Accurate segmenting of cervical tumors in PET imaging based on similarity between adjacent slices

Comput Biol Med. 2018 Jun 1:97:30-36. doi: 10.1016/j.compbiomed.2018.04.009. Epub 2018 Apr 16.

Abstract

Because in PET imaging cervical tumors are close to the bladder with high capacity for the secreted 18FDG tracer, conventional intensity-based segmentation methods often misclassify the bladder as a tumor. Based on the observation that tumor position and area do not change dramatically from slice to slice, we propose a two-stage scheme that facilitates segmentation. In the first stage, we used a graph-cut based algorithm to obtain initial contouring of the tumor based on local similarity information between voxels; this was achieved through manual contouring of the cervical tumor on one slice. In the second stage, initial tumor contours were fine-tuned to more accurate segmentation by incorporating similarity information on tumor shape and position among adjacent slices, according to an intensity-spatial-distance map. Experimental results illustrate that the proposed two-stage algorithm provides a more effective approach to segmenting cervical tumors in 3D18FDG PET images than the benchmarks used for comparison.

Keywords: Cervical PET; Graph-cut; Similarity-based variational model; Tumor segmentation.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Female
  • Humans
  • Image Interpretation, Computer-Assisted / methods*
  • Positron-Emission Tomography / methods*
  • Uterine Cervical Neoplasms / diagnostic imaging*