Application of a Virtual Imaging Framework for Investigating a Deep Learning-Based Reconstruction Method for 3D Quantitative Photoacoustic Computed Tomography
This work addresses the need for more robust validation in qPACT reconstruction, which is crucial for improving imaging accuracy in medical applications like breast imaging, though it is incremental as it focuses on enhancing existing validation approaches.
The researchers tackled the challenge of validating deep learning-based reconstruction methods for 3D quantitative photoacoustic computed tomography (qPACT) by developing a realistic virtual imaging testbed for breast imaging, evaluating the method across subject variability and physical factors like noise and aberrations to identify its strengths and limitations.
Quantitative photoacoustic computed tomography (qPACT) is a promising imaging modality for estimating physiological parameters such as blood oxygen saturation. However, developing robust qPACT reconstruction methods remains challenging due to computational demands, modeling difficulties, and experimental uncertainties. Learning-based methods have been proposed to address these issues but remain largely unvalidated. Virtual imaging (VI) studies are essential for validating such methods early in development, before proceeding to less-controlled phantom or in vivo studies. Effective VI studies must employ ensembles of stochastically generated numerical phantoms that accurately reflect relevant anatomy and physiology. Yet, most prior VI studies for qPACT relied on overly simplified phantoms. In this work, a realistic VI testbed is employed for the first time to assess a representative 3D learning-based qPACT reconstruction method for breast imaging. The method is evaluated across subject variability and physical factors such as measurement noise and acoustic aberrations, offering insights into its strengths and limitations.