Segmentation of 3D micro-Computed Tomographic ($\mathrm{\mu }$CT) images of rock samples is essential for further Digital Rock Physics (DRP) analysis, however, conventional methods such as thresholding and watershed segmentation are susceptible to user-bias. Deep Convolutional Neural Networks (CNNs) have produced accurate pixelwise semantic (multi-category) segmentation results with natural images and $\mathrm{\mu }$CT rock images, however, physical accuracy is not well documented. The performance of 4 CNN architectures is tested for 2D and 3D cases in 10 configurations. Manually segmented $\mathrm{\mu }$CT images of Mt. Simon Sandstone guided by QEMSCANs are treated as ground truth and used as training and validation data, with a high voxelwise accuracy (over 99%) achieved. Downstream analysis is used to validate physical accuracy. The topology of each mineral is measured, the pore space absolute permeability and single/mixed wetting multiphase flow is modelled with direct simulation. These physical measures show high variance, with models that achieve 95%+ in voxelwise accuracy possessing permeabilities and connectivities orders of magnitude off. A network architecture is introduced as a hybrid fusion of U-Net and ResNet, combining short and long skip connections in a Network-in-Network configuration, which overall outperforms U-Net and ResNet variants in some minerals, while outperforming SegNet in all minerals in voxelwise and physical accuracy measures. The network architecture and the dataset volume fractions influence accuracy trade-off since sparsely occurring minerals are over-segmented by lower accuracy networks such as SegNet at the expense of under-segmenting other minerals which can be alleviated with loss weighting. This is an especially important consideration when training a physically accurate model for segmentation.

3D微型计算机断层扫描（$\mathrm{\mu }$岩石样品的CT图像对于进一步的数字岩石物理（DRP）分析至关重要，但是，诸如阈值化和分水岭分割之类的常规方法容易受到用户偏见的影响。深度卷积神经网络（CNN）使用自然图像生成了准确的像素级语义（多类别）分割结果，并且$\mathrm{\mu }$但是，CT岩石图像的物理精度还没有得到很好的证明。针对10种配置下的2D和3D情况，测试了4种CNN架构的性能。手动分段$\mathrm{\mu }$山的CT图像。由QEMSCAN指导的Simon Sandstone被视为基本事实，并用作训练和验证数据，具有很高的体素精度（超过99％）。下游分析用于验证物理准确性。测量每种矿物的拓扑结构，通过直接模拟对孔隙空间绝对渗透率和单/混合润湿多相流进行建模。这些物理量度显示出很高的方差，在体素方向上达到95％+的模型的磁导率和连通性相差几个数量级。引入了一种网络体系结构，将其作为U-Net和ResNet的混合融合，在网络中网络配置中组合了短跳和长跳连接，在某些矿产方面总体上优于U-Net和ResNet变体，同时在体素和物理准确性方面的表现优于所有矿物中的SegNet。网络架构和数据集的体积分数会影响精度的权衡，因为稀疏出现的矿物会被较低精度的网络（例如SegNet）过度分割，而其他部分矿物的分割不足，可以通过损失加权来缓解。当训练物理上精确的分割模型时，这是一个特别重要的考虑因素。