To develop an artificial intelligence-based deep learning model for early screening and detection of periodontal diseases using periodontal images captured by a portable oral endoscope. A dataset consisting of 811 clinical oral periodontal images collected via endoscopy was constructed. After data cleaning and high-quality annotation, it was divided into 271 healthy and 540 unhealthy periodontal images, with an 8:2 split for training and validation. The YOLOv11 deep learning model was used for analysis and early detection of periodontal diseases. Model performance was evaluated using precision, recall, and mean average precision. In the validation set, for binary classification the model achieved a precision of 0.727, a recall rate of 0.583, and a mean average precision of 0.632 at an IOU (Intersection over Union) threshold of 0.5. For multiclass detection, the model’s precision for identifying gingival recession was 0.671, for gingival swollen was 0.609, and for detecting dental calculus was 0.573. The developed deep learning model enables low-cost early screening and detection of periodontal diseases, providing an important direction for the application of artificial intelligence in early periodontal disease screening.

Salivary duct carcinoma (SDC) is a highly aggressive salivary gland malignancy with poor prognosis. The aim was to investigate the prognostic factors and survival outcomes in a cohort of SDC patients. This study retrospectively analyzed the clinicopathological data of 61 SDC patients treated at the First Medical Center of the PLA General Hospital between January 2010 and December 2020. Univariate and multivariate Cox proportional hazards models were used to identify prognostic factors for overall survival (OS). Fine-Gray subdistribution hazard model was used to analyze prognostic factors for cancer-specific mortality. Of the 61 patients, the parotid gland was the most common primary site (70.5

BackgroundWe developed olecranon-type tracheotomy and expansion forceps (OTEF) for emergency tracheotomy in patients experiencing acute airway obstruction. By using OTEF, medical rescue personnel can perform emergency tracheotomy more quickly and accurately on their own, while conventional tracheotomy requires the cooperation of two surgeons.MethodsIn this study, 24 adult cadavers that had died within 24 h were randomly assigned to the OTEF or PDT groups. Tracheotomies were performed by the same physician, using the OTEF technique for the OTEF group and the percutaneous dilational tracheotomy technique for the PDT group. The collected data included basic cadaver characteristics, operative time, incision length, and intraoperative tracheal wall injuries.ResultsIn the OTEF group, the mean tracheotomy completion time was 96.83 ± 8.82 s, with a mean incision length of 13.67 ± 3.67 mm. In the PDT group, the mean tracheotomy completion time was 566.50 ± 47.14 s, and the mean incision length was 20.67 ± 4.76 mm. Compared with the PDT group, the OTEF group demonstrated significantly shorter operative times (P < 0.05) and smaller incision lengths (P < 0.05).ConclusionOTEF enables efficient and minimally traumatic tracheostomies in emergency settings with minimal environmental and positioning requirements. In disaster sites or even on battlefields where medical personnel are in short supply, this device can enhance the battlefield rescue skills and emergency response capabilities of non-medical rescue workers, effectively alleviate rescue pressure and save the lives of the injured.

OBJECTIVE:We aimed to develop an AI-based model that uses a portable electronic oral endoscope to capture intraoral images of patients for the detection of oral cancer. SUBJECTS AND METHODS:From September 2019 to October 2023, 205 high-quality annotated images of oral cancer were collected using a portable oral electronic endoscope at the Chinese PLA General Hospital for this study. The U-Net and ResNet-34 deep learning models were employed for oral cancer detection. The performance of these models was evaluated using several metrics: Dice coefficient, Intersection over Union (IoU), Loss, Precision, Recall, and F1 Score. RESULTS:During the algorithm model training phase, the Dice values were approximately 0.8, the Loss values were close to 0, and the IoU values were around 0.7. In the validation phase, the highest Dice values ranged between 0.4 and 0.5, while the Loss values increased, and the training loss began to decrease gradually. In the test phase, the model achieved a maximum Precision of 0.96 with a confidence threshold of 0.990. Additionally, with a confidence threshold of 0.010, the highest F1 score reached was 0.58. CONCLUSION:This study provides an initial demonstration of the potential of deep learning models in identifying oral cancer.

