Unsupervised segmentation method for cuboidal cell nuclei in histological prostate images based on minimum cross entropy
作者：
Highlights：
• We propose a segmentation method for cuboidal cells nuclei in prostate images.
• We validate the method by quantitative evaluation.
• We compare the method with other segmentation methods.
• The method allows segmentation with a mean accuracy of 97%.
• The method is effective in images of normal, hyperplasia and cancer tissue.
摘要
•We propose a segmentation method for cuboidal cells nuclei in prostate images.•We validate the method by quantitative evaluation.•We compare the method with other segmentation methods.•The method allows segmentation with a mean accuracy of 97%.•The method is effective in images of normal, hyperplasia and cancer tissue.
论文关键词：Prostate cancer,Segmentation of cuboidal cells,Segmentation of nuclei,Minimum cross entropy
论文评审过程：Available online 13 July 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.079
