Leveraging Adaptive Color Augmentation in Convolutional Neural Networks for Deep Skin Lesion Segmentation
This work addresses early diagnosis of skin cancer through automated segmentation, but it is incremental as it builds on existing convolutional neural network methods with a specific augmentation approach.
The paper tackled the problem of skin lesion segmentation in dermatoscopic images by proposing an adaptive color augmentation technique to improve model performance, achieving a Dice Ratio of 0.891 with 0.943 sensitivity and 0.932 specificity on the ISIC 2018 Testing Set.
Fully automatic detection of skin lesions in dermatoscopic images can facilitate early diagnosis and repression of malignant melanoma and non-melanoma skin cancer. Although convolutional neural networks are a powerful solution, they are limited by the illumination spectrum of annotated dermatoscopic screening images, where color is an important discriminative feature. In this paper, we propose an adaptive color augmentation technique to amplify data expression and model performance, while regulating color difference and saturation to minimize the risks of using synthetic data. Through deep visualization, we qualitatively identify and verify the semantic structural features learned by the network for discriminating skin lesions against normal skin tissue. The overall system achieves a Dice Ratio of 0.891 with 0.943 sensitivity and 0.932 specificity on the ISIC 2018 Testing Set for segmentation.