Hierarchical Pruning for Simplification of Convolutional Neural Networks in Diabetic Retinopathy Classification.

Convolutional neural networks (CNNs) are widely used in automatic detection and analysis of diabetic retinopathy (DR). Although CNNs have proper detection performance, their structural and computational complexity is troublesome. In this study, the problem of reducing CNN's structural complexity for DR analysis is addressed by proposing a hierarchical pruning method. The original VGG16-Net is modified to have fewer parameters and is employed for DR classification. To have an appropriate feature extraction, pre-trained model parameters on Image-Net dataset are used. Hierarchical pruning gradually eliminates the connections, filter channels, and filters to simplify the network structure. The proposed pruning method is evaluated using the Messidor image dataset which is a public dataset for DR classification. Simulation results show that by applying the proposed simplification method, 35% of the feature maps are pruned resulting in only 1.89% accuracy drop. This simplification could make CNN suitable for implementation inside medical diagnostic devices.

Low Complexity CNN Structure for Automatic Bleeding Zone Detection in Wireless Capsule Endoscopy Imaging.

Wireless capsule endoscopy (WCE) is a swallowable device used for screening different parts of the human digestive system. Automatic WCE image analysis methods reduce the duration of the screening procedure and alleviate the burden of manual screening by medical experts. Recent studies widely employ convolutional neural networks (CNNs) for automatic analysis of WCE images; however, these studies do not consider CNN's structural and computational complexities. In this paper, we address the problem of simplifying the CNN's structure. A low complexity CNN structure for bleeding zone detection is proposed which takes a single patch as input and then outputs a segmented patch of the same size. The proposed network is inspired by the FCN paradigm with a simplified structure. Since it is based on image patches, the resulting network benefits from moderate-sized intermediate feature maps. Moreover, the problem of redundant computations in patch-based methods is circumvented by non-overlapping patch processing. The proposed method is evaluated using the publicly available KID dataset for WCE image analysis. Experimental results show that the proposed network has better accuracy and AUC than previous structures while requiring less computational operations.