Convolutional Neural Network Architectures for the Automated Diagnosis of Celiac Disease

In this work, convolutional neural networks (CNNs) are applied for the computer assisted diagnosis of celiac disease based on endoscopic images of the duodenum. To evaluate which network configurations are best suited for the classification of celiac disease, several different CNN networks were trained using different numbers of layers and filters and different filter dimensions. The results of the CNNs are compared with the results of popular general purpose image representations such as Improved Fisher Vectors and LBP-based methods as well as a feature representations especially designed for the classification of celiac disease. We will show that the deeper CNN architectures outperform these comparison approaches and that combining CNNs with linear support vector machines furtherly improves the classification rates for about 3-7% leading to distinctly better results (up to 97%) than those of the comparison methods.