2309 skin conditions and crowd-sourced high-level knowledge dataset for building a computer aided diagnosis system

Worldwide, it is believed that there are between 1000 to 2000 skin conditions of which 20% are difficult to diagnose. An intelligent computer-aided diagnosing system not only helps patients with no or little access to health services but also can benefit typical general practitioners, who have received minimal dermatology training. We have built a challenging dataset containing 2309 images from 44 different skin conditions. As most state-of-the-art visual recognition techniques fail to perform on this dataset, we provide crowd-sourced high-level knowledge of these images to enable the development of a “human in the loop” approach. This achieves higher recognition rates by combining visual features, and human provided information. The high-level knowledge was obtained through employing 361 “Amazon Mechanical Turk” workers (non-medical experts), who answered a set of predefined perceptual questions that represents the humans´ understanding of lesions in the images. We have made the images, and the high-level knowledge information publicly available. In this paper, we present the data, methods of using it, and performances of three baseline techniques. This paper and its associated data will be very useful to facilitate the development of computer aided medical diagnostic techniques.