OBJECTIVES: We propose a YOLOv11-TDSP model for improving the accuracy of dental abnormality detection on panoramic oral X-ray images. METHODS: The SHSA single-head attention mechanism was integrated with C2PSA in the backbone layer to construct a new C2PSA_SHSA attention mechanism. The computational redundancy was reduced by applying single-head attention to some input channels to enhance the efficiency and detection accuracy of the model. A small object detection layer was then introduced into the head layer to correct the easily missed and false detections of small objects. Two rounds of structured pruning were implemented to reduce the number of model parameters, avoid overfitting, and improve the average precision. Before training, data augmentation techniques such as brightness enhancement and gamma contrast adjustment were employed to enhance the generalization ability of the model. RESULTS: The experiment results showed that the optimized YOLOv11-TDSP model achieved an accuracy of 94.5%, a recall rate of 92.3%, and an average precision of 95.8% for detecting dental abnormalities. Compared with the baseline model YOLOv11n, these metrics were improved by 6.9%, 7.4%, and 5.6%, respectively. The number of parameters and computational cost of the YOLOv11-TDSP model were only 12% and 13% of those of the high-precision YOLOv11x model, respectively. CONCLUSIONS The lightweight YOLOv11-TDSP model is capable of highly accurate identification of various dental diseases on panoramic oral X-ray images.
Radiography, Panoramic/methods* ; Humans ; Algorithms ; Tooth Abnormalities/diagnostic imaging*

Objective To explore the effects of heated humidified high flow nasal cannulae (HFNC) oxygen therapy among patients with pulmonary fibrosis. Methods A total of 60 patients in accord with diagnostics guide for idiopathic pulmonary fibrosis and admitted to Department of Respiratory at a Class III Grade A hospital in Tianjin for pulmonary fibrosis were selected by convenience sampling from May 2016 to March 2017. They received oxygen inhalation through nasal cannula for 24 hours and sequentially HFNC oxygen therapy for 24 hours respectively. The blood gas analysis,degree of comfort,severity of dyspnea and incidence of complications were compared two,four and twenty-four hours after adopting oxygen inhalation through nasal cannula and HFNC oxygen therapy. Results There were statistically significant differences in PaO2,SpO2,base excess (BE) and respiratory rate (RR) between oxygen inhalation through nasal cannula and HFNC oxygen therapy (P<0.05). The degree of comfort and severity of dyspnea significantly improved by HFNC oxygen therapy (P<0.05). There was a statistically significant difference in the incidence of complications (P<0.05). However,there was no statistically significant differences in PaCO2and PH between two oxygen methods (P>0.05). Conclusions The application of HFNC can increase PaO2and SpO2,and slow RR among patients with pulmonary fibrosis. Meanwhile,it can also effectively improve the severity of dyspnea,promote patients′ comfort and reduce the incidence of complications.