Automatic Diagnosis of Breast Cancer using Thermographic Color Analysis and SVM Classifier

摘要

Breast cancer is the commonly found cancer in women. Studies show that the detection at the earliest can bring down the mortality rate. Infrared Breast thermography uses the temperature changes in breast to arrive at diagnosis. Due to increased cell activity, the tumor and the surrounding areas has higher temperature emitting higher infrared radiations. These radiations are captured by thermal camera and indicated in pseudo colored image. Each colour of thermogram is related to specific range of temperature. The breast thermogram interpretation is primarily based on colour analysis and asymmetry analysis of thermograms visually and subjectively. This study presents analysis of breast thermograms based on segmentation of region of interest which is extracted as hot region followed by colour analysis. The area and contours of the hottest regions in the breast images are used to indicate abnormalities. These features are further given to ANN classifier for automated analysis. The results are compared with doctor's diagnosis to confirm that infra-red thermography is a reliable diagnostic tool in breast cancer identification.