Automatic leukocyte nucleus segmentation by intuitionistic fuzzy divergence based thresholding

Abstract

Abstract-The paper proposes a robust approach to automatic segmentation of leukocyte"s nucleus from microscopic blood smear images under normal as well as noisy environment by employing a new exponential intuitionistic fuzzy divergence based thresholding technique. The algorithm minimizes the divergence between the actual image and the ideally thresholded image to search for the final threshold. A new divergence formula based on exponential intuitionistic fuzzy entropy has been proposed. Further, to increase its noise handling capacity, a neighborhood-based membership function for the image pixels has been designed. The proposed scheme has been applied on 110 normal and 54 leukemia (chronic myelogenous leukemia) affected blood samples. The nucleus segmentation results have been validated by three expert haematologists. The algorithm achieves an average segmentation accuracy of 98.52% in noise-free environment. It beats the competitor algorithms in terms of several other metrics. The proposed scheme with neighborhood based membership function outperforms the competitor algorithms in terms of segmentation accuracy under noisy environment. It achieves 93.90% and 94.93% accuracies for Speckle and Gaussian noises respectively. The average area under the ROC curves comes out to be 0.9514 in noisy conditions, which proves the robustness of the proposed algorithm.

Robust leukocyte segmentation in blood microscopic images based on intuitionistic fuzzy divergence

“…Due to influence of nucleus segmentation on robustness of leukocyte detection, four competitor nucleus segmentation algorithms including Otsu method [7], nucleus segmentation using Gram-Schmidt orthogonalization (GSO) [3], intuitionistic fuzzy divergence based for gray level thresholding (IFD_g) [9] and proposed algorithm based on intuitionistic fuzzy divergence using *a component of L*a*b color space have been compared. where Aalgorithm and Aexpert denotes segmented area by algorithm and expert respectively.…”

“…Detailed description about derivation of divergence formula and threshold selection is discussed in [9].…”

“…Leukocyte segmentation algorithm using hedgeoperator based fuzzy divergence measure developed in [8]. A robust approach for segmentation of leukocyte's nucleus by new exponential intuitionistic fuzzy divergence based thresholding technique is presented in [9].The method includes minimization of intuitionistic fuzzy divergence between the ideally thresholded image and actual image. Paper [10] involves Leucocyte segmentation for leukemia detection.…”

“…Few papers such as [6,9,16] are devoted toward achieving robust segmentation performance. A common drawback observed in these papers is that they don't test images taken from various database so robustness of these method are not authentic (trustworthy) enough.…”

Automated identification of keratinization and keratin pearl area from in situ oral histological images

“…As pre-processing task, colour space transformation provides better information in many applications especially when image contrast enhancement has been taken into consideration (Jati et al, 2014;Mukherjee et al, 2014;Yadav et al, 2013). In view of this, different colour channels from six frequently used colour transformation techniques such as RGB, YDbDr, CMY, HSV, YUV and Lab are extracted (Fig.…”