Dermatological skin cancer

Dermoscopy is a widely used diagnostic technique that improves the diagnosis of benign and malignant pigmented skin lesions in comparison to examination with the unaided eye. Dermoscopy images are also a suitable source to train artificial neural networks to diagnose pigmented skin lesions automatically. Previously, dermoscopy images were used successfully to train an artificial neural network to differentiate melanomas, the deadliest type of skin cancer, from melanocytic nevi. Although the results were promising, the study, like most earlier studies, suffered from small sample size and the lack of dermoscopy images other than melanoma or nevi. Recent advances in graphics card capabilities and machine learning techniques set new benchmarks for the complexity of neural networks and raised expectations that automated diagnostic systems will soon be available to diagnose all kinds of pigmented skin lesions without human expertise. Training of neural-network based diagnostic algorithms require a large number of annotated images but the number of high-quality dermoscopy images with reliable diagnoses is limited or restricted to only a few classes of diseases.