Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications

Journal of Imaging, vol. 7, pp. 44

Abstract

The reconstruction of computed tomography (CT) images is an active area of research. Following the rise of deep learning methods, many data-driven models have been proposed in recent years. In this work, we present the results of a data challenge that we organized, bringing together algorithm experts from different institutes to jointly work on quantitative evaluation of several data-driven methods on two large, public datasets during a ten day sprint. We focus on two applications of CT, namely, low-dose CT and sparse-angle CT. This enables us to fairly compare different methods using standardized settings. As a general result, we observe that the deep learning-based methods are able to improve the reconstruction quality metrics in both CT applications while the top performing methods show only minor differences in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). We further discuss a number of other important criteria that should be taken into account when selecting a method, such as the availability of training data, the knowledge of the physical measurement model and the reconstruction speed.

Authors 11

1. Johannes Leuschner corresponding

   University of Bremen

   Affiliation as printed

   Center for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, Germany

2. Maximilian Schmidt

   University of Bremen

   Affiliation as printed

   Center for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, Germany

3. Poulami Somanya Ganguly Aachen Mathematical Institute

   Leiden University · Centrum Wiskunde & Informatica

   Affiliation as printed

   Centrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The Netherlands

   The Mathematical Institute, Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands

4. Vladyslav Andriiashen

   Centrum Wiskunde & Informatica

   Affiliation as printed

   Centrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The Netherlands

5. Sophia Bethany Coban

   Centrum Wiskunde & Informatica

   Affiliation as printed

   Centrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The Netherlands

6. Alexander H. Denker

   University of Bremen

   Affiliation as printed

   Center for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, Germany

7. Dominik F. Bauer

   Heidelberg University

   Affiliation as printed

   Computer Assisted Clinical Medicine, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany

8. Amir Hadjifaradji

   University of British Columbia

   Affiliation as printed

   School of Biomedical Engineering, University of British Columbia, 2222 Health Sciences Mall, Vancouver, BC V6T 1Z3, Canada

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

   Leiden University · Centrum Wiskunde & Informatica

   Affiliation as printed

   Centrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The Netherlands

   Leiden Institute of Advanced Computer Science, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands

10. Peter Maaß

    University of Bremen

    Affiliation as printed

    Center for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, Germany

11. Maureen A.J.M. van Eijnatten corresponding

    Centrum Wiskunde & Informatica · Eindhoven University of Technology

    Affiliation as printed

    Centrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The Netherlands

    Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 3, 5612 AE Eindhoven, The Netherlands