Skin cancer reorganization and classification with deep neural network
This work addresses the need for automated tools to assist in early melanoma detection, potentially reducing reliance on dermatologists, but it appears incremental as it builds on existing models like Google Inception v3.
The authors tackled the problem of automatic skin cancer detection by developing a deep learning system for lesion segmentation and melanoma diagnosis, achieving high accuracy in both tasks.
As one kind of skin cancer, melanoma is very dangerous. Dermoscopy based early detection and recarbonization strategy is critical for melanoma therapy. However, well-trained dermatologists dominant the diagnostic accuracy. In order to solve this problem, many effort focus on developing automatic image analysis systems. Here we report a novel strategy based on deep learning technique, and achieve very high skin lesion segmentation and melanoma diagnosis accuracy: 1) we build a segmentation neural network (skin_segnn), which achieved very high lesion boundary detection accuracy; 2) We build another very deep neural network based on Google inception v3 network (skin_recnn) and its well-trained weight. The novel designed transfer learning based deep neural network skin_inceptions_v3_nn helps to achieve a high prediction accuracy.