# Distribution-informed and wavelength-flexible data-driven photoacoustic oximetry

arXiv: https://arxiv.org/abs/2403.14863 · HTML: https://mlsanity.com/paper/2403.14863/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 70 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 8 of 8)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Surgical Data Science -- from Concepts toward Clinical Translation](https://mlsanity.com/paper/2011.02284/) (2020)
- [Recurrent Neural Networks (RNNs): A gentle Introduction and Overview](https://mlsanity.com/paper/1912.05911/) (2019)
- [Deep learning for biomedical photoacoustic imaging: A review](https://mlsanity.com/paper/2011.02744/) (2020)
- [Moving beyond simulation: data-driven quantitative photoacoustic imaging using tissue-mimicking phantoms](https://mlsanity.com/paper/2306.06748/) (2023)
- [Eigenspectra optoacoustic tomography achieves quantitative blood oxygenation imaging deep in tissues](https://mlsanity.com/paper/1511.05846/) (2015)
- [O-Net: A Convolutional Neural Network for Quantitative Photoacoustic Image Segmentation and Oximetry](https://mlsanity.com/paper/1911.01935/) (2019)
- [Unsupervised Domain Transfer with Conditional Invertible Neural Networks](https://mlsanity.com/paper/2303.10191/) (2023)

## Built on by (most cited first, 1 of 1)

- [Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts](https://mlsanity.com/paper/2604.19176/) (2026)

## Abstract (arXiv)

Significance: Photoacoustic imaging (PAI) promises to measure spatially-resolved blood oxygen saturation, but suffers from a lack of accurate and robust spectral unmixing methods to deliver on this promise. Accurate blood oxygenation estimation could have important clinical applications, from cancer detection to quantifying inflammation. Aim: This study addresses the inflexibility of existing data-driven methods for estimating blood oxygenation in PAI by introducing a recurrent neural network architecture. Approach: We created 25 simulated training dataset variations to assess neural network performance. We used a long short-term memory network to implement a wavelength-flexible network architecture and proposed the Jensen-Shannon divergence to predict the most suitable training dataset. Results: The network architecture can handle arbitrary input wavelengths and outperforms linear unmixing and the previously proposed learned spectral decolouring method. Small changes in the training data significantly affect the accuracy of our method, but we find that the Jensen-Shannon divergence correlates with the estimation error and is thus suitable for predicting the most appropriate training datasets for any given application. Conclusions: A flexible data-driven network architecture combined with the Jensen-Shannon Divergence to predict the best training data set provides a promising direction that might enable robust data-driven photoacoustic oximetry for clinical use cases.