当前位置: X-MOL 学术mSphere › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection.
mSphere ( IF 4.8 ) Pub Date : 2020-09-09 , DOI: 10.1128/msphere.00836-20
Artur Yakimovich 1 , Moona Huttunen 2, 3 , Jerzy Samolej 2 , Barbara Clough 3, 4 , Nagisa Yoshida 4, 5, 6 , Serge Mostowy 5, 6 , Eva-Maria Frickel 3, 4 , Jason Mercer 1, 3
Affiliation  

The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified data sets for rapid network evolution. Here, we present a novel strategy, termed “mimicry embedding,” for rapid application of neural network architecture-based analysis of pathogen imaging data sets. Embedding of a novel host-pathogen data set, such that it mimics a verified data set, enables efficient deep learning using high expressive capacity architectures and seamless architecture switching. We applied this strategy across various microbiological phenotypes, from superresolved viruses to in vitro and in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of two- and three-dimensional microscopy data sets. The results suggest that transfer learning from pretrained network data may be a powerful general strategy for analysis of heterogeneous pathogen fluorescence imaging data sets.

中文翻译:

模拟嵌入促进了基于图像的病原体检测的高级神经网络训练。

使用深度神经网络 (DNN) 分析复杂的生物医学图像显示出巨大的前景,但由于缺乏用于快速网络进化的大型验证数据集而受到阻碍。在这里,我们提出了一种新的策略,称为“模拟嵌入”,用于快速应用基于神经网络架构的病原体成像数据集分析。嵌入新的宿主病原体数据集,使其模仿经过验证的数据集,使用高表达能力架构和无缝架构切换实现高效的深度学习。我们将此策略应用于各种微生物表型,从超分辨病毒到体外体内寄生虫感染。我们证明了模拟嵌入能够有效和准确地分析二维和三维显微镜数据集。结果表明,来自预训练网络数据的迁移学习可能是分析异质病原体荧光成像数据集的强大通用策略。
更新日期:2020-09-10
down
wechat
bug