Academic Journal

Clinical Equivalence of a CNN-Based Automated Soft Tissue Landmark Detection System on 2D Facial Images.

Bibliographic Details
Title: Clinical Equivalence of a CNN-Based Automated Soft Tissue Landmark Detection System on 2D Facial Images.
Authors: Türkün, Argun Ege, Kalender, Müslim Ege, Kurt, Murat, Doğan, Servet
Source: Diagnostics (2075-4418); May2026, Vol. 16 Issue 10, p1464, 19p
Subject Terms: Convolutional neural networks, Orthodontics, Deep learning, Annotations, Statistical accuracy, Statistical reliability
Abstract: Background/Objectives: The aim of this study was to evaluate and compare the accuracy, reliability, and time efficiency of a convolutional neural network (CNN)-based deep learning model with manual annotation in the identification of soft tissue landmarks on two-dimensional (2D) facial images for orthodontic applications. Materials and Methods: Three-dimensional (3D) facial scans were obtained from 100 participants (50 females, 50 males) aged 18–25 years using the Revopoint Pop2 3D Scanner. Frontal and profile 2D images were extracted from the 3D models. Manual landmark identification was performed by a single investigator using LabelMe software, marking 22 landmarks on frontal images and 15 landmarks on profile images. A novel CNN model was developed and trained on these manually annotated images. The model's automatic landmark identifications were compared with manual annotations in terms of positional error, identification time, and reproducibility. Results: The CNN model achieved a mean localization accuracy of 96.07%. The mean prediction error ranged from 2.3% to 4.5% across various anatomical points. Trichion, Menton, and Gonion points exhibited relatively higher error rates. The model significantly reduced the annotation time compared to manual identification (manual method: 237 s per image). Intra-observer reliability analysis demonstrated excellent agreement for manual landmarking (ICC: 0.85–0.95). The AI model provided consistent predictions for identical inputs. Conclusions: The deep learning-based model demonstrated comparable accuracy to manual landmark identification while significantly improving the annotation speed and reproducibility. These results suggest that CNN-based systems offer a promising alternative for clinical orthodontic analysis and digital workflow integration. [ABSTRACT FROM AUTHOR]
Copyright of Diagnostics (2075-4418) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=20754418&ISBN=&volume=16&issue=10&date=20260515&spage=1464&pages=1464-1482&title=Diagnostics (2075-4418)&atitle=Clinical%20Equivalence%20of%20a%20CNN-Based%20Automated%20Soft%20Tissue%20Landmark%20Detection%20System%20on%202D%20Facial%20Images.&aulast=T%C3%BCrk%C3%BCn%2C%20Argun%20Ege&id=DOI:10.3390/diagnostics16101464
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: edb
DbLabel: Complementary Index
An: 194119316
RelevancyScore: 1061
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1060.76293945313
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Clinical Equivalence of a CNN-Based Automated Soft Tissue Landmark Detection System on 2D Facial Images.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Türkün%2C+Argun+Ege%22">Türkün, Argun Ege</searchLink><br /><searchLink fieldCode="AR" term="%22Kalender%2C+Müslim+Ege%22">Kalender, Müslim Ege</searchLink><br /><searchLink fieldCode="AR" term="%22Kurt%2C+Murat%22">Kurt, Murat</searchLink><br /><searchLink fieldCode="AR" term="%22Doğan%2C+Servet%22">Doğan, Servet</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Diagnostics (2075-4418); May2026, Vol. 16 Issue 10, p1464, 19p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Orthodontics%22">Orthodontics</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Annotations%22">Annotations</searchLink><br /><searchLink fieldCode="DE" term="%22Statistical+accuracy%22">Statistical accuracy</searchLink><br /><searchLink fieldCode="DE" term="%22Statistical+reliability%22">Statistical reliability</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background/Objectives: The aim of this study was to evaluate and compare the accuracy, reliability, and time efficiency of a convolutional neural network (CNN)-based deep learning model with manual annotation in the identification of soft tissue landmarks on two-dimensional (2D) facial images for orthodontic applications. Materials and Methods: Three-dimensional (3D) facial scans were obtained from 100 participants (50 females, 50 males) aged 18–25 years using the Revopoint Pop2 3D Scanner. Frontal and profile 2D images were extracted from the 3D models. Manual landmark identification was performed by a single investigator using LabelMe software, marking 22 landmarks on frontal images and 15 landmarks on profile images. A novel CNN model was developed and trained on these manually annotated images. The model's automatic landmark identifications were compared with manual annotations in terms of positional error, identification time, and reproducibility. Results: The CNN model achieved a mean localization accuracy of 96.07%. The mean prediction error ranged from 2.3% to 4.5% across various anatomical points. Trichion, Menton, and Gonion points exhibited relatively higher error rates. The model significantly reduced the annotation time compared to manual identification (manual method: 237 s per image). Intra-observer reliability analysis demonstrated excellent agreement for manual landmarking (ICC: 0.85–0.95). The AI model provided consistent predictions for identical inputs. Conclusions: The deep learning-based model demonstrated comparable accuracy to manual landmark identification while significantly improving the annotation speed and reproducibility. These results suggest that CNN-based systems offer a promising alternative for clinical orthodontic analysis and digital workflow integration. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Diagnostics (2075-4418) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=194119316
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/diagnostics16101464
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 1464
    Subjects:
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Orthodontics
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Annotations
        Type: general
      – SubjectFull: Statistical accuracy
        Type: general
      – SubjectFull: Statistical reliability
        Type: general
    Titles:
      – TitleFull: Clinical Equivalence of a CNN-Based Automated Soft Tissue Landmark Detection System on 2D Facial Images.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Türkün, Argun Ege
      – PersonEntity:
          Name:
            NameFull: Kalender, Müslim Ege
      – PersonEntity:
          Name:
            NameFull: Kurt, Murat
      – PersonEntity:
          Name:
            NameFull: Doğan, Servet
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20754418
          Numbering:
            – Type: volume
              Value: 16
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Diagnostics (2075-4418)
              Type: main
ResultId 1