Objective To objectively identify whether people with phlegm-dampness constitution suffer from hypertension or not using deep learning semantic segmentation model and residual neural network,so as to promote the modernization of tongue manifestation research,and provide a more objective and scientific basis for clinical decision-making in traditional Chinese medicine(TCM).Methods The tongue regions of 547 subjects were outlined and labeled using the Label Me image labeling tool,followed by tongue body segmentation using the U-Net segmentation algorithm which separated the tongue body from the complex background.In the subsequent study,3 deep learning models,namely ResNet-34,ResNet-50 and YOLOv5,were used to classify the tongue manifestations of hypertensive patients and the sub-health both with phlegm-dampness,and to construct the corresponding classification models whose performances were objectively evaluated by drawing confusion matrix and calculating F1 value and accuracy.Results The experimental results showed that all 3 models performed well in the classification task.ResNet-34 vs ResNet-50 had F1 values of 91.46%vs 92.08%,accuracies of 92.87%vs 93.05%,precisions of 90.48%vs 95.26%,and recall rates of 92.89%vs 89.11%.YOLOv5 had an overall accuracy of 85.6%,achieving 85.3%and 85.7%accuracies in the specific classifications for hypertensive patients with phlegm-dampness and the sub-health with phlegm-dampness.Conclusion All 3 models(ResNet-34,ResNet-50 and YOLOv5)performed well in the classification task,with ResNet-50 being the best.It proves that the deep learning model can better accomplish the classification and recognition of tongue manifestations,which reflects the great potential of deep learning in the automated classification for TCM tongue diagnosis,and also provides a strong technical support for the modernization and objectivity of TCM diagnosis.

Objective To observe the characteristics of sublingual collaterals of patients with hypertension and the correlation between TCM syndromes and characteristics of sublingual collaterals based on image data.Methods Totally 303 patients with hypertension were selected from three hospitals in Anhui Province from October 2022 to April 2024,and were divided into liver fire hyperactivity syndrome,yin deficiency and yang hyperactivity syndrome,phlegm and blood stasis syndrome,and yin yang deficiency syndrome according to the syndromes.The patients'sublingual collateral images were captured using smartphones,and the AI open platform system for TCM tongue diagnosis was used to obtain the color,length,width,tortuous degree and concurrent manifestations of the sublingual collaterals,as well as the characteristic indexes,such as color HSV,Lab value,etc.of sublingual collaterals,using a combination of computer vision and manual interpretation,so as to analyze the correlation between the TCM syndromes and the characteristics of the sublingual collaterals.Results The color,length,width,tortuous degree and concurrent manifestations of sublingual collaterals in different syndrome types were statistically significant.The values of V,Lab-L,Lab-a and Lab-b in the phlegm and blood stasis syndrome were significantly lower than those in other syndrome types.The S value of yin-yang deficiency syndrome was significantly lower than that of other syndromes(P＜0.05).Correlation analysis showed that the color of sublingual collaterals was negatively correlated with the values of S,V,Lab-L,Lab-a and Lab-b of patients with different syndrome types(P＜0.05).The degree of stasis of sublingual collaterals in the phlegm and blood stasis syndrome was higher than that in other groups.Conclusion There are differences in color,length,width,tortuous degree and concurrent manifestations among the sublingual collaterals of patients with hypertension,and there is close correlation between the color of sublingual collaterals and its parameters.The objective index of sublingual collaterals is sensitive to hypertension,which is basically consistent with the theory and clinical conclusion of TCM,and can be used as the basis for syndrome differentiation and treatment.

Objective To objectively identify whether people with phlegm-dampness constitution suffer from hypertension or not using deep learning semantic segmentation model and residual neural network,so as to promote the modernization of tongue manifestation research,and provide a more objective and scientific basis for clinical decision-making in traditional Chinese medicine(TCM).Methods The tongue regions of 547 subjects were outlined and labeled using the Label Me image labeling tool,followed by tongue body segmentation using the U-Net segmentation algorithm which separated the tongue body from the complex background.In the subsequent study,3 deep learning models,namely ResNet-34,ResNet-50 and YOLOv5,were used to classify the tongue manifestations of hypertensive patients and the sub-health both with phlegm-dampness,and to construct the corresponding classification models whose performances were objectively evaluated by drawing confusion matrix and calculating F1 value and accuracy.Results The experimental results showed that all 3 models performed well in the classification task.ResNet-34 vs ResNet-50 had F1 values of 91.46%vs 92.08%,accuracies of 92.87%vs 93.05%,precisions of 90.48%vs 95.26%,and recall rates of 92.89%vs 89.11%.YOLOv5 had an overall accuracy of 85.6%,achieving 85.3%and 85.7%accuracies in the specific classifications for hypertensive patients with phlegm-dampness and the sub-health with phlegm-dampness.Conclusion All 3 models(ResNet-34,ResNet-50 and YOLOv5)performed well in the classification task,with ResNet-50 being the best.It proves that the deep learning model can better accomplish the classification and recognition of tongue manifestations,which reflects the great potential of deep learning in the automated classification for TCM tongue diagnosis,and also provides a strong technical support for the modernization and objectivity of TCM diagnosis.

