Abstract

Methods have been proposed in recent years aimed at pushing photoacoustic imaging resolution beyond the acoustic diffraction limit, among which those based on random speckle illumination show particular promise. In this Letter, we propose a data-driven deep learning approach to processing the added spatiotemporal information resulting from speckle illumination, where the neural network learns the distribution of absorbers from a series of different samplings of the imaged area. In ex-vivo experiments based on the tomography configuration with prominent artifacts, our method successfully breaks the acoustic diffraction limit and delivers better results in identifying individual targets when compared against a selection of other leading methods.

© 2024 Optica Publishing Group

Super-resolution photoacoustic fluctuation imaging with multiple speckle illumination

Thomas Chaigne, Jérôme Gateau, Marc Allain, Ori Katz, Sylvain Gigan, Anne Sentenac, and Emmanuel Bossy
Optica 3(1) 54-57 (2016)

Untrained neural network enabling fast and universal structured-illumination microscopy

Zitong Ye, Xiaoyan Li, Yile Sun, Yuran Huang, Xu Liu, Yubing Han, and Cuifang Kuang
Opt. Lett. 49(9) 2205-2208 (2024)

Sub-Nyquist sampling-based high-frequency photoacoustic computed tomography

Songde Liu, Chenxi Zhang, Junyi Zhang, Xingyang Liu, Benpeng Zhu, and Chao Tian
Opt. Lett. 49(7) 1648-1651 (2024)

Label-free STORM principle realized by super-Rayleigh speckle in photoacoustic imaging

Penghuan Liu
Opt. Lett. 44(19) 4642-4645 (2019)

High-frequency surface-micromachined optical ultrasound transducer array for 3D micro photoacoustic computed tomography

Zhiyu Yan and Jun Zou
Opt. Lett. 49(5) 1181-1184 (2024)