01911nas a2200253   4500000000100000000000100001008004100002260001200043653002200055653002400077653002400101653001800125100001600143700001500159700002500174700001800199700001700217245012100234856008000355300001000435490000600445520119200451022001401643       2021                            d  c06/202110aDigital Pathology10aNuclei Segmentation10aWhole Slide Imaging10aDeep Learning1 aLoay Hassan1 aAdel Saleh1 aMohamed Abdel-Nasser1 aOsama A. Omer1 aDomenec Puig00aPromising Deep Semantic Nuclei Segmentation Models for Multi-Institutional Histopathology Images of Different Organs  uhttps://www.ijimai.org/journal/sites/default/files/2021-05/ijimai_6_6_4.pdf  a35-450 v63 aNuclei segmentation in whole-slide imaging (WSI) plays a crucial role in the field of computational pathology. It is a fundamental task for different applications, such as cancer cell type classification, cancer grading, and cancer subtype classification. However, existing nuclei segmentation methods face many challenges, such as color variation in histopathological images, the overlapping and clumped nuclei, and the ambiguous boundary between different cell nuclei, that limit their performance. In this paper, we present promising deep semantic nuclei segmentation models for multi-institutional WSI images (i.e., collected from different scanners) of different organs. Specifically, we study the performance of pertinent deep learning-based models with nuclei segmentation in WSI images of different stains and various organs. We also propose a feasible deep learning nuclei segmentation model formed by combining robust deep learning architectures. A comprehensive comparative study with existing software and related methods in terms of different evaluation metrics and the number of parameters of each model, emphasizes the efficacy of the proposed nuclei segmentation models.   a1989-1660