Virus identification in electron microscopy images by residual mixed attention network

Virus identification in electron microscopy images by residual mixed attention network
复制标题

通过残余混合注意网络识别电子显微镜图像中的病毒

DOI:
10.1016/j.cmpb.2020.105766
复制
发表时间:
2020-09
影响因子:
6.1
通讯作者:
Hua Han
Hua Han
中科院分区:
工程技术2区
文献类型:
--
作者:
Chi Xiao;Xi Chen;Qiwei Xie;Guoqing Li;Hao Xiao;Jingdong Song;Hua Han

文献摘要

参考文献

相似文献

背景与目的:电子显微镜(EM)图像病毒鉴定被认为是病原体诊断和再发感染性病原体的前沿方法之一。然而,现有的方法要么侧重于单个病毒的检测,要么需要大量的人工标记工作来分割病毒。在这项工作中,我们重点研究了病毒分类的任务,并提出了一种有效而简单的方法来识别不同的病毒。方法:提出一种残差混合注意网络(RMAN)进行病毒分类。该网络采用通道关注、自底向上和自顶向下两种关注方式,并采用端到端训练的残差架构,适合处理EM病毒图像,减少了人工标注的负担。结果:我们通过在透射电子显微镜病毒图像数据集上的大量实验验证了所提出的网络。我们的RMAN在12个病毒类别上的错误率为4.285%,超过了最先进的网络,甚至超过了人类专家。此外,消融研究和类激活映射(CAM)的可视化进一步证明了该方法的有效性。结论:提出的自动化方法有助于医学病毒学的发展,为病毒学家提供了一种高精度的病毒识别方法,并有助于病毒的诊断。
Background and Objective:Virus identification in electron microscopy (EM) images is considered as one of the front-line method in pathogen diagnosis and re-emerging infectious agents. However, the existing methods either focused on the detection of a single virus or required large amounts of manual labeling work to segment virus. In this work, we focus on the task of virus classification and propose an effective and simple method to identify different viruses.Methods:We put forward a residual mixed attention network (RMAN) for virus classification. The proposed network uses channel attention, bottom-up and top-down attention, and incorporates a residual architecture in an end-to-end training manner, which is suitable for dealing with EM virus images and reducing the burden of manual annotation.Results:We validate the proposed network through extensive experiments on a transmission electron microscopy virus image dataset. The top-1 error rate of our RMAN on 12 virus classes is 4.285%, which surpasses that of state-of-the-art networks and even human experts. In addition, the ablation study and the visualization of class activation mapping (CAM) further demonstrate the effectiveness of our method.Conclusions:The proposed automated method contributes to the development of medical virology, which provides virologists with a high-accuracy approach to recognize viruses as well as assist in the diagnosis of viruses.
DOI: 10.1016/s0140-6736(77)92002-5
发表时间: 1977-03
期刊: The Lancet
影响因子: --
作者:
S. Pattyn;G. Groen;W. Jacob;P. Piot;G. Courteille
通讯作者: S. Pattyn;G. Groen;W. Jacob;P. Piot;G. Courteille
DOI: 10.3390/v6124902
发表时间: 2014-12-09
期刊: Viruses
影响因子: --
作者:
Goldsmith CS
通讯作者: Goldsmith CS
DOI: 10.1016/j.micron.2005.10.001
发表时间: 2006
期刊: Micron (Oxford, England : 1993)
影响因子: --
作者:
Curry A;Appleton H;Dowsett B
通讯作者: Dowsett B
DOI: 10.3201/eid0903.020327
发表时间: 2003-03
影响因子: 11.8
作者:
Hazelton PR;Gelderblom HR
通讯作者: Gelderblom HR
DOI: 10.1111/j.1365-2672.2010.04737.x
发表时间: 2010-10-01
影响因子: 4
作者:
Laue, M.;Bannert, N.
通讯作者: Bannert, N.