Rotation equivariant and invariant neural networks for microscopy image analysis
Rotation equivariant and invariant neural networks for microscopy image analysis
复制标题
DOI：
10.1093/bioinformatics/btz353
复制
发表时间：
2019-07-15
期刊：
影响因子：
5.8
通讯作者：
Ma, Jian
中科院分区：
文献类型：
--
作者：
Chidester, Benjamin;Zhou, Tianming;Ma, Jian
神经网络已被广泛用于分析高通量显微图像。然而，通过对特定任务的已知不变性进行编码，可以显著提高神经网络的性能。与从显微镜图像数据自动化细胞表型的目标高度相关的是旋转不变性。在这里，我们考虑了两种方案的应用，用于编码卷积神经网络中的旋转等变性和不变性，即组等变CNN（G-CNN），以及一种具有简单，高效的圆锥卷积的新架构，用于分类显微镜图像。我们还集成了二维离散傅立叶变换（2D-DFT）作为编码全局旋转不变性的有效手段。我们将我们的新方法称为圆锥卷积和DFT网络（CFNet）。结果与标准CNN相比，我们评估了CFNet和G-CNN对于几种不同图像分类任务的功效，包括亚细胞蛋白质定位的模拟和真实的显微镜图像，并证明了性能的提高。我们相信CFNet有潜力改进许多高通量显微镜图像分析应用程序。可用性和实施CFNet的源代码可在以下网址获得：https://github.com/bchidest/CFNet.Supplementary信息补充数据可在在线生物信息学上获得。
Motivation Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet).Results We evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications.Availability and implementation Source code of CFNet is available at: https://github.com/bchidest/CFNet.Supplementary informationSupplementary data are available at Bioinformatics online.