Deep Sylvester Posterior Inference for Adaptive Compressed Sensing in Ultrasound Imaging

TL;DR

This paper presents an adaptive, real-time ultrasound imaging method that intelligently selects scan-lines to maximize information gain, significantly improving reconstruction accuracy and speed over traditional static sampling approaches.

Contribution

It introduces a novel adaptive subsampling technique using a Sylvester Normalizing Flow encoder for real-time Bayesian inference to optimize ultrasound scan-line selection.

Findings

Outperforms baseline sampling methods in reconstruction accuracy.

Achieves real-time inference at 66Hz, suitable for live ultrasound imaging.

Reduces mean absolute reconstruction error by 15%.

Abstract

Ultrasound images are commonly formed by sequential acquisition of beam-steered scan-lines. Minimizing the number of required scan-lines can significantly enhance frame rate, field of view, energy efficiency, and data transfer speeds. Existing approaches typically use static subsampling schemes in combination with sparsity-based or, more recently, deep-learning-based recovery. In this work, we introduce an adaptive subsampling method that maximizes intrinsic information gain in-situ, employing a Sylvester Normalizing Flow encoder to infer an approximate Bayesian posterior under partial observation in real-time. Using the Bayesian posterior and a deep generative model for future observations, we determine the subsampling scheme that maximizes the mutual information between the subsampled observations, and the next frame of the video. We evaluate our approach using the EchoNet cardiac ultrasound video dataset and demonstrate that our active sampling method outperforms competitive baselines, including uniform and variable-density random sampling, as well as equidistantly spaced scan-lines, improving mean absolute reconstruction error by 15%. Moreover, posterior inference and the sampling scheme generation are performed in just 0.015 seconds (66Hz), making it fast enough for real-time 2D ultrasound imaging applications.