Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration

Pulsed laser diodes are used in photoacoustic tomography (PAT) as excitation sources because of their low cost, compact size, and high pulse repetition rate. In combination with multiple single-element ultrasound transducers (SUTs) the imaging speed of PAT can be improved.However, during PAT image r...

Full description

Saved in:
Bibliographic Details
Main Authors: Rajendran, Praveenbalaji, Pramanik, Manojit
Other Authors: School of Chemical and Biomedical Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/152692
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-152692
record_format dspace
spelling sg-ntu-dr.10356-1526922023-12-29T06:47:55Z Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration Rajendran, Praveenbalaji Pramanik, Manojit School of Chemical and Biomedical Engineering Engineering::Bioengineering Photoacoustic Tomography Radius Calibration Pulsed laser diodes are used in photoacoustic tomography (PAT) as excitation sources because of their low cost, compact size, and high pulse repetition rate. In combination with multiple single-element ultrasound transducers (SUTs) the imaging speed of PAT can be improved.However, during PAT image reconstruction, the exact radius of each SUT is required for accurate reconstruction. Here we developed a novel deep learning approach to alleviate the need for radius calibration. We used a convolutional neural network (fully dense U-Net) aided with a convolutional long short-term memory block to reconstruct the PAT images. Our analysis on the test set demonstrates that the proposed network eliminates the need for radius calibration and improves the peak signal-to-noise ratio by ~73% without compromising the image quality. In vivo imaging was used to verify the performance of the network. Ministry of Education (MOE) Accepted version Ministry of Education–Singapore (RG144/18) 2021-09-16T05:26:47Z 2021-09-16T05:26:47Z 2021 Journal Article Rajendran, P. & Pramanik, M. (2021). Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration. Optics Letters, 46(18), 4510-4513. https://dx.doi.org/10.1364/OL.434513 0146-9592 https://hdl.handle.net/10356/152692 10.1364/OL.434513 2-s2.0-85114461734 18 46 4510 4513 en RG144/18 Optics Letters © 2021 Optical Society of America. All rights reserved. This paper was published in Optics Letters and is made available with permission of Optical Society of America. 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
Photoacoustic Tomography
Radius Calibration
spellingShingle Engineering::Bioengineering
Photoacoustic Tomography
Radius Calibration
Rajendran, Praveenbalaji
Pramanik, Manojit
Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration
description Pulsed laser diodes are used in photoacoustic tomography (PAT) as excitation sources because of their low cost, compact size, and high pulse repetition rate. In combination with multiple single-element ultrasound transducers (SUTs) the imaging speed of PAT can be improved.However, during PAT image reconstruction, the exact radius of each SUT is required for accurate reconstruction. Here we developed a novel deep learning approach to alleviate the need for radius calibration. We used a convolutional neural network (fully dense U-Net) aided with a convolutional long short-term memory block to reconstruct the PAT images. Our analysis on the test set demonstrates that the proposed network eliminates the need for radius calibration and improves the peak signal-to-noise ratio by ~73% without compromising the image quality. In vivo imaging was used to verify the performance of the network.
author2 School of Chemical and Biomedical Engineering
author_facet School of Chemical and Biomedical Engineering
Rajendran, Praveenbalaji
Pramanik, Manojit
format Article
author Rajendran, Praveenbalaji
Pramanik, Manojit
author_sort Rajendran, Praveenbalaji
title Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration
title_short Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration
title_full Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration
title_fullStr Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration
title_full_unstemmed Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration
title_sort deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration
publishDate 2021
url https://hdl.handle.net/10356/152692
_version_ 1787136552550268928