Comparison of Methods to Segment Variable-Contrast XCT Images of Methane-Bearing Sand Using U-Nets Trained on Single Dataset Sub-Volumes
Comparison of Methods to Segment Variable-Contrast XCT Images of Methane-Bearing Sand Using U-Nets Trained on Single Dataset Sub-Volumes
复制标题
DOI：
10.3390/methane2010001
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
F. Alvarez-Borges;O. N. King;B. N. Madhusudhan;T. Connolley;Mark Basham;Sharif I. Ahmed
中科院分区：
文献类型：
--
作者：
F. Alvarez-Borges;O. N. King;B. N. Madhusudhan;T. Connolley;Mark Basham;Sharif I. Ahmed
甲烷（CH 4）水合物分解和释放是目前使用X射线计算机断层扫描（XCT）研究的潜在地质灾害。图像分割是这类研究的重要数据处理步骤。然而，由于灰度对比度的差异，它通常是耗时的，计算资源密集型的，依赖于操作员的，并且针对每个XCT数据集进行定制。本文利用卷积神经网络U-Nets对水合物形成过程中含甲烷砂岩的同步XCT图像进行分割，提取孔隙度和甲烷含气饱和度。评估了三种以前从未尝试过的U-Net部署：（1）定制的3D分层方法，（2）2D多标签，多轴方法和（3）RootPainter，具有交互式校正的2D U-Net应用程序。U-Net使用小型的、有针对性的手工注释数据集进行训练，以减少操作员的时间。结果表明，这三种方法的分割精度均优于主流的分水岭和阈值分割技术。低对比度数据的准确性略有降低，这会影响体积分数的测量，但与重量法相比，误差很小。此外，在低对比度图像上训练的U-Net模型可以用于分割高对比度数据集，而无需进一步训练。这证明了模型的可移植性，它可以在短时间内加速大型数据集的分割。
Methane (CH4) hydrate dissociation and CH4 release are potential geohazards currently investigated using X-ray computed tomography (XCT). Image segmentation is an important data processing step for this type of research. However, it is often time consuming, computing resource-intensive, operator-dependent, and tailored for each XCT dataset due to differences in greyscale contrast. In this paper, an investigation is carried out using U-Nets, a class of Convolutional Neural Network, to segment synchrotron XCT images of CH4-bearing sand during hydrate formation, and extract porosity and CH4 gas saturation. Three U-Net deployments previously untried for this task are assessed: (1) a bespoke 3D hierarchical method, (2) a 2D multi-label, multi-axis method and (3) RootPainter, a 2D U-Net application with interactive corrections. U-Nets are trained using small, targeted hand-annotated datasets to reduce operator time. It was found that the segmentation accuracy of all three methods surpass mainstream watershed and thresholding techniques. Accuracy slightly reduces in low-contrast data, which affects volume fraction measurements, but errors are small compared with gravimetric methods. Moreover, U-Net models trained on low-contrast images can be used to segment higher-contrast datasets, without further training. This demonstrates model portability, which can expedite the segmentation of large datasets over short timespans.