Enhancing synthetic training data for quantitative photoacoustic tomography with generative deep learning

TL;DR

This paper explores advanced deep learning methods, including GAN-based strategies, to improve the realism and generalisability of synthetic training data for quantitative photoacoustic tomography, aiming to better estimate tissue oxygenation levels.

Contribution

It introduces two GAN-based approaches to enhance synthetic data quality and domain adaptation, improving sO2 estimation from photoacoustic images.

Findings

CycleGAN improves domain adaptation for real tissues.

AmbientGANs generate paired training data effectively.

Enhanced synthetic data leads to better sO2 estimation accuracy.

Abstract

Multiwavelength photoacoustic images encode information about a tissue's optical absorption distribution. This can be used to estimate its blood oxygen saturation distribution (sO2), an important physiological indicator of tissue health and pathology. However the wavelength dependence of the light fluence distribution complicates the recovery of accurate estimates, in particular, preventing the use of a straightforward spectroscopic inversion. Deep learning approaches have been shown effective at producing accurate estimates of sO2 from simulated data. Though, the translation of generic supervised learning approaches to real tissues is prevented by the lack of real `paired' training data (multiwavelength PA images of in vivo tissues with their corresponding sO2 distributions). Here, we discuss i) why networks trained on images simulated using conventional means are unlikely to generalise their performance on real tissues, and ii) the prospects of using two generative adversarial network based strategies to improve the generalisability of sO2-estimating networks trained on synthetic data: a) CycleGAN-driven unsupervised domain adaptation of conventionally simulated images, and b) the generation of paired training data using AmbientGANs.