Breast cancer nuclei segmentation with fuzzy clustering method

In this thesis, an approach for nuclei breast cancer detection and segmentation in histopathological images is proposed. This approach relies on a fuzzy clustering method, which is pre-trained on an auxiliary domain with very large labelled images, and coupled with an additional network composed of fully connected layers. In this thesis, fuzzy clustering mean is used for clustering and segmentation and get the effective ways for breast cancer nuclei detection. Wherefore, a fuzzy clustering mean has been used to detect the centers of breast cancer nuclei, then the extracted centers were compared with the ground truth samples. The mentioned methods were applied by using 489 images from 810 histological images. that this work passes through many experimental stages, of detection and segmentation by applying a combinations of more than one effective methods. KEYWORDS:Image segmentation, Fuzzy clustering mean, Nuclei image