Towards robust quantitative photoacoustic tomography via learned iterative methods

TL;DR

This paper introduces a model-based learned iterative approach for quantitative photoacoustic tomography, improving reconstruction accuracy and generalizability with limited training data by integrating model information into deep learning methods.

Contribution

It develops and compares learned iterative reconstruction methods based on gradient descent, Gauss-Newton, and Quasi-Newton techniques for QPAT, enhancing robustness with scarce data.

Findings

Learned iterative methods outperform classical approaches in noisy conditions.

The approach generalizes well with limited training data.

Testing on simulated and digital twin datasets shows improved accuracy.

Abstract

Photoacoustic tomography (PAT) is a medical imaging modality that can provide high-resolution tissue images based on the optical absorption. Classical reconstruction methods for quantifying the absorption coefficients rely on sufficient prior information to overcome noisy and imperfect measurements. As these methods utilize computationally expensive forward models, the computation becomes slow, limiting their potential for time-critical applications. As an alternative approach, deep learning-based reconstruction methods have been established for faster and more accurate reconstructions. However, most of these methods rely on having a large amount of training data, which is not the case in practice. In this work, we adopt the model-based learned iterative approach for the use in Quantitative PAT (QPAT), in which additional information from the model is iteratively provided to the updating networks, allowing better generalizability with scarce training data. We compare the performance of different learned updates based on gradient descent, Gauss-Newton, and Quasi-Newton methods. The learning tasks are formulated as greedy, requiring iterate-wise optimality, as well as end-to-end, where all networks are trained jointly. The implemented methods are tested with ideal simulated data as well as against a digital twin dataset that emulates scarce training data and high modeling error.