19 March 2015 Improved segmentation of abnormal cervical nuclei using a graph-search based approach
Author Affiliations +
Abstract
Reliable segmentation of abnormal nuclei in cervical cytology is of paramount importance in automation-assisted screening techniques. This paper presents a general method for improving the segmentation of abnormal nuclei using a graph-search based approach. More specifically, the proposed method focuses on the improvement of coarse (initial) segmentation. The improvement relies on a transform that maps round-like border in the Cartesian coordinate system into lines in the polar coordinate system. The costs consisting of nucleus-specific edge and region information are assigned to the nodes. The globally optimal path in the constructed graph is then identified by dynamic programming. We have tested the proposed method on abnormal nuclei from two cervical cell image datasets, Herlev and H and E stained liquid-based cytology (HELBC), and the comparative experiments with recent state-of-the-art approaches demonstrate the superior performance of the proposed method.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ling Zhang, Shaoxiong Liu, Tianfu Wang, Siping Chen, Milan Sonka, "Improved segmentation of abnormal cervical nuclei using a graph-search based approach", Proc. SPIE 9420, Medical Imaging 2015: Digital Pathology, 94200W (19 March 2015); doi: 10.1117/12.2082856; https://doi.org/10.1117/12.2082856
PROCEEDINGS
7 PAGES


SHARE
Back to Top