Objectives We assessed the potential prognostic significance of the preoperative systemic inflammation index, platelet-to-lymphocyte ratio, and neutrophil-to-lymphocyte ratio in patients who underwent surgical resection. Subjects and Methods This retrospective study included 224 patients with clinicopathologically confirmed squamous carcinoma of the tongue who underwent surgery between August 2009 and December 2017. The optimal cut-off values for the indices were determined by receiver operating characteristic curves. Correlations between the indices and clinicopathological variables were determined by Pearson chi-square or Fisher exact tests. The Kaplan-Meier test was used to compare overall survival between groups (high and low values); the log-rank or Breslow test was used to assess differences in survival. Univariate and multivariate Cox regression models were used to analyze predictive values of the indices as independent indicators of overall survival. Bilateral p values of Significant association was found between the indices and sex, tissue grade, tumor location, and lymph nodes metastases (p < 0.05). On Kaplan-Meier analysis, patients with lower values of the indices had longer overall survival (p < 0.05). Univariate and multivariate Cox regression models identified age, lymph node metastases, and neutrophil-to-lymphocyte ratio as independent predictors of overall survival. Conclusion The studied indices have potential prognostic significance in patients with squamous tongue cancer.

OBJECTIVES:This paper aims to investigate the application of intraoral scanning and cone beam computed tomography (CBCT) registration implant robot in dental implant surgery. METHODS:The data of 40 cases with dental defect of robot-assisted implantation from November 2023 to May 2024 were retrospectively analyzed. Before the operation, the intraoral scan data and CBCT data of the positioning markers were automatically fused with the initial CBCT images, and the registration error was calculated. The average registration error of positioning markers was determined during the operation, and the implantation accuracy was analyzed after the operation. RESULTS:The intraoral scan data and CBCT data of 40 patients with dental defect wearing positioning markers were successfully registered with the initial CBCT image, and the registration errors were (0.157±0.026) mm and (0.154±0.033) mm, respectively. Statistical analysis showed no statistical significance between them. The registration errors of the marker was (0.037 3±0.003 6) mm. A total of 55 implants were performed, and the total deviations of the implant point and the apical point were (0.78±0.41) and (0.89±0.28) mm, respectively. The transverse deviations of the implant point and the apical point were (0.44±0.36) and (0.58±0.25) mm, respectively. The depth deviations of the implant point and the apical point were (0.51±0.32) and (0.54±0.36) mm, respectively. The deviation of the implant angle was 1.24°±0.67°. CONCLUSIONS:The fusion technology based on intraoral scanning and CBCT registration can meet the accuracy requirements of preoperative registration of oral implant robots. The technology increases the choice of registration methods before robot-assisted dental implant surgery and reduces the multiple radiation exposuresof the patient.

目的 探讨 CT 及 MRI 等多模态图像自动配准融合技术联合手术机器人在面侧深区肿瘤诊疗中的意义.资料与方法回顾性分析2019年8月—2021年8月解放军总医院第一医学中心收治的面侧深区肿瘤患者45例,术前行机器人辅助CT、MRI图像自动配准融合并计算配准误差,术中行机器人导航下穿刺活检术及肿瘤切除手术,术后行病理检查验证穿刺准确度.分析机器人自动配准融合技术引导下的穿刺准确度、穿刺并发症、配准融合误差等.结果 45 例患者CT、MRI图像全部实现自动配准融合,基于互信息类方法评价融合误差绝对值为 0.88±0.06.良、恶性肿瘤的不同部位肿瘤例数比较,差异无统计学意义(χ2=6.515,P>0.05).机器人导航穿刺活检术取材45例,恶性肿瘤与良性肿瘤/病变分别为29例和 16例;肿瘤切除手术取材37例,恶性肿瘤和良性肿瘤/病变分别为23 例和14例;根据病理诊断,穿刺准确率为97.3%(36/37).结论 基于多模态CT、MRI图像自动配准融合技术联合机器人导航系统可提高面侧深区肿瘤诊断的准确性,有助于向临床提供更合理的治疗选择.

