Efficient Diagnosis of Breast Cancer Using Statistical Parameters

Abstract: Breast cancer has become the leading cause of cancer deaths among women. To decrease the related mortality, disease must be treated early, but it is hard to detect and diagnose tumors at an early stage. Manual attempt have proven to be time taking and inefficient in many cases. Hence there is a need for efficient methods that diagnoses the cancerous cell without involvement of humans with high accuracy. This paper proposes an automated technique using artificial neural network as decision making tools in the field of breast cancer. Image Processing plays significant role in cancer detection when input data is in the form of images. Statistical parameter analysis of image is important in mammogram classification. Statistical parameters are extracted by using image processing The statistical parameter include entropy, mean, energy, correlation, texture, standard deviation, variance, MSE, PSNR. We have also include the comparative analysis of Statistical parameter using bar graph. This parameters will act as a inputs to ANN which will diagnose and give the result whether image is cancerous or non-cancerous.

Keywords: Artificial neural network, Image processing, Statistical parameter, ANN.