Dense Dilated UNet: Deep Learning for 3D Photoacoustic Tomography Image Reconstruction

Abstract

In photoacoustic tomography (PAT), the acoustic pressure waves produced by optical excitation are measured by an array of detectors and used to reconstruct an image. Sparse spatial sampling and limited-view detection are two common challenges faced in PAT. Reconstructing from incomplete data using standard methods results in severe streaking artifacts and blurring. We propose a modified convolutional neural network (CNN) architecture termed Dense Dilation UNet (DD-UNet) for correcting artifacts in 3D PAT. The DD-Net leverages the benefits of dense connectivity and dilated convolutions to improve CNN performance. We compare the proposed CNN in terms of image quality as measured by the multiscale structural similarity index metric to the Fully Dense UNet (FD-UNet). Results demonstrate that the DD-Net consistently outperforms the FD-UNet and is able to more reliably reconstruct smaller image features.

References in corpus (11)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Densely Connected Convolutional Networks
• Training Very Deep Networks
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal
• Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
• Model based learning for accelerated, limited-view 3D photoacoustic tomography
• Dilated Residual Networks
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• Joint Reconstruction of Absorbed Optical Energy Density and Sound Speed Distribution in Photoacoustic Computed Tomography: A numerical Investigation
• Deep learning for photoacoustic imaging: a survey
• Full-Wave Iterative Image Reconstruction in Photoacoustic Tomography with Acoustically Inhomogeneous Media