Machine Learning Techniques for the Segmentation of Tomographic Image Data of Functional Materials

Abstract

In this paper, various kinds of applications are presented, in which tomographic image data depicting microstructures of materials are semantically segmented by combining machine learning methods and conventional image processing steps. The main focus of this paper is the grain-wise segmentation of time-resolved CT data of an AlCu specimen which was obtained in between several Ostwald ripening steps. The poorly visible grain boundaries in 3D CT data were enhanced using convolutional neural networks (CNNs). The CNN architectures considered in this paper are a 2D U-Net, a multichannel 2D U-Net and a 3D U-Net where the latter was trained at a lower resolution due to memory limitations. For training the CNNs, ground truth information was derived from 3D X-ray diffraction (3DXRD) measurements. The grain boundary images enhanced by the CNNs were then segmented using a marker-based watershed algorithm with an additional postprocessing step for reducing oversegmentation. The segmentation results obtained by this procedure were quantitatively compared to ground truth information derived by the 3DXRD measurements. A quantitative comparison between segmentation results indicates that the 3D U-Net performs best among the considered U-Net architectures. Additionally, a scenario, in which "ground truth" data is only available in one time step, is considered. Therefore, a CNN was trained only with CT and 3DXRD data from the last measured time step. The trained network and the image processing steps were then applied to the entire series of CT scans. The resulting segmentations exhibited a similar quality compared to those obtained by the network which was trained with the entire series of CT scans.

Characterization of metals in four dimensions

“…Naturally, these techniques have also been applied to analyze and extract information from the reconstructed datasets. For instance, neural networks and random forests have both been employed to solve the segmentation problem, wherein each pixel is assigned to a particular phase [124,125]; evolutionary algorithms have also been used to solve the alignment problem associated with interrupted in situ scans, including DCT [126,127]; finally, deep learning has demonstrated success in detecting key features and tracking their evolution over time [128][129][130]. These examples represent only the tip of the iceberg.…”

Automatic identification of crossovers in cryo‐EM images of murine amyloid protein A fibrils with machine learning

“…However, the methods of statistical learning, in particular CNNs, provide a promising technique with regard to automated image analysis. 2016; Petrich et al, 2017;Rivenson et al, 2017;Furat et al, 2019). 6.…”

“…Due to its fully convolutional nature, the input and output sizes of the network are arbitrary. 2016; Petrich et al, 2017;Rivenson et al, 2017;Furat et al, 2019). Integrating these techniques into the analysis process of fibril images is a promising approach that could drastically reduce the efforts needed to process these images using completely interactive approaches alone.…”

“…Our approach therefore combines conventional tools of morphological image analysis (Soille, 2013) with machine learning techniques. The combination of these two methodologies has already proven valuable for different kinds of segmentation tasks (Petrich et al, 2017;Furat et al, 2019). Figure 1 shows an overview of the proposed approach which can also serve as an outline for this paper.…”

Advanced Deep Learning‐Based 3D Microstructural Characterization of Multiphase Metal Matrix Composites

“…[16] Chowdhury et al used DL for the recognition of dendritic morphologies, [17] and Furat et al showed the application of CNNs for grain-wise segmentation of 3D CT data on Al-Cu alloy. [18] In this study, we investigate the 3D microstructure of an AlSi 12 CuMgNi alloy reinforced with 7%vol of Al 2 O 3 -Saffil short fibers and 15%vol of SiC particles. We show the application of an advanced DL method for the semantic segmentation of all phases present in this multiphase material.…”