基于深度学习及改进模糊KMeans的寻常型银屑病智能诊断方法-《中国医学物理学杂志》

文章信息/Info

Title:: Intelligent diagnosis of psoriasis vulgaris based on deep learning and improved fuzzy KMeans

作者:: 石丽平1; 杜笑青2; 李静1; 刘丽娟1; 张国强1; 1.河北医科大学第一医院皮肤科，河北石家庄 050000； 2.中国人民解放军联勤保障部队第九八〇医院皮肤科，河北石家庄 050000

Author(s):: SHI Liping1; DU Xiaoqing2; LI Jing1; LIU Lijuan1; ZHANG Guoqiang1; 1. Department of Dermatology, the First Hospital of Hebei Medical University, Shijiazhuang 050000, China 2. Department of Dermatology, the 980th Hospital of PLA Joint Logistic Support Force, Shijiazhuang 050000, China

Keywords:: Keywords: psoriasis vulgaris improved fuzzy KMeans clustering algorithm Visual Geometry Group 13 deep convolutional neural network

摘要:: 为了解决寻常型银屑病在样本分布不平衡的数据中可能会导致的深度学习模型诊断效果下降等问题，通过结合改进模糊KMeans聚类算法对高聚类复杂度数据的处理能力以及Visual Geometry Group 13（VGG13）深度卷积神经网络模型的预测能力，提出一种基于改进模糊KMeans聚类算法的VGG13深度卷积神经网络（VGG13-KMeans）模型，并将其应用于寻常型银屑病的诊断任务中。实验结果表明，相较于VGG13以及ResNet18两种方法，本文方法更适用于对银屑病特征的识别。

Abstract:: Abstract: In order to address issues such as the decline in diagnostic performance of deep learning models due to imbalanced data distribution in psoriasis vulgaris, a VGG13-based deep convolutional neural network model is proposed by integrating the processing capability of the improved fuzzy KMeans clustering algorithm for highly clustered complex data and the predictive capability of VGG13 deep convolutional neural network model. The model is applied to the diagnosis of psoriasis vulgaris, and the experimental results indicate that compared with VGG13 and resNet18, the proposed approach based on deep learning and improved fuzzy KMeans is more suitable for identifying psoriasis features.