Data preprocessing for automatic WMH segmentation with FCNNs

  1. P. Duque
  2. J. M. Cuadra
  3. E. Jiménez
  4. Mariano Rincón-Zamorano
Libro:
From Bioinspired Systems and Biomedical Applications to Machine Learning: 8th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2019, Almería, Spain, June 3–7, 2019, Proceedings, Part II
  1. José Manuel Ferrández Vicente (dir. congr.)
  2. José Ramón Álvarez-Sánchez (dir. congr.)
  3. Félix de la Paz López (dir. congr.)
  4. Javier Toledo Moreo (dir. congr.)
  5. Hojjat Adeli (coord.)

Editorial: Springer Suiza

ISBN: 978-3-030-19651-6

Año de publicación: 2019

Páginas: 452-460

Tipo: Capítulo de Libro

DIALNET GOOGLE SCHOLAR

Resumen

Automatic segmentation of brain white matter hyperintensities(WMH) is a challenging problem. Recently, the proposals basedon Fully Convolutional Neural Networks (FCNN) are giving very good results, as it is demostrated by the top WMH challenge architectures.However, the problem is non completely solved yet. In this paper we analyze the influence of preprocessing stages of the input data on a fully convolutional network (FCNN) based on the U-NET architecture. Results demostrate that standarization, skull stripping and contrast enhancement significantly influence the results of segmentation.

Fuente de los datos: Dialnet