Convolutional Neural Networks with Template-Based Data Augmentation for Functional Lung Image Quantification.

Journal: Academic radiology
Published Date: Sep 6, 2018

Abstract

RATIONALE AND OBJECTIVES: We propose an automated segmentation pipeline based on deep learning for proton lung MRI segmentation and ventilation-based quantification which improves on our previously reported methodologies in terms of computational efficiency while demonstrating accuracy and robustness. The large data requirement for the proposed framework is made possible by a novel template-based data augmentation strategy. Supporting this work is the open-source ANTsRNet-a growing repository of well-known deep learning architectures first introduced here.

Authors

  • Nicholas J Tustison
    a Department of Radiology and Medical Imaging.
  • Brian B Avants
    Cingulate, Hampton, New Hampshire.
  • Zixuan Lin
    Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, Virginia.
  • Xue Feng
    Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, Virginia.
  • Nicholas Cullen
    Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania.
  • Jaime F Mata
    Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, Virginia.
  • Lucia Flors
    Department of Radiology, University of Missouri, Columbia, Missouri.
  • James C Gee
    Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
  • Talissa A Altes
    Department of Radiology, University of Missouri, Columbia, Missouri.
  • John P Mugler Iii
    Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, Virginia.
  • Kun Qing
    Radiology & Medical Imaging, University of Virginia, Charlottesville, Virginia, United States of America.

Keywords

External Resources

Popular Topics
Recent Journals