Cargando…

Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human

The development of high‐performance imaging processing algorithms is a core area of photoacoustic tomography. While various deep learning based image processing techniques have been developed in the area, their applications in 3D imaging are still limited due to challenges in computational cost and...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Wenhan, Zhang, Huijuan, Huang, Chuqin, Shijo, Varun, Xu, Chenhan, Xu, Wenyao, Xia, Jun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10582405/
https://www.ncbi.nlm.nih.gov/pubmed/37530209
http://dx.doi.org/10.1002/advs.202301277
_version_ 1785122323322372096
author Zheng, Wenhan
Zhang, Huijuan
Huang, Chuqin
Shijo, Varun
Xu, Chenhan
Xu, Wenyao
Xia, Jun
author_facet Zheng, Wenhan
Zhang, Huijuan
Huang, Chuqin
Shijo, Varun
Xu, Chenhan
Xu, Wenyao
Xia, Jun
author_sort Zheng, Wenhan
collection PubMed
description The development of high‐performance imaging processing algorithms is a core area of photoacoustic tomography. While various deep learning based image processing techniques have been developed in the area, their applications in 3D imaging are still limited due to challenges in computational cost and memory allocation. To address those limitations, this work implements a 3D fully‐dense (3DFD) U‐net to linear array based photoacoustic tomography and utilizes volumetric simulation and mixed precision training to increase efficiency and training size. Through numerical simulation, phantom imaging, and in vivo experiments, this work demonstrates that the trained network restores the true object size, reduces the noise level and artifacts, improves the contrast at deep regions, and reveals vessels subject to limited view distortion. With these enhancements, 3DFD U‐net successfully produces clear 3D vascular images of the palm, arms, breasts, and feet of human subjects. These enhanced vascular images offer improved capabilities for biometric identification, foot ulcer evaluation, and breast cancer imaging. These results indicate that the new algorithm will have a significant impact on preclinical and clinical photoacoustic tomography.
format Online
Article
Text
id pubmed-10582405
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-105824052023-10-19 Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human Zheng, Wenhan Zhang, Huijuan Huang, Chuqin Shijo, Varun Xu, Chenhan Xu, Wenyao Xia, Jun Adv Sci (Weinh) Research Articles The development of high‐performance imaging processing algorithms is a core area of photoacoustic tomography. While various deep learning based image processing techniques have been developed in the area, their applications in 3D imaging are still limited due to challenges in computational cost and memory allocation. To address those limitations, this work implements a 3D fully‐dense (3DFD) U‐net to linear array based photoacoustic tomography and utilizes volumetric simulation and mixed precision training to increase efficiency and training size. Through numerical simulation, phantom imaging, and in vivo experiments, this work demonstrates that the trained network restores the true object size, reduces the noise level and artifacts, improves the contrast at deep regions, and reveals vessels subject to limited view distortion. With these enhancements, 3DFD U‐net successfully produces clear 3D vascular images of the palm, arms, breasts, and feet of human subjects. These enhanced vascular images offer improved capabilities for biometric identification, foot ulcer evaluation, and breast cancer imaging. These results indicate that the new algorithm will have a significant impact on preclinical and clinical photoacoustic tomography. John Wiley and Sons Inc. 2023-08-02 /pmc/articles/PMC10582405/ /pubmed/37530209 http://dx.doi.org/10.1002/advs.202301277 Text en © 2023 The Authors. Advanced Science published by Wiley‐VCH GmbH https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Articles
Zheng, Wenhan
Zhang, Huijuan
Huang, Chuqin
Shijo, Varun
Xu, Chenhan
Xu, Wenyao
Xia, Jun
Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human
title Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human
title_full Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human
title_fullStr Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human
title_full_unstemmed Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human
title_short Deep Learning Enhanced Volumetric Photoacoustic Imaging of Vasculature in Human
title_sort deep learning enhanced volumetric photoacoustic imaging of vasculature in human
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10582405/
https://www.ncbi.nlm.nih.gov/pubmed/37530209
http://dx.doi.org/10.1002/advs.202301277
work_keys_str_mv AT zhengwenhan deeplearningenhancedvolumetricphotoacousticimagingofvasculatureinhuman
AT zhanghuijuan deeplearningenhancedvolumetricphotoacousticimagingofvasculatureinhuman
AT huangchuqin deeplearningenhancedvolumetricphotoacousticimagingofvasculatureinhuman
AT shijovarun deeplearningenhancedvolumetricphotoacousticimagingofvasculatureinhuman
AT xuchenhan deeplearningenhancedvolumetricphotoacousticimagingofvasculatureinhuman
AT xuwenyao deeplearningenhancedvolumetricphotoacousticimagingofvasculatureinhuman
AT xiajun deeplearningenhancedvolumetricphotoacousticimagingofvasculatureinhuman