ELNet:Automatic classification and segmentation for esophageal lesions using convolutional neural network

Automatic and accurate esophageal lesion classification segmentation is of great significance to clinically estimate the statuses diseases make suitable diagnostic schemes. Due individual variations visual similarities lesions in shapes, colors, textures, current clinical methods remain subject potential high-risk time-consumption issues. In this paper, we propose an Esophageal Lesion Network (ELNet) for automatic using deep convolutional neural networks (DCNNs). The underlying method automatically integrates dual-view contextual information extract global features local lesion-specific network proposed annotation at pixel level. For established large-scale database 1051 white-light endoscopic images, ten-fold cross-validation used validation. Experiment results show that framework achieves with sensitivity 0.9034, specificity 0.9718, accuracy 0.9628, 0.8018, 0.9655, 0.9462. All these indicate our enables efficient, accurate, reliable diagnosis clinics.