KEYWORDS: 3D modeling, Photoacoustic tomography, Model-based design, Image restoration, Data modeling, 3D image reconstruction, Reconstruction algorithms, Tissues, Acoustics, Monte Carlo methods
Three-dimensional quantitative photoacoustic tomography (3D-QPAT) aims to recover tissue chromophore concentrations from multispectral images but is often hampered by the unknown light fluence and the transfer function of the scanner. Inversion schemes that use hybrid light transport and acoustic propagation models may be used to address this challenge. While model-based inversions have shown promising results in in silico and tissue phantom studies, limitations in accuracy arose from limited view artefacts. This study evaluated reconstruction methods such as time-reversal, maximum a posteriori, iterative least square and total variation to improve the accuracy of 3D-QPAT inversion techniques.
In Photoacoustic Tomography (PAT), the aim is to estimate the initial pressure distribution based on measured ultrasound data. While several approaches utilizing deep learning for PAT have been proposed, many of these do not provide estimates on the reliability of the reconstruction. In this work, we propose a deep learning approach for the Bayesian inverse problem for PAT based on the uncertainty quantification variational autoencoder. The approach enables simultaneous image reconstruction and reliability estimation.
In the inverse problem of photoacoustic tomography (PAT), initial pressure distribution induced by the photoa-coustic effect is estimated from a set of measured ultrasound data. In the recent decade, utilization of various deep learning approaches for the inverse problem of PAT have been proposed. However, many of these approaches do not provide information of the uncertainties of the reconstructed images. In this work, we propose a deep learning based approach for the Bayesian inverse problem of PAT based on variational autoencoders. The approach is evaluated using numerical simulations and compared against posterior distribution obtained using a conventional Bayesian image reconstruction approach. The approach is shown to provide rapid and accurate reconstructions with reliability estimates.
In this work, a computationally efficient forward model for photoacoustic tomography is presented. The approach is able to produce accurate photoacoustic images with significantly reduced computational cost compared to a conventional approach.
Photoacoustic tomography (PAT) is an imaging modality developed during the past few decades. In the inverse problem of PAT, the aim is to estimate the spatial distribution of an initial pressure p0 generated by the photoacoustic effect, when photoacoustic time-series pt measured on the boundary of the imaged target are given. To produce accurate photoacoustic images, the forward model linking p0 to pt has to model the measurement setup and the underlying physics to a sufficient accuracy. Use of an inaccurate model can lead to significant errors in the solution of the inverse problem. In this work, we study the effect and compensation of modelling errors due to uncertainties in ultrasound sensor locations in PAT using Bayesian approximation error modelling. The approach is evaluated with simulated and experimental data using various levels of measurement noise, uncertainties in sensor locations and varying sensor geometries. The results indicate that even small errors in the modelling of ultrasound sensor locations can lead to large errors in the solution of the inverse problem. Furthermore, the magnitude of these errors is affected by the amount of measurement noise and the measurement
The modelling errors can, however, be well compensated by the approximation error modelling.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.