浏览全部资源
扫码关注微信
1.上海市黄浦区香山中医医院(上海 200020)
2.上海交通大学(上海 200241)
3.上海中医药大学(上海 201203)
陈杰,男,博士,主治医师,主要从事中医内科疾病的临床及四诊信息化研究工作
许家佗,教授,博士研究生导师;E-mail:xjt@fudan.edu.cn
纸质出版日期:2024-11-10,
收稿日期:2024-03-24,
移动端阅览
陈杰,王皓轩,钱卓雅,等.舌象图像深度特征在慢性失眠疗效评价中的应用[J].上海中医药杂志,2024,58(11):86-89.
CHEN Jie,WANG Haoxuan,QIAN Zhuoya,et al.Application of deep features of tongue images in evaluating efficacy of treatments for chronic insomnia[J].Shanghai Journal of Traditional Chinese Medicine,2024,58(11):86-89.
陈杰,王皓轩,钱卓雅,等.舌象图像深度特征在慢性失眠疗效评价中的应用[J].上海中医药杂志,2024,58(11):86-89. DOI: 10.16305/j.1007-1334.2024.2403035.
CHEN Jie,WANG Haoxuan,QIAN Zhuoya,et al.Application of deep features of tongue images in evaluating efficacy of treatments for chronic insomnia[J].Shanghai Journal of Traditional Chinese Medicine,2024,58(11):86-89. DOI: 10.16305/j.1007-1334.2024.2403035.
目的
2
基于舌象深度特征构建慢性失眠常见中医证型的疗效评价模型。
方法
2
基于220例健康人舌象,应用深度卷积神经网络(ResNet50)分别对241例痰热扰心证、185例心脾两虚证、266例心肾不交证慢性失眠患者舌象进行二分类学习,得到验证集超过95%分类准确率的3个不同基准模型,将其参数固定后,再将中药治疗前后的图像分别输入该模型,获得相应的概率输出,即该病例治疗前后的健康似然度,并进行分析。
结果
2
治疗期间,慢性失眠不同证型中药治疗有效病例舌象特征健康似然度呈线性升高趋势;中药治疗无效病例的舌象特征健康似然度的变化情况与中医证型有关,分别呈线性下降(痰热扰心证)、先升后降至治疗前水平(心脾两虚证)以及缓慢上升(心肾不交证)的趋势。
结论
2
基于舌象深度特征的慢性失眠疗效评价方法及可视化呈现,具有良好的客观性、可读性。
Objective
2
To construct an efficacy evaluation model for common traditional Chinese medicine (TCM) syndromes of chronic insomnia based on deep features of tongue images.
Methods
2
Based on the tongue images of 220 healthy controls, the deep convolutional neural network (ResNet50) was used to conduct binary classification learning on the tongue images of 241 patients with chronic insomnia of phlegm-heat disturbing the heart syndrome, 185 patients with heart-spleen deficiency syndrome, and 266 patients with heart-kidney non-interaction syndrome. Three different benchmark models with a classification accuracy of more than 95% in the verification set were obtained. After fixing their parameters, the images before and after TCM treatment were input into the model respectively to obtain the corresponding probability output, that is, the health likelihood of the case before and after treatment, and analysis was carried out.
Results
2
During the treatment period, the health likelihood of tongue image features of effective cases of TCM treatment for different syndromes of chronic insomnia showed a linear increasing trend; the change of health likelihood of tongue image features of ineffective cases of TCM treatment was related to TCM syndromes, showing a linear decreasing trend (phlegm-heat disturbing the heart syndrome), first increasing and then decreasing to the pre-treatment level (heart-spleen deficiency syndrome), and a slow increasing trend (heart-kidney non-interaction syndrome), respectively.
Conclusion
2
The efficacy evaluation method and visual presentation of treatment for chronic insomnia based on deep features of tongue images have good objectivity and readability.
慢性失眠疗效评价舌象特征深度神经网络深度学习中医诊断人工智能
chronic insomniaefficacy evaluationtongue image featuresdeep neural networkdeep learningtraditional Chinese medicine diagnosisartificial intelligence
中国睡眠研究会.中国失眠症诊断和治疗指南(一)[J].临床医学研究与实践, 2017, 2(27): 201.
吴艳,刘炳林.失眠症中药新药临床试验设计的考虑[J].中国临床药理学杂志, 2022, 38(3): 285-288.
聂慧,王奇.基于结局指标相关性的中医证候疗效评价[J].中医杂志, 2011, 52(2): 111-113.
崔龙涛,邸智,于波,等.亚健康状态大学生中药干预前后面色图像分析[J].上海中医药大学学报, 2012, 26(2): 56-59.
黄景斌,江涛,许家佗,等.补益气血中药对气血亏虚型亚健康女性月经周期舌象图像指标的影响[J].中华中医药杂志, 2021, 36 (9): 5219-5222.
黄景斌,许家佗,张志枫,等.基于舌象图像分区指标的糖尿病疗效评价[J].中华中医药杂志, 2017, 32(3): 1148-1151.
崔骥,许家佗,邸智,等.大学生亚健康状态中药干预前后脉图分析[J].中华中医药杂志, 2013, 28(5): 1564-1567.
江涛,屠立平,许家佗.中医舌象智能诊断技术研究述评及展望[J].中国中医药信息杂志, 2024, 31(7): 182-187.
江涛.基于深度学习的舌象智能诊断研究与应用[D].上海:上海中医药大学, 2020.
JIANG T, LU Z, HU X J, et al.Deep learning multi-label tongue image analysis and its application in a population undergoing routine medical checkup[J]. Evid Based Complement Alternat Med, 2022, 2022: 3384209.
XIAN H M, XIE Y Y, YANG Z Z, et al.Automatic tongue image quality assessment using a multi-task deep learning model[J]. Front Physiol, 2022, 13: 966214.
ZHU X L, MA Y H, GUO D, et al.A framework to predict gastric cancer based on tongue features and deep learning[J]. Micromachines(Basel), 2022, 14(1): 53.
American Academy of Sleep Medicine.International classification of sleep disorders(3rd ed)[M]. Darien, IL: American Academy of Sleep Medicine, 2014: 19-21.
周仲瑛.中医内科学[M].北京:中国中医药出版社, 2007: 148-150.
BACKHAUS J, JUNGHANNS K, BROOCKS A, et al.Test-retest reliability and validity of the Pittsburgh Sleep Quality Index in primary insomnia[J]. J Psychosom Res, 2002, 53(3): 737-740.
XU W, FU Y L, ZHU D. ResNet and its application to medical image processing:Research progress and challenges[J]. Comput Methods Programs Biomed, 2023, 240: 107660.
RUSSAKOVSKY O,DENG J,SU H,KRAUSE J,et al.Imagenet large scale visual recognition challenge[J]. Int J Comput Vis, 2015, 115: 211-252.
ZHANG Z J. Improved adam optimizer for deep neural networks[J]. IWQoS, 2018, 2018: 1-2.
陈杰,李军,管鑫,等.中药复方对不同证型慢性失眠患者舌象图像指标的影响[J].中华中医药杂志, 2024, 39(6): 2844-2848.
KRIZHEVSKY A, SUTSKEVER I, HINTON G E.Imagenet classification with deep convolutional neural networks[J]. Commun ACM, 2017, 60(6): 84-90.
邓宏勇.从循证中医到智慧中医:自动系统评价技术和中医快速循证决策[J].上海中医药杂志, 2024, 58(3): 1-5.
0
浏览量
0
下载量
0
CSCD
0
CNKI被引量
关联资源
相关文章
相关作者
相关机构