Trainable segmentation for transmission electron microscope images of inorganic nanoparticles.
Trainable segmentation for transmission electron microscope images of inorganic nanoparticles.
复制标题
无机纳米颗粒的透射电子显微镜图像的可训练分割。
DOI：
10.1111/jmi.13110
复制
发表时间：
2022-12
影响因子：
2
通讯作者：
Slater, Thomas J. A.
中科院分区：
文献类型：
--
作者：
Bell, Cameron G.;Treder, Kevin P.;Kim, Judy S.;Schuster, Manfred E.;Kirkland, Angus, I;Slater, Thomas J. A.
关键词：
我们提出了一种在Python包ParticleSpy中实现的可训练分割方法。该方法采用用户标记的像素，用于训练分类器并从透射电子显微镜图像中分割无机纳米颗粒的图像。这个实现基于可训练的怀卡托知识分析环境（WEKA）分割，但它是用Python编写的，允许很大程度的灵活性，这意味着它可以使用其他Python包轻松扩展。我们发现，可训练分割比全局或局部阈值方法提供更好的准确性，并且只需100个用户标记的像素即可产生准确的分割。当用于纳米颗粒的透射电子显微镜图像时，可训练分割在全局/局部阈值和神经网络之间呈现出准确性和训练时间的平衡。我们还定量研究了可训练分割组件、其过滤器内核和分类器的有效性，以展示ParticleSpy中不同过滤器内核的用例以及不同数据类型的最准确分类器。一组过滤器内核被识别，有效地区分粒子与背景，但保留不同的功能。在分类器方面，我们发现不同的分类器对不同的图像对比度表现最佳;具体来说，随机森林分类器对高对比度ADF图像表现最佳，但QDA和高斯朴素贝叶斯分类器对低对比度TEM图像表现更好。
We present a trainable segmentation method implemented within the python package ParticleSpy. The method takes user labelled pixels, which are used to train a classifier and segment images of inorganic nanoparticles from transmission electron microscope images. This implementation is based on the trainable Waikato Environment for Knowledge Analysis (WEKA) segmentation, but is written in python, allowing a large degree of flexibility and meaning it can be easily expanded using other python packages. We find that trainable segmentation offers better accuracy than global or local thresholding methods and requires as few as 100 user‐labelled pixels to produce an accurate segmentation. Trainable segmentation presents a balance of accuracy and training time between global/local thresholding and neural networks, when used on transmission electron microscope images of nanoparticles. We also quantitatively investigate the effectiveness of the components of trainable segmentation, its filter kernels and classifiers, in order to demonstrate the use cases for the different filter kernels in ParticleSpy and the most accurate classifiers for different data types. A set of filter kernels is identified that are effective in distinguishing particles from background but that retain dissimilar features. In terms of classifiers, we find that different classifiers perform optimally for different image contrast; specifically, a random forest classifier performs best for high‐contrast ADF images, but that QDA and Gaussian Naïve Bayes classifiers perform better for low‐contrast TEM images.
登录
查看更多内容
影响因子：
10.8
作者：
Goris B;De Beenhouwer J;De Backer A;Zanaga D;Batenburg KJ;Sánchez-Iglesias A;Liz-Marzán LM;Van Aert S;Bals S;Sijbers J;Van Tendeloo G
通讯作者：
Van Tendeloo G
影响因子：
8
作者：
Sauvola, J;Pietikäinen, M
通讯作者：
Pietikäinen, M
影响因子：
5.8
作者：
Arganda-Carreras, Ignacio;Kaynig, Verena;Seung, H. Sebastian
通讯作者：
Seung, H. Sebastian
影响因子：
2.8
作者：
Slater, Thomas J. A.;Wang, Yi-Chi;Allen, Christopher S.
通讯作者：
Allen, Christopher S.
影响因子：
5.2
作者：
Sipkens, Timothy A.;Frei, Max;Rogak, Steven N.
通讯作者：
Rogak, Steven N.