SIIM-ISIC Melanoma Classification With DenseNet
Yiming Zhang, Chong Wang
Abstract
The mortality rate of melanoma is very high, but it can usually be cured by minor surgery. A Fast and accurate diagnosis can greatly benefit doctors and patients. In many medical fields, the performance of the recent deep-learning-based model is close to or even exceed the level of human experts. In this paper, to help dermatologists improve the efficiency of melanoma analysis, we employ the DenseNet model to complete the recognition of melanomas in skin lesion images. The proposed model is trained and evaluated with the ISIC2020 dataset. Besides, Experimental results show that our method achieves superior performance over the other deep-learning approaches. Our DenseNet model gains 0.925 with AUC metric, which is higher than approaches with VGG and ResNet backbone.