DensePANet: An improved generative adversarial network for photoacoustic tomography image reconstruction from sparse data

TL;DR

DensePANet is a novel GAN-based approach that significantly improves photoacoustic tomography image reconstruction from sparse data, utilizing a modified UNet architecture for enhanced performance.

Contribution

The paper introduces DensePANet with a new FD-UNet++ generator, advancing deep learning methods for sparse PAT image reconstruction.

Findings

Outperforms existing deep learning techniques in reconstruction quality

Effective on both in-vivo and simulated datasets

Reduces artifacts in sparse data reconstructions

Abstract

Image reconstruction is an essential step of every medical imaging method, including Photoacoustic Tomography (PAT), which is a promising modality of imaging, that unites the benefits of both ultrasound and optical imaging methods. Reconstruction of PAT images using conventional methods results in rough artifacts, especially when applied directly to sparse PAT data. In recent years, generative adversarial networks (GANs) have shown a powerful performance in image generation as well as translation, rendering them a smart choice to be applied to reconstruction tasks. In this study, we proposed an end-to-end method called DensePANet to solve the problem of PAT image reconstruction from sparse data. The proposed model employs a novel modification of UNet in its generator, called FD-UNet++, which considerably improves the reconstruction performance. We evaluated the method on various in-vivo and simulated datasets. Quantitative and qualitative results show the better performance of our model over other prevalent deep learning techniques.