Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligenc...Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligence(AI)to study the spotted tongue recognition of traditional Chinese medicine(TCM).Methods A model of spotted tongue recognition and extraction is designed,which is based on the principle of image deep learning and instance segmentation.This model includes multiscale feature map generation,region proposal searching,and target region recognition.Firstly,deep convolution network is used to build multiscale low-and high-abstraction feature maps after which,target candidate box generation algorithm and selection strategy are used to select high-quality target candidate regions.Finally,classification network is used for classifying target regions and calculating target region pixels.As a result,the region segmentation of spotted tongue is obtained.Under non-standard illumination conditions,various tongue images were taken by mobile phones,and experiments were conducted.Results The spotted tongue recognition achieved an area under curve(AUC)of 92.40%,an accuracy of 84.30%with a sensitivity of 88.20%,a specificity of 94.19%,a recall of 88.20%,a regional pixel accuracy index pixel accuracy(PA)of 73.00%,a mean pixel accuracy(m PA)of73.00%,an intersection over union(Io U)of 60.00%,and a mean intersection over union(mIo U)of 56.00%.Conclusion The results of the study verify that the model is suitable for the application of the TCM tongue diagnosis system.Spotted tongue recognition via multiscale convolutional neural network(CNN)would help to improve spot classification and the accurate extraction of pixels of spot area as well as provide a practical method for intelligent tongue diagnosis of TCM.展开更多
OBJECTIVE: To characterize the tongue and pulse manifestations in asymptomatic coronavirus disease 2019(COVID-19) cases in Shanghai. METHODS: We conducted a clinical study of 668 patients with asymptomatic infections ...OBJECTIVE: To characterize the tongue and pulse manifestations in asymptomatic coronavirus disease 2019(COVID-19) cases in Shanghai. METHODS: We conducted a clinical study of 668 patients with asymptomatic infections in which we analyzed the tongue and pulse features in the Shanghai New International Expo Center mobile cabin hospital. The medical records of the patients, including tongue color, tongue coating, and pulse manifestations, were reviewed by healthcare workers. RESULTS: In total, 668 COVID-19 cases were included in the study. Patient age ranged from 5 to 96 years, with a median of 44.0(IQR 33.0-53.0) years. Among the patients, 6.14% had comorbidities. The most common comorbid condition was diabetes(1.65%), followed by hypertension(0.89%), coronary heart disease(0.89%), thrombotic diseases(0.89%), congestive heart failure(0.60%), and stroke(0.45%). Pink-red(75.4%) was the most common tongue color, followed by red(23.4%) and pale red(1.2%). Tongue coating color and thickness were classified as white fur(9.28%), thin and yellow fur(48.65%), white greasy fur(8.98%), yellow greasy fur(24.70%), and less coating(8.39%). In addition, a large number of patients(n = 300, 44.91%) presented superficial and rapid pulses, and 250 patients(37.4%) exhibited a slippery pulse. CONCLUSION: Our preliminary results showed that wind, heat, and dampness were the main etiologies of the severe acute respiratory syndrome coronavirus 2 Omicron(B.1.1.529) variant infection in traditional Chinese medicine. Furthermore, the main symptoms of the disease may be wind-heat invading the lung syndrome or damp-heat with the exuberance of virulence syndrome, which is of most significance in COVID-19 treatment.展开更多
基金Anhui Province College Natural Science Fund Key Project of China(KJ2020ZD77)the Project of Education Department of Anhui Province(KJ2020A0379)。
文摘Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligence(AI)to study the spotted tongue recognition of traditional Chinese medicine(TCM).Methods A model of spotted tongue recognition and extraction is designed,which is based on the principle of image deep learning and instance segmentation.This model includes multiscale feature map generation,region proposal searching,and target region recognition.Firstly,deep convolution network is used to build multiscale low-and high-abstraction feature maps after which,target candidate box generation algorithm and selection strategy are used to select high-quality target candidate regions.Finally,classification network is used for classifying target regions and calculating target region pixels.As a result,the region segmentation of spotted tongue is obtained.Under non-standard illumination conditions,various tongue images were taken by mobile phones,and experiments were conducted.Results The spotted tongue recognition achieved an area under curve(AUC)of 92.40%,an accuracy of 84.30%with a sensitivity of 88.20%,a specificity of 94.19%,a recall of 88.20%,a regional pixel accuracy index pixel accuracy(PA)of 73.00%,a mean pixel accuracy(m PA)of73.00%,an intersection over union(Io U)of 60.00%,and a mean intersection over union(mIo U)of 56.00%.Conclusion The results of the study verify that the model is suitable for the application of the TCM tongue diagnosis system.Spotted tongue recognition via multiscale convolutional neural network(CNN)would help to improve spot classification and the accurate extraction of pixels of spot area as well as provide a practical method for intelligent tongue diagnosis of TCM.
基金Supported by National Key R&D Program of China (2018YFC1705900)State Administration of Traditional Chinese Medicine,Traditional Chinese Medicine on Prevention and Treatment of Novel Coronavirus Pneumonia Emergency and Special Project (2022ZYLCYJ05-4)Shanghai University of Traditional Chinese Medicine,Traditional Chinese Medicine on Prevention and Treatment of Novel Coronavirus Pneumonia Emergency and Special Project (2022YJ-03, 2022YJ-06)。
文摘OBJECTIVE: To characterize the tongue and pulse manifestations in asymptomatic coronavirus disease 2019(COVID-19) cases in Shanghai. METHODS: We conducted a clinical study of 668 patients with asymptomatic infections in which we analyzed the tongue and pulse features in the Shanghai New International Expo Center mobile cabin hospital. The medical records of the patients, including tongue color, tongue coating, and pulse manifestations, were reviewed by healthcare workers. RESULTS: In total, 668 COVID-19 cases were included in the study. Patient age ranged from 5 to 96 years, with a median of 44.0(IQR 33.0-53.0) years. Among the patients, 6.14% had comorbidities. The most common comorbid condition was diabetes(1.65%), followed by hypertension(0.89%), coronary heart disease(0.89%), thrombotic diseases(0.89%), congestive heart failure(0.60%), and stroke(0.45%). Pink-red(75.4%) was the most common tongue color, followed by red(23.4%) and pale red(1.2%). Tongue coating color and thickness were classified as white fur(9.28%), thin and yellow fur(48.65%), white greasy fur(8.98%), yellow greasy fur(24.70%), and less coating(8.39%). In addition, a large number of patients(n = 300, 44.91%) presented superficial and rapid pulses, and 250 patients(37.4%) exhibited a slippery pulse. CONCLUSION: Our preliminary results showed that wind, heat, and dampness were the main etiologies of the severe acute respiratory syndrome coronavirus 2 Omicron(B.1.1.529) variant infection in traditional Chinese medicine. Furthermore, the main symptoms of the disease may be wind-heat invading the lung syndrome or damp-heat with the exuberance of virulence syndrome, which is of most significance in COVID-19 treatment.