目的:探讨眉弓下联合口内切口术式对颧骨颧弓复合体骨折治疗满意度的影响及安全性.方法:选取2017年6月～2019年5月我院收治的82例颧骨颧弓复合体骨折患者,随机分为两组,每组41例.对照组采用冠状切口,观察组采用眉弓下联合口内切口.比较两组术后3个月优良率、切口长度、手术时间、术中出血量、住院时间、术后6个月治疗满意度、并发症及术前、术后6h、24h应激反应指标[醛固酮(ALD)、皮质醇(Cor)、促肾上腺皮质激素(ACTH)].结果:观察组术后3个月优良率(95.12％)与对照组(97.56％)相比,差异无统计学意义(P＞0.05);观察组切口长度、手术时间、术中出血量、住院时间均低于对照组(P＜0.05);术后6h、24h两组Cor、ALD、ACTH水平均呈升高趋势,但观察组低于对照组(P＜0.05);观察组术后6个月治疗满意度(97.56％)高于对照组(80.49％)(P＜0.05);组间并发症发生率(2.44％、7.32％)比较,差异无统计学意义(P＞0.05).结论:眉弓下联合口内切口术式治疗简单型颧骨颧弓复合体骨折,可达到良好解剖复位,缩短切口长度、手术时间,减少术中出血量,减轻术后早期应激反应,加快患者术后的恢复,提高治疗满意度.

This study aimed to build a home use deep learning segmentation model to identify the scope of caries lesions. A total of 494 caries photographs of molars and premolars collected via endoscopy were selected. Subsequently, these photographs were labeled by physicians and underwent segmentation training by using DeepLabv3+, and then verification and evaluation were performed. The mean accuracy was 0.993, the sensitivity was 0.661, the specificity was 0.997, the Dice coefficient was 0.685, and the intersection over union (IoU) was 0.529. Therefore, the present deep learning segmentation model can identify and segment the scope of caries.

ObjectiveThe etiology of apical diseases is diverse, and most are due to incomplete root canal therapy. The common clinical manifestations include gingival abscess, fistula and bone destruction. The currently existing limitation of procedures is that surgeons cannot visually evaluate the surgical areas. We sought to combine mixed reality (MR) technology with a 3-dimensional (3D) printed surgical template to achieve visualization in apical surgery. Notably, no reports have described this application.MethodsWe created visual 3D (V3D) files and transferred them into the HoloLens system. We explained the surgical therapy plan to the patient using a mixed reality head-mounted display (MR-HMD). Then, the 3D information was preliminarily matched with the operative area, and the optimal surgical approach was determined by combining this information with 3D surgical guide plate technology.ResultsWe successfully developed a suitable surgical workflow and confirmed the optimal surgical approach from the buccal side. We completely exposed the apical lesion and removed the inflammatory granulation tissue.ConclusionWe are the first group to use the MR technique in apical surgery. We integrated the MR technique with a 3D surgical template to successfully accomplish the surgery. Desirable outcomes using minimally invasive therapy could be achieved with the MR technique.

Oral squamous cell carcinoma (OSCC) is the most common malignant epithelial tumor in the oral cavity. Emerging evidence has demonstrated the important function roles of long noncoding RNAs (lncRNAs) in human cancers. LncRNA promoter of CDKN1A antisense DNA damage activated RNA (PANDAR) functions as an oncogene in multiple carcinomas, whereas its function in OSCC has not been investigated yet. The aim of our study is to investigate the possible regulatory mechanism of PANDAR in OSCC. First of all, PANDAR was highly expressed in OSCC cells and loss-of-function assays mediated by CRISPR-dCas9 observed that PANDAR silencing restrained cell proliferation and promoted cell apoptosis. Then we found and confirmed the interaction between PANDAR and serine and arginine rich splicing factor 7 (SRSF7). Subsequently, serine/threonine-protein kinase pim-1 (PIM1) was proved to be regulated by PANDAR in SRSF7-dependant way. Rescue experiments validated that PANDAR modulated the proliferation and apoptosis in OSCC through PIM1. In conclusion, PANDAR bound with SRSF7 to increase PIM1 expression, hence promoting the development of OSCC. These data shed new lights into the seeking for effective diagnostic biomarkers and therapeutic targets for OSCC patients.

目的:观察B超结合新型内窥镜取出颅颌面颈部散在多处异物的临床应用疗效.方法:统计近5年解放军总医院收治的颅颌面颈部多处散在异物滞留患者,分析在B超结合新型内窥镜下行异物取出的临床资料,观察临床疗效.结果:滞留于患者颌面部的多处异物采用该技术全部完整取出,手术安全性良好,充分发挥超声以及内窥镜的优势,术中解剖定位准确,术后患者无明显手术并发症,缩短了手术时间.结论:采用B超结合新型内窥镜手术缩小了异物搜索范围,减少了对患者正常组织的副损伤,为医生寻找并定位异物提供方向性,是一种安全有效的异物取出方法.

目的 观察并研究机器人辅助定位下平阳霉素注射治疗口腔颌面部脉管畸形的临床疗效.方法 收集2017—2021年本院收治的有完整临床资料的共20例口腔颌面颈部脉管畸形患者进行回顾性分析,所有患者均采用机器人辅助定位平阳霉素药物注射治疗,观察并记录患者预后情况,复查颌面部增强CT或者MRI评价瘤体大小变化作为疗效评价指标.结果 20例患者均在机器人辅助下顺利完成手术,临床有效率95％,术后无药物不良反应发生.该技术手术安全性良好,充分发挥机器人定位准确的优势,采用退针给药的方法增强药物与脉管畸形病变内皮细胞作用面积,充分发挥药物治疗作用,缩短平阳霉素药物注射间隔时间.结论 机器人辅助定位并平阳霉素药物注射治疗脉管畸形安全有效,创伤小,精度高,可重复注射治疗,最大程度保留原始器官外形及功能发挥,临床应用价值高.

背景 现代战场环境中气道损伤是导致可救治伤员死亡的重要原因,能否及时进行气道开放成为挽救气道损伤伤员生命的关键.紧急气道开放装置的研究具有现实需求.目的 研发一种可用于战现场气道损伤紧急气管切开的刻度式气管切开撑开一体钳,探索战现场紧急气管切开新方法.方法 使用18只小型猪,随机分为3组,每组6只,分别进行环甲膜切开术(surgical cricothyrotomy,SC)、外科气管切开术(surgical tracheotomy,ST)以及使用新研发的刻度式气管切开撑开一体钳快速气管切开术(scale-type tracheotomy and expansion pliers forceps,STEF),记录操作用时及血氧饱和度变化情况.结果 18只小型猪均成功完成了气道开放,建立了通畅的呼吸通道.SC组、ST组、STEF组小型猪血氧饱和度达到90％以上用时分别为(60.0±4.8)s、(117.5±5.7)s、(28.3±2.8)s.血氧饱和度折线在上升阶段斜率分别为kSC=1.56、kST=1.46、kSTEF=1.54,STEF组建立的气道通气效率与SC组、ST组基本相同.所有小型猪手术出血极少.结论 使用刻度式气管切开撑开一体钳进行的紧急气管切开术在操作时间上优于环甲膜切开术与外科气管切开术,操作简便,在战现场气道损伤救治时具有明显的优势.

BACKGROUND:Interstitial brachytherapy (BT) is becoming an accepted treatment option for head and neck cancer patients for whom surgery poses high risks. Multimodal, image-guided, robotic surgery has the potential to allow precise seed implantation into tumors. Our aim was to introduce a new multimodal, image-guided surgical robot during the performance of interstitial BT for the treatment of tumors in the head and neck regions.METHODS:Clinical data for three patients were analyzed, retrospectively; patients had received 125 I seed implantations from July 2019 to October 2019. Multimodal, image-guided, robotic surgery was performed in all patients. Postoperative computed tomography data were imported to software to evaluate the accuracy of the seed position and the operation times.RESULTS:The mean placement error of the 125 I seed was 1.9 ± 0.74 mm. The mean operation time is 47 minutes.CONCLUSION:The experimental results showed that the Remebot has promise for use during BT for the head and neck.

Abstract Objective: The current study aimed to investigate the functional roles and clinical significance of microRNA-148a (miR-148a) in the progression of oral squamous cell carcinoma (OSCC). Methods: Relative expression of miR-148a in OSCC cells and tissues were detected using quantitative real-time polymerase chain reaction (qRT-PCR). Chi-square test was performed to estimate the relationship between miR-148a expression and clinical characteristics of OSCC patients. Cell transfection was carried out using Lipofectamine® 2000. Biological behaviors of tumor cells were detected using 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) and transwell assays. Bioinformatics analysis and luciferase reporter assay were used to identify the target genes of miR-148a. Protein expression was detected through Western blot analysis. Results: MiR-148a expression was obviously decreased in OSCC tissues and cells, and such down-regulation was closely correlated with lymph node metastasis (P=0.027) and tumor node metastasis (TNM) stage (P=0.001) of OSCC patients. miR-148a overexpression could significantly impair OSCC cell proliferation, migration and invasion in vitro (P<0.05 for all). Insulin-like growth factor-I receptor (IGF-IR) was a potential target of miR-148a. MiR-148a could inhibit ERK/MAPK signaling pathway through targeting IGF-IR. Conclusion: MiR-148a plays an anti-tumor role in OSCC and inhibits OSCC progression through suppressing ERK/MAPK pathway via targeting IGF-IR.

n amendment to this paper has been published and can be accessed via the original article.

目的 研究一种利用耳屏内联合颌下小切口入路制备隧道复位固定髁突颈部及基部骨折的方法,并观察其临床疗效.方法 选择2012年1月至2018年1月30例髁突颈部中低位骨折患者,采用耳屏内联合颌下小切口入路,制造隧道式入路进行手术治疗.术后随访测量张口度、CT检查骨折断端对位情况及钛板有无变形、移位.结果 ①30例患者术中恢复正常咬合关系,术后复查无一例出现咬合紊乱;②张口度分析采用重复测量设计资料的方差分析进行检验(P＜0.05),术前及术后1～12个月复查,患者平均张口度分别为(5.43±2.012)mm,(14.83±2.135)mm,(19.67±2.123)mm,(32.20±2.140)mm,(32.23 ±1.633)mm,(32.40±1.653)mm,患者术后张口度逐渐改善;③术后1、3、6、12个月复查CT显示骨折断端对位愈合,钛钉钛板无松动、变形、移位;④瘢痕位于耳内及颌下,位置隐蔽.⑤1例患者术后出现口角轻度歪斜症状,予以神经营养治疗,术后6个月复查症状消失.结论 耳屏内联合颌下小切口隧道式入路治疗髁突颈部及基部骨折,显露充分,复位精确,实现早期张口功能训练及咬合关系恢复的同时,可做到瘢痕隐蔽,有效保护了面神经、颞浅动静脉、翼外肌等重要解剖结构,为临床髁突颈部及基部骨折手术入路的选择提供新的参考.

目的 对比研究计算机辅助光学导航与电磁导航下精准牙种植手术的优缺点.方法 下颌牙列缺损拟行牙种植手术患者10例,采集患者颌骨CBCT影像,5例在计算机辅助光学导航下行牙种植手术,5例在计算机辅助电磁导航下行牙种植手术.术后拍摄CBCT进行种植位点评估.结果 两组患者均获得了良好的治疗效果,所有植体均植入理想的颌骨位置中.两组患者植体整体角度偏差范围不超过25°,植入深度偏差均不超过1.4 mm;光学导航组植体植入角度偏差小于电磁导航组(t=3.5,P＜0.05),两组患者植体植入深度差异无显著性(P＞0.05).结论 计算机辅助光学导航与电磁导航下均可完成精准牙种植手术,在应用过程中,两者各有优势和不足,电磁导航对于手术室环境要求较苛刻,在常规环境中精度略低于光学导航.在进一步研究中如果可以将光学导航和电磁导航相结合进行精准牙种植手术,将大大提高计算机辅助导航在牙种植领域的应用范围,特别是为复杂牙种植手术提供新的助力.

目的 探讨一清片联合西地碘含片治疗重度慢性牙周炎的临床疗效.方法 选择2018年1月—2018年10月首都医科大学附属北京潞河医院收治的128例重度慢性牙周炎患者作为研究对象,所有患者按照治疗方式差异分为对照组和治疗组,每组各64例.对照组患者含服西地碘含片,1片/次,3次/d.治疗组在对照组治疗基础上口服一清片,4片/次,3～4次/d.两组均连续治疗3个月.观察两组的临床疗效,比较两组的牙周指标、炎性因子水平.结果 治疗后,对照组和治疗组的总有效率分别为 70.31%、90.63%,两组比较差异有统计学意义(P＜0.05).治疗后,两组患者龈沟出血指数(SBI)、附着丧失(AL)、菌斑指数(PLI)、牙周袋深度(PD)、牙龈指数(GI)均显著下降,同组治疗前后比较差异有统计学意义(P＜0.05);且治疗组牙周指标均明显于低于对照组,两组比较差异有统计学意义(P＜0.05).治疗后,两组患者白细胞介素-6 (IL-6)、白细胞介素-1β(IL-1β)、C反应蛋白(CRP)、肿瘤坏死因子-α(TNF-α)水平均显著下降,同组治疗前后比较差异有统计学意义(P＜0.05);且治疗组炎性因子水平明显低于对照组,两组比较差异有统计学意义(P＜0.05).结论 一清片联合西地碘含片治疗重度慢性牙周炎具有较好的临床疗效,能缓解患者临床症状,改善患者牙周指标,降低患者炎症反应,具有一定的临床推广.