Effective Melanoma Recognition Using Deep Convolutional Neural Network with Covariance Discriminant Loss

Abstract

Melanoma recognition is challenging due to data imbalance and high intra-class variations and large inter-class similarity. Aiming at the issues, we propose a melanoma recognition method using deep convolutional neural network with covariance discriminant loss in dermoscopy images. Deep convolutional neural network is trained under the joint supervision of cross entropy loss and covariance discriminant loss, rectifying the model outputs and the extracted features simultaneously. Specifically, we design an embedding loss, namely covariance discriminant loss, which takes the first and second distance into account simultaneously for providing more constraints. By constraining the distance between hard samples and minority class center, the deep features of melanoma and non-melanoma can be separated effectively. To mine the hard samples, we also design the corresponding algorithm. Further, we analyze the relationship between the proposed loss and other losses. On the International Symposium on Biomedical Imaging (ISBI) 2018 Skin Lesion Analysis dataset, the two schemes in the proposed method can yield a sensitivity of 0.942 and 0.917, respectively. The comprehensive results have demonstrated the efficacy of the designed embedding loss and the proposed methodology.

Knowledge, Attitude, and Practice toward Skin Cancer among Patients of Dermatology Clinics and Medical Students/General Practitioners

“…In addition to the findings related to KAP, it is worth noting that recent advancements in image-based techniques, particularly the contributions of artificial intelligence (AI) and machine learning, have shown promising results in the early detection and diagnosis of melanoma. Studies have demonstrated the potential of deep learning algorithms for automated melanoma detection [ 43 , 44 ], as well as the application of multiple instance learning approaches to improve the classification of dysplastic nevi [ 45 , 46 ]. These technological advancements could potentially enhance skin cancer prevention and early intervention efforts by supporting clinicians and empowering patients to identify concerning lesions.…”

Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review

“…This model achieved an area under the curve of 90.3%, sensitivity of 86.5%, and specificity of 73.6% compared to the intuitive diagnoses of dermatologists (sensitivity of 77% and specificity of 61.4%), and it can provide valuable assistance to dermatologists in making informed medical decisions that can help to reduce the number of unnecessary excisions. Guo et al proposed a deep convolutional neural network trained with both cross-entropy and covariance discriminant loss [37]. This approach improves the model outputs and extracted features simultaneously, and a new embedding loss is designed to separate the features of melanoma and nonmelanoma images more effectively.…”