Diagnosis of Breast Cancer by K-Mean Clustering and Otsu Thresholding Segmentation Methods

Breast cancer has increased decidedly among women. But with early diagnosis, a positive response to treatment can be given. Researchers are conducting various studies in imaging methods detect the disease and accurately. In this study, 9 cancerous images taken from TCİA image data bank were detected by K-mean clustering Otsu threshold method. Performance metrics evaluated comparing them marked reference (ground truth) radiologist. For process, TPR (True Positive Rate) 0.89, FPR (False 0.14, similarity 0.67, accuracy 0.87, sensitivity exact hit ratio 0.86, specificity F Score 0.87 found, respectively. Otsu, 0.84, 0.12, 0.73, 0.84 calculated. The aim of study is determine tumor boundaries more accurately use devices field health pixel-based segmentation. As result, both successful used close each other.