A novel approach for melanoma detection utilizing GAN synthesis and vision transformer

Abstract

Background and objective:Melanoma, a malignant form of skin cancer, is a critical health concern worldwide. Early and accurate detection plays a pivotal role in improving patient’s conditions. Current diagnosis of skin cancer largely relies on visual inspections such as dermoscopy examinations, clinical screening and histopathological examinations. However, these approaches are characterized by low efficiency, high costs, and a lack of guaranteed accuracy. Consequently, deep learning based techniques have emerged in the field of melanoma detection, successfully aiding in improving the accuracy of diagnosis. However, the high similarity between benign and malignant melanomas, combined with the class imbalance issue in skin lesion datasets, present a significant challenge in further improving the diagnosis accuracy. We propose a two-stage framework for melanoma detection to address these issues. Methods:In the first stage, we use Style Generative Adversarial Networks with Adaptive discriminator augmentation synthesis to generate realistic and diverse melanoma images, which are then combined with the original dataset to create an augmented dataset. In the second stage, we utilize a vision Transformer of BatchFormer to extract features and detect melanoma or non-melanoma skin lesions on the augmented dataset obtained in the previous step, specifically, we employed a dual-branch training strategy in this process. Results:Our experimental results on the ISIC2020 dataset demonstrate the effectiveness of the proposed approach, showing a significant improvement in melanoma detection. The method achieved an accuracy of 98.43%, an AUC value of 98.63%, and an F1 value of 99.01%, surpassing some existing methods. Conclusion:The method is feasible, efficient, and achieves early melanoma screening. It significantly enhances detection accuracy and can assist physicians in diagnosis to a great extent.