Deep Learning for Accelerated Ultrasound Imaging
This addresses the need for efficient ultrasound imaging in medical applications, offering a software-based solution to avoid hardware changes or computationally expensive algorithms, though it appears incremental as it builds on existing deep learning and sparsity concepts.
The paper tackled the problem of reconstructing high-quality ultrasound images from limited data in portable, 3-D, or ultra-fast systems, proposing a deep learning method that interpolates missing RF data using sparsity in the Fourier domain, with experimental results showing it effectively reduces data rate without sacrificing image quality.
In portable, 3-D, or ultra-fast ultrasound (US) imaging systems, there is an increasing demand to reconstruct high quality images from limited number of data. However, the existing solutions require either hardware changes or computationally expansive algorithms. To overcome these limitations, here we propose a novel deep learning approach that interpolates the missing RF data by utilizing the sparsity of the RF data in the Fourier domain. Extensive experimental results from sub-sampled RF data from a real US system confirmed that the proposed method can effectively reduce the data rate without sacrificing the image quality.