Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging

Modern data-driven machine learning research that enables revolutionary advances in image analysis has now become a critical tool to redefine how skin lesions are documented, mapped, and tracked. We propose a 3D whole body imaging prototype to enable automated evaluation and mapping of skin lesions. A modular camera rig arranged in a cylindrical configuration is designed to automatically capture synchronised images from multiple angles for entire body scanning. We develop algorithms for 3D body image reconstruction, data processing and skin lesion detection based on deep convolutional neural networks. We also propose a customised, intuitive and flexible interface that allows the user to interact and collaborate with the machine to understand the data. The experimental results using synthetic and real images demonstrate the effectiveness of the proposed solution by providing multiple views of the target skin lesion, enabling further 3D geometry analysis. Skin lesions are identified as outliers which deserve more attention from a skin cancer physician. Our detector leverage expert annotated labels to learn representations of each lesion, while capturing the effects of anatomical variability. The time needed for recording skin information is reduced to just a few seconds, although about half an hour more is needed to process the capture information to high quality information. The proposed 3D whole body imaging system can be used by dermatological clinics, allowing for fast documentation of lesions, quick and accurate analysis of the entire body to detect suspicious lesions. Because of its automated examination, the method might be used for screening or epidemiological investigations. With shorted time required for recording high quality skin information, doctors could have more time and more detailed information to provide better quality treatment.