English

Deep Learning-Based Reconstruction of Interventional Tools from Four X-Ray Projections for Tomographic Interventional Guidance

Medical Physics 2021-11-25 v2 Image and Video Processing

Abstract

Image guidance for minimally invasive interventions is usually performed by acquiring fluoroscopic images using a C-arm system. However, the projective data provide only limited information about the spatial structure and position of interventional tools such as stents, guide wires or coils. In this work we propose a deep learning-based pipeline for real-time tomographic (four-dimensional) interventional guidance at acceptable dose levels. In the first step, interventional tools are extracted from four cone-beam CT projections using a deep convolutional neural network (CNN). These projections are then reconstructed and fed into a second CNN, which maps this highly undersampled reconstruction to a segmentation of the interventional tools. Our pipeline is capable of reconstructing interventional tools from only four x-ray projections without the need for a patient prior with very high accuracy. Therefore, the proposed approach is capable of overcoming the drawbacks of today's interventional guidance and could enable the development of new minimally invasive radiological interventions by providing full spatiotemporal information about the interventional tools.

Keywords

Cite

@article{arxiv.2009.10993,
  title  = {Deep Learning-Based Reconstruction of Interventional Tools from Four X-Ray Projections for Tomographic Interventional Guidance},
  author = {Elias Eulig and Joscha Maier and Michael Knaup and N. Robert Bennett and Klaus Hörndler and Adam S. Wang and Marc Kachelrieß},
  journal= {arXiv preprint arXiv:2009.10993},
  year   = {2021}
}

Comments

Updated with final version of this article, as published in Medical Physics; 14 pages, 12 figures