Deep learning improves contrast in low-fluence photoacoustic imaging

Ali Hariri; Kamran Alipour; Yash Mantri; Jurgen P Schulze; Jesse V Jokerst

doi:10.1364/BOE.395683

Deep learning improves contrast in low-fluence photoacoustic imaging

Biomed Opt Express. 2020 May 29;11(6):3360-3373. doi: 10.1364/BOE.395683. eCollection 2020 Jun 1.

Authors

Ali Hariri^{1

2}, Kamran Alipour^{3

2}, Yash Mantri⁴, Jurgen P Schulze^{3

5}, Jesse V Jokerst^{1

6

7}

Affiliations

¹ Department of NanoEngineering, University of California, San Diego, La Jolla, CA 92093, USA.
² These authors contributed equally to this paper.
³ Department of Computer Science, University of California, San Diego, La Jolla, CA 92093, USA.
⁴ Department of BioEngineering, University of California, San Diego, La Jolla, CA 92093, USA.
⁵ Qualcomm Institute, University of California, San Diego, La Jolla, CA 92093, USA.
⁶ Department of Radiology, University of California, San Diego, La Jolla, CA 92093, USA.
⁷ Material Science Program, University of California, San Diego, La Jolla, CA 92093, USA.

Abstract

Low fluence illumination sources can facilitate clinical transition of photoacoustic imaging because they are rugged, portable, affordable, and safe. However, these sources also decrease image quality due to their low fluence. Here, we propose a denoising method using a multi-level wavelet-convolutional neural network to map low fluence illumination source images to its corresponding high fluence excitation map. Quantitative and qualitative results show a significant potential to remove the background noise and preserve the structures of target. Substantial improvements up to 2.20, 2.25, and 4.3-fold for PSNR, SSIM, and CNR metrics were observed, respectively. We also observed enhanced contrast (up to 1.76-fold) in an in vivo application using our proposed methods. We suggest that this tool can improve the value of such sources in photoacoustic imaging.

Abstract

Grants and funding