Design and Implementation of a Real-Time Embedded System for Early Skin Cancer Detection

Early diagnosis of skin cancer is crucial for improving survival rates and reducing treatment costs. In this paper, an edge skin cancer diagnostic system based on hardware and software co-design is proposed. The software level is centred on an optimised lightweight neural network and proposes a multi-domain knowledge distillation framework SSMD-KD, which designs and introduces the MFKD multi-layer feature distillation loss to replace the original single-layer distillation method, and fuses the patient's clinical meta-data with the skin image features at the same time. The distillation framework uses ResNet50 and MobileNetV2 as teacher and student models, and combines quantitative training to achieve model compression and optimisation. The optimised models were run on a Xilinx Zynq-7020 SoC heterogeneous platform via a custom accelerator, supporting UVC protocol USB dermatoscope input, HDMI real-time display and Wi-Fi data transfer.Experiments on the ISIC2019 dataset showed that the system had a classification accuracy of 86% on on the test set across 8 classes of skin lesions, with an inference speed of 14.28 FPS and a power consumption of only 2.9W , validating the feasibility of the system for efficient and low-power skin cancer early diagnosis in edge environments.