Objective: To address the lack of fine-grained clinical recognition for specific Yang deficiency syndrome subtypes and the limitations of conventional object detection models in extracting irregular, low-contrast tongue phenotypes. This study aims to develop an objective subtype recognition framework based on an improved You Only Look Once nano (YOLO11n) architecture, using a standardized visual phenotype matrix to translate macroscopic traditional Chinese medicine (TCM) descriptions into quantifiable clinical targets. Methods: This cross-sectional diagnostic study consecutively enrolled adult inpatients admitted to the Department of Thyroid and Breast Surgery, The First Affiliated Hospital of Wannan Medical University (Yijishan Hospital), between September 1, 2024 and June 1, 2025, who were suspected of having Yang deficiency constitution based on initial TCM consultation. Clinical tongue image data were collected for analysis. Based on an Expert Visual Phenotype Annotation Matrix, a five-category recognition system was established, including the following TCM syndrome subtypes: spleen-dampness exuberance syndrome, mild kidney Yang deficiency syndrome, upper heat and lower cold syndrome, simultaneous Yin-Yang deficiency syndrome, and Yin deficiency and fluid depletion syndrome (negative control). The proposed Yang deficiency YOLO (YD-YOLO) model, built upon the YOLO11n baseline, integrates the Cross Stage Partial with kernel size 2 (C3k2)-GhostBottleneck-Dynamic Convolution (GBDC) module into the backbone to adaptively extract low-contrast features, and embeds the multipath aggregation coordinate attention (MACA) mechanism into the neck to suppress background interference through multi-scale spatial coordination. Gradient-weighted class activation mapping (Grad-CAM) was used to visualize feature attribution and evaluate the biological plausibility of the model’s focus. Model performance was evaluated through ablation and comparative experiments using mean average precision (mAP), precision, recall, F1 score, inference speed (frames per second, FPS), overall accuracy, Cohen’s kappa, and the area under the receiver operating characteristic (ROC) curve (AUC). Results: Based on the final inclusion of 1 186 clinical cases, the YD-YOLO model had an overall accuracy of 91.5%, a Cohen’s kappa of 0.912, and an mAP@50 of 0.731 [higher than the YOLO11n baseline (0.681)], with AUC ranging from 0.91 to 0.97 across all TCM syndrome subtypes. Among the TCM syndrome subtypes, the mild kidney Yang deficiency syndrome had the highest mAP@50 (0.900), and the inference speed reached 89.00 FPS. Grad-CAM analysis showed that the model localized activation to key TCM pathological features, such as marginal tooth marks and focal root coatings, while suppressing non-diagnostic oral background noise. Conclusion The YD-YOLO model demonstrates the feasibility of deep learning for the fine-grained classification of TCM Yang deficiency subtypes. By integrating visual phenotype quantification with model interpretability, the proposed framework provides an objective basis for syndrome differentiation, supporting the development of standardized digital diagnostic systems and the provision of clinical decision support in TCM practice.

Objective To study the effect of contusion and exhaustive exercise on satellite cells' activation and Pax7/CBF1/DAPT contents in skeletal muscles of rats,and reveal the repair mechanism of the skeletal muscle injury.Methods Twenty-four seven-week-old male Sprague-Dawley(SD)rats were randomly divided into a control(C)group,an immediately after exhaustive exercise(E0)group,a 24 hours after exhaustive exercise(E24)group and a 48 hours after exhaustive exercise(E48)group,each of 6.Other 18 SD rats were randomly divided into 3 groups,6 rats in each group:an immediately after contusion group(D0),a 24h post-contusion group(D24)and a 48h post-contusion group(D48).All groups were killed at different time points after exhaustive exercise and the contusion respectively while the control group was at resting state,and their serum was extracted.The right gastrocnemius muscles were resected and divided into 2 parts:one was used immediately for culturing satellite cells,while the other was stored in the bridge at-80℃.All the serum and gastrocnemius muscles were tested for Pax7,CBF1 and DAPT contents using the enzyme-linked immunosorbent assay(ELISA).Moreover,three-day-old newborn rats were also slaughtered for the above experiment.Results The results of culture in vitro showed that one day after the culture began a small amount of spindle satellite cells could be seen in the newborn rats,but the satellite cells of other groups were growing slowly.However,on the third day and the fifth day,the spindle satellite cells of each group began to proliferate in quantity and reached the peak.Then all the satellite cells had a good proliferation until the seventh day after serial passage,and some patial fusions to microtubules occurred.The biggest cell number and proliferation rate was in newborn rats,but no skeletal muscle satellite cell was found in the control group.At the same time,the number and the proliferation rate of skeletal muscle satellite cells in contusion groups were significantly higher than the exhaustive exercise groups.The results of Elisa showed that the contents of CBF1 and Pax7 in skeletal muscles in exhaustive groups and contusion groups,were significantly upregulated,compared to the control group(P＜0.05).Amomg them,the CBF1 content in group D0,together with the Pax7 content in group D24 and D48,was significantly higher than that of the other groups(P＜0.05).On the other hand,the content of DAPT in skeletal muscles of exhaustive groups and contusion groups,compared to the control group,was significantly downregulated (P＜0.05).To be more specific,the value of group D0 was significantly lower than that of the other groups (P＜0.05).However,there was no significant difference in it among group E0,E24 and E48.Conclusions Contusion and exhaustive exercise can activate the skeletal muscle satellite cells to proliferate and differentiate.The number of activated skeletal muscle satellite cells in the contusion groups is significantly larger than that of exhaustive groups maybe due to the stronger stimulating by contusion.Both contusion and exhaustive exercise increase the contents of Pax7 and CBF1 in skeletal muscles,but decrease that of DAPT.The Pax7 and CBF1 may play a positive regulating role in terms of activating skeletal satellite cells and repairing skeletal muscle injury,while DAPT may play a negative regulating role.