What question did this study set out to answer?

This study aims to enhance imaging speed and quality in sparse-view photoacoustic tomography using a generative adversarial network.

May 6, 2026PhotoacousticsOpen Access

A generative adversarial network with multi-scale structural features for sparse-view photoacoustic tomography reconstruction

View Full Paper

Ask AI

Bookmark

Authors

JLJialin LiJilin University XLXudong LuoSuzhou Vocational Institute of Industrial Technology YMYiming MaHarbin Institute of Technology

Discussion

Member takes

Implication

Generative adversarial network improves peak signal-to-noise ratio in biomedical imaging with sparse-view photoacoustic tomography, indicating better quality imaging outcomes.

Key Points

This study aims to enhance imaging speed and quality in sparse-view photoacoustic tomography using a generative adversarial network.
Implemented a generative adversarial network with multiscale structural features.
Incorporated pyramid squeeze attention block for feature extraction.
Designed dual gradient regularized adversarial loss for stability in detail enhancement.
Achieved improvements in peak signal-to-noise ratio and structural similarity index by 1.128% and 1.176% under 128 views.
Under 64 views, improvements were 2.442% and 0.536% for peak signal-to-noise ratio and structural similarity index, respectively.
Demonstrated effective artifact suppression and detail recovery consistent with full-view reconstruction.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/69faa2b504f884e66b533377 https://doi.org/10.1016/j.pacs.2026.100828

View Full Paper

Ask AI

Bookmark

Implication

Generative adversarial network improves peak signal-to-noise ratio in biomedical imaging with sparse-view photoacoustic tomography, indicating better quality imaging outcomes.

A generative adversarial network with multi-scale structural features for sparse-view photoacoustic tomography reconstruction

Discussion

Member takes

Implication

Key Points

Cite This Study

A generative adversarial network with multi-scale structural features for sparse-view photoacoustic tomography reconstruction

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider