Real-time segmentation for tomographic imaging

IEEE International Workshop on Machine Learning for Signal Processing (MLSP), vol. 15, pp. 1–6

Abstract

In tomography, reconstruction and analysis is often performed once the acquisition has been completed due to the computational cost of the 3D imaging algorithms. In contrast, real-time reconstruction and analysis can avoid costly repetition of experiments and enable optimization of experimental parameters. Recently, it was shown that by reconstructing a subset of arbitrarily oriented slices, real-time quasi-3D reconstruction can be attained. Here, we extend this approach by including realtime segmentation, thereby enabling real-time analysis during the experiment. We propose to use a convolutional neural network (CNN) to perform real-time image segmentation and introduce an adapted training strategy in order to apply CNNs to arbitrarily oriented slices. We evaluate our method on both simulated and real-world data. The experiments show that our approach enables realtime tomographic segmentation for real-world applications and outperforms standard unsupervised segmentation methods.

Authors 4

1. Richard Schoonhoven

   Centrum Wiskunde & Informatica

   Affiliation as printed

   Computational Imaging Group, Centrum Wiskunde & Informatica, Amsterdam, Netherlands

2. Jan‐Willem Buurlage

   Centrum Wiskunde & Informatica

   Affiliation as printed

   Computational Imaging Group, Centrum Wiskunde & Informatica, Amsterdam, Netherlands

3. Daniël M. Pelt

   Centrum Wiskunde & Informatica

   Affiliation as printed

   Computational Imaging Group, Centrum Wiskunde & Informatica, Amsterdam, Netherlands

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

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science, Leiden, Netherlands