Accelerated model‐based iterative reconstruction strategy for sparse‐view photoacoustic tomography aided by multi‐channel autoencoder priors

Photoacoustic tomography (PAT) commonly works in sparse view due to data acquisition limitations. However, reconstruction suffers from serious deterioration (e.g., severe artifacts) using traditional algorithms under sparse view. Here, a novel accelerated model‐based iterative reconstruction strateg...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Journal of biophotonics Ročník 17; číslo 1; s. e202300281 - n/a
Hlavní autori:	Song, Xianlin, Zhong, Wenhua, Li, Zilong, Peng, Shuchong, Zhang, Hongyu, Wang, Guijun, Dong, Jiaqing, Liu, Xuan, Xu, Xiaoling, Liu, Qiegen
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Weinheim WILEY‐VCH Verlag GmbH & Co. KGaA 01.01.2024 Wiley Subscription Services, Inc
Predmet:	Algorithms Blood vessels Computer Simulation Constraint modelling Data acquisition Experimental data Image Processing, Computer-Assisted - methods Image reconstruction Iterative methods model‐based iterative reconstruction multichannel autoencoder priors Phantoms, Imaging Photoacoustic effect photoacoustic tomography sparse view Tomography Tomography, X-Ray Computed - methods multichannel autoencoder priors model-based iterative reconstruction sparse view photoacoustic tomography
ISSN:	1864-063X, 1864-0648, 1864-0648
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Photoacoustic tomography (PAT) commonly works in sparse view due to data acquisition limitations. However, reconstruction suffers from serious deterioration (e.g., severe artifacts) using traditional algorithms under sparse view. Here, a novel accelerated model‐based iterative reconstruction strategy for sparse‐view PAT aided by multi‐channel autoencoder priors was proposed. A multi‐channel denoising autoencoder network was designed to learn prior information, which provides constraints for model‐based iterative reconstruction. This integration accelerates the iteration process, leading to optimal reconstruction outcomes. The performance of the proposed method was evaluated using blood vessel simulation data and experimental data. The results show that the proposed method can achieve superior sparse‐view reconstruction with a significant acceleration of iteration. Notably, the proposed method exhibits excellent performance under extremely sparse condition (e.g., 32 projections) compared with the U‐Net method, with an improvement of 48% in PSNR and 12% in SSIM for in vivo experimental data. A novel accelerated model‐based iterative reconstruction strategy for sparse‐view PAT aided by multi‐channel autoencoder priors was proposed. A multi‐channel denoising autoencoder network was designed to learn prior information, which provides constraints for model‐based iterative reconstruction. This integration accelerates the iteration process, leading to optimal reconstruction outcomes. The results show that the proposed method can achieve superior sparse‐view reconstruction with a significant acceleration of iteration. Notably, the proposed method exhibits excellent performance under extremely sparse condition.
Bibliografia:	Xianlin Song, Wenhua Zhong, and Zilong Li contributed equally to this work. ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1864-063X 1864-0648 1864-0648
DOI:	10.1002/jbio.202300281