Deep learning for automated mandibular canal segmentation in CBCT scans.

Objective: This study aims to develop a framework for automated mandibular canal segmentation in cone beam computed tomography (CBCT) scans. The dataset, source code, and trained models are publicly accessible, allowing for reproducibility and further development by the research community. Methods:...

Descripción completa

Detalles Bibliográficos
Publicado en:BMC Oral Health Vol. 25; no. 1; pp. 1 - 11
Autores principales: Huang, Jingna, Jie, Ji, Ma, Huibin, Xie, Shimin, Liao, Huangan, Ouyang, Kexiong, Xin, Weini
Formato: diagnostic images equations & formulas research tables/charts Journal Article
Publicado: BioMed Central 10/29/2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=188948164&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 188948164
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        14726831
        1CIC
      jtl: BMC Oral Health
      issn: 14726831
      maglogo: N
    pubinfo:
      dt: 10/29/2025
      vid: 25
      iid: 1
      pid: 24147
      pub: BioMed Central
    artinfo:
      ui:
        188948164
        188948164
        188948164
        10.1186/s12903-025-07098-5
        188948164
      ppf: 1
      ppct: 10
      formats:
      tig:
        atl: Deep learning for automated mandibular canal segmentation in CBCT scans.
      aug:
        au:
          Huang, Jingna
          Jie, Ji
          Ma, Huibin
          Xie, Shimin
          Liao, Huangan
          Ouyang, Kexiong
          Xin, Weini
        affil: https://ror.org/02gxych78 Hospital of Stomatology Shantou University Medical College, 515000, Shantou, China
      sug:
        subj:
          Mandibular Canal Anatomy and Histology
          Mandibular Canal Radiography
          Tomography, X-Ray Computed
          Deep Learning
          Automation
          Image Processing, Computer Assisted
          Conceptual Framework
          Human
          Male
          Female
          Funding Source
          Descriptive Statistics
          Confidence Intervals
          Dentistry
          Technology, Dental
          Nerve Compression Syndromes Prevention and Control
          Data Analysis Software
          Sensitivity and Specificity
          Algorithms
          Access to Information
          Inferior Alveolar Nerve Anatomy and Histology
          Surgery, Oral
          Surgical Patients
          China
          Academic Medical Centers
          Adult
          Middle Age
          Random Sample
          Adult: 19-44 years
          Middle Aged: 45-64 years
          Male
          Female
      ab: Objective: This study aims to develop a framework for automated mandibular canal segmentation in cone beam computed tomography (CBCT) scans. The dataset, source code, and trained models are publicly accessible, allowing for reproducibility and further development by the research community. Methods: A total of 236 CBCT scans were collected from the Stomatology Hospital of the Shantou University Medical College, and the mandibular canals in these scans were manually annotated with fine granularity. A custom-designed 3D U-Net, named ManCan_ResU-Net, along with two commonly used 3D U-Net models, was employed as candidate models. The soft Dice Similarity Coefficient (DSC) loss was used as the loss function. During inference, a post-processing step involving connected components analysis and removal of small disconnected objects was applied to refine the segmentation results. Model performance was evaluated using following metrics: voxel accuracy (ACC), sensitivity (SEN), specificity (SPE), DSC, Hausdorff distance (HD), 95th percentile Hausdorff distance (HD95), average surface distance (ASD), and average symmetric surface distance (ASSD). Results: The MCSTU dataset, which contains a development dataset (218 CBCT images) and an independent test dataset (18 CBCT images) with fine-grained annotations, has been made publicly available. The validation loss of ManCan_ResU-Net was lower than those of two commonly used models. Incorporating post-processing significantly improved model performance, particularly by reducing the HD metric. On the hold-out test dataset, the ManCan_ResU-Net model achieved ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.86 (0.83–0.87), 1 (1–1), 0.85 (0.83–0.86), 10.1 (8.67–13.6), 1.8 (1.6–2.2), 0.69 (0.58–0.85), and 0.72 (0.6–0.83), respectively. On the test dataset, the ManCan_ResU-Net model obtained ACC, SEN, SPE, DSC, HD, HD95, ASD, ASSD with 95% confidence interval of 1 (1–1), 0.93 (0.91–0.95), 1 (1–1), 0.80 (0.79–0.81), 21.3 (11.7–53.9), 2.59 (2.33–3), 1 (0.96–1.21), and 0.92 (0.861–1), respectively. Both the code and trained models are publicly available. Conclusion: The proposed segmentation framework achieved strong performance on both the hold-out and independent test datasets. In the future, after further validation of the model's generalization ability, it may be applied in real clinical settings for oral surgery planning.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        equations & formulas
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N