Academic Journal
Προβολή σε EDS

Vision-Language Model as a 'Zero-Shot' Assistant for Evaluating Condylar Osseous Changes in Cone-beam Computed Tomography.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Vision-Language Model as a 'Zero-Shot' Assistant for Evaluating Condylar Osseous Changes in Cone-beam Computed Tomography.
Συγγραφείς: Chen K; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: dentistfrankchen@outlook.com., Zhang A; Department of Biophysics, Johns Hopkins University, Baltimore, Maryland, USA., Xie X; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: dentistxxj@mail.ccmu.edu.cn., Bai Y; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: byuxing@ccmu.edu.cn.
Πηγή: International dental journal [Int Dent J] 2026 Oct; Vol. 76 (5), pp. 109817. Date of Electronic Publication: 2026 Aug 13.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Elsevier Country of Publication: England NLM ID: 0374714 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1875-595X (Electronic) Linking ISSN: 00206539 NLM ISO Abbreviation: Int Dent J Subsets: MEDLINE
Imprint Name(s): Publication: 2021- : London : Elsevier
Original Publication: London : FDI World Dental
Ιατρικοί όροι (MeSH): Cone-Beam Computed Tomography*/methods , Mandibular Condyle*/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted*/methods , Artificial Intelligence*, Humans ; Large Language Models ; Sensitivity and Specificity ; Generative Artificial Intelligence
Περίληψη: Introduction and Aims: Interpreting condylar osseous changes on CBCT is challenging for general practitioners. This study evaluated the 'zero-shot' diagnostic performance and utility of Vision-Language Models (VLMs) as AI assistants for detecting condylar abnormalities.
Methods: We analysed 72 CBCT images from the EHPN study for internal validation and constructed a balanced sample of 70 images from the MMDental dataset for external validation, with dual-radiologist consensus as the ground truth. Three frontier VLMs (Gemini-3, GPT-5.2, and Qwen3-VL) were used to evaluate representative sagittal slices without prior fine-tuning. Performance was measured by diagnostic accuracy, sensitivity, specificity, and balanced accuracy, while the Quality Assessment of Medical AI-generated Information (QAMAI) framework assessed the quality of AI-generated structured reports. This study was reported following STARD-AI and CLAIM guidelines as primary checklists, with TRIPOD-LLM as a supplementary framework.
Results: Gemini-3 achieved the highest diagnostic accuracy (90.3%; 95% CI: 81.0%-95.5%), outperforming GPT-5.2 (75.0%) and Qwen3-VL (55.6%). External validation on a constructed balanced sample from the MMDental dataset confirmed these findings, with Gemini-3 achieving 90.00% accuracy. Regarding report generation, Gemini-3 surpassed the other models across five QAMAI dimensions, providing more accurate, clear, and clinically useful justifications aligned with diagnostic standards.
Conclusion: VLMs, particularly Gemini-3, exhibit zero-shot capabilities in identifying condylar changes and generating high-quality diagnostic reports. While these models maintain a conservative diagnostic tendency, they demonstrate potential as preliminary, training-free screening aids in oral maxillofacial radiology. Further multicentre validation is warranted to establish clinical utility.
Clinical Relevance: Cloud-based VLMs could offer accessible screening assistance by allowing general practitioners to query condylar findings via simple web interfaces without specialized hardware. These tools may contribute to structured reporting workflows, though their diagnostic consistency in routine practice remains to be established, and they should complement rather than replace expert clinical judgment.
(Copyright © 2026 The Authors. Published by Elsevier Inc. All rights reserved.)
Competing Interests: Conflict of interest None disclosed. No author has received consulting fees, honoraria, or other payments from AI model providers (Google, OpenAI, Alibaba) or related entities.
Contributed Indexing: Keywords: Artificial Intelligence; Cone-beam computed tomography; LLM; Temporomandibular Joint; Vision-language model
Entry Date(s): Date Created: 20260813 Date Completed: 20260916 Latest Revision: 20260916
Update Code: 20260916
PubMed Central ID: PMC13499149
DOI: 10.1016/j.identj.2026.109817
PMID: 42594712
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://www.doi.org/10.1016/j.identj.2026.109817?
