# Reconstructing undersampled photoacoustic microscopy images using deep learning

arXiv: https://arxiv.org/abs/2006.00251 · HTML: https://mlsanity.com/paper/2006.00251/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2020.

## Built on by (most cited first, 7 of 7)

- [Self-similarity-based super-resolution of photoacoustic angiography from hand-drawn doodles](https://mlsanity.com/paper/2305.01165/) (2023)
- [Speeding up Photoacoustic Imaging using Diffusion Models](https://mlsanity.com/paper/2312.08834/) (2023)
- [Joint Segmentation and Image Reconstruction with Error Prediction in Photoacoustic Imaging using Deep Learning](https://mlsanity.com/paper/2407.02653/) (2024)
- [Framework Construction of an Adversarial Federated Transfer Learning Classifier](https://mlsanity.com/paper/2211.04734/) (2022)
- [Super-Resolution on Rotationally Scanned Photoacoustic Microscopy Images Incorporating Scanning Prior](https://mlsanity.com/paper/2312.07226/) (2023)
- [Resolution Enhancement of Under-sampled Photoacoustic Microscopy Images using Implicit Neural Representations](https://mlsanity.com/paper/2410.19786/) (2024)
- [Deformable Convolution Module with Globally Learned Relative Offsets for Fundus Vessel Segmentation](https://mlsanity.com/paper/2507.18354/) (2025)

## Abstract (arXiv)

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 may effectively shorten the imaging time without substantially sacrificing the image quality.