Machine learning analysis of self-assembled colloidal cones
Machine learning analysis of self-assembled colloidal cones
复制标题
自组装胶体锥的机器学习分析
DOI：
10.1039/d1sm01466h
复制
发表时间：
2022
期刊：
影响因子：
3.4
通讯作者：
Gu, X. Wendy
中科院分区：
文献类型：
--
作者：
Doan, David;Echeveste, Daniel J.;Kulikowski, John;Gu, X. Wendy
光学和共聚焦显微镜是用来成像的自组装的微尺度胶体颗粒。自组装结构的密度和尺寸通常通过手工量化，但这是非常繁琐的。在这里，我们研究机器学习是否可以用来提高识别的速度和准确性。该方法适用于双光子光刻胶锥的密集阵列的共焦图像。RetinaNet是一种使用卷积神经网络的深度学习实现，用于识别自组装的锥体堆栈。使用Blender生成合成数据，以补充机器学习模型的实验训练数据。该合成数据捕获共焦图像的关键特征，包括z方向的切片和高斯噪声。我们发现，最好的性能是用合成数据和实验数据的混合物训练的模型。该模型的平均精度（mAP）达到了10.85%，并且精确地测量了不同锥体直径的自组装堆叠尺寸的组装程度和分布。从合成数据的质量以及不同大小的圆锥体的差异方面讨论了机器学习和手工标记数据之间的微小差异。
Optical and confocal microscopy is used to image the self-assembly of microscale colloidal particles. The density and size of self-assembled structures is typically quantified by hand, but this is extremely tedious. Here, we investigate whether machine learning can be used to improve the speed and accuracy of identification. This method is applied to confocal images of dense arrays of two-photon lithographed colloidal cones. RetinaNet, a deep learning implementation that uses a convolutional neural network, is used to identify self-assembled stacks of cones. Synthetic data is generated using Blender to supplement experimental training data for the machine learning model. This synthetic data captures key characteristics of confocal images, including slicing in the z-direction and Gaussian noise. We find that the best performance is achieved with a model trained on a mixture of synthetic data and experimental data. This model achieves a mean Average Precision (mAP) of ∼85%, and accurately measures the degree of assembly and distribution of self-assembled stack sizes for different cone diameters. Minor discrepancies between machine learning and hand labeled data is discussed in terms of the quality of synthetic data, and differences in cones of different sizes.