Computer-supported angiogenesis quantification using image analysis and statistical averaging

IEEE Trans Inf Technol Biomed. 2008 Sep;12(5):650-7. doi: 10.1109/TITB.2008.926463.

Abstract

Angiogenesis is a complex process, involving multiple crosstalks among tumor, endothelial, and stromal cells in order to establish a biochemical network for oxygen and nutrients supply, necessary for the promotion of tumor growth. In this sense, measuring angiogenic activity is considered an informative marker of tumor growth or its inhibition. One of the most popular testbeds for the study of angiogenesis is developing chick embryo and its chorioallantoic membrane (CAM). In this paper, an automated image analysis and statistical processing method for the extraction of features informative for the angiogenic process is proposed and a Web-based tool that provides an unbiased quantification of the microvessel density and growth in angiogenic CAM images is described. The applicability of the tool is tested in two datasets, concerning: 1) the quantification and subsequent detection of tumor growth at different stages of embryonic development and 2) the inhibitory effect of dexamethasone (i.e., an inhibitor of the angiogenesis phenomenon) over a series of CAM samples. Experimental results presented in this paper indicate the efficiency of the automated angiogenesis quantification method regarding both tumor growth and inhibition detection.

MeSH terms

  • Algorithms*
  • Angiography / methods*
  • Animals
  • Artificial Intelligence*
  • Chick Embryo / blood supply*
  • Chick Embryo / diagnostic imaging*
  • Data Interpretation, Statistical
  • Neovascularization, Pathologic / diagnostic imaging*
  • Pattern Recognition, Automated / methods*
  • Radiographic Image Enhancement / methods
  • Radiographic Image Interpretation, Computer-Assisted / methods*
  • Reproducibility of Results
  • Sensitivity and Specificity