Application of generated mask method based on Mask R-CNN in classification and detection of melanoma

A B S T R A C T Objective: Melanoma is a type of malignant skin cancer with high mortality, and its incidence is increasing rapidly in recent years. At present, the best treatment is surgical resection after early diagnosis. However, due to the high visual similarity between melanoma and benign melanocytic nevus, coupled with the scarcity and imbalance of data, traditional methods are difficult to achieve good recognition and detection results. Similarly, many machine learning methods have been applied to the task of skin disease detection and classification. However, the accuracy and sensitivity of the experiments are still not satisfactory. Therefore, this paper proposed a method to identify melanoma more efficiently and accurately. Method: We implemented a Mixed Skin Lesion Picture Generate method based on Mask R-CNN (MSLPMR) to solve the problem of data imbalance. Besides, we designed a melanoma detection framework of Mask-DenseNet+ based on MSLP-MR. This method used Mask R-CNN to introduce the method of mask segmentation, and combined with the idea of ensemble learning to integrate multiple classifiers for weighted prediction. Compared with the ablation experiments, the accuracy, sensitivity and AUC of the proposed network classification are improved by 2.56%, 29.33% and 0.0345. Result: The experimental results on the ISIC dataset shown that the accuracy of the algorithm is 90.61%, the sensitivity reaches 78.00%, which is higher than the original methods; the specificity reaches 93.43%; and the AUC reaches 0.9502. Conclusion: The method is feasible and effective, and achieves the preliminary goal of melanoma detection. It is greatly improved the detection accuracy and reached the level of visual diagnosis of doctors. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This study proposed a new method for melanoma detection, which successfully addressed the issues of data imbalance and low accuracy by introducing mask segmentation and ensemble learning. Experimental results on the ISIC dataset demonstrated significant improvements in accuracy, sensitivity, and AUC of the proposed method.