Deep learning for photoacoustic tomography from sparse data
From MaRDI portal
Publication:4990712
DOI10.1080/17415977.2018.1518444zbMATH Open1465.94008arXiv1704.04587OpenAlexW2962850795WikidataQ64322970 ScholiaQ64322970MaRDI QIDQ4990712FDOQ4990712
Authors: Stephan Antholzer, Markus Haltmeier, Johannes Schwab 
Publication date: 31 May 2021
Published in: Inverse Problems in Science and Engineering (Search for Journal in Brave)
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.
Full work available at URL: https://arxiv.org/abs/1704.04587
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
deep learninginverse problemsimage reconstructionsparse dataconvolutional neural networksphotoacoustic tomography
Learning and adaptive systems in artificial intelligence (68T05) Neural nets and related approaches to inference from stochastic processes (62M45) Biomedical imaging and signal processing (92C55) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Inverse problems for integral equations (45Q05) Numerical methods for inverse problems for integral equations (65R32)
Cites Work
- Pattern recognition and machine learning.
- Deep learning
- The mathematics of computerized tomography
- Explicit inversion formulae for the spherical mean Radon transform
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Determining a Function from Its Mean Values Over a Family of Spheres
- Thermoacoustic tomography with variable sound speed
- Inversion of Spherical Means and the Wave Equation in Even Dimensions
- A series solution and a fast algorithm for the inversion of the spherical mean Radon transform
- Variational methods in imaging
- Analysis of bounded variation penalty methods for ill-posed problems
- Iterative Methods for Total Variation Denoising
- Universal inversion formulas for recovering a function from spherical means
- On steepest-descent-Kaczmarz methods for regularizing systems of nonlinear ill-posed equations
- Reconstruction and time reversal in thermoacoustic tomography in acoustically homogeneous and inhomogeneous media
- Uniqueness of reconstruction and an inversion procedure for thermoacoustic and photoacoustic tomography with variable sound speed
- Temporal back-projection algorithms for photoacoustic tomography with integrating line detectors
- Mathematics of photoacoustic and thermoacoustic tomography
- A direct method for photoacoustic tomography with inhomogeneous sound speed
- On the adjoint operator in photoacoustic tomography
- A Galerkin least squares approach for photoacoustic tomography
- Natural language processing (almost) from scratch
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- A mollification approach for inverting the spherical mean Radon transform
- Analysis of Iterative Methods in Photoacoustic Tomography with Variable Sound Speed
- A novel compressed sensing scheme for photoacoustic tomography
- Inversion of circular means and the wave equation on convex planar domains
- Sampling Conditions for the Circular Radon Transform
- Operator learning approach for the limited view problem in photoacoustic tomography
- Sparsity in inverse geophysical problems
- Efficient regularization with wavelet sparsity constraints in photoacoustic tomography
- Fourier reconstruction in optoacoustic imaging using truncated regularized inverse k -space interpolation
Cited In (24)
- Big in Japan: regularizing networks for solving inverse problems
- Networks for nonlinear diffusion problems in imaging
- Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
- Utilizing Variational Autoencoders in the Bayesian Inverse Problem of Photoacoustic Tomography
- On the randomised stability constant for inverse problems
- LU-Net: combining LSTM and U-Net for sinogram synthesis in sparse-view SPECT reconstruction
- Image decomposition algorithm for dual-energy computed tomography via fully convolutional network
- On Learning the Invisible in Photoacoustic Tomography with Flat Directionally Sensitive Detector
- Sampling type method combined with deep learning for inverse scattering with one incident wave
- Compressed sensing photoacoustic tomography reduces to compressed sensing for undersampled Fourier measurements
- Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
- A data and knowledge driven approach for SPECT using convolutional neural networks and iterative algorithms
- Unsupervised knowledge-transfer for learned image reconstruction
- Normalizing flow regularization for photoacoustic tomography
- Biomedical image reconstruction: from the foundations to deep neural networks
- Learn an index operator by CNN for solving diffusive optical tomography: a deep direct sampling method
- Learning to scan: a deep reinforcement learning approach for personalized scanning in CT imaging
- A review on deep learning in medical image reconstruction
- Data-consistent neural networks for solving nonlinear inverse problems
- A Data-Driven Iteratively Regularized Landweber Iteration
- NETT: solving inverse problems with deep neural networks
- Numerical solution of inverse problems by weak adversarial networks
- On learned operator correction in inverse problems
- A Galerkin least squares approach for photoacoustic tomography
Uses Software
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)
