Pixel-wise deep learning for improving image reconstruction in photoacoustic tomography

Abstract

Photoacoustic tomography involves absorption of pulsed light and subsequent generation of ultrasound, which when detected using an array of sensors can produce clinically useful images. Practical considerations limit the number of sensors and their “view” of the region of interest (ROI), which can result in significant reconstruction artifacts. Iterative-reconstruction methods can improve image quality but are computationally expensive. Another approach to improve reconstructed images is to use convolution neural networks (CNN) as a post-processing step for removing artifacts. However, missing or heavily obscured features typically cannot be recovered using this approach. We present a new pixel-wise deep learning (PDL) approach that employs pixel-wise interpolation to window ROI-specific raw photoacoustic data and then directly performs the image reconstruction within the CNN framework. The utility of this approach was demonstrated on simulated photoacoustic data from a 64-element semi-circular sensor array. The training and testing datasets comprised of 500 images from a synthetic vasculature phantom and 50 images of an anatomically realistic vasculature obtained from micro-CT images, respectively. The structural similarity index of the PDL-reconstructed images (0.91 ± 0.03) indicated superior image quality compared to those obtained using the iterative reconstruction (0.82 ± 0.09) and CNN-based artifact removal (0.79 ± 0.07).