Resolution Enhancement of Under-Sampled Photoacoustic Microscopy Images Using Neural Representation

Abstract

Acoustic-Resolution Photoacoustic Microscopy (AR-PAM) has demonstrated great potential in subcutaneous vascular imaging. However, its spatial resolution is limited by the system's Point Spread Function (PSF). To enhance resolution, various deconvolution-based methods can be employed. Traditional deconvolution methods, such as Richardson-Lucy deconvolution and model-based deconvolution, typically use the PSF as prior knowledge to improve spatial resolution. However, accurately measuring the system's PSF is challenging, leading to the widespread adoption of low vision deconvolution methods, which often suffer from inaccurate deconvolution. Another major challenge of AR-PAM is the long scanning time. To accelerate image acquisition, downsampling can be applied to reduce scanning time. Subsequently, interpolation methods are commonly used to recover high-resolution images from the downsampled measurements. However, conventional interpolation methods struggle to achieve high-fidelity image recovery, particularly under high downsampling conditions. In this study, we propose a method based on Implicit Neural Representations (INR) to simultaneously address the challenges of unknown PSF and under-sampled image recovery. By leveraging INR, we learn a continuous mapping from spatial positions to initial acoustic pressure, effectively compensating for the discretization of the image space and enhancing the resolution of AR-PAM. Specifically, we treat the PSF as a learnable parameter to mitigate inaccuracies in PSF measurement. We qualitatively and quantitatively evaluated the proposed method on leaf vein data, mouse brain data, and real in vivo AR-PAM data, demonstrating superior performance compared to existing methods in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM).