Search

Currently, most studies employ supervised learning techniques to train networks on three-dimensional tooth data to perform annotation tasks. However, these methods often perform poorly on cases of missing teeth, severe misalignments, or incomplete jaw structures, exhibiting weak generalization capabilities. To address these issues, a new approach based on a pre-trained SAM large model and prompt-based segmentation techniques was introduced. Initially, the model was fine-tuned on the MICCAI 3DTeethSeg'22 public dataset. Then, the three-dimensional dental models were projected onto multiple two-dimensional views, and the SAM network was utilized for image segmentation. After segmentation, each pixel's label was mapped back to the original three-dimensional triangular facets to complete the three-dimensional tooth segmentation. This approach was tested on 900 relatively ideal 3D upper and lower teeth data in the dataset, achieving results comparable to mainstream technologies. For complex cases such as missing teeth, misaligned teeth, and incomplete upper and lower jaws, it exhibited significantly better performance than existing technologies, showcasing enhanced generalizability and stability.(目前，大多研究采用有监督学习方法在牙齿的三维数据上训练网络，完成分割任务，但在处理缺牙、严重错位或颌部不完整的牙齿时效果不佳，泛化能力较弱。为此，提出了一种基于预训练分割一切模型（segment anything model，SAM）和提示分割技术的方法。首先，在2022年国际医学图像计算和计算机辅助干预会议（MICCAI 2022）的三维牙齿公开数据集上微调模型。然后，将三维牙齿模型投影至多个二维视图，利用SAM网络进行图像分割。再将每个像素的标签映射回原始的三维三角形面片，完成三维牙齿分割。在该数据集中，测试了900个较理想的三维上下牙数据，取得了与主流技术相当的结果。对于缺牙、牙齿错位以及上下颚不完整的复杂情况，本文方法表现出显著优于现有技术的效果，展示了更强的泛化能力和稳定性。)

Purpose: To investigate the prognosis of advanced oral squamous cell carcinoma (AOSCC) patients undergoing neck dissection with sternocleidomastoid muscle (SCM) preservation and resection., Methods: From January 2013 to June 2017, a total of 235 AOSCC patients(stage Ⅲ and stage Ⅳ) who were diagnosed and underwent neck dissection at the Department of Oral and Maxillofacial Surgery, College and Hospital of Stomatology, Guangxi Medical University, were collected and followed-up. The differences in overall survival（OS）, local recurrence-free survival (LRFS) and regional recurrence-free survival (RRFS) were compared between different surgical procedures. SPSS 25.0 software package was used for statistical analysis., Results: Among 235 patients with postoperative follow-up, 101 patients retained the SCM during operation, and 134 patients had SCM removed. There was no significant difference in 5-year survival rate and 5-year regional recurrence rate between the SCM preservation group and the SCM resection group. Kaplan-Meier method of univariate analysis showed that SCM preservation or resection had no significant difference in OS, LRFS and RRFS. Cox multivariate regression analysis results showed that there was no significant difference between different surgical procedures in OS, LRFS and RRFS, while N stage and postoperative chemoradiotherapy were independent influencing factors for OS, LRFS and RRFS in AOSCC patients., Conclusions: Neck dissection with SCM preservation in AOSCC patients has no effect on survival and recurrence (including local recurrence and regional recurrence). It is feasible for AOSCC patients to undergo SCM-preserving neck dissection when metastatic cervical lymph nodes do not invade SCM. N stage and postoperative chemoradiotherapy affect the prognosis of AOSCC patients.

To study hydrological features and physical and chemical characteristics of urban stream located in the plain river network area in the process of water resources regulation, and to discuss the forming and composition of nitrogen in urban stream based on water resources regulation. Effects of water regulation on the ammonium release from sediments in urban stream were studied under the condition of experimental simulation. The results showed that diurnal variation of water depth under the action of water resources regulation was significant. The value of DO in the overlying water along the water resources regulation path tended to decrease, while the concentration of permanganate index tended to increase. The concentration of nitrate in overlying water along the water resources regulation path gradually decreased, while the concentration of ammonium significantly increased. DO and permanganate index were the main factors influencing the concentrations of nitrate and ammonium in overlying water. Ammonium released from the sediments was an important source of ammonium in overlying water. Water resources regulation had a significant influence (P < 0. 05) on the concentration of ammonium in overlying water, but had no significant influence on the amount of cumulative ammonium released from sediments (P > 0. 05).