# O-Net: A Convolutional Neural Network for Quantitative Photoacoustic Image Segmentation and Oximetry

arXiv: https://arxiv.org/abs/1911.01935 · HTML: https://mlsanity.com/paper/1911.01935/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2019.

## Built on by (most cited first, 4 of 4)

- [Semantic segmentation of multispectral photoacoustic images using deep learning](https://mlsanity.com/paper/2105.09624/) (2021)
- [Distribution-informed and wavelength-flexible data-driven photoacoustic oximetry](https://mlsanity.com/paper/2403.14863/) (2024)
- [Quantitative photoacoustic oximetry imaging by multiple illumination learned spectral decoloring](https://mlsanity.com/paper/2102.11201/) (2021)
- [Application of a Virtual Imaging Framework for Investigating a Deep Learning-Based Reconstruction Method for 3D Quantitative Photoacoustic Computed Tomography](https://mlsanity.com/paper/2510.03431/) (2025)

## Abstract (arXiv)

Estimation of blood oxygenation with spectroscopic photoacoustic imaging is a promising tool for several biomedical applications. For this method to be quantitative, it relies on an accurate method of the light fluence in the tissue. This is difficult deep in heterogeneous tissue, where different wavelengths of light can experience significantly different attenuation. In this work, we developed a new deep neural network to simultaneously estimate the oxygen saturation in blood vessels and segment the vessels from the surrounding background tissue. The network was trained on estimated initial pressure distributions from three-dimensional Monte Carlo simulations of light transport in breast tissue. The network estimated vascular SO2 in less than 50 ms with as little as 5.1% median error and better than 95% segmentation accuracy. Overall, these results show that the blood oxygenation can be quantitatively mapped in real-time with high accuracy.