Adaptive Histogram Equalization For Detecting Cancer In Digital Mammogram

Saranya Sathyamurthy, Dr. C. Lakshmi

Abstract: Breast cancer is a malignant tumor (a collection of cancer cells) arising from the cells of the breast. Breast cancer is the most common cancer among American women. One in every eight women in the United States develops breast cancer. According to the American Cancer society, over 200, 000 new cases of invasive breast cancer are diagnosed each year. Nearly 40, 000 women are expected to die of breast cancer in 2012. After 50 years of age, yearly mammograms are recommended (American College of Obstetrics and Gyanecology). Patients with a family history or specific risk factors might have a different screening schedule including starting screening mammograms at an earlier age. In this paper, an algorithm for extracting masses in mammographic image is done. Here, we use adaptive Histogram equalization, to provide enhancement to the image. Then, we go for feature extraction using gradient vector flow field. Training of the samples is done using PNN and the tumor is detected. The results are indicated to be effective and efficient.

Keywords: Adaptive histogram Equalization, Gradient Vector Flow field, Feature Extraction PNN Training and Classification

How to Cite?: Saranya Sathyamurthy, Dr. C. Lakshmi, "Adaptive Histogram Equalization For Detecting Cancer In Digital Mammogram", Volume 2 Issue 5, May 2013, International Journal of Science and Research (IJSR), Pages: 309-310, https://www.ijsr.net/getabstract.php?paperid=IJSROFF2013228, DOI: https://dx.doi.org/10.21275/IJSROFF2013228