Deep learning approach to improve tangential resolution in photoacoustic tomography

In circular scan photoacoustic tomography (PAT), the axial resolution is spatially invariant and is limited by the bandwidth of the detector. However, the tangential resolution is spatially variant and is dependent on the aperture size of the detector. In particular, the tangential resolution improv...

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/10356/146545
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-146545
record_format dspace
spelling sg-ntu-dr.10356-1465452023-12-29T06:50:07Z Deep learning approach to improve tangential resolution in photoacoustic tomography Rajendran, Praveenbalaji Pramanik, Manojit School of Chemical and Biomedical Engineering Engineering::Bioengineering Photoacoustic Tomography (PAT) Tangential Resolution In circular scan photoacoustic tomography (PAT), the axial resolution is spatially invariant and is limited by the bandwidth of the detector. However, the tangential resolution is spatially variant and is dependent on the aperture size of the detector. In particular, the tangential resolution improves with the decreasing aperture size. However, using a detector with a smaller aperture reduces the sensitivity of the transducer. Thus, large aperture size detectors are widely preferred in circular scan PAT imaging systems. Although several techniques have been proposed to improve the tangential resolution, they have inherent limitations such as high cost and the need for customized detectors. Herein, we propose a novel deep learning architecture to counter the spatially variant tangential resolution in circular scanning PAT imaging systems. We used a fully dense U-Net based convolutional neural network architecture along with 9 residual blocks to improve the tangential resolution of the PAT images. The network was trained on the simulated datasets and its performance was verified by experimental in vivo imaging. Results show that the proposed deep learning network improves the tangential resolution by eight folds, without compromising the structural similarity and quality of image. Ministry of Education (MOE) Published version Ministry of Education - Singapore (RG144/18) 2021-02-25T08:28:57Z 2021-02-25T08:28:57Z 2020 Journal Article Rajendran, P., & Pramanik, M. (2020). Deep learning approach to improve tangential resolution in photoacoustic tomography. Biomedical Optics Express, 11(12), 7311-7323. doi:10.1364/BOE.410145 2156-7085 https://hdl.handle.net/10356/146545 10.1364/BOE.410145 33408998 2-s2.0-85097030446 12 11 7311 7323 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
Photoacoustic Tomography (PAT)
Tangential Resolution
spellingShingle Engineering::Bioengineering
Photoacoustic Tomography (PAT)
Tangential Resolution
Rajendran, Praveenbalaji
Pramanik, Manojit
Deep learning approach to improve tangential resolution in photoacoustic tomography
description In circular scan photoacoustic tomography (PAT), the axial resolution is spatially invariant and is limited by the bandwidth of the detector. However, the tangential resolution is spatially variant and is dependent on the aperture size of the detector. In particular, the tangential resolution improves with the decreasing aperture size. However, using a detector with a smaller aperture reduces the sensitivity of the transducer. Thus, large aperture size detectors are widely preferred in circular scan PAT imaging systems. Although several techniques have been proposed to improve the tangential resolution, they have inherent limitations such as high cost and the need for customized detectors. Herein, we propose a novel deep learning architecture to counter the spatially variant tangential resolution in circular scanning PAT imaging systems. We used a fully dense U-Net based convolutional neural network architecture along with 9 residual blocks to improve the tangential resolution of the PAT images. The network was trained on the simulated datasets and its performance was verified by experimental in vivo imaging. Results show that the proposed deep learning network improves the tangential resolution by eight folds, without compromising the structural similarity and quality of image.
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 approach to improve tangential resolution in photoacoustic tomography
title_short Deep learning approach to improve tangential resolution in photoacoustic tomography
title_full Deep learning approach to improve tangential resolution in photoacoustic tomography
title_fullStr Deep learning approach to improve tangential resolution in photoacoustic tomography
title_full_unstemmed Deep learning approach to improve tangential resolution in photoacoustic tomography
title_sort deep learning approach to improve tangential resolution in photoacoustic tomography
publishDate 2021
url https://hdl.handle.net/10356/146545
_version_ 1787136644202102784