic Tomography
- On Learning the Invisible in Photoacoustic Tomography with Flat Directionally Sensitive Detector
- Normalizing flow regularization for photoacoustic tomography
- Stability bounds for the unfolded forward-backward algorithm
- A modulus iteration method for nonnegatively constrained photoacoustic image reconstruction
- The method of the approximate inverse for limited-angle CT
- Neural networks for Bayesian inverse problems governed by a nonlinear ODE
This page was built for publication: Deep learning for photoacoustic tomography from sparse data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4990712)
