期刊
NEUROCOMPUTING
卷 425, 期 -, 页码 173-180出版社
ELSEVIER
DOI: 10.1016/j.neucom.2020.04.001
关键词
Deep reinforcement learning; Image segmentation; Deep belief network; Multi-factor learning curve; Gold immunochromatographic strip
资金
- International Science and Technology Co-operation Project of Fujian Province of China [2019I0003]
- Korea Foundation for Advanced Studies
- Fundamental Research Funds for the Central Universities of China [20720190009]
- Open Fund of Engineering Research Center of Big Data Application in Private Health Medicine of China [KF2020002]
- Open Fund of Provincial Key Laboratory of Eco-Industrial Green Technology-Wuyi University of China
This paper presents a novel image segmentation method based on deep reinforcement learning for quantitative analysis of Gold Immunochromatographic Strips (GICS). Experimental results demonstrate that the proposed method outperforms existing image segmentation methods in distinguishing between the test line and control line on GICS images.
Gold immunochromatographic strip (GICS) is a widely used lateral flow immunoassay technique. A novel image segmentation method is developed in this paper for quantitative analysis of GICS based on the deep reinforcement learning (DRL), which can accurately distinguish the test line and the control line in the GICS images. The deep belief network (DBN) is employed in the deep Q network in our DRL algorithm. Meanwhile, the multi-factor learning curve is introduced in the DRL algorithm to dynamically adjust the capacity of the replay buffer and the sampling size, which leads to enhanced learning efficiency. It is worth mentioning that the states, actions, and rewards in the developed DRL algorithm are determined based on the characteristics of GICS images. Experiment results demonstrate the feasibility and reliability of the proposed DRL-based image segmentation method and show that the proposed new image segmentation method outperforms some existing image segmentation methods for quantitative analysis of GICS images. (c) 2020 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据