Towards CT-quality Ultrasound Imaging using Deep Learning
This work addresses image quality issues in ultrasound imaging for medical diagnosis, offering a step towards solving a full wave propagation inverse problem, but it is incremental as it builds on existing deep learning and simulation approaches.
The paper tackled the problem of ultrasound image quality by reconstructing CT-quality images from simulated ultrasound RF data using Multi-Resolution CNNs, achieving results that mimic computationally heavy despeckling methods with orders of magnitude faster computation for real-time applications.
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.