Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network

Abstract

Deep Neural Networks (DNNs) show a significant impact on medical imaging. One significant problem with adopting DNNs for skin cancer classification is that the class frequencies in the existing datasets are imbalanced. This problem hinders the training of robust and well-generalizing models. Data Augmentation addresses this by using existing data more effectively. However, standard data augmentation implementations are manually designed and produce only limited reasonably alternative data. Instead, Generative Adversarial Networks (GANs) is utilized to generate a much broader set of augmentations. This paper proposes a novel enhancement for the progressive generative adversarial networks (PGAN) using self-attention mechanism. Self-attention mechanism is used to directly model the long-range dependencies in the feature maps. Accordingly, self-attention complements PGAN to generate fine-grained samples that comprise clinically-meaningful information. Moreover, the stabilization technique was applied to the enhanced generative model. To train the generative models, ISIC 2018 skin lesion challenge dataset was used to synthesize highly realistic skin lesion samples for boosting further the classification result. We achieve an accuracy of 70.1% which is 2.8% better than the non-augmented one of 67.3%.

References in corpus (9)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Data Augmentation Generative Adversarial Networks
• OCNet: Object Context Network for Scene Parsing
• GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
• Data Augmentation for Skin Lesion Analysis
• Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble
• A Convolutional Encoder Model for Neural Machine Translation
• Data, Depth, and Design: Learning Reliable Models for Skin Lesion Analysis

Cited by in corpus (2)

• Realistic Ultrasound Image Synthesis for Improved Classification of Liver Disease
• Skin disease diagnosis with deep learning: a review