Cell tracking using deep neural networks with multi-task learning

作者：

Highlights：

• A multi-task observation model, consisting of an offline and an online stage.

• The model uses conjunct CNNs to extract features.

• An optimized model update strategy is used.

• A cell tracking dataset is built for single-cell tracking.

摘要

•A multi-task observation model, consisting of an offline and an online stage.•The model uses conjunct CNNs to extract features.•An optimized model update strategy is used.•A cell tracking dataset is built for single-cell tracking.

论文关键词：Cell tracking,Deep learning,Convolutional Neural Networks,Multi-task learning

论文评审过程：Received 3 May 2016, Revised 31 July 2016, Accepted 16 November 2016, Available online 24 November 2016, Version of Record 22 March 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.11.010