NETT regularization for compressed sensing photoacoustic tomography

We discuss several methods for image reconstruction in compressed sensing photoacoustic tomography (CS-PAT). In particular, we apply the deep learning method of [H. Li, J. Schwab, S. Antholzer, and M. Haltmeier. NETT: Solving Inverse Problems with Deep Neural Networks (2018), arXiv:1803.00092], which is based on a learned regularizer, for the first time to the CS-PAT problem. We propose a network architecture and training strategy for the NETT that we expect to be useful for other inverse problems as well. All algorithms are compared and evaluated on simulated data, and validated using experimental data for two different types of phantoms. The results one the hand indicate great potential of deep learning methods, and on the other hand show that significant future work is required to improve their performance on real-word data.

[1]  Jong Chul Ye,et al.  Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis , 2016, ArXiv.

[2]  M. Haltmeier,et al.  Temporal back-projection algorithms for photoacoustic tomography with integrating line detectors , 2007 .

[3]  Mark A. Anastasio,et al.  Deep Learning-Guided Image Reconstruction from Incomplete Data , 2017, ArXiv.

[4]  Patrick L. Combettes,et al.  Proximal Splitting Methods in Signal Processing , 2009, Fixed-Point Algorithms for Inverse Problems in Science and Engineering.

[5]  Stephan Antholzer,et al.  NETT: solving inverse problems with deep neural networks , 2018, Inverse Problems.

[6]  Stephan Antholzer,et al.  Deep learning for photoacoustic tomography from sparse data , 2017, Inverse problems in science and engineering.

[7]  Markus Haltmeier,et al.  Inversion of Spherical Means and the Wave Equation in Even Dimensions , 2007, SIAM J. Appl. Math..

[8]  Markus Haltmeier,et al.  Sampling Conditions for the Circular Radon Transform , 2016, IEEE Transactions on Image Processing.

[9]  Thomas Pock,et al.  Variational Networks: Connecting Variational Methods and Deep Learning , 2017, GCPR.

[10]  Heinz H. Bauschke,et al.  Fixed-Point Algorithms for Inverse Problems in Science and Engineering , 2011, Springer Optimization and Its Applications.

[11]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[12]  Markus Haltmeier,et al.  Compressed sensing and sparsity in photoacoustic tomography , 2016, 1605.09249.

[13]  Andreas Hauptmann,et al.  Model-Based Learning for Accelerated, Limited-View 3-D Photoacoustic Tomography , 2017, IEEE Transactions on Medical Imaging.

[14]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[15]  Stephan Antholzer,et al.  Deep null space learning for inverse problems: convergence analysis and rates , 2018, Inverse Problems.

[16]  Janek Gröhl,et al.  Reconstruction of initial pressure from limited view photoacoustic images using deep learning , 2018, BiOS.

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Jonas Adler,et al.  Learned Primal-Dual Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[19]  Istvan A. Veres,et al.  Photoacoustic projection imaging using a 64-channel fiber optic detector array , 2015, Photonics West - Biomedical Optics.

[20]  Hu Chen,et al.  Low-dose CT via convolutional neural network. , 2017, Biomedical optics express.

[21]  Stephan Antholzer,et al.  Deep Learning Versus $\ell^{1}$ -Minimization for Compressed Sensing Photoacoustic Tomography , 2018, 2018 IEEE International Ultrasonics Symposium (IUS).

[22]  Markus Haltmeier,et al.  Photoacoustic tomography using a Mach-Zehnder interferometer as an acoustic line detector. , 2007, Applied optics.

[23]  Guenther Paltauf,et al.  64-line-sensor array: fast imaging system for photoacoustic tomography , 2014, Photonics West - Biomedical Optics.

[24]  O. Scherzer,et al.  Necessary and sufficient conditions for linear convergence of ℓ1‐regularization , 2011 .

[25]  Markus Haltmeier,et al.  A sparsification and reconstruction strategy for compressed sensing photoacoustic tomography. , 2017, The Journal of the Acoustical Society of America.

[26]  Thomas Berer,et al.  All-optical photoacoustic projection imaging. , 2017, Biomedical optics express.

[27]  Marta Betcke,et al.  Accelerated high-resolution photoacoustic tomography via compressed sensing , 2016, Physics in medicine and biology.

[28]  Stephan Antholzer,et al.  Big in Japan: Regularizing Networks for Solving Inverse Problems , 2018, Journal of Mathematical Imaging and Vision.

[29]  Stephan Antholzer,et al.  Real-time photoacoustic projection imaging using deep learning , 2018, 1801.06693.

[30]  Robert Nuster,et al.  Piezoelectric line detector array for photoacoustic tomography , 2017, Photoacoustics.

[31]  慧 廣瀬.  A Mathematical Introduction to Compressive Sensing , 2015 .

[32]  Markus Haltmeier,et al.  A Novel Compressed Sensing Scheme for Photoacoustic Tomography , 2015, SIAM J. Appl. Math..

[33]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[34]  Stephan Antholzer,et al.  Photoacoustic image reconstruction via deep learning , 2018, BiOS.