Computational Nuclei Segmentation Methods in Digital Pathology: A Survey

Pathology is an important field in modern medicine. In particular, the step of nuclei segmentation is an important step in cancer analysis, diagnosis, and grading because cancer analysis, diagnosis, classification, and grading are highly dependent on the quality (accuracy) of nuclei segmentation. In the conventional cancer diagnosis, pathologists analyze biopsies to make diagnostic and prognostic assessments, mainly based on the cell morphology and architecture distribution. In recent years, computerized approaches are rapidly developing in the field of digital pathology, and applications related to nuclei detection, segmentation and classification are increasing. These approaches will play an important role of minimizing human intervention, integrating relevant second opinions, and providing traceable clinical information. In the past, much effort has been devoted to automation of nuclei segmentation and methods to deal with nuclei complex structure. This review provides the summary of the techniques and experimental materials used for nuclei segmentation.

Automated summary

Pathology is crucial in modern medicine, with nuclei segmentation being particularly important in cancer analysis, diagnosis, and grading. Traditional cancer diagnosis relies on cell morphology and architecture distribution, but computerized approaches in digital pathology are rapidly advancing, offering new avenues for nuclei detection, segmentation, and classification.