EdgeSRIE: A hybrid deep learning framework for real-time speckle reduction and image enhancement on portable ultrasound systems

TL;DR

EdgeSRIE is a lightweight hybrid deep learning framework that enables real-time speckle reduction and image enhancement on portable ultrasound systems, balancing high image quality with low computational cost.

Contribution

The paper introduces EdgeSRIE, a novel hybrid deep learning framework optimized for real-time ultrasound imaging on low-resource hardware, combining unsupervised despeckling and deblurring modules.

Findings

Achieved highest CNR and AGM compared to baselines.

Enabled real-time inference at over 60 fps on portable hardware.

Maintained low computational complexity with under 20K parameters.

Abstract

Speckle patterns in ultrasound images often obscure anatomical details, leading to diagnostic uncertainty. Recently, various deep learning (DL)-based techniques have been introduced to effectively suppress speckle; however, their high computational costs pose challenges for low-resource devices, such as portable ultrasound systems. To address this issue, EdgeSRIE, which is a lightweight hybrid DL framework for real-time speckle reduction and image enhancement in portable ultrasound imaging, is introduced. The proposed framework consists of two main branches: an unsupervised despeckling branch, which is trained by minimizing a loss function between speckled images, and a deblurring branch, which restores blurred images to sharp images. For hardware implementation, the trained network is quantized to 8-bit integer precision and deployed on a low-resource system-on-chip (SoC) with limited power consumption. In the performance evaluation with phantom and in vivo analyses, EdgeSRIE achieved the highest contrast-to-noise ratio (CNR) and average gradient magnitude (AGM) compared with the other baselines (different 2-rule-based methods and other 4-DL-based methods). Furthermore, EdgeSRIE enabled real-time inference at over 60 frames per second while satisfying computational requirements (< 20K parameters) on actual portable ultrasound hardware. These results demonstrated the feasibility of EdgeSRIE for real-time, high-quality ultrasound imaging in resource-limited environments.