Skin lesion classification using CNNs with grouping of multi-scale attention and class-specific loss weighting. (November 2022)

• Record Type: Journal Article
• Authors: Qian, Shenyi; Ren, Kunpeng; Zhang, Weiwei; Ning, Haohan
• Is Part Of: Computer methods and programs in biomedicine. Volume 226(2022)
• Publication Date: 2022-11
• Subjects: Skin lesion classification -- Dermoscopy -- Deep learning -- Attention mechanism -- Class imbalance; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107166
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Proposing a grouping of multi-scale attention blocks (GMAB) which introduces different scale attention branch to expand the DCNN model. Using the GMAB to extract multi-scale fine-grained features so as to improve the model's ability to focus on the lesion area, leading to the performance improvement of DCNN. Attention blocks has a simple structure and few parameters, which can be applied in various DCNN structures and trained in an end-to-end manner. Adopting the method of class-specific loss weighting for the problem of category imbalance. The results show that this method can significantly increase the accuracy of easily misclassification samples. The accuracy of our proposed method reaches 91.6%, the AUC reaches 97.1%, the sensitivity reaches 73.5%, and the specificity reaches 96.4%. Abstract: As one of the most common cancers globally, the incidence of skin cancer has been rising. Dermoscopy-based classification has become the most effective method for the diagnosis of skin lesion types due to its accuracy and non-invasive characteristics, which plays a significant role in reducing mortality. Although a great breakthrough of the task of skin lesion classification has been made with the application of convolutional neural network, the inter-class similarity and intra-class variation in skin lesions images, the high class imbalance of the dataset and the lack of ability to focus on the lesion area all affect the classification results of the model. In order to solve these problems, on the one hand, we use the grouping of multi-scale attention blocks (GMAB) to extract multi-scale fine-grained features so as to improve the model's ability to focus on the lesion area. On the other hand, we adopt the method of class-specific loss weighting for the problem of category imbalance. In this paper, we propose a deep convolution neural network dermatoscopic image classification method based on the grouping of multi-scale attention blocks and class-specific loss weighting. We evaluated our model on the HAM10000 dataset, and the results showed that the ACC and AUC of the proposed method were 91.6% and 97.1% respectively, which can achieve good results in dermatoscopic classification tasks.