# Deep Learning for Photoacoustic Tomography from Sparse Data

arXiv: https://arxiv.org/abs/1704.04587 · HTML: https://mlsanity.com/paper/1704.04587/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2017.

## Built on by (most cited first, 17 of 17)

- [Fourier Neural Operator Networks: A Fast and General Solver for the Photoacoustic Wave Equation](https://mlsanity.com/paper/2108.09374/) (2021)
- [Moving beyond simulation: data-driven quantitative photoacoustic imaging using tissue-mimicking phantoms](https://mlsanity.com/paper/2306.06748/) (2023)
- [Utilizing variational autoencoders in the Bayesian inverse problem of photoacoustic tomography](https://mlsanity.com/paper/2204.06270/) (2022)
- [Ptychographic Image Reconstruction from Limited Data via Score-Based Diffusion Models with Physics-Guidance](https://mlsanity.com/paper/2502.18767/) (2025)
- [On Learning the Invisible in Photoacoustic Tomography with Flat Directionally Sensitive Detector](https://mlsanity.com/paper/2204.10001/) (2022)
- [Dense Dilated UNet: Deep Learning for 3D Photoacoustic Tomography Image Reconstruction](https://mlsanity.com/paper/2104.03130/) (2021)
- [Survey of Deep Learning Methods for Inverse Problems](https://mlsanity.com/paper/2111.04731/) (2021)
- [Differentiable Uncalibrated Imaging](https://mlsanity.com/paper/2211.10525/) (2022)
- [Stability Bounds for the Unfolded Forward-Backward Algorithm](https://mlsanity.com/paper/2412.17888/) (2024)
- [Compressed Sensing for Photoacoustic Computed Tomography Using an Untrained Neural Network](https://mlsanity.com/paper/2105.14255/) (2021)
- [Cross-domain Self-supervised Framework for Photoacoustic Computed Tomography Image Reconstruction](https://mlsanity.com/paper/2301.06681/) (2023)
- [Learning end-to-end inversion of circular Radon transforms in the partial radial setup](https://mlsanity.com/paper/2308.14144/) (2023)
- [Design, Implementation and Analysis of a Compressed Sensing Photoacoustic Projection Imaging System](https://mlsanity.com/paper/2402.15750/) (2024)
- [The method of the approximate inverse for limited-angle CT](https://mlsanity.com/paper/2510.04369/) (2025)
- [Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts](https://mlsanity.com/paper/2604.19176/) (2026)
- [Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention](https://mlsanity.com/paper/2607.25576/) (2026)
- [PAGS: Autofocusing Photoacoustic Tomography via Speed-of-Sound-Adaptive Gaussian Splatting](https://mlsanity.com/paper/2608.25472/) (2026)

## Abstract (arXiv)

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.