Segmentation of overlapping cervical cells: A variational method with star-shape prior

Abstract

Accurate and automatic detection and delineation of cervical cells are two critical precursor steps to automatic Pap smear image analysis and detecting pre-cancerous changes in the uterine cervix. To overcome noise and cell occlusion, many segmentation methods resort to incorporating shape priors, mostly enforcing elliptical shapes (e.g. [1]). However, elliptical shapes do not accurately model cervical cells. In this paper, we propose a new continuous variational segmentation framework with star-shape prior using directional derivatives to segment overlapping cervical cells in Pap smear images. We show that our star-shape constraint better models the underlying problem and outperforms state-of-the-art methods in terms of accuracy and speed.

Ähnliche Arbeiten