An Automatic Nucleus Segmentation and CNN Model based Classification Method of White Blood Cell

作者：

Highlights：

• A generalized white blood cell (WBC) nucleus segmentation method is proposed.

• We localize WBC by showing a statistical analysis on four public databases.

• We compare the proposed WBC nucleus segmentation method on four public databases.

• A new CNN model is proposed to classify four types of white blood cell.

• We evaluate and compare the proposed CNN model by using nine evaluation metrics.

摘要

•A generalized white blood cell (WBC) nucleus segmentation method is proposed.•We localize WBC by showing a statistical analysis on four public databases.•We compare the proposed WBC nucleus segmentation method on four public databases.•A new CNN model is proposed to classify four types of white blood cell.•We evaluate and compare the proposed CNN model by using nine evaluation metrics.

论文关键词：White blood cell,Nucleus segmentation,CNN,Convolutional layer,Classification metrics

论文评审过程：Received 16 August 2019, Revised 3 January 2020, Accepted 15 January 2020, Available online 16 January 2020, Version of Record 1 February 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113211