3D Convolutional Neural Networks for Dendrite Segmentation Using Fine-Tuning and Hyperparameter Optimization

X-ray computed tomography reconstructions showing the dendritic growth of an Al-Zn alloy across time steps. Folders beginning with "c-" contain image volumes, while other folders contain manually segmented images used for training 3D convolutional neural networks. These networks are used to segment dendrites across all published image volumes.