Dendritic microstructures are ubiquitous in nature and are the primary solidification morphologies in metallic materials. Techniques such as x-ray computed tomography (XCT) have provided new insights into dendritic phase transformation phenomena. However, manual identification of dendritic morphologies in microscopy data can be both labor intensive and potentially ambiguous. The analysis of 3D datasets is particularly challenging due to their large sizes (terabytes) and the presence of artifacts scattered within the imaged volumes. In this study, we trained 3D convolutional neural networks (CNNs) to segment 3D datasets. Three CNN architectures were investigated, including a new 3D version of FCDense. We show that using hyperparameter optimization (HPO) and fine-tuning techniques, both 2D and 3D CNN architectures can be trained to outperform the previous state of the art. The 3D U-Net architecture trained in this study produced the best segmentations according to quantitative metrics (pixel-wise accuracy of 99.84% and a boundary displacement error of 0.58 pixels), while 3D FCDense produced the smoothest boundaries and best segmentations according to visual inspection. The trained 3D CNNs are able to segment entire 852 x 852 x 250 voxel 3D volumes in only ~60 seconds, thus hastening the progress towards a deeper understanding of phase transformation phenomena such as dendritic solidification.
翻译:Dentritic 微结构在性质上是无处不在的,是金属材料中的主要固化形态。X光计算断层成像仪(XCT)等技术为进化阶段转变现象提供了新的洞察力。然而,在显微镜数据中人工辨识进化形态既可能是劳动密集型的,也可能是潜在的模糊的。对3D数据集的分析尤其具有挑战性,因为其大小(字节)很大,并且存在分布在图像量内的文物。在本研究中,我们培训了3D 的3D 直流神经网络(CNNs)到 3D 数据集。对三个CNN 结构进行了调查,包括一个新的 3D FCDensense 版本。我们表明,使用超参数优化(HPO)和微调技术,2D和3D WNCN 结构能够超越原艺术的状态。本研究中训练的3D U-Net结构根据量化指标(99.84%的精度准确度,以及FD-CD 3D 的深度变异度) 生成了3D 3x 3x 和直观检查段, 3x 最精确的深度的深度, 级为3D X 级的深度的深度, 级的深度到直观分解为0.8D 。