Objective To observe the characteristics of sublingual collaterals of patients with hypertension and the correlation between TCM syndromes and characteristics of sublingual collaterals based on image data.Methods Totally 303 patients with hypertension were selected from three hospitals in Anhui Province from October 2022 to April 2024,and were divided into liver fire hyperactivity syndrome,yin deficiency and yang hyperactivity syndrome,phlegm and blood stasis syndrome,and yin yang deficiency syndrome according to the syndromes.The patients'sublingual collateral images were captured using smartphones,and the AI open platform system for TCM tongue diagnosis was used to obtain the color,length,width,tortuous degree and concurrent manifestations of the sublingual collaterals,as well as the characteristic indexes,such as color HSV,Lab value,etc.of sublingual collaterals,using a combination of computer vision and manual interpretation,so as to analyze the correlation between the TCM syndromes and the characteristics of the sublingual collaterals.Results The color,length,width,tortuous degree and concurrent manifestations of sublingual collaterals in different syndrome types were statistically significant.The values of V,Lab-L,Lab-a and Lab-b in the phlegm and blood stasis syndrome were significantly lower than those in other syndrome types.The S value of yin-yang deficiency syndrome was significantly lower than that of other syndromes(P＜0.05).Correlation analysis showed that the color of sublingual collaterals was negatively correlated with the values of S,V,Lab-L,Lab-a and Lab-b of patients with different syndrome types(P＜0.05).The degree of stasis of sublingual collaterals in the phlegm and blood stasis syndrome was higher than that in other groups.Conclusion There are differences in color,length,width,tortuous degree and concurrent manifestations among the sublingual collaterals of patients with hypertension,and there is close correlation between the color of sublingual collaterals and its parameters.The objective index of sublingual collaterals is sensitive to hypertension,which is basically consistent with the theory and clinical conclusion of TCM,and can be used as the basis for syndrome differentiation and treatment.

It is believed that qi and blood disharmony is the key pathogenesis of essential hypertension， for which mildly regulating qi and blood is recommended. According to the different pathological states and related causes of qi and blood disorders， essential hypertension can be divided into five syndrome types for differentiation and treatment. In terms of blood deficiency and liver constraint， it is recommended to nourish the blood and soften the liver， rectify qi to resolve constraint， using Xiao Yao Powder （逍遥散） or self-made Qihua Jieyu Decoction （七花解郁汤）. For qi stagnation and blood stasis， the method of regulating qi and harmonizing blood， dissolving stasis and unblocking collaterals should be used， with self-made Guitao Tongluo Decoction （桂桃通络汤）. For phlegm-dampness internal obstruction， it is recommended to move qi and promote urination， dissolve phlegm and eliminate dampness， using self-made Zhuanqi Sanzhuo Formula （转气散浊方）. For binding of phlegm and stasis， dissolving phlegm and dispelling stasis， dredging the bowels and directing the turbid downward is advised， and self-made Sanren Tiaozhi Formula （三仁调脂方） can be used. In terms of deficiency of both qi and blood， it is recommended to boost qi and nourish blood， supplement deficiency and consolidate the root， using Gui Pi Decoction （归脾汤） or self-made Shenqi Zaizao Decoction （参芪再造汤）.

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 (mPA) of 73.00%, an intersection over union (IoU) of 60.00%, and a mean intersection over union (mIoU) 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.

OBJECTIVE: To observe the effects of a traditional Chinese medicine (TCM) capsule for replenishing qi, nourishing yin and activating blood on Notch/Hes1 signaling pathway in the renal tissue and vascular endothelial CD34 and CD144 expressions in a rat model of diabetic nephropathy. METHODS: Rat models of early-stage diabetic nephropathy were established by left nephrectomy and high- fat and high- sugar feeding combined with intraperitoneal injection of STZ. The rats were randomized into model group, benazepril group, and high-, moderate-, and low-dose TCM capsule groups for corresponding treatments, with 6 normal rats as the control group. After 8 weeks of drug treatment, blood glucose and 24-h urinary albumin of the rats were measured, and the renal histopathology was observed with HE staining; Hes1 expression in the renal tissue was detected with immunohistochemical staining, and the renal expressions of CD34 and CD144 were detected using Western blotting. RESULTS: Compared with the normal control group, the rat models of diabetic nephropathy showed obvious abnormalities in 24- h urinary albumin and expressions of Hes1, CD34 and CD144d. The TCM capsule at both the high and moderate doses significantly reduced 24-h urinary albumin in the rats; the renal expressions of Hes1 and CD34 was significantly reduced in all the dose groups, and the expression of CD144 was significantly reduced in the high- dose group. Compared with benazepril group, the TCM capsule obviously reduced CD34 expression at all the 3 doses and lowered CD144 expression at the low dose. Histopathologically, the rats in the model group showed glomerular hypertrophy, increased mesenteric matrix, thickening and widening of the mesenteric membrane, and nodular hyperplasia. These pathologies were obviously alleviated by treatment with the TCM capsule at the high and moderate doses. CONCLUSIONS The Traditional Chinese medicine (TCM) capsule for replenishing qi, nourishing yin and activating blood can reduce Hes1, CD34 and CD144 in kidney tissue of model rats, play a protective role on kidney function and delay the development of DN.
Animals ; Diabetic Nephropathies ; Drugs, Chinese Herbal ; Medicine, Chinese Traditional ; Qi ; Rats ; Signal Transduction ; Transcription Factor HES-1