A deep learning approach using synthetic images for segmenting and estimating 3D orientation of nanoparticles in EM images.

Journal: Computer methods and programs in biomedicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVE: Nanoparticles present properties that can be applied to a wide range of fields such as biomedicine, electronics or optics. The type of properties depends on several characteristics, being some of them related with the particle structure. A proper characterization of nanoparticles is crucial since it could affect their applications. To characterize a particle shape and size, the nanotechnologists employ Electron Microscopy (EM) to obtain images of nanoparticles and perform measures over them. This task could be tedious, repetitive and slow, we present a Deep Learning method based on Convolutional Neural Networks (CNNs) to detect, segment, infer orientations and reconstruct microscope images of nanoparticles. Since machine learning algorithms depend on annotated data and there is a lack of annotated datasets of nanoparticles, our work makes use of artificial datasets of images resembling real nanoparticles photographs.

Authors

  • Antón Cid-Mejías
    Biomedical Informatics Group (GIB), Escuela Técnica Superior de Ingenieros Informáticos, Universidad Politécnica de Madrid, Campus de Montegancedo S/N, Madrid 28660, Spain.
  • Raul Alonso-Calvo
    Biomedical Informatics Group, Universidad Politécnica de Madrid, Madrid, Spain.
  • Helena Gavilán
    Instituto de Ciencia de Materiales de Madrid, ICMM/CSIC, Cantoblanco, Madrid 28049, Spain.
  • José Crespo
    Biomedical Informatics Group (GIB), Escuela Técnica Superior de Ingenieros Informáticos, Universidad Politécnica de Madrid, Campus de Montegancedo S/N, Madrid 28660, Spain.
  • Victor Maojo
    Biomedical Informatics Group, DIA & DLSIIS, ETSI Informáticos, Universidad Politécnica de Madrid, Boadilla del Monte, Spain.