An Ultra-Fast Method for Simulation of Realistic Ultrasound Images

TL;DR

This paper introduces a novel ultra-fast ultrasound image simulation method based on Fourier transform, significantly improving data augmentation efficiency and quality for CNN training in medical ultrasound applications.

Contribution

The paper presents a new Fourier transform-based simulation technique that is vastly faster and produces more realistic images than traditional methods like Field II.

Findings

Simulation speed increased by approximately 36,000 times

Synthetic data improved lesion segmentation accuracy

Method outperforms existing simulation tools in fidelity

Abstract

Convolutional neural networks (CNNs) have attracted a rapidly growing interest in a variety of different processing tasks in the medical ultrasound community. However, the performance of CNNs is highly reliant on both the amount and fidelity of the training data. Therefore, scarce data is almost always a concern, particularly in the medical field, where clinical data is not easily accessible. The utilization of synthetic data is a popular approach to address this challenge. However, but simulating a large number of images using packages such as Field II is time-consuming, and the distribution of simulated images is far from that of the real images. Herein, we introduce a novel ultra-fast ultrasound image simulation method based on the Fourier transform and evaluate its performance in a lesion segmentation task. We demonstrate that data augmentation using the images generated by the proposed method substantially outperforms Field II in terms of Dice similarity coefficient, while the simulation is almost 36000 times faster (both on CPU).