Effective Reconstruction of Backprojection images through Attention Mechanism

Venkata Chowdary; Venkata Sai Hithesh Reddy; Thejeshwar Reddy; Sunil Kumar; M. Rajasekaran

doi:10.2991/978-94-6463-471-6_85

<Previous Article In Volume

Next Article In Volume>

Effective Reconstruction of Backprojection images through Attention Mechanism

Authors

Venkata Chowdary¹, Venkata Sai Hithesh Reddy¹, Thejeshwar Reddy¹, Sunil Kumar¹, M. Rajasekaran¹^{, *}

¹Department of Computer Science and Engineering, Madanapalle Institute of Technology and Science, Madanapalle, 517325, India

^*Corresponding author.

Corresponding Author

M. Rajasekaran

Available Online 30 July 2024.

DOI: 10.2991/978-94-6463-471-6_85 How to use a DOI?
Keywords: photoacoustic imaging; frequency domain; Deep Learning; U-Net; Attention
Abstract: Compared to time-domain photoacoustic imaging, frequency-domain photoacoustic (FDPA) imaging has much more potential in a clinical setting because of its smaller size and lower cost. Elements. However, because of its poorer signal-to-noise ratio, the FDPA system requires sophisticated image reconstruction techniques. In FDPA imaging, most image reconstruction techniques rely on analytical or model-based schemes [1]. This work developed an image reconstruction technique based on deep learning that can directly reconstruct back-projection images and enhance their quality. This architecture was inspired by U Net, which uses attention gates at the skip connections and a sequence of encoders and decoders after that. A comparison is made between the outcomes and direct translational networks built on vanilla U Net. By using our proposed model, we observed an improvement of about 10% on both PSNR and SSIM metrics.
Copyright: © 2024 The Author(s)
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
Series: Advances in Computer Science Research
Publication Date: 30 July 2024
ISBN: 978-94-6463-471-6
ISSN: 2352-538X
DOI: 10.2991/978-94-6463-471-6_85 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Venkata Chowdary
AU  - Venkata Sai Hithesh Reddy
AU  - Thejeshwar Reddy
AU  - Sunil Kumar
AU  - M. Rajasekaran
PY  - 2024
DA  - 2024/07/30
TI  - Effective Reconstruction of Backprojection images through Attention Mechanism
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 897
EP  - 903
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_85
DO  - 10.2991/978-94-6463-471-6_85
ID  - Chowdary2024
ER  -

download .riscopy to clipboard