Waveform-Specific Performance of Deep Learning-Based Super-Resolution for Ultrasound Contrast Imaging

TL;DR

This paper evaluates how different waveform-specific deep learning approaches impact super-resolution ultrasound contrast imaging, highlighting chirp pulses' robustness in noisy conditions and advancing microbubble localization techniques.

Contribution

It introduces CNN-based deconvolution methods tailored for various ultrasound pulse types, analyzing their effectiveness and robustness in super-resolution microbubble localization.

Findings

Chirp pulses outperform others in low SNR conditions.

Short pulses provide the best accuracy in noise-free environments.

CNNs can accurately localize microbubbles across different waveforms.

Abstract

Resolving arterial flows is essential for understanding cardiovascular pathologies, improving diagnosis, and monitoring patient condition. Ultrasound contrast imaging uses microbubbles to enhance the scattering of the blood pool, allowing for real-time visualization of blood flow. Recent developments in vector flow imaging further expand the imaging capabilities of ultrasound by temporally resolving fast arterial flow. The next obstacle to overcome is the lack of spatial resolution. Super-resolved ultrasound images can be obtained by deconvolving radiofrequency (RF) signals before beamforming, breaking the link between resolution and pulse duration. Convolutional neural networks (CNNs) can be trained to locally estimate the deconvolution kernel and consequently super-localize the microbubbles directly within the RF signal. However, microbubble contrast is highly nonlinear, and the potential of CNNs in microbubble localization has not yet been fully exploited. Assessing deep learning-based deconvolution performance for non-trivial imaging pulses is therefore essential for successful translation to a practical setting, where the signal-to-noise ratio is limited, and transmission schemes should comply with safety guidelines. In this study, we train CNNs to deconvolve RF signals and localize the microbubbles driven by harmonic pulses, chirps, or delay-encoded pulse trains. Furthermore, we discuss potential hurdles for in-vitro and in-vivo super-resolution by presenting preliminary experimental results. We find that, whereas the CNNs can accurately localize microbubbles for all pulses, a short imaging pulse offers the best performance in noise-free conditions. However, chirps offer a comparable performance without noise, but are more robust to noise and outperform all other pulses in low-signal-to-noise ratio conditions.