Iterative h‐minima‐based marker‐controlled watershed for cell nucleus segmentation

Abstract

Automated microscopy imaging systems facilitate high-throughput screening in molecular cellular biology research. The first step of these systems is cell nucleus segmentation, which has a great impact on the success of the overall system. The markercontrolled watershed is a technique commonly used by the previous studies for nucleus segmentation. These studies define their markers finding regional minima on the intensity/gradient and/or distance transform maps. They typically use the h-minima transform beforehand to suppress noise on these maps. The selection of the h value is critical; unnecessarily small values do not sufficiently suppress the noise, resulting in false and oversegmented markers, and unnecessarily large ones suppress too many pixels, causing missing and undersegmented markers. Because cell nuclei show different characteristics within an image, the same h value may not work to define correct markers for all the nuclei. To address this issue, in this work, we propose a new watershed algorithm that iteratively identifies its markers, considering a set of different h values. In each iteration, the proposed algorithm defines a set of candidates using a particular h value and selects the markers from those candidates provided that they fulfill the size requirement. Working with widefield fluorescence microscopy images, our experiments reveal that the use of multiple h values in our iterative algorithm leads to better segmentation results, compared to its counterparts. V C 2016 International Society for Advancement of Cytometry

Object‐Oriented Segmentation of Cell Nuclei in Fluorescence Microscopy Images

“…Visual results obtained by the algorithms for various subimages: ( a ) annotated nuclei in the gold standard, ( b ) results by the proposed object‐oriented method, ( c ) results by the iterative voting method , ( d ) results by the single‐pass voting method , ( e ) results by the adaptive h‐minima method , ( f ) results by the ARGraphs method , and ( g ) results by the iterative h‐minima method . The subimage sizes have been scaled for better visualization.…”

“…Afterward, considering the correctly identified pixels of only the true positive nuclei as true positive pixels, the pixel‐level precision, recall, and F ‐score metrics are calculated. Note that in this work, we used the same nucleus‐ and pixel‐level quantitative evaluation with our previous studies , the results of which will be provided for comparison.…”

“…They then identify regions with larger votes as nucleus centers . It is also possible to use pixel gradients to detect the markers of a marker‐controlled watershed algorithm and grow the markers identified on the distance transforms . Level set algorithms commonly employ the pixel gradients to refine the nucleus boundaries found by the shape‐based methods.…”

The Feature Selection Problem in Computer–Assisted Cytology

“…The watershed is the state-of-the-art method of image segmentation. It is widely used for cell nuclei segmentation (Yang et al, 2006;Cheng and Rajapakse, 2009;Jung and Kim, 2010;Irshad et al, 2014;Koyuncu et al, 2016). The classical watershed algorithm treats the image as a topographic surface I T M .…”

“…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).…”