Breast Tumor Segmentation on Medical Images using Combination of Fuzzy Clustering and Threshold

Abstract

Breast tumor segmentation and boundary detection are crucial stages in breast cancer therapy and follow-up. Radiologists can minimize the high workload of breast cancer analysis by automating this difficult process. This article established a system for accurately segmenting breast tumors and non-infected areas of the breast on medical imaging using a combination of Fuzzy Clustering Means and Threshold (FCMT). This computer-aided diagnostic method works on each breast slice without any training for segmentation and boundary detection. Two databases of breast mammogram images have been used: the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) and a private dataset. We used preprocessing techniques such as contrast augmentation before applying the FCMT for segmentation to increase the image quality. To assess the effectiveness of the devised approach, the dice coefficient (F1-score) and Intersection over Union (IOU) were computed. Using the proposed FCMT segmentation technique, the mean IOU of 97.34 and an F1-score of 95.39 were attained. According to the results of the experiments, the method shown is more durable and accurate when it comes to separating tumor growth on medical images.