Kernel Induced Rough c-means clustering for lymphocyte image segmentation

Blood microscopic image segmentation is a fundamental tool for automated diagnosis of hematological disorders. In particular, lymphoblast image segmentation acts as the foundation for all image based leukemia diagnostic system. Precision in image segmentation is a necessary condition for improving t...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohapatra, S., Patra, D., Kumar, S., Satpathi, S.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Approximation methods
Blood
clustering
Clustering algorithms
Image color analysis
Image segmentation
Kernel
Lymphocyte
parametric kernel
rough sets
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Blood microscopic image segmentation is a fundamental tool for automated diagnosis of hematological disorders. In particular, lymphoblast image segmentation acts as the foundation for all image based leukemia diagnostic system. Precision in image segmentation is a necessary condition for improving the diagnostic accuracy in automated cytology. Since the diagnostic information content of the segmented images are plentiful, suitable segmentation routines need to be developed for better disease recognition. In this paper, Kernel Induced Rough C-means (KIRCM) clustering algorithm is introduced for the segmentation of human lymphocyte images. Rough C-means clustering (RCM) is performed in higher dimensional feature space to obtain improved segmentation accuracy and to facilitate automated Acute Lymphoblastic Leukemia (ALL) detection. Comparative analysis reveals that use of rough sets in kernel space clustering for leukocyte segmentation gives the proposed scheme an edge over existing schemes.
DOI:10.1109/IHCI.2012.6481865