Exploring Advances in Transformers and CNN for Skin Lesion Diagnosis on Small Datasets

Skin cancer is one of the most common types of cancer in the world. Different computer-aided diagnosis systems have been proposed to tackle skin lesion diagnosis, most of them based on deep convolutional neural networks. However, recent advances in computer vision achieved state-of-the-art results in many tasks, notably transformer-based networks. We explore and evaluate advances in computer vision architectures, training methods and multimodal feature fusion for skin lesion diagnosis task. Experiments show that PiT (0.800 +/- 0.006), CoaT (0.780 +/- 0.024) and ViT (0.771 +/- 0.018) transformer-based backbone models with MetaBlock fusion achieved state-of-the-art results for balanced accuracy on PAD-UFES-20 dataset.