Abstract
Existing nuclei segmentation methods have obtained limited results with multi-center and multi-organ whole-slide images (WSIs) due to the use of different stains, scanners, overlapping, clumped nuclei, and the ambiguous boundary between adjacent cell nuclei. In an attempt to address these problems, we propose an efficient stain-aware nuclei segmentation method based on deep learning for multi-center WSIs. Unlike all related works that exploit a single-stain template from the dataset to normalize WSIs, we propose an efficient algorithm to select a set of stain templates based on stain clustering. Individual deep learning models are trained based on each stain template, and then, an aggregation function based on the Choquet integral is employed to combine the segmentation masks of the individual models. With a challenging multi-center multi-organ WSIs dataset, the experimental results demonstrate that the proposed method outperforms the state-of-art nuclei segmentation methods with aggregated Jaccard index (AJI) and F1-scores of 73.23% and 89.32%, respectively, while achieving a lower number of parameters.
Highlights
To assess the efficacy of the proposed method, we used a well-known and very challenging multi-center multi-organ whole-slide images (WSIs) dataset called MoNuSeg [14], which was made available by the Indian Institute of Technology Guwahati
The key elements of the proposed method were the stain template selection algorithm based on the K-means clustering technique, stain normalization, construction of individual nuclei segmentation models, and the aggregation function based on the Choquet integral that produced the final nuclei segmentation masks
In this article, we proposed a stain template selection algorithm to select a set of WSIs from the multi-center WSI dataset to serve as stain target templates
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. The digital pathology revolution has begun by digitizing glass slides using a wholeslide image (WSI) scanner. Pathologists analyze the WSIs manually on a monitor using an image viewer [1]. Over the last few years, digital pathology has been employed in research, academic, and medical institutions in collecting data, managing databases, as well as designing robust studies for millions of specimens. The manual analysis performed by pathologists (i.e., the visual assessment of WSIs) is time consuming, especially in tasks like nuclei cell segmentation and counting [2,3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
