MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data

Photoacoustic imaging (PAI) is an emerging hybrid imaging technology that combines the advantages of optical and ultrasound imaging. Despite its excellent imaging capabilities, PAI still faces numerous challenges in clinical applications, particularly sparse spatial sampling and limited view detecti...

Full description

Saved in:
Bibliographic Details
Main Authors: Liangjie Wang, Yi-Chao Meng, Yiming Qian
Format: Article
Language:English
Published: Elsevier 2025-02-01
Series:Photoacoustics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S221359792400096X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850073966379532288
author Liangjie Wang
Yi-Chao Meng
Yiming Qian
author_facet Liangjie Wang
Yi-Chao Meng
Yiming Qian
author_sort Liangjie Wang
collection DOAJ
description Photoacoustic imaging (PAI) is an emerging hybrid imaging technology that combines the advantages of optical and ultrasound imaging. Despite its excellent imaging capabilities, PAI still faces numerous challenges in clinical applications, particularly sparse spatial sampling and limited view detection. These limitations often result in severe streak artifacts and blurring when using standard methods to reconstruct images from incomplete data. In this work, we propose an improved convolutional neural network (CNN) architecture, called multi-scale dense UNet (MSD-Net), to correct artifacts in 2D photoacoustic tomography (PAT). MSD-Net exploits the advantages of multi-scale information fusion and dense connections to improve the performance of CNN. Experimental validation with both simulated and in vivo datasets demonstrates that our method achieves better reconstructions with improved speed.
format Article
id doaj-art-e3c0000b8bfb49bbab3e39efc195e506
institution DOAJ
issn 2213-5979
language English
publishDate 2025-02-01
publisher Elsevier
record_format Article
series Photoacoustics
spelling doaj-art-e3c0000b8bfb49bbab3e39efc195e5062025-08-20T02:46:40ZengElsevierPhotoacoustics2213-59792025-02-014110067910.1016/j.pacs.2024.100679MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse dataLiangjie Wang0Yi-Chao Meng1Yiming Qian2Institute of Fiber Optics, Shanghai University, Shanghai 201800, China; Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai University, Shanghai 200444, ChinaInstitute of Fiber Optics, Shanghai University, Shanghai 201800, China; Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai University, Shanghai 200444, China; Correspondence to: Institute of Fiber Optics, School of Communication and Information Engineering, Shanghai University.Institute of Fiber Optics, Shanghai University, Shanghai 201800, China; Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai University, Shanghai 200444, ChinaPhotoacoustic imaging (PAI) is an emerging hybrid imaging technology that combines the advantages of optical and ultrasound imaging. Despite its excellent imaging capabilities, PAI still faces numerous challenges in clinical applications, particularly sparse spatial sampling and limited view detection. These limitations often result in severe streak artifacts and blurring when using standard methods to reconstruct images from incomplete data. In this work, we propose an improved convolutional neural network (CNN) architecture, called multi-scale dense UNet (MSD-Net), to correct artifacts in 2D photoacoustic tomography (PAT). MSD-Net exploits the advantages of multi-scale information fusion and dense connections to improve the performance of CNN. Experimental validation with both simulated and in vivo datasets demonstrates that our method achieves better reconstructions with improved speed.http://www.sciencedirect.com/science/article/pii/S221359792400096XBiomedical imagingPhotoacoustic imagingDeep learningConvolutional networks
spellingShingle Liangjie Wang
Yi-Chao Meng
Yiming Qian
MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data
Photoacoustics
Biomedical imaging
Photoacoustic imaging
Deep learning
Convolutional networks
title MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data
title_full MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data
title_fullStr MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data
title_full_unstemmed MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data
title_short MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data
title_sort msd net multi scale dense convolutional neural network for photoacoustic image reconstruction with sparse data
topic Biomedical imaging
Photoacoustic imaging
Deep learning
Convolutional networks
url http://www.sciencedirect.com/science/article/pii/S221359792400096X
work_keys_str_mv AT liangjiewang msdnetmultiscaledenseconvolutionalneuralnetworkforphotoacousticimagereconstructionwithsparsedata
AT yichaomeng msdnetmultiscaledenseconvolutionalneuralnetworkforphotoacousticimagereconstructionwithsparsedata
AT yimingqian msdnetmultiscaledenseconvolutionalneuralnetworkforphotoacousticimagereconstructionwithsparsedata