Proliferation Index Evaluation in Breast Cancer Using ImageJ and ImmunoRatio Applications

Abstract

Background: Proliferation index (PI) plays a critical role in distinguishing surrogate biological subtypes of breast cancer and, thus, determining the optimal therapeutic scheme. The commonly applied method of determining PI is visual semiquantitative scoring. The most precise way of PI evaluation is formal counting of nuclei on a digital picture using software equipped with a pointer function. The less time-consuming solution may be using image analysis software enabling automatic counting of nuclei, such as the free web application ImmunoRatio.

Materials and methods: We analyzed a group of 98 patients diagnosed with invasive breast carcinoma. A digital image of the hot-spot was taken from each case. Cell Counter plug-in of ImageJ platform was employed to precisely count brown- and blue-stained nuclei. The same images were analyzed using ImmunoRatio. The results were compared using Pearson's and Spearman's coefficients. The agreement was assessed with Cohen's kappa.

Results: Pearson's correlation coefficient was 0.84 (p<0.05), Spearman's correlation coefficient was 0.83 (p<0.05). Moderate agreement was shown by Cohen's kappa calculation (K= 0.47; p<0.05).

Conclusion: As many as 26 cases were classified to different biological subtypes depending on the method of PI assessment. Thus, ImmunoRatio needs further improvement to be a reliable diagnostic tool.

Keywords: ImageJ; ImmunoRatio; Ki-67; Proliferation index; breast cancer; cell counter; image analysis.