Robust pulmonary nodule segmentation in CT: improving performance for juxtapleural cases

  • Authors:

  • K. Okada;V. Ramesh;A. Krishnan;M. Singh;U. Akdemir

  • Affiliations:

  • Real-Time Vision & Modeling Dept., Siemens Corporate Research, Princeton;Real-Time Vision & Modeling Dept., Siemens Corporate Research, Princeton;CAD Program, Siemens Medical Solutions, Malvern;Real-Time Vision & Modeling Dept., Siemens Corporate Research, Princeton;Real-Time Vision & Modeling Dept., Siemens Corporate Research, Princeton

  • Venue:
  • MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Two novel methods are proposed for robust segmentation of pulmonary nodules in CT images. The proposed solutions locate and segment a nodule in a semi-automatic fashion with a marker indicating the target. The solutions are motivated for handling the difficulty to segment juxtapleural, or wall-attached, nodules by using only local information without a global lung segmentation. They are realized as extensions of the recently proposed robust Gaussian fitting approach. Algorithms based on i) 3D morphological opening with anisotropic structuring element and ii) extended mean shift with a Gaussian repelling prior are presented. They are empirically compared against the robust Gaussian fitting solution by using a large clinical high-resolution CT dataset. The results show 8% increase, resulting in 95% correct segmentation rate for the dataset.