High-resolution photoacoustic microscopy with deep penetration through learning

Optical-resolution photoacoustic microscopy (OR-PAM) enjoys superior spatial resolution and has received intense attention in recent years. The application, however, has been limited to shallow depths because of strong scattering of light in biological tissues. In this work, we propose to achieve de...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shengfu Cheng, Yingying Zhou, Jiangbo Chen, Huanhao Li, Lidai Wang, Puxiang Lai
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2022
Materias:	Photoacoustic microscopy Deep penetration Deep learning Physics QC1-999 Acoustics. Sound QC221-246 Optics. Light QC350-467
Acceso en línea:	https://doaj.org/article/8a40713c4e134cddb8ff73eaf88118d3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8a40713c4e134cddb8ff73eaf88118d3
record_format	dspace
spelling	oai:doaj.org-article:8a40713c4e134cddb8ff73eaf88118d32021-11-14T04:32:49ZHigh-resolution photoacoustic microscopy with deep penetration through learning2213-597910.1016/j.pacs.2021.100314https://doaj.org/article/8a40713c4e134cddb8ff73eaf88118d32022-03-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2213597921000732https://doaj.org/toc/2213-5979Optical-resolution photoacoustic microscopy (OR-PAM) enjoys superior spatial resolution and has received intense attention in recent years. The application, however, has been limited to shallow depths because of strong scattering of light in biological tissues. In this work, we propose to 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 photoacoustic microscopy (AR-PAM) setup. A generative adversarial network (GAN) was trained in this study and improved the imaging lateral resolution of AR-PAM from 54.0 µm to 5.1 µm, comparable to that of a typical OR-PAM (4.7 µm). The feasibility of the network was evaluated with living mouse ear data, producing superior microvasculature images that outperforms blind deconvolution. The generalization of the network was validated with in vivo mouse brain data. Moreover, it was shown experimentally that the deep-learning method can retain high resolution at tissue depths beyond one optical transport mean free path. Whilst it can be further improved, the proposed method provides new horizons to expand the scope of OR-PAM towards deep-tissue imaging and wide applications in biomedicine.Shengfu ChengYingying ZhouJiangbo ChenHuanhao LiLidai WangPuxiang LaiElsevierarticlePhotoacoustic microscopyDeep penetrationDeep learningPhysicsQC1-999Acoustics. SoundQC221-246Optics. LightQC350-467ENPhotoacoustics, Vol 25, Iss , Pp 100314- (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Photoacoustic microscopy Deep penetration Deep learning Physics QC1-999 Acoustics. Sound QC221-246 Optics. Light QC350-467
spellingShingle	Photoacoustic microscopy Deep penetration Deep learning Physics QC1-999 Acoustics. Sound QC221-246 Optics. Light QC350-467 Shengfu Cheng Yingying Zhou Jiangbo Chen Huanhao Li Lidai Wang Puxiang Lai High-resolution photoacoustic microscopy with deep penetration through learning
description	Optical-resolution photoacoustic microscopy (OR-PAM) enjoys superior spatial resolution and has received intense attention in recent years. The application, however, has been limited to shallow depths because of strong scattering of light in biological tissues. In this work, we propose to 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 photoacoustic microscopy (AR-PAM) setup. A generative adversarial network (GAN) was trained in this study and improved the imaging lateral resolution of AR-PAM from 54.0 µm to 5.1 µm, comparable to that of a typical OR-PAM (4.7 µm). The feasibility of the network was evaluated with living mouse ear data, producing superior microvasculature images that outperforms blind deconvolution. The generalization of the network was validated with in vivo mouse brain data. Moreover, it was shown experimentally that the deep-learning method can retain high resolution at tissue depths beyond one optical transport mean free path. Whilst it can be further improved, the proposed method provides new horizons to expand the scope of OR-PAM towards deep-tissue imaging and wide applications in biomedicine.
format	article
author	Shengfu Cheng Yingying Zhou Jiangbo Chen Huanhao Li Lidai Wang Puxiang Lai
author_facet	Shengfu Cheng Yingying Zhou Jiangbo Chen Huanhao Li Lidai Wang Puxiang Lai
author_sort	Shengfu Cheng
title	High-resolution photoacoustic microscopy with deep penetration through learning
title_short	High-resolution photoacoustic microscopy with deep penetration through learning
title_full	High-resolution photoacoustic microscopy with deep penetration through learning
title_fullStr	High-resolution photoacoustic microscopy with deep penetration through learning
title_full_unstemmed	High-resolution photoacoustic microscopy with deep penetration through learning
title_sort	high-resolution photoacoustic microscopy with deep penetration through learning
publisher	Elsevier
publishDate	2022
url	https://doaj.org/article/8a40713c4e134cddb8ff73eaf88118d3
work_keys_str_mv	AT shengfucheng highresolutionphotoacousticmicroscopywithdeeppenetrationthroughlearning AT yingyingzhou highresolutionphotoacousticmicroscopywithdeeppenetrationthroughlearning AT jiangbochen highresolutionphotoacousticmicroscopywithdeeppenetrationthroughlearning AT huanhaoli highresolutionphotoacousticmicroscopywithdeeppenetrationthroughlearning AT lidaiwang highresolutionphotoacousticmicroscopywithdeeppenetrationthroughlearning AT puxianglai highresolutionphotoacousticmicroscopywithdeeppenetrationthroughlearning
_version_	1718429967887368192

High-resolution photoacoustic microscopy with deep penetration through learning

Ejemplares similares