Assesment of Tumor in Breast MRI using Kapur's Thresholding and Active Contour Segmentation

Abstract

The cancer is a dangerous disease and untreated cancer lead to death. Breast Cancer (BC) mostly affects women community due to various reasons ranging from the genetic to the lifestyle. The screening of BC normally involves in a personal check followed by a clinical level confirmation with a biopsy test and the imaging procedures. The biopsy is a commonly employed invasive technique considered to identify the occurrence and the stage of the cancer. The imaging procedure based on a chosen modality is widely preferred in clinics, due to its non-invasive nature. The proposed work aims to develop a tumor segmentation system to examine the BC tumors using the breast MRI. The proposed technique implements the Cuckoo-Search (CS) based Kapur's thresholding and the Active-Contour (AC) segmentation to extract the tumor from the threshold breast MRI. Finally, a comparison among the ground-truth and the extracted BC tumor is performed to authenticate the performance of the proposed methodology. The outcome of this research confirms that, proposed system helps to attain a segmentation accuracy of >99% on the chosen breast MRIs.