F1: Clinical Engineering

A COMPREHENSIVE ANALYSIS ON BREAST CANCER CLASSIFICATION WITH RADIAL BASIS FUNCTION AND GAUSSIAN MIXTURE MODEL

Sunil Kumar Prabhakar, Harikumar Rajaguru, 

Bannari Amman Institute of Technology, India

Cancer is a type of deadly disease where a particular group of cells display growth which becomes uncontrollable after a certain period of time. Breast Cancer is a type of cancer which affects the inner lining of the milk ducts. The symptoms of breast cancer include the shape alteration of the breast size, nipple discharge, swelling of the lymph node and pain in the nipple. There are several types of breast cancer like lobular carcinoma, ductal carcinoma, invasive lobular carcinoma, inflammatory breast carcinoma etc. The risk factor of breast cancer includes factors like sex, hormonal fluctuations, alcohol intake, environmental and genetic factors, other abnormalities in the human body along with a high fat diet. In this work, a simple, cost effective and non-invasive strategy to detect the breast cancer at an early stage is proposed with the help of techniques such as Gaussian Mixture Model (GMM) and Radial Basis Function (RBF). As cancer staging is divided into clinical and pathological stage, the TNM (Tumour Node Metasis) prognostic tools are identified and the TNM variables such as tumour size, history of breast feeding, menstrual cycle, hereditary, food habits, etc. are used as input variables for both the types of classifiers. The data collection was obtained from 75 breast cancer patients at the cancer centre of Kuppuswamy Naidu Memorial Hospital, Coimbatore, India. The Performance Metrics taken here are Specificity,Sensitivity, Accuracy, Perfect Classification, Missed Classification , False Alarm and Performance Index. Results show an average accuracy of 89.60% is obtained with GMM classifier and an average accuracy of 92.75% is obtained with RBF classifier.

Organised by

Endorsed by

 

        Supported by
 

 

                          
     

       

                             
           
 

        Supporting Media