Unknown

Dataset Information

0

Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning.


ABSTRACT: 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.

SUBMITTER: DiSpirito A 

PROVIDER: S-EPMC7858223 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

altmetric image

Publications

Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning.

DiSpirito Anthony A   Li Daiwei D   Vu Tri T   Chen Maomao M   Zhang Dong D   Luo Jianwen J   Horstmeyer Roarke R   Yao Junjie J  

IEEE transactions on medical imaging 20210203 2


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 unde  ...[more]

Similar Datasets

| S-EPMC7943731 | biostudies-literature
| S-EPMC11348209 | biostudies-literature
| S-EPMC7408120 | biostudies-literature
| S-EPMC9926190 | biostudies-literature
| S-EPMC6363787 | biostudies-literature
| S-EPMC10754953 | biostudies-literature
| S-EPMC5427497 | biostudies-literature
| S-EPMC8917167 | biostudies-literature
| S-EPMC5587733 | biostudies-literature
| S-EPMC7081314 | biostudies-literature