Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy

In acoustic resolution photoacoustic microscopy (AR-PAM), a high numerical aperture focused ultrasound transducer (UST) is used for deep tissue high resolution photoacoustic imaging. There is a significant degradation of lateral resolution in the out-of-focus region. Improvement in out-of-focus reso...

Full description

Saved in:
Bibliographic Details
Main Authors: Sharma, Arunima, Pramanik, Manojit
Other Authors: School of Chemical and Biomedical Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/146548
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-146548
record_format dspace
spelling sg-ntu-dr.10356-1465482023-12-29T06:49:05Z Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy Sharma, Arunima Pramanik, Manojit School of Chemical and Biomedical Engineering Engineering::Bioengineering Acoustic Resolution Photoacoustic Microscopy (AR-PAM) Ultrasound Transducer (UST) In acoustic resolution photoacoustic microscopy (AR-PAM), a high numerical aperture focused ultrasound transducer (UST) is used for deep tissue high resolution photoacoustic imaging. There is a significant degradation of lateral resolution in the out-of-focus region. Improvement in out-of-focus resolution without degrading the image quality remains a challenge. In this work, we propose a deep learning-based method to improve the resolution of AR-PAM images, especially at the out of focus plane. A modified fully dense U-Net based architecture was trained on simulated AR-PAM images. Applying the trained model on experimental images showed that the variation in resolution is ∼10% across the entire imaging depth (∼4 mm) in the deep learning-based method, compared to ∼180% variation in the original PAM images. Performance of the trained network on in vivo rat vasculature imaging further validated that noise-free, high resolution images can be obtained using this method. Ministry of Education (MOE) Published version Ministry of Education - Singapore (RG144/18). 2021-02-26T00:43:34Z 2021-02-26T00:43:34Z 2020 Journal Article Sharma, A., & Pramanik, M. (2020). Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy. Biomedical Optics Express, 11(12), 6826-6839. doi:10.1364/BOE.411257 2156-7085 https://hdl.handle.net/10356/146548 10.1364/BOE.411257 33408964 2-s2.0-85096861842 12 11 6826 6839 en Biomedical Optics Express © 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Bioengineering
Acoustic Resolution Photoacoustic Microscopy (AR-PAM)
Ultrasound Transducer (UST)
spellingShingle Engineering::Bioengineering
Acoustic Resolution Photoacoustic Microscopy (AR-PAM)
Ultrasound Transducer (UST)
Sharma, Arunima
Pramanik, Manojit
Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy
description In acoustic resolution photoacoustic microscopy (AR-PAM), a high numerical aperture focused ultrasound transducer (UST) is used for deep tissue high resolution photoacoustic imaging. There is a significant degradation of lateral resolution in the out-of-focus region. Improvement in out-of-focus resolution without degrading the image quality remains a challenge. In this work, we propose a deep learning-based method to improve the resolution of AR-PAM images, especially at the out of focus plane. A modified fully dense U-Net based architecture was trained on simulated AR-PAM images. Applying the trained model on experimental images showed that the variation in resolution is ∼10% across the entire imaging depth (∼4 mm) in the deep learning-based method, compared to ∼180% variation in the original PAM images. Performance of the trained network on in vivo rat vasculature imaging further validated that noise-free, high resolution images can be obtained using this method.
author2 School of Chemical and Biomedical Engineering
author_facet School of Chemical and Biomedical Engineering
Sharma, Arunima
Pramanik, Manojit
format Article
author Sharma, Arunima
Pramanik, Manojit
author_sort Sharma, Arunima
title Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy
title_short Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy
title_full Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy
title_fullStr Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy
title_full_unstemmed Convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy
title_sort convolutional neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy
publishDate 2021
url https://hdl.handle.net/10356/146548
_version_ 1787136611006283776