WORLD JOURNAL OF ADVANCE
HEALTHCARE RESEARCH

Dr. Prasanna G. Shete* and Dr. Gajanan K. Kharate

ABSTRACT

The paper discusses an approach involving digital image processing for estimating the extent of cancer in a breast tissue sample. The process aims at providing a reliable, repeatable, fast and cost-effective method that could replace the traditional method of manual examination and subsequent estimation. The markers discussed in the paper are the Human Epidermal Growth Factor Receptor (HER2) and the Estrogen Receptor (ER) that give clear indications of the presence of cancer cells in the tissue sample. ER and PR evaluation, a modified watershed algorithm designed for eliminating errors arising due to over-segmentation in traditional watershed algorithm is proposed to provide comparatively more accurate results. HER2 evaluation, the ratio of extent of staining to the total size of image gives an estimate of the extent of cancer cell spread. An innovative approach of classifying and correlating the makers on single patient, known as three marker method. The statistical result analysis is validated with doctors. IHC marker i.e. HER2 is evaluated, the percentage of staining is calculated in terms of ratio of stain pixel count to the total pixel count. The evaluation of HER2 is obtained through simulation software (MATLAB) using intensity based algorithm and same is run on embedded processor evaluation board Devkit 8500. The results are validated with doctors. The statistical analysis is given in Table IV.