Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular Imaging
Linear-array-based photoacoustic computed tomography (PACT) has been widely used in vascular imaging due to its low cost and high compatibility with current ultrasound systems. However, linear-array transducers have inherent limitations for three-dimensional imaging due to the poor elevation resolut...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/20/7725 |
_version_ | 1797470047586746368 |
---|---|
author | Wenhan Zheng Huijuan Zhang Chuqin Huang Kaylin McQuillan Huining Li Wenyao Xu Jun Xia |
author_facet | Wenhan Zheng Huijuan Zhang Chuqin Huang Kaylin McQuillan Huining Li Wenyao Xu Jun Xia |
author_sort | Wenhan Zheng |
collection | DOAJ |
description | Linear-array-based photoacoustic computed tomography (PACT) has been widely used in vascular imaging due to its low cost and high compatibility with current ultrasound systems. However, linear-array transducers have inherent limitations for three-dimensional imaging due to the poor elevation resolution. In this study, we introduced a deep learning-assisted data process algorithm to enhance the image quality in linear-array-based PACT. Compared to our earlier study where training was performed on 2D reconstructed data, here, we utilized 2D and 3D reconstructed data to train the two networks separately. We then fused the image data from both 2D and 3D training to get features from both algorithms. The numerical and in vivo validations indicate that our approach can improve elevation resolution, recover the true size of the object, and enhance deep vessels. Our deep learning-assisted approach can be applied to translational imaging applications that require detailed visualization of vascular features. |
first_indexed | 2024-03-09T19:31:15Z |
format | Article |
id | doaj.art-f60942934d5a45648f05c89fb120c064 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T19:31:15Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-f60942934d5a45648f05c89fb120c0642023-11-24T02:24:41ZengMDPI AGSensors1424-82202022-10-012220772510.3390/s22207725Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular ImagingWenhan Zheng0Huijuan Zhang1Chuqin Huang2Kaylin McQuillan3Huining Li4Wenyao Xu5Jun Xia6Department of Biomedical Engineering, University at Buffalo North Campus, Buffalo, NY 14260, USADepartment of Biomedical Engineering, University at Buffalo North Campus, Buffalo, NY 14260, USADepartment of Biomedical Engineering, University at Buffalo North Campus, Buffalo, NY 14260, USADepartment of Biomedical Engineering, University at Buffalo North Campus, Buffalo, NY 14260, USADepartment of Computer Science and Engineering, University at Buffalo North Campus, Buffalo, NY 14260, USADepartment of Computer Science and Engineering, University at Buffalo North Campus, Buffalo, NY 14260, USADepartment of Biomedical Engineering, University at Buffalo North Campus, Buffalo, NY 14260, USALinear-array-based photoacoustic computed tomography (PACT) has been widely used in vascular imaging due to its low cost and high compatibility with current ultrasound systems. However, linear-array transducers have inherent limitations for three-dimensional imaging due to the poor elevation resolution. In this study, we introduced a deep learning-assisted data process algorithm to enhance the image quality in linear-array-based PACT. Compared to our earlier study where training was performed on 2D reconstructed data, here, we utilized 2D and 3D reconstructed data to train the two networks separately. We then fused the image data from both 2D and 3D training to get features from both algorithms. The numerical and in vivo validations indicate that our approach can improve elevation resolution, recover the true size of the object, and enhance deep vessels. Our deep learning-assisted approach can be applied to translational imaging applications that require detailed visualization of vascular features.https://www.mdpi.com/1424-8220/22/20/7725photoacoustic tomographydeep learningvascular imagingresolution improvement3D reconstruction |
spellingShingle | Wenhan Zheng Huijuan Zhang Chuqin Huang Kaylin McQuillan Huining Li Wenyao Xu Jun Xia Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular Imaging Sensors photoacoustic tomography deep learning vascular imaging resolution improvement 3D reconstruction |
title | Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular Imaging |
title_full | Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular Imaging |
title_fullStr | Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular Imaging |
title_full_unstemmed | Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular Imaging |
title_short | Deep-E Enhanced Photoacoustic Tomography Using Three-Dimensional Reconstruction for High-Quality Vascular Imaging |
title_sort | deep e enhanced photoacoustic tomography using three dimensional reconstruction for high quality vascular imaging |
topic | photoacoustic tomography deep learning vascular imaging resolution improvement 3D reconstruction |
url | https://www.mdpi.com/1424-8220/22/20/7725 |
work_keys_str_mv | AT wenhanzheng deepeenhancedphotoacoustictomographyusingthreedimensionalreconstructionforhighqualityvascularimaging AT huijuanzhang deepeenhancedphotoacoustictomographyusingthreedimensionalreconstructionforhighqualityvascularimaging AT chuqinhuang deepeenhancedphotoacoustictomographyusingthreedimensionalreconstructionforhighqualityvascularimaging AT kaylinmcquillan deepeenhancedphotoacoustictomographyusingthreedimensionalreconstructionforhighqualityvascularimaging AT huiningli deepeenhancedphotoacoustictomographyusingthreedimensionalreconstructionforhighqualityvascularimaging AT wenyaoxu deepeenhancedphotoacoustictomographyusingthreedimensionalreconstructionforhighqualityvascularimaging AT junxia deepeenhancedphotoacoustictomographyusingthreedimensionalreconstructionforhighqualityvascularimaging |