[1]姜荣荣,高佳奕,杨 涛.基于司外揣内原理的中医“舌象-体质”深度学习模型构建研究[J].医学信息,2022,35(18):10-13.[doi:10.3969/j.issn.1006-1959.2022.18.003]
　JIANG Rong-rong,GAO Jia-yi,YANG Tao.Research on the Construction of Deep Learning Model of “Tongue Manifestation-Physical Constitution” in Traditional Chinese Medicine Based on the Principle of “Governing Exterior to Infer Interior”[J].Journal of Medical Information,2022,35(18):10-13.[doi:10.3969/j.issn.1006-1959.2022.18.003]
点击复制

基于司外揣内原理的中医“舌象-体质”深度学习模型构建研究()
分享到：

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
35卷
期数:
2022年18期
页码:
10-13
栏目:
中医药信息学
出版日期:
2022-09-15

文章信息/Info

Title:
Research on the Construction of Deep Learning Model of “Tongue Manifestation-Physical Constitution” in Traditional Chinese Medicine Based on the Principle of “Governing Exterior to Infer Interior”
文章编号:
1006-1959（2022）18-0010-04
作者:
姜荣荣; 高佳奕; 杨 涛
（1.南京中医药大学护理学院，江苏 南京 210023；2.南京中医药大学人工智能与信息与信息技术学院，江苏 南京 210023；3.江苏省中医外用药开发与应用工程研究中心，江苏 南京 210023）
Author(s):
JIANG Rong-rong; GAO Jia-yi; YANG Tao
(1.School of Nursing,Nanjing University of Chinese Medicine,Nanjing 210023,Jiangsu,China;2.School of Artificial Intelligence and Information Technology,Nanjing University of Chinese Medicine,Nanjing 210023,Jiangsu,China;3.Jiangsu Provincial Engineering Research Center of TCM External Medication Development and Application, Nanjing 210023,Jiangsu,China)
关键词:
司外揣内; 中医舌象; 中医体质; 深度学习; 体质辨识模型
Keywords:
Governing exterior to infer interior; Chinese medicinetongue manifestation; Chinese medicine physical constitution; Deep learning; Constitution identification model
分类号:
R2-03；TP391.1；TP183
DOI:
10.3969/j.issn.1006-1959.2022.18.003
文献标志码:
A
摘要:
司外揣内是中医诊断和健康评估的重要手段，中医体质辨识是这一理论的典型应用，传统的中医体质辨识依赖中医体质评分量表进行判定，效率低下。本文将深度学习技术应用到中医体质辨识领域，基于司外揣内原理，将多尺度舌象信息融入注意力模块中，以残差方式堆叠，将图像模态和文本模型的舌象信息融合，构建中医体质辨识模型，并在数据集上进行训练和测试，以期实现较为精准的体质判别。
Abstract:
Governing exterior to infer interior is an important means of traditional Chinese medicine diagnosis and health assessment,traditional Chinese medicineconstitution identification is a typical application of this theory.However traditional Chinese medicine constitution identification relies on traditionalChinese medicine constitution rating scale, which is inefficient. In this paper, deep learning technology is applied to the field of traditional Chinese medicine constitution identification. Based on the principle of inferring the inside from the outside, the multi-scale tongue manifestation information is integrated into the attention module, stacked in a residual manner, and the tongue manifestation information of the image mode and the text model is fused to construct the traditionalChinese medicine constitution identification model. Training and testing are performed on the data set in order to achieve more accurate constitution discrimination.

参考文献/References:

[1]王琦,盛增秀.中医体质学说[M].南京:江苏科技出版社,1982,15.[2]刘四军,周成成,林秋姗,等.《中医体质分类与判定表》的简化研究[J].广州中医药大学学报,2021,38(8):1734-1739.[3]周妍妍,康倩倩,于淼,等.《黄帝内经》体质分类解析[J].中国中医基础医学杂志,2020,26(7):866-868.[4]崔笛,杨殿兴,殷海宽,等.中医阴阳五行人体质分类法的建构[J].时珍国医国药,2018,29(5):1173-1175.[5]严辉.中医体质量表应用现状的文献计量与内容分析[D].北京:北京中医药大学,2018.[6]刘亚平,田松.明清医家体质分型的探析[J].中医药信息,2017,34(6):50-51.[7]彭立,吕崇山,钱林超.中医体质分类中的舌象特征研究及辨舌验体质的可行性探讨[J].中医杂志,2017,58(12):1002-1004.[8]严玲,周作建,宋懿花,等.基于ML-kNN多标记学习的中医体质辨识模型研究[J].世界科学技术-中医药现代化,2020,22(10):3558-3562.[9]陆冠龙,黄益栓,张琦,等.融合舌象和形体特征的辅助中医体质辨识模型研究[J].时珍国医国药,2019,30(1):244-246.[10]潘思行,林育,周苏娟,等.基于神经网络和支持向量机的中医体质辨识模型研究[J].世界科学技术-中医药现代化,2020,22(4):1341-1347.[11]Feng X,Jiang Y,Yang X,et al.Computer vision algorithms and hardware implementations: A survey[J].Integration,2019,69(1):309-320.[12]Woo S,Park J,Lee JY,et al.CBAM: Convolutional Block Attention Module.In: Ferrari V,Hebert M,Sminchisescu C,et al.(eds) Computer Vision-ECCV 2018.ECCV 2018.Lecture Notes in Computer Science,11211,Springer Cham[EB/OL].https://doi.org/10.1007/978-3-030-01234-2_1,2018-10-06/2022-08-15.[13]Manli S,Zhanjie S,Xiaoheng J,et al.Learning Pooling for Convolutional Neural Network[J].Neurocomputing,2017,224:96-104.[14]Kingma D,Ba J.Adam: A Method for Stochastic Optimization[C].ICLR 2015,San Diego,CA,2014:1-15.[15]Anna B,Sergey G.Threshold optimization for F measure of macro-averaged precision and recall[J].Pattern Recognition,2020,102:107250.[16]Kwasniewska A,Rumiński J,Rad P.Deep features class activation map for thermal face detection and tracking[C]//2017 10Th international conference on human system interactions (HSI).IEEE,2017:41-47.

更新日期/Last Update: 1900-01-01