Dpe-Botnet : Dual Position Encoding Bottleneck Transformer Network For Skin Lesion Classification

Skin cancer is the most common cancer worldwide, and therein the malignant melanoma may lead to less than 5-year life expectancy. Early detection and recognition of skin lesion types have great effect on proper treatment to increase the patient’s survival rate. With the progress of various imaging modalities, automatic skin lesion recognition has attracted substantial research attention, and recent deep learning methods using the existing network architectures such as VGGNet, ResNet, have demonstrated remarkable performance gain. This study aims to present a novel unified convolution and transformer network, called bottleneck transformer network, for simultaneously modeling local interaction and global dependency, and further exploits a dual learnable position encoding module for enhancing the position modeling capability in the bottleneck transformer. We implement our bottleneck transformer on the baseline DenseNet, and experiments on two benchmark datasets: HAM10000 and ISIC2017 evaluate that our proposed method outperform the state-of-the-art deep learning methods.