Estimating the ultrasound attenuation coefficient using convolutional neural networks -- a feasibility study

TL;DR

This study explores using convolutional neural networks to estimate ultrasound tissue attenuation coefficients directly from RF signals, demonstrating promising accuracy and interpretability in a feasibility assessment.

Contribution

It introduces a CNN-based method for direct AC estimation from RF ultrasound data, with physical interpretability of the model weights.

Findings

Mean absolute error of 0.08 for 10 mm patches

CNN weights have physical meaning

Feasibility of deep learning for AC estimation

Abstract

Attenuation coefficient (AC) is a fundamental measure of tissue acoustical properties, which can be used in medical diagnostics. In this work, we investigate the feasibility of using convolutional neural networks (CNNs) to directly estimate AC from radio-frequency (RF) ultrasound signals. To develop the CNNs we used RF signals collected from tissue mimicking numerical phantoms for the AC values in a range from 0.1 to 1.5 dB/(MHz*cm). The models were trained based on 1-D patches of RF data. We obtained mean absolute AC estimation errors of 0.08, 0.12, 0.20, 0.25 for the patch lengths: 10 mm, 5 mm, 2 mm and 1 mm, respectively. We explain the performance of the model by visualizing the frequency content associated with convolutional filters. Our study presents that the AC can be calculated using deep learning, and the weights of the CNNs can have physical interpretation.