基于深度学习的舌象特征分析  

Tongue Image Analysis in Traditional Chinese Medicine Based on Deep Learning

作　　者：李渊彤 罗裕升 朱珍民[2,3] LI Yuan-tong;LUO Yu-sheng;ZHU Zhen-min(College of Information Engineering,Xiangtan University,Xiangtan,Hunan 411105,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100080,China;Beijing Key Laboratory of Mobile Computing and Pervasive Device,Beijing 100080,China)

机构地区：[1]湘潭大学信息工程学院,湖南湘潭411105 [2]中国科学院计算机技术研究所,北京100080 [3]移动计算与新型终端北京重点实验室,北京100080

出　　处：《计算机科学》2020年第11期148-158,共11页Computer Science

基　　金：国家重点研发计划项目(2018YFC2000605)。

摘　　要：中医舌诊因其直观稳定且易于观察的特点,以及具有较高的临床应用价值和快捷方便的实用性,成为了一个重要的研究课题。目前,将医学图像处理技术、人工智能技术和中医专家的临床经验相结合,实现了对中医舌诊的客观化、定量化和自动化,这是当前中医舌诊现代化研究的主流方向。文中研究了基于迁移学习和深度学习的舌体精确分割和舌象特征识别的关键技术,提出了一种基于区域关联的单像素损失函数的舌体分割方法,新的损失函数不仅考虑到了区域像素之间的关联关系,而且有效利用了像素标签语义的监督信息,能够更好地指导模型进行训练学习,在测试集上的MIoU指标达到了96.32%。然后,针对舌象几何特征提出了一个融合空间转换网络和VGG16模型的舌象几何特征分析模型,使用了空间转换网络来显式地学习空间不变性,并复用了VGG16模型的卷积部分,使得可以用舌体分割任务学习到的知识来进行参数迁移学习。通过两组对比实验,验证了空间转换网络对提高模型空间不变性的有效性,以及舌体分割的知识迁移能使模型更快、更平稳地收敛。同时,提出了一个融合深度纹理编码网络和VGG16模型的舌象纹理特征分类模型,使用深度纹理编码网络能将卷积得到的有序特征图编码成无序的纹理语义表示,以更有效地表达纹理信息。通过实验对比分析验证了深度纹理编码网络的无序编码对舌象纹理语义表示的有效性。The traditional Chinese medicine tongue diagnosis,because of its intuition and easy to be observed,as well as its high clinical value,convenience and practicability,has become one of the important research subjects.At present,the combination of medical image processing technology,artificial intelligence technology and clinical experience of Chinese medicine experts to achieve objectification,quantification and automation of TCM tongue diagnosis is the mainstream of modernization research of TCM tongue diagnosis.In this paper,the key techniques of tongue segmentation and tongue image feature recognition based on migration learning and deep learning are studied.A tongue segmentation method based on region-based single pixel loss function is proposed.It can instruct the training and learning of the model by combining the color correlation and the semantic correlation between neighboring pixels,and the semantic information of target pixel labels.The experiments show that it partly improves the segmentation effect of the model,the MIoU index on the test set reached 96.32%.Then,a classification model of the tongue image geometric features,which combines spatial transformation network and VGG16 model,is proposed to identify and extract the geometric features of tongue image,providing a basis for syndromic inference of tongue image.Considering the orderliness of the geometric features of the data on the two-dimensional plane,the spatial transformation network is used to explicitly learn the spatial invariance in the model.And the convolution part of the VGG16 model is reused,so that the knowledge learned from the tongue segmentation task can be used for parameter transfer learning.Through two sets of comparative experiments,the validity of the spatial transformation network is proved to improve the spatial invariance of the model,and the knowledge of transfer learning is proved to make the model converge faster and more smoothly.At the same time,a classification model of the tongue image texture features,based on the dee

关 键 词：中医舌诊 舌象分析 舌体分割 深度学习 迁移学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]