Deep Learning in Ultrasound Elastography Imaging

TL;DR

This paper reviews how deep learning techniques like CNNs and RNNs are applied to ultrasound elastography for improved tissue characterization, discussing recent advances, challenges, and future directions.

Contribution

It provides a comprehensive overview of deep learning frameworks used in ultrasound elastography and analyzes recent algorithmic and clinical developments.

Findings

Deep learning enhances tissue stiffness imaging accuracy.

Various neural network architectures are adapted for elastography.

Challenges include data scarcity and model interpretability.

Abstract

It is known that changes in the mechanical properties of tissues are associated with the onset and progression of certain diseases. Ultrasound elastography is a technique to characterize tissue stiffness using ultrasound imaging either by measuring tissue strain using quasi-static elastography or natural organ pulsation elastography, or by tracing a propagated shear wave induced by a source or a natural vibration using dynamic elastography. In recent years, deep learning has begun to emerge in ultrasound elastography research. In this review, several common deep learning frameworks in the computer vision community, such as multilayer perceptron, convolutional neural network, and recurrent neural network are described. Then, recent advances in ultrasound elastography using such deep learning techniques are revisited in terms of algorithm development and clinical diagnosis. Finally, the current challenges and future developments of deep learning in ultrasound elastography are prospected.