skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Unsupervised disentanglement strategy for mitigating artifact in photoacoustic tomography under extremely sparse view

Photoacoustics (Munich), 2024-08, Vol.38, p.100613-100613, Article 100613 [Peer Reviewed Journal]

2024 ;2024 The Authors. ;2024 The Authors 2024 ;ISSN: 2213-5979 ;EISSN: 2213-5979 ;DOI: 10.1016/j.pacs.2024.100613 ;PMID: 38764521

Full text available

Citations Cited by
  • Title:
    Unsupervised disentanglement strategy for mitigating artifact in photoacoustic tomography under extremely sparse view
  • Author: Zhong, Wenhua ; Li, Tianle ; Hou, Shangkun ; Zhang, Hongyu ; Li, Zilong ; Wang, Guijun ; Liu, Qiegen ; Song, Xianlin
  • Subjects: Mitigating artifact ; Photoacoustic tomography ; Sparse view ; Unsupervised disentanglement strategy
  • Is Part Of: Photoacoustics (Munich), 2024-08, Vol.38, p.100613-100613, Article 100613
  • Description: Traditional methods under sparse view for reconstruction of photoacoustic tomography (PAT) often result in significant artifacts. Here, a novel image to image transformation method based on unsupervised learning artifact disentanglement network (ADN), named PAT-ADN, was proposed to address the issue. This network is equipped with specialized encoders and decoders that are responsible for encoding and decoding the artifacts and content components of unpaired images, respectively. The performance of the proposed PAT-ADN was evaluated using circular phantom data and the animal in vivo experimental data. The results demonstrate that PAT-ADN exhibits excellent performance in effectively removing artifacts. In particular, under extremely sparse view (e.g., 16 projections), structural similarity index and peak signal-to-noise ratio are improved by ~188% and ~85% in in vivo experimental data using the proposed method compared to traditional reconstruction methods. PAT-ADN improves the imaging performance of PAT, opening up possibilities for its application in multiple domains.
  • Publisher: Germany: Elsevier GmbH
  • Language: English
  • Identifier: ISSN: 2213-5979
    EISSN: 2213-5979
    DOI: 10.1016/j.pacs.2024.100613
    PMID: 38764521
  • Source: PubMed Central database
    Directory of Open Access Journals at publisher websites
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait