Suppr超能文献

利用卷积神经网络预测细胞运动的未来方向。

Predicting the future direction of cell movement with convolutional neural networks.

机构信息

Department of Biosciences and Informatics, Keio University, Yokohama-shi, Kanagawa, Japan.

Faculty of Pharmacy, Sanyo-Onoda City University, Sanyo-Onoda, Yamaguchi, Japan.

出版信息

PLoS One. 2019 Sep 4;14(9):e0221245. doi: 10.1371/journal.pone.0221245. eCollection 2019.

Abstract

Image-based deep learning systems, such as convolutional neural networks (CNNs), have recently been applied to cell classification, producing impressive results; however, application of CNNs has been confined to classification of the current cell state from the image. Here, we focused on cell movement where current and/or past cell shape can influence the future cell movement. We demonstrate that CNNs prospectively predicted the future direction of cell movement with high accuracy from a single image patch of a cell at a certain time. Furthermore, by visualizing the image features that were learned by the CNNs, we could identify morphological features, e.g., the protrusions and trailing edge that have been experimentally reported to determine the direction of cell movement. Our results indicate that CNNs have the potential to predict the future direction of cell movement from current cell shape, and can be used to automatically identify those morphological features that influence future cell movement.

摘要

基于图像的深度学习系统,如卷积神经网络(CNN),最近已被应用于细胞分类,取得了令人瞩目的成果;然而,CNN 的应用仅限于根据图像对当前细胞状态进行分类。在这里,我们专注于细胞运动,其中当前和/或过去的细胞形状可能会影响未来的细胞运动。我们证明,CNN 可以从细胞在某个特定时间的单个图像斑块中,准确地预测未来的细胞运动方向。此外,通过可视化 CNN 学习到的图像特征,我们可以识别形态特征,例如实验报道的确定细胞运动方向的突起和后缘。我们的结果表明,CNN 有可能根据当前细胞形状预测细胞运动的未来方向,并可用于自动识别影响未来细胞运动的形态特征。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/83d6/6726366/d18278dab9a2/pone.0221245.g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验