Deep learning versus ${\ell }^1$-minimization for compressed sensing photoacoustic tomography

Abstract

We investigate compressed sensing (CS) techniques for reducing the number of measurements in photoacoustic tomography (PAT). High resolution imaging from CS data requires particular image reconstruction algorithms. The most established reconstruction techniques for that purpose use sparsity and ${\ell }^1$-minimization. Recently, deep learning appeared as a new paradigm for CS and other inverse problems. In this paper, we compare a recently invented joint ${\ell }^1$-minimization algorithm with two deep learning methods, namely a residual network and an approximate nullspace network. We present numerical results showing that all developed techniques perform well for deterministic sparse measurements as well as for random Bernoulli measurements. For the deterministic sampling, deep learning shows more accurate results, whereas for Bernoulli measurements the ${\ell }^1$-minimization algorithm performs best. Comparing the implemented deep learning approaches, we show that the nullspace network uniformly outperforms the residual network in terms of the mean squared error (MSE).

This work has been presented at the Joint Photoacoustics Session with the 2018 IEEE International Ultrasonics Symposium Kobe, October 22-25, 2018

References in corpus (7)

• Model based learning for accelerated, limited-view 3D photoacoustic tomography
• Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Deep Learning-Guided Image Reconstruction from Incomplete Data
• Photoacoustic image reconstruction via deep learning
• A New Sparsification and Reconstruction Strategy for Compressed Sensing Photoacoustic Tomography
• Real-time photoacoustic projection imaging using deep learning

Cited by in corpus (6)

• Deep learning for biomedical photoacoustic imaging: A review
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• Limited View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning
• Deep learning for photoacoustic imaging: a survey
• Simultaneous reconstruction of the initial pressure and sound speed in photoacoustic tomography using a deep-learning approach
• NETT Regularization for Compressed Sensing Photoacoustic Tomography