Hybrid Deep Learning and Data Augmentation for Disease Candidate Extraction

Nowadays, skin cancer is one of the most popular diseases which affected by ozone depletion, chemical environmental pollution and so on. It is very important for recognizing and treatments. There are many devices that support to capture high-quality skin image to be able for disease diagnose by expert systems. However, the difficult problem is that extracting region of interesting (ROI) for disease diagnosis. This paper presents an approach candidate diseased region extraction using hybrid deep learning of the Residual neural network (ResNet50) architecture and the Atrous convolutional neural network (ACNN). Then the ROI is fed to recognition system for diseased diagnoses. The imbalance of recall measures between classes affected the performance of existing models is deal with data augmentation technique. The proposed learning architecture is suitable for multi skin diseases segmentation and solved under fitting and avoided overfitting problems, achieved improving performance when used hybrid of learning models. Experimental results illustrated that the segmentation system based on deep feature processing combine with data augmentation reach high accuracy.