Towards CT-quality Ultrasound Imaging using Deep Learning

TL;DR

This paper demonstrates that deep learning, specifically multi-resolution CNNs, can produce CT-quality ultrasound images from RF data and replicate despeckling methods efficiently, enabling real-time medical imaging improvements.

Contribution

The work introduces a CNN-based approach to reconstruct high-quality ultrasound images and imitate despeckling techniques, significantly reducing computational costs.

Findings

Reconstructed CT-quality images from simulated RF data.

CNN effectively mimics despeckling methods with lower computational load.

Achieved real-time imaging potential.

Abstract

The cost-effectiveness and practical harmlessness of ultrasound imaging have made it one of the most widespread tools for medical diagnosis. Unfortunately, the beam-forming based image formation produces granular speckle noise, blurring, shading and other artifacts. To overcome these effects, the ultimate goal would be to reconstruct the tissue acoustic properties by solving a full wave propagation inverse problem. In this work, we make a step towards this goal, using Multi-Resolution Convolutional Neural Networks (CNN). As a result, we are able to reconstruct CT-quality images from the reflected ultrasound radio-frequency(RF) data obtained by simulation from real CT scans of a human body. We also show that CNN is able to imitate existing computationally heavy despeckling methods, thereby saving orders of magnitude in computations and making them amenable to real-time applications.