Tensor classification of N-point correlation function features for histology tissue segmentation

Med Image Anal. 2009 Feb;13(1):156-66. doi: 10.1016/j.media.2008.06.020. Epub 2008 Jul 25.

Abstract

In this paper, we utilize the N-point correlation functions (N-pcfs) to construct an appropriate feature space for achieving tissue segmentation in histology-stained microscopic images. The N-pcfs estimate microstructural constituent packing densities and their spatial distribution in a tissue sample. We represent the multi-phase properties estimated by the N-pcfs in a tensor structure. Using a variant of higher-order singular value decomposition (HOSVD) algorithm, we realize a robust classifier that provides a multi-linear description of the tensor feature space. Validated results of the segmentation are presented in a case-study that focuses on understanding the genetic phenotyping differences in mouse placentae.

MeSH terms

  • Algorithms*
  • Animals
  • Female
  • Image Enhancement / methods
  • Image Interpretation, Computer-Assisted / methods*
  • Mice
  • Microscopy / methods*
  • Pattern Recognition, Automated / methods*
  • Placenta / cytology*
  • Pregnancy
  • Pregnancy, Animal
  • Reproducibility of Results
  • Sensitivity and Specificity