Robust RF Data Normalization for Deep Learning

TL;DR

This paper introduces a novel RF data normalization method that improves deep learning performance in ultrasound imaging by addressing the limitations of conventional normalization techniques.

Contribution

It proposes individual standardization of RF data as a more effective normalization approach for deep neural networks in ultrasound image processing.

Findings

Individual standardization outperforms conventional normalization methods.

Proposed normalization enhances deep learning model performance in phase aberration correction.

Conventional normalization reduces model generality across different RF datasets.

Abstract

Radio frequency (RF) data contain richer information compared to other data types, such as envelope or B-mode, and employing RF data for training deep neural networks has attracted growing interest in ultrasound image processing. However, RF data is highly fluctuating and additionally has a high dynamic range. Most previous studies in the literature have relied on conventional data normalization, which has been adopted within the computer vision community. We demonstrate the inadequacy of those techniques for normalizing RF data and propose that individual standardization of each image substantially enhances the performance of deep neural networks by utilizing the data more efficiently. We compare conventional and proposed normalizations in a phase aberration correction task and illustrate how the former enhances the generality of trained models.