Homodyned K-distribution: parameter estimation and uncertainty quantification using Bayesian neural networks
This work addresses a domain-specific challenge in quantitative ultrasound for medical imaging, offering an incremental improvement in parameter estimation.
The authors tackled the problem of reliably estimating Homodyned K-distribution parameters for ultrasound speckle statistics, which require large data, by proposing a Bayesian Neural Network that estimates these parameters and quantifies uncertainty.
Quantitative ultrasound (QUS) allows estimating the intrinsic tissue properties. Speckle statistics are the QUS parameters that describe the first order statistics of ultrasound (US) envelope data. The parameters of Homodyned K-distribution (HK-distribution) are the speckle statistics that can model the envelope data in diverse scattering conditions. However, they require a large amount of data to be estimated reliably. Consequently, finding out the intrinsic uncertainty of the estimated parameters can help us to have a better understanding of the estimated parameters. In this paper, we propose a Bayesian Neural Network (BNN) to estimate the parameters of HK-distribution and quantify the uncertainty of the estimator.