Fast ultrasonic imaging using end-to-end deep learning

IEEE International Ultrasonics Symposium, pp. 1–4

Abstract

Ultrasonic imaging algorithms used in many clinical and industrial applications consist of three steps: A data pre-processing, an image formation and an image post-processing step. For efficiency, image formation often relies on an approximation of the underlying wave physics. A prominent example is the Delay-And-Sum (DAS) algorithm used in reflectivity-based ultrasonic imaging. Recently, deep neural networks (DNNs) are being used for the data pre-processing and the image postprocessing steps separately. In this work, we propose a novel deep learning architecture that integrates all three steps to enable end-to-end training. We examine turning the DAS image formation method into a network layer that connects data pre-processing layers with image post-processing layers that perform segmentation. We demonstrate that this integrated approach clearly outperforms sequential approaches that are trained separately. While network training and evaluation is performed only on simulated data, we also showcase the potential of our approach on real data from a non-destructive testing scenario.

Authors 5

1. Georgios Pilikos

   Centrum Wiskunde & Informatica

   Affiliation as printed

   Computational Imaging, Centrum Wiskunde & Informatica, Amsterdam, NL

2. Lars Hörchens
   Affiliation as printed

   Applus+ E&I Technology Centre, Rotterdam, NL

3. Kees Joost Batenburg Aachen Leiden Institute of Advanced Computer Science

   Leiden University · Centrum Wiskunde & Informatica

   Affiliation as printed

   Computational Imaging, Centrum Wiskunde & Informatica, Amsterdam, NL

   Leiden Institute of Advanced Computer Science, Leiden University, Leiden, NL

4. Tristan van Leeuwen

   Centrum Wiskunde & Informatica · Utrecht University

   Affiliation as printed

   Computational Imaging, Centrum Wiskunde & Informatica, Amsterdam, NL

   Mathematical Institute, Utrecht University, Utrecht, NL

5. Felix F. Lucka

   Centrum Wiskunde & Informatica · University College London

   Affiliation as printed

   Centre for Medical Image Computing, University College London, London, UK

   Computational Imaging, Centrum Wiskunde & Informatica, Amsterdam, NL