Automated segmentation of Mitotic Cells for in vitro histological evaluation of oral squamous cell carcinoma

摘要

In in vitro histological assessment, mitotic cells play one of the key roles for the diagnosis of oral squamous cell carcinoma (OSCC). In view of this, our paper aims to develop a computer assisted mitotic cell segmentation scheme for automated recognition from microscopic images of OSCC. The methodology includes multilevel thresholding, statistical moment features and classification and regression tree (CART) model. Performance of the proposed algorithm has also been evaluated.