Breast cancer (Ductal Carcinoma) detection and classification software using fuzzy pattern recognition

• Main Authors: Lorenzo, Eric Meyn C., Montalban, Ivan Gregg C., Real, John Reginald G., So Kua, Donard V.
• Format: text
• Language: English
• Published: Animo Repository 2007
• Subjects: Breast > Radiography > Automation; Image processing > Digital techniques; Computer Engineering
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/14313
• Institution: De La Salle University

The research deals on the detection and classification of Breast Carcinoma particularly Ductal Carcinoma. The study takes on the characteristics and definitions of Ductal Carcinoma by having a digital image from stained breast tissue samples, as seen in the microscope, analyzed and evaluated using Image Processing (first module) and Fuzzy Pattern Recognition (second module). The first module analyzes the Terminal Duct Lobular Unit (TDLU) by implementing a number of processing techniques such as Nuclei Extraction, Filtering and Feature Extraction to name a few. The second module uses Fuzzy Membership Functions to evaluate the degree and level at which the image is an Invasive Carcinoma (malignant) or Noninvasive (benign) and if invasive, would it be an Invasive Ductal Carcinoma NST (no specific type) or of a different type. The overall accuracy of the study is 95%.