文献速递牙体牙髓病口腔修复与种植

基于人工智能平台在磨牙锥形束CT扫描中检测根尖周透射影的诊断准确性

Diagnostic accuracy of an artificial intelligence-based platform in detecting periapical radiolucencies on cone-beam computed tomography scans of molars.
PubMed 文献 · J Dent · 2025-05-31

本回顾性研究分析134颗磨牙(327个牙根)的术前与术后锥形束CT扫描,比较人工智能平台Diagnocat与两名经验丰富的牙髓科医生独立评估的根尖周透射影检测结果。术前未根充磨牙中,Diagnocat牙水平敏感度93.9%、根水平86.2%,特异度牙水平65.2%、根水平79.9%,AUC牙水平0.76、根水平0.79。术后根充磨牙扫描中阳性预测值和F1评分显著降低。

要点

  • Diagnocat在未根充磨牙的锥形束CT中检测根尖周透射影敏感度高但特异度中等。
  • 术后根充磨牙扫描中Diagnocat的阳性预测值和F1评分显著降低。
  • 作者指出需人工监督以防过度诊断,并需进一步研究优化平台性能。

核心结论

  • Diagnocat在检测未根充磨牙锥形束CT中的根尖周透射影方面显示出前景,敏感度高但特异度中等,需人工监督以防过度诊断。
  • 在根充磨牙的术后扫描中诊断性能显著下降。
  • 需要进一步研究以优化平台性能并支持其融入临床实践。

研究设计与样本

  • 回顾性研究,分析134颗磨牙(327个牙根)的术前和术后锥形束CT扫描。
  • 以两名经验丰富的牙髓科医生独立评估为参考标准,比较Diagnocat检测的根尖周透射影。
  • 在牙水平和根水平评估敏感度、特异度、准确性、阳性预测值、阴性预测值、F1评分和受试者工作特征曲线下面积(AUC-ROC)。

主要发现

  • 术前未根充磨牙扫描中,Diagnocat牙水平敏感度93.9%、根水平86.2%,牙水平特异度65.2%、根水平79.9%。
  • 术前未根充磨牙扫描中,牙水平准确性79.1%、根水平82.6%,牙水平阳性预测值71.8%、根水平75.8%。
  • 术前未根充磨牙扫描中,牙水平阴性预测值91.8%、根水平88.8%,牙水平F1评分81.3%、根水平80.7%。
  • AUC在牙水平为0.76、根水平为0.79。
  • 术后扫描显示阳性预测值(牙水平54.2%、根水平46.9%)和F1评分(牙水平67.2%、根水平59.2%)显著降低。

临床怎么用

  • 作者指出,如Diagnocat等人工智能平台可协助临床医生在锥形束CT扫描中检测根尖周透射影,提高诊断效率并支持决策。
  • 作者强调,人类专业知识仍必不可少,以尽量减少过度诊断的风险并避免不必要的治疗。
  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性;作者在结论中指出需要进一步研究以优化平台性能并支持其融入临床实践。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: This study aimed to evaluate the diagnostic performance of an artificial intelligence (AI)-based platform (Diagnocat) in detecting periapical radiolucencies (PARLs) in cone-beam computed tomography (CBCT) scans of molars. Specifically, we assessed Diagnocat's performance in detecting PARLs in non-root-filled molars and compared its diagnostic performance between preoperative and postoperative scans. METHODS: This retrospective study analyzed preoperative and postoperative CBCT scans of 134 molars (327 roots). PARLs detected by Diagnocat were compared with assessments independently performed by two experienced endodontists, serving as the reference standard. Diagnostic performance was assessed at both tooth and root levels using sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the receiver operating characteristic curve (AUC-ROC). RESULTS: In preoperative scans of non-root-filled molars, Diagnocat demonstrated high sensitivity (teeth: 93.9 %, roots: 86.2 %), moderate specificity (teeth: 65.2 %, roots: 79.9 %), accuracy (teeth: 79.1 %, roots: 82.6 %), PPV (teeth: 71.8 %, roots: 75.8 %), NPV (teeth: 91.8 %, roots: 88.8 %), and F1 score (teeth: 81.3 %, roots: 80.7 %) for PARL detection. The AUC was 0.76 at the tooth level and 0.79 at the root level. Postoperative scans showed significantly lower PPV (teeth: 54.2 %; roots: 46.9 %) and F1 scores (teeth: 67.2 %; roots: 59.2 %). CONCLUSION: Diagnocat shows promise in detecting PARLs in CBCT scans of non-root-filled molars, demonstrating high sensitivity but moderate specificity, highlighting the need for human oversight to prevent overdiagnosis. However, diagnostic performance declined significantly in postoperative scans of root-filled molars. Further research is needed to optimize the platform's performance and support its integration into clinical practice. CLINICAL SIGNIFICANCE: AI-based platforms such as Diagnocat can assist clinicians in detecting PARLs in CBCT scans, enhancing diagnostic efficiency and supporting decision-making. However, human expertise remains essential to minimize the risk of overdiagnosis and avoid unnecessary treatment.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Allihaibi M, Koller G, Mannocci F, et al. Diagnostic accuracy of an artificial intelligence-based platform in detecting periapical radiolucencies on cone-beam computed tomography scans of molars. J Dent. 2025. PMID: 40456383. doi:10.1016/j.jdent.2025.105854

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。