Characterizing Patterns in Phase Contrast X-Ray Computed Tomography Images of the Patellar Cartilage with Deep Transfer Learning

Anas Abidin, Adora D'Souza, Paola Coan, Axel Wismueller

Abstract: This study aims to systematically assess the efficacy of deep transfer learning methods for classifying between healthy and diseased tissue patterns as obtained in Phase contrast X-ray computed tomography (PCI-CT) of the human cartilage matrix. We extracted features from two different convolutional neural network architectures, CaffeNet and Inception-v3 for characterizing such patterns. These features were quantitatively evaluated in a supervised classification task measured by the area (AUC) under the Receiver Operating Characteristic (ROC) curve as well as with unsupervised clustering using t-Distributed Stochastic Neighbor Embedding (t-SNE). The best classification performance, for CaffeNet, was observed when using features from the last convolutional layer and the last fully connected layer (AUCs >0.91). Meanwhile, off-the-shelf features from Inception-v3 produced similar classification performance (AUC >0.95). Visualization of clustering results, confirmed adequate characterization of chondrocyte patterns for reliably distinguishing between healthy and osteoarthritic tissue classes. Such techniques, can be potentially used for detecting the presence of osteoarthritis related changes in the human patellar cartilage.

Keywords: Deep learning, CaffeNet, Inception Network, Phase Contrast, cartilage imaging

Author Affiliation: University of Rochester, University of Rochester, Ludwig Maximilians University, University of Rochester