Automatic Frame Selection Using MLP Neural Network in Ultrasound Elastography

TL;DR

This paper presents an MLP-based method for automatically selecting optimal RF frame pairs in ultrasound elastography to improve strain image quality, trained on in-vivo data and tested on diverse datasets.

Contribution

Introduces a novel MLP classifier for automatic frame selection in elastography, enhancing strain image quality over traditional frame-picking methods.

Findings

Higher quality strain images achieved with the proposed method.

Fast testing phase of 1.9 ms for frame selection.

Effective on both in-vivo and phantom datasets.

Abstract

Ultrasound elastography estimates the mechanical properties of the tissue from two Radio-Frequency (RF) frames collected before and after tissue deformation due to an external or internal force. This work focuses on strain imaging in quasi-static elastography, where the tissue undergoes slow deformations and strain images are estimated as a surrogate for elasticity modulus. The quality of the strain image depends heavily on the underlying deformation, and even the best strain estimation algorithms cannot estimate a good strain image if the underlying deformation is not suitable. Herein, we introduce a new method for tracking the RF frames and selecting automatically the best possible pair. We achieve this by decomposing the axial displacement image into a linear combination of principal components (which are calculated offline) multiplied by their corresponding weights. We then use the calculated weights as the input feature vector to a multi-layer perceptron (MLP) classifier. The output is a binary decision, either 1 which refers to good frames, or 0 which refers to bad frames. Our MLP model is trained on in-vivo dataset and tested on different datasets of both in-vivo and phantom data. Results show that by using our technique, we would be able to achieve higher quality strain images compared to the traditional methods of picking up pairs that are 1, 2 or 3 frames apart. The training phase of our algorithm is computationally expensive and takes few hours, but it is only done once. The testing phase chooses the optimal pair of frames in only 1.9 ms.