    Name: ScienceDirect (all content) (s7799221)
    Category: fullText
    Text: View record from ScienceDirect
    MouseOverText: View record from ScienceDirect
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=1875595X&ISBN=&volume=76&issue=5&date=20261001&spage=109817&pages=109817&title=International dental journal&atitle=Vision-Language%20Model%20as%20a%20%27Zero-Shot%27%20Assistant%20for%20Evaluating%20Condylar%20Osseous%20Changes%20in%20Cone-beam%20Computed%20Tomography.&aulast=Chen%20K&id=DOI:10.1016/j.identj.2026.109817
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42594712
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Vision-Language Model as a 'Zero-Shot' Assistant for Evaluating Condylar Osseous Changes in Cone-beam Computed Tomography.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Chen+K%22">Chen K</searchLink>; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: dentistfrankchen@outlook.com.<br /><searchLink fieldCode="AU" term="%22Zhang+A%22">Zhang A</searchLink>; Department of Biophysics, Johns Hopkins University, Baltimore, Maryland, USA.<br /><searchLink fieldCode="AU" term="%22Xie+X%22">Xie X</searchLink>; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: dentistxxj@mail.ccmu.edu.cn.<br /><searchLink fieldCode="AU" term="%22Bai+Y%22">Bai Y</searchLink>; Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, Beijing, China. Electronic address: byuxing@ccmu.edu.cn.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%220374714%22">International dental journal</searchLink> [Int Dent J] 2026 Oct; Vol. 76 (5), pp. 109817. <i>Date of Electronic Publication: </i>2026 Aug 13.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Elsevier%22">Elsevier </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>0374714 <i>Publication Model: </i>Print-Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1875-595X (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2200206539%22">00206539 </searchLink><i>NLM ISO Abbreviation: </i>Int Dent J <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: 2021- : London : Elsevier<br /><i>Original Publication</i>: London : FDI World Dental
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Cone-Beam+Computed+Tomography%22">Cone-Beam Computed Tomography*</searchLink>/<searchLink fieldCode="MM" term="%22Cone-Beam+Computed+Tomography+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Mandibular+Condyle%22">Mandibular Condyle*</searchLink>/<searchLink fieldCode="MM" term="%22Mandibular+Condyle+diagnostic+imaging%22">diagnostic imaging</searchLink> <br /><searchLink fieldCode="MM" term="%22Radiographic+Image+Interpretation%2C+Computer-Assisted%22">Radiographic Image Interpretation, Computer-Assisted*</searchLink>/<searchLink fieldCode="MM" term="%22Radiographic+Image+Interpretation%2C+Computer-Assisted+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Artificial+Intelligence%22">Artificial Intelligence*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Large+Language+Models%22">Large Language Models</searchLink> ; <searchLink fieldCode="MH" term="%22Sensitivity+and+Specificity%22">Sensitivity and Specificity</searchLink> ; <searchLink fieldCode="MH" term="%22Generative+Artificial+Intelligence%22">Generative Artificial Intelligence</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Introduction and Aims: Interpreting condylar osseous changes on CBCT is challenging for general practitioners. This study evaluated the 'zero-shot' diagnostic performance and utility of Vision-Language Models (VLMs) as AI assistants for detecting condylar abnormalities.<br />Methods: We analysed 72 CBCT images from the EHPN study for internal validation and constructed a balanced sample of 70 images from the MMDental dataset for external validation, with dual-radiologist consensus as the ground truth. Three frontier VLMs (Gemini-3, GPT-5.2, and Qwen3-VL) were used to evaluate representative sagittal slices without prior fine-tuning. Performance was measured by diagnostic accuracy, sensitivity, specificity, and balanced accuracy, while the Quality Assessment of Medical AI-generated Information (QAMAI) framework assessed the quality of AI-generated structured reports. This study was reported following STARD-AI and CLAIM guidelines as primary checklists, with TRIPOD-LLM as a supplementary framework.<br />Results: Gemini-3 achieved the highest diagnostic accuracy (90.3%; 95% CI: 81.0%-95.5%), outperforming GPT-5.2 (75.0%) and Qwen3-VL (55.6%). External validation on a constructed balanced sample from the MMDental dataset confirmed these findings, with Gemini-3 achieving 90.00% accuracy. Regarding report generation, Gemini-3 surpassed the other models across five QAMAI dimensions, providing more accurate, clear, and clinically useful justifications aligned with diagnostic standards.<br />Conclusion: VLMs, particularly Gemini-3, exhibit zero-shot capabilities in identifying condylar changes and generating high-quality diagnostic reports. While these models maintain a conservative diagnostic tendency, they demonstrate potential as preliminary, training-free screening aids in oral maxillofacial radiology. Further multicentre validation is warranted to establish clinical utility.<br />Clinical Relevance: Cloud-based VLMs could offer accessible screening assistance by allowing general practitioners to query condylar findings via simple web interfaces without specialized hardware. These tools may contribute to structured reporting workflows, though their diagnostic consistency in routine practice remains to be established, and they should complement rather than replace expert clinical judgment.<br /> (Copyright © 2026 The Authors. Published by Elsevier Inc. All rights reserved.)
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: Conflict of interest None disclosed. No author has received consulting fees, honoraria, or other payments from AI model providers (Google, OpenAI, Alibaba) or related entities.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>Artificial Intelligence; Cone-beam computed tomography; LLM; Temporomandibular Joint; Vision-language model
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260813 <i>Date Completed: </i>20260916 <i>Latest Revision: </i>20260916
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260916
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13499149
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1016/j.identj.2026.109817
– Name: AN
  Label: PMID
  Group: ID
  Data: 42594712
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42594712
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.identj.2026.109817
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 109817
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Large Language Models
        Type: general
      – SubjectFull: Sensitivity and Specificity
        Type: general
      – SubjectFull: Generative Artificial Intelligence
        Type: general
      – SubjectFull: Cone-Beam Computed Tomography methods
        Type: general
      – SubjectFull: Mandibular Condyle diagnostic imaging
        Type: general
      – SubjectFull: Radiographic Image Interpretation, Computer-Assisted methods
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
    Titles:
      – TitleFull: Vision-Language Model as a 'Zero-Shot' Assistant for Evaluating Condylar Osseous Changes in Cone-beam Computed Tomography.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen K
      – PersonEntity:
          Name:
            NameFull: Zhang A
      – PersonEntity:
          Name:
            NameFull: Xie X
      – PersonEntity:
          Name:
            NameFull: Bai Y
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: 2026 Oct
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1875-595X
          Numbering:
            – Type: volume
              Value: 76
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: International dental journal
              Type: main
ResultId 1