Deep data compression for approximate ultrasonic image formation

Utrecht University Repository (Utrecht University)

Abstract

In many ultrasonic imaging systems, data acquisition and image formation are performed on separate computing devices. Data transmission is becoming a bottleneck, thus, efficientdata compression is essential. Compression rates can be improved by considering the fact that many image formation methods rely on approximations of wave-matter interactions, and only use the corresponding part of the data. Tailored data compression could exploit this, but extracting the useful part of the data efficiently is not always trivial. In this work, we tackle this problem using deep neural networks, optimized to preserve the image quality of a particular image formation method. The Delay-And-Sum (DAS) algorithm is examined which is used in reflectivity-based ultrasonic imaging. We propose a novel encoder-decoder architecture with vector quantization and formulate image formation as a network layer for endto- end training. Experiments demonstrate that our proposed data compression tailored for a specific image formation method obtains significantly better results as opposed to compression agnostic to subsequent imaging. We maintain high image quality at much higher compression rates than the theoretical lossless compression rate derived from the rank of the linear imaging operator. This demonstrates the great potential of deep ultrasonic data compression tailored for a specific image formation method. Index Terms—deep learning, compression, Delay-And-Sum, fast ultrasonic imaging, end-to-end training

Authors 7

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. K.J. 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. T. 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 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

6. Mathematical Modeling
7. Sub Mathematical Modeling