Automated Segmentation of Nuclei in Breast Cancer Histopathology Images

Abstract

The process of Nuclei detection in high-grade breast cancer images is quite challenging in the case of image processing techniques due to certain heterogeneous characteristics of cancer nuclei such as enlarged and irregularly shaped nuclei, highly coarse chromatin marginalized to the nuclei periphery and visible nucleoli. Recent reviews state that existing techniques show appreciable segmentation accuracy on breast histopathology images whose nuclei are dispersed and regular in texture and shape; however, typical cancer nuclei are often clustered and have irregular texture and shape properties. This paper proposes a novel segmentation algorithm for detecting individual nuclei from Hematoxylin and Eosin (H&E) stained breast histopathology images. This detection framework estimates a nuclei saliency map using tensor voting followed by boundary extraction of the nuclei on the saliency map using a Loopy Back Propagation (LBP) algorithm on a Markov Random Field (MRF). The method was tested on both whole-slide images and frames of breast cancer histopathology images. Experimental results demonstrate high segmentation performance with efficient precision, recall and dice-coefficient rates, upon testing high-grade breast cancer images containing several thousand nuclei. In addition to the optimal performance on the highly complex images presented in this paper, this method also gave appreciable results in comparison with two recently published methods—Wienert et al. (2012) and Veta et al. (2013), which were tested using their own datasets.

Computational method for unsupervised segmentation of lymphoma histological images based on fuzzy 3-partition entropy and genetic algorithm

“…The segmentation of Paramanandam et al (2016) presented a poor performance across all lesions. The parameter of this algorithm corresponding to the width of a typical region of interest was set to 4, which was shown to be an adequate value for application on the images used.…”

“…A common limitation of this method among the lesions was the identification of two nuclei as one object, indicated by red rectangles. ( Comaniciu & Meer, 2002 ) 79.74% 48% 86% 1.21 Vahadane and Sethi (2013) 77.07% 21% 88% 1.16 Wienert et al (2012) 78.53% 47% 84% 1.25 de Oliveira et al (2013) 70.60% 67% 71% 1.43 Phoulady et al (2016) 71.97% 70% 72% 3.77 Paramanandam et al (2016) 81.85% 4% 96% 0.42…”

“…In order to evaluate the proposed method and the aforementioned techniques, Tables 4-6 show their quantitative per-formance. These results were obtained by the metrics of accuracy, sensitivity, specificity and variation of information of the proposed method, mean-shift and techniques of Vahadane and Sethi (2013) , Wienert et al (2012) , de Oliveira et al (2013 , Phoulady et al (2016) and Paramanandam et al (2016) .…”

“…The metrics of accuracy, sensitivity, specificity and variation of information were applied for quantitative evaluations. The performance of the proposed algorithm was compared to the results provided by the mean-shift technique ( Comaniciu & Meer, 2002 ) and the approaches proposed by de Oliveira et al (2013) ;Phoulady, Goldgof, Hall, and Mouton (2016) ; Vahadane and Sethi (2013) ; Wienert et al (2012) and Paramanandam et al (2016) .…”

The Feature Selection Problem in Computer–Assisted Cytology

“…Sometimes, even for a human, it can be hard to extract nuclei from clumps. Nuclei had until recently been segmented using classical segmentation methods such as intensity thresholding, the watershed method or active contours (Irshad et al, 2014;Yang et al, 2006;Więcławek and Piętka, 2015;Koyuncu et al, 2016;Piórkowski, 2016;Paramanandam et al, 2016;Kłeczek et al, 2017).…”