Scholarlink

Background <p>Missed detection of the second mesiobuccal canal (MB2) in maxillary first molars is a recognized contributor to endodontic failure. Although cone-beam computed tomography (CBCT) enhances three-dimensional visualization of root canal anatomy, image interpretation remains observer-dependent and variable.</p> Objective <p>To develop and validate a deep learning (DL) model for automated detection of MB2 canals on CBCT images and to evaluate its impact on the diagnostic performance of junior dentists.</p> Methods <p>CBCT scans from 1,022 patients were annotated by expert consensus using comprehensive volumetric evaluation. A two-stage DL framework—region-of-interest localization using a modified VGG16 network followed by classification with a ConvNeXt–Transformer architecture-was trained on 1,944 ROIs and evaluated on an independent test set of 100 ROIs (50 MB2-positive, 50 MB2-negative). Three junior dentists assessed the test set with and without DL assistance.</p> Results <p>The proposed model achieved a sensitivity of 0.84, specificity of 0.86, positive predictive value of 0.86, negative predictive value of 0.84, F1-score of 0.85, and an area under the receiver operating characteristic curve (AUC) of 0.85, outperforming benchmark CNN architectures. DL assistance increased junior dentists’ F1-scores (0.78–0.82 manually vs. 0.82–0.88 with assistance) and improved inter-reader agreement (Fleiss’ κ: 0.730 to 0.880).</p> Conclusions <p>The proposed DL framework demonstrated balanced diagnostic performance for MB2 detection and enhanced diagnostic consistency among junior clinicians. Deep learning may serve as an adjunctive decision-support tool in endodontic imaging and education. Further multicenter validation is warranted to establish generalizability and clinical applicability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning–based detection of the second mesiobuccal canal in maxillary first molars using cone-beam computed tomography

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月9日

查看全文
  • Jiao Lin,
  • Jialing Liu,
  • Yuxin Jiang,
  • Yang Liu,
  • Bixin Wen,
  • Shihao Li,
  • Chenglong Li

摘要

Background

Missed detection of the second mesiobuccal canal (MB2) in maxillary first molars is a recognized contributor to endodontic failure. Although cone-beam computed tomography (CBCT) enhances three-dimensional visualization of root canal anatomy, image interpretation remains observer-dependent and variable.

Objective

To develop and validate a deep learning (DL) model for automated detection of MB2 canals on CBCT images and to evaluate its impact on the diagnostic performance of junior dentists.

Methods

CBCT scans from 1,022 patients were annotated by expert consensus using comprehensive volumetric evaluation. A two-stage DL framework—region-of-interest localization using a modified VGG16 network followed by classification with a ConvNeXt–Transformer architecture-was trained on 1,944 ROIs and evaluated on an independent test set of 100 ROIs (50 MB2-positive, 50 MB2-negative). Three junior dentists assessed the test set with and without DL assistance.

Results

The proposed model achieved a sensitivity of 0.84, specificity of 0.86, positive predictive value of 0.86, negative predictive value of 0.84, F1-score of 0.85, and an area under the receiver operating characteristic curve (AUC) of 0.85, outperforming benchmark CNN architectures. DL assistance increased junior dentists’ F1-scores (0.78–0.82 manually vs. 0.82–0.88 with assistance) and improved inter-reader agreement (Fleiss’ κ: 0.730 to 0.880).

Conclusions

The proposed DL framework demonstrated balanced diagnostic performance for MB2 detection and enhanced diagnostic consistency among junior clinicians. Deep learning may serve as an adjunctive decision-support tool in endodontic imaging and education. Further multicenter validation is warranted to establish generalizability and clinical applicability.