Application of deep learning to improve tangential resolution in photoacoustic tomography

Abstract

In circular scanning geometry based Photoacoustic tomographic (PAT) imaging systems, the axial resolution is spatially invariant and is limited by the bandwidth of the detector. However, the tangential resolution is spatially varying and is dependent on the aperture size of the detector. Conventionally, large aperture size detectors are the preferred choice for detection element in circular view PAT imaging systems but it hampers the tangential resolution. Although several techniques have been proposed to improve the tangential resolution, they are also hindered by their inherent limitations. Herein, we propose a deep learning architecture to counter the spatially variant tangential resolution in circular scanning PAT.We used a (U-Net) based CNN architecture to improve the tangential resolution of the acquired PAT images. Our results suggest the proposed deep learning architecture improves the tangential resolution of the acquired by five folds, without compromising the image quality.