Automated nuclear segmentation in skin histopathological images using multi-scale radial line scanning

Abstract

Segmentation of cell nuclei is an important step towards automatic analysis of microscopic images. This paper presents an automated technique for nuclear segmentation in skin histopathological images. The proposed technique first detects nuclear seeds using a bank of generalized Laplacian of Gaussian (gLoG) kernels. Based on the detected nuclear seeds, a multi-scale radial line scanning (mRLS) method combined with dynamic programming (DP) is utilized to delineate a set of candidate nuclear boundaries. The gradient, intensity and shape information are then integrated to determine the optimal boundary for each nucleus in the image. Experimental results on 28 H&E stained skin histopathological images show that the proposed technique is superior to conventional schemes in nuclear segmentation.