Cellular Image Segmentation using Morphological Operators and Extraction of Features for Quantitative Measurement

Anuranjeeta^1*, Sanjay Saxena¹, K. K. Shukla² and Shiru Sharma¹

¹School of Biomedical Engineering, Indian Institute of Technology, Banaras Hindu University, Varanasi, India. ²Department of Computer Engineering, Indian Institute of Technology, Banaras Hindu University, Varanasi, India. Corresponding Author Email: anuranjeeta.rs.bme11@itbhu.ac.in  

DOI : http://dx.doi.org/10.13005/bbra/2139

ABSTRACT: To address the issue of blurriness, artifacts, overlapping of cells and uneven dying of histopathology images of breast cancer cells, a computer assisted image analysis and feature extraction method has been proposed in the present paper which include pre-processing, enhancement, segmentation and features extraction. The proposed method is based on the dysplastic features that work on the computation of features for differentiation of benign and malignant cells. Morphological measures have been significantly used to analyse these features. The purpose of choosing morphological operators is based on the fact that these operators principally utilize regularities and distribution of the structural features of cells. Analysis of cell morphology is an important factor as it aids in the complete evaluation of the microscopic cells, examination of the cell behaviour, and also provides the quantitative measure of area, perimeter, intensity and texture, etc. present in large populations of cells. For the implementation of proposed method publicly available image data set of 58 images (26 malignant and 32 benign) has been used. It is observed that malignant cells have considerably greater magnitude for computed features as compared to benign. Significant variation in feature values is also found in case of malignant cells. Apart from this, an efficient approach of segmenting cells present in the histopathology images has been shown, that will provide assistance to the pathologist to identify malignant cells. The results reported here can be  further used in the classification of cells into benign and malignant categories.

KEYWORDS: Image processing; Segmentation; Cancer; Histopathology; Morphological features

[ HTML Full Text]