Skip to main content

Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning.

Publication ,  Journal Article
DiSpirito, A; Li, D; Vu, T; Chen, M; Zhang, D; Luo, J; Horstmeyer, R; Yao, J
Published in: IEEE transactions on medical imaging
February 2021

One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed. In this study, we propose a novel application of deep learning principles to reconstruct undersampled PAM images and transcend the trade-off between spatial resolution and imaging speed. We compared various convolutional neural network (CNN) architectures, and selected a Fully Dense U-net (FD U-net) model that produced the best results. To mimic various undersampling conditions in practice, we artificially downsampled fully-sampled PAM images of mouse brain vasculature at different ratios. This allowed us to not only definitively establish the ground truth, but also train and test our deep learning model at various imaging conditions. Our results and numerical analysis have collectively demonstrated the robust performance of our model to reconstruct PAM images with as few as 2% of the original pixels, which can effectively shorten the imaging time without substantially sacrificing the image quality.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

IEEE transactions on medical imaging

DOI

EISSN

1558-254X

ISSN

0278-0062

Publication Date

February 2021

Volume

40

Issue

2

Start / End Page

562 / 570

Related Subject Headings

  • Spectrum Analysis
  • Nuclear Medicine & Medical Imaging
  • Neural Networks, Computer
  • Microscopy
  • Mice
  • Image Processing, Computer-Assisted
  • Deep Learning
  • Animals
  • 46 Information and computing sciences
  • 40 Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
DiSpirito, A., Li, D., Vu, T., Chen, M., Zhang, D., Luo, J., … Yao, J. (2021). Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning. IEEE Transactions on Medical Imaging, 40(2), 562–570. https://doi.org/10.1109/tmi.2020.3031541
DiSpirito, Anthony, Daiwei Li, Tri Vu, Maomao Chen, Dong Zhang, Jianwen Luo, Roarke Horstmeyer, and Junjie Yao. “Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning.IEEE Transactions on Medical Imaging 40, no. 2 (February 2021): 562–70. https://doi.org/10.1109/tmi.2020.3031541.
DiSpirito A, Li D, Vu T, Chen M, Zhang D, Luo J, et al. Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning. IEEE transactions on medical imaging. 2021 Feb;40(2):562–70.
DiSpirito, Anthony, et al. “Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning.IEEE Transactions on Medical Imaging, vol. 40, no. 2, Feb. 2021, pp. 562–70. Epmc, doi:10.1109/tmi.2020.3031541.
DiSpirito A, Li D, Vu T, Chen M, Zhang D, Luo J, Horstmeyer R, Yao J. Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning. IEEE transactions on medical imaging. 2021 Feb;40(2):562–570.

Published In

IEEE transactions on medical imaging

DOI

EISSN

1558-254X

ISSN

0278-0062

Publication Date

February 2021

Volume

40

Issue

2

Start / End Page

562 / 570

Related Subject Headings

  • Spectrum Analysis
  • Nuclear Medicine & Medical Imaging
  • Neural Networks, Computer
  • Microscopy
  • Mice
  • Image Processing, Computer-Assisted
  • Deep Learning
  • Animals
  • 46 Information and computing sciences
  • 40 Engineering