Finite-element reconstruction of 2D circular scanning photoacoustic tomography with detectors in far-field condition

Optical resolution photoacoustic computed microscopy

Optical resolution photoacoustic microscopy (ORPAM) has demonstrated both high resolution and rich contrast imaging of optical chromophores in biologic tissues. To date, sensitivity remains a major challenge for ORPAM, which limits the capability of resolving biologic microvascular networks. In this study, we propose and evaluate a new ORPAM modality termed as optical resolution photoacoustic computed microscopy (ORPACM), through the combination of a two-dimensional laser-scanning system with a medical ultrasonographic platform. Apart from conventional ORPAMs, we record multiple photoacoustic (PA) signals using a 128-element ultrasonic transducer array for each pulse excitation. Then, we apply a reconstruction algorithm to recover one depth-resolved PA signal referred to as an A-line, which reveals more detailed information compared with conventional single-element transducer-based ORPAMs. In addition, we carried out both in vitro and in vivo experiments as well as quantitative analyses to show the advanced features of ORPACM.

Deep-Learning Image Reconstruction for Real-Time Photoacoustic System

Recent advances in photoacoustic (PA) imaging have enabled detailed images of microvascular structure and quantitative measurement of blood oxygenation or perfusion. Standard reconstruction methods for PA imaging are based on solving an inverse problem using appropriate signal and system models. For handheld scanners, however, the ill-posed conditions of limited detection view and bandwidth yield low image contrast and severe structure loss in most instances. In this paper, we propose a practical reconstruction method based on a deep convolutional neural network (CNN) to overcome those problems. It is designed for real-time clinical applications and trained by large-scale synthetic data mimicking typical microvessel networks. Experimental results using synthetic and real datasets confirm that the deep-learning approach provides superior reconstructions compared to conventional methods.