College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230000, China.
Anhui International Joint Research Center for Ancient Architecture Intellisencing and Multi-Dimensional Modeling, Anhui Jianzhu University, Hefei 230000, China.
Biomed Res Int. 2023 Jan 5;2023:5146543. doi: 10.1155/2023/5146543. eCollection 2023.
Skin cancer has a high mortality rate, and early detection can greatly reduce patient mortality. Convolutional neural network (CNN) has been widely applied in the field of computer-aided diagnosis. To improve the ability of convolutional neural networks to accurately classify skin lesions, we propose a multiscale feature fusion model for skin lesion classification. We use a two-stream network, which are a densely connected network (DenseNet-121) and improved visual geometry group network (VGG-16). In the feature fusion module, we construct multireceptive fields to obtain multiscale pathological information and use generalized mean pooling (GeM pooling) to reduce the spatial dimensionality of lesion features. Finally, we built and tested a system with the developed skin lesion classification model. The experiments were performed on the dataset ISIC2018, which can achieve a good classification performance with a test accuracy of 91.24% and macroaverages of 95%.
皮肤癌死亡率高，早期发现可大大降低患者死亡率。卷积神经网络（CNN）已广泛应用于计算机辅助诊断领域。为提高卷积神经网络准确分类皮肤病变的能力，我们提出了一种用于皮肤病变分类的多尺度特征融合模型。我们使用双流网络，即密集连接网络（DenseNet-121）和改进的视觉几何组网络（VGG-16）。在特征融合模块中，我们构建了多感受野以获取多尺度病理信息，并使用广义均值池化（GeM pooling）来降低病变特征的空间维度。最后，我们构建并测试了一个基于所开发的皮肤病变分类模型的系统。实验在 ISIC2018 数据集上进行，可实现 91.24%的测试精度和 95%的宏平均值的良好分类性能。
