Image analysis for neuroblastoma classification: segmentation of cell nuclei

Conf Proc IEEE Eng Med Biol Soc. 2006:2006:4844-7. doi: 10.1109/IEMBS.2006.260837.

Abstract

Neuroblastoma is a childhood cancer of the nervous system. Current prognostic classification of this disease partly relies on morphological characteristics of the cells from H&E-stained images. In this work, an automated cell nuclei segmentation method is developed. This method employs morphological top-hat by reconstruction algorithm coupled with hysteresis thresholding to both detect and segment the cell nuclei. Accuracy of the automated cell nuclei segmentation algorithm is measured by comparing its outputs to manual segmentation. The average segmentation accuracy is 90.24+/-5.14%

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Algorithms
  • Automation
  • Brain Neoplasms / diagnosis*
  • Brain Neoplasms / pathology*
  • Cell Nucleus / metabolism*
  • Diagnosis, Differential
  • Equipment Design
  • Humans
  • Image Interpretation, Computer-Assisted / instrumentation
  • Image Processing, Computer-Assisted / instrumentation*
  • Image Processing, Computer-Assisted / methods*
  • Medical Oncology / instrumentation*
  • Medical Oncology / methods
  • Neuroblastoma / diagnosis*
  • Neuroblastoma / pathology*
  • Pattern Recognition, Automated
  • Prognosis
  • Reproducibility of Results