This document summarizes a study that investigated using deep learning to classify x-ray images of quarantine items. Researchers collected x-ray image data of 21 quarantine item classes and used it to train a convolutional neural network model. The model achieved an overall accuracy of 25.5% on the test set, with higher accuracy for some classes like banana and dracaena, and lower accuracy for others like tree ear mushroom and asparagus that had poorer visibility in x-rays. While the overall accuracy was low, the confusion matrix showed the model could differentiate between classes to some degree. Improving the model would require more image data per scan type to better generalize object shapes and labels.