High-resolution photoacoustic microscopy with deep penetration through learning

• DOI: 10.1016/j.pacs.2021.100314
• Publication Date: 2021-11-03T08:27:32Z
• Authors: Shengfu Cheng; Yingying Zhou; Jiangbo Chen; Huanhao Li; Lidai Wang; Puxiang Lai
• Keywords: Generative adversarial network

Optical-resolution photoacoustic microscopy (OR-PAM) enjoys superior spatial resolution and has received intense attention in recent years. The application, however, been limited to shallow depths because of strong scattering light biological tissues. In this work, we propose achieve deep-penetrating OR-PAM performance by using deep learning enabled image transformation on blurry living mouse vascular images that were acquired with an acoustic-resolution (AR-PAM) setup. A generative adversarial network (GAN) was trained study improved the imaging lateral AR-PAM from 54.0 µm 5.1 µm, comparable a typical (4.7 µm). feasibility evaluated ear data, producing microvasculature outperforms blind deconvolution. generalization validated vivo brain data. Moreover, it shown experimentally deep-learning method can retain high at tissue beyond one optical transport mean free path. Whilst be further improved, proposed provides new horizons expand scope towards deep-tissue wide applications biomedicine.