Color analysis of thermograms for breast cancer detection

Abstract

Breast cancer is the most common cancer in women. Findings show that early detection of breast cancer can improve survival rate. Mammography is the standard method of diagnosing breast cancer; but Infrared Breast thermography is an imaging technique that provides information based on the temperature changes in breast. This information is precancerous alarms that may lead to tumor. Thermography helps to detect cancer in its early stages, thus survival is possible. Thermal or Infrared radiations emitted from human body are higher around the regions where an tumour is present essentially due to increased cell activity. The thermal information can be shown in a pseudo coloured image where each colour represents a specific range of temperature. Clinical interpretation of breast thermogram is primarily based on colour analysis of the heat patterns visually and subjectively. This study endeavours to present analysis of breast thermogram based on segmentation of region of interest which is extracted a hot region followed by color analysis. The shape, size and borders of the hottest regions of the images can help to determine features which are used to detect abnormalities. The abnormality of breast thermograms is indicated by these features and it is confirmed by comparing with doctors diagnosis. Hence suitability of infrared thermography as a diagnostic tool in breast cancer detection is establihed through this study.