Medical imaging systems installed in different hospitals and labs generate images in bulk, which could support medics to analyze infections or injuries. Manual inspection becomes difficult when there exist more images, therefore, intelligent systems are usually required for real-time diagnosis. Melanoma is one of the most common and severe forms of skin cancer that begins from the cells beneath the skin. Through dermoscopic images, it is possible to diagnose the infection at the early stages. In this regard, different approaches have been exploited for improved results. In this study, we propose a two-stream deep neural network information fusion framework for multiclass skin cancer classification. The proposed technique follows two streams: initially, a fusion-based contrast enhancement technique is proposed, which feeds enhanced images to the pretrained DenseNet201 architecture. The extracted features are later optimized using a skewness-controlled moth–flame optimization algorithm. In the second stream, deep features from the fine-tuned MobileNetV2 pretrained network are extracted and down-sampled using the proposed feature selection framework. Finally, most discriminant features from both networks are fused using a new parallel multimax coefficient correlation method. A multiclass extreme learning machine classifier is used to classify lesion images. The testing process is initiated on three imbalanced skin data sets—HAM10000, ISBI2018, and ISIC2019. The simulations are performed without performing any data augmentation step in achieving an accuracy of 96.5%, 98%, and 89%, respectively. A fair comparison with the existing techniques reveals the improved performance of our proposed algorithm.

中文翻译：

---

基于双流深度神经网络的复杂皮肤癌类型分类智能系统

安装在不同医院和实验室的医学成像系统可以批量生成图像，这可以支持医务人员分析感染或受伤情况。当图像较多时，人工检查变得困难，因此通常需要智能系统进行实时诊断。黑色素瘤是最常见和最严重的皮肤癌之一，起源于皮下细胞。通过皮肤镜图像，可以在早期诊断感染。在这方面，已采用不同的方法来改进结果。在这项研究中，我们提出了一种用于多类皮肤癌分类的双流深度神经网络信息融合框架。所提出的技术遵循两个流：最初，提出了一种基于融合的对比度增强技术，它将增强的图像提供给预训练的 DenseNet201 架构。提取的特征随后使用偏度控制的蛾火优化算法进行优化。在第二个流中，使用建议的特征选择框架从微调的 MobileNetV2 预训练网络中提取和下采样的深层特征。最后，使用新的并行多最大系数相关方法融合来自两个网络的大多数判别特征。多类极限学习机分类器用于对病变图像进行分类。测试过程是在三个不平衡的皮肤数据集——HAM10000、ISBI2018 和 ISIC2019 上启动的。在不执行任何数据增强步骤的情况下执行模拟，分别实现了 96.5%、98% 和 89% 的准确度。