Accuracy of artificial intelligence-based detection of dental crowding and spacing on cone-beam computed tomography.
9 affiliations
- 1Kazimierczak Clinic, Dworcowa 13/u6a, Bydgoszcz, 85-009, Poland.
- 2Faculty of Medicine, Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, Bydgoszcz, 85-067, Poland.
- 3Department of Diagnostic Imaging, Poznan University of Medical Sciences, Poznań, 61- 701, Poland.
- 4Private Practice Dental Clinic Jankowscy, Czerwonego Krzyża 24, Żary, 68-200, Poland.
- 5Faculty of Medicine, Bydgoszcz University of Science and Technology, Kaliskiego 7, Bydgoszcz, 85-796, Poland.
- 6Department of Radiology and Diagnostic Imaging, Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, Bydgoszcz, 85-067, Poland.
- 7Kazimierczak Clinic, Dworcowa 13/u6a, Bydgoszcz, 85-009, Poland. [email protected].
- 8Faculty of Medicine, Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, Bydgoszcz, 85-067, Poland. [email protected].
- 9Department of Radiology and Diagnostic Imaging, Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, Bydgoszcz, 85-067, Poland. [email protected].
Abstract
Background
To evaluate the accuracy of an artificial intelligence (AI) system for detecting anterior dental crowding and spacing on cone-beam computed tomography (CBCT) and to characterise clinically relevant patterns of diagnostic failure.Methods
In this retrospective diagnostic accuracy study, CBCT scans from 88 patients were analysed. AI-generated diagnoses at the tooth-pair level were compared with a reference standard based on a modified Little's Irregularity Index (mLII) that incorporates signed contact-point displacement. Diagnostic performance - sensitivity, specificity, positive and negative predictive values, and Cohen's κ - was assessed at the tooth-pair level (n = 875) across five thresholds (± 0.5 to ± 2.5 mm). Arch-level performance was assessed using the conventional Little's Irregularity Index (LII). Statistical significance was set at α = 0.05, and all estimates are reported with 95% confidence intervals.Results
At the tooth-pair level, sensitivity for crowding ranged from 28.8% to 42.0%, whereas specificity remained high (81.9-88.9%). Agreement with the reference standard was fair (maximum κ = 0.247). A consistent blind spot was identified at the maxillary central-incisor pair (11-21), where no crowded cases were detected despite confirmed irregularities. Spacing detection was poor (sensitivity 10-25%). At the arch level, detection improved with increasing severity of irregularity (38.8-75.0%) but remained incomplete and was accompanied by a high false-positive rate (41.2% in perfectly aligned arches).Conclusions
The AI system showed limited sensitivity and only fair agreement for detecting anterior crowding and spacing on CBCT. Clinically relevant irregularities, including those at the anterior midline, may be missed. Because crowding and spacing are most reliably assessed from clinical examination and intraoral records rather than from CBCT, AI-based CBCT assessments should be interpreted with caution and cannot replace clinician evaluation.
Related
- Reference Standards in Artificial Intelligence Detection of Apical Periodontitis: A Narrative Review of What Reported Accuracy Measures
- Harnessing Artificial Intelligence to Predict Dental Crowding in Modern Orthodontic Practice: A Comprehensive Review
- Performance Assessment of an Artificial Intelligence System Used for Case Detection in a Large Community-based Diabetic Retinopathy Screening Program: A Retrospective Diagnostic Accuracy Validation Study.
- Perceptions of artificial intelligence for radiographic image accuracy: a cross-sectional survey of radiology personnel
- Artificial Intelligence‐Assisted Automated Optical Coherence Tomography Analysis for Percutaneous Coronary Intervention Planning: From Plaque Analysis to Precision Lesion Preparation and Stent Optimization
BibTeX
@article{kazimierczak2026accuracy,
title = {{Accuracy of artificial intelligence-based detection of dental crowding and spacing on cone-beam computed tomography.}},
author = {Natalia Kazimierczak and Łukasz Wanczura and Tomasz Kulczyk and Tomasz Jankowski and Agnieszka Jankowska and Emilia Zielińska and Emilia Czarnecka and Małgorzata Dittrich and Wiktoria Biegała and Zbigniew Serafin and Wojciech Kazimierczak},
journal = {BMC oral health},
year = {2026},
month = jul,
doi = {10.1186/s12903-026-09405-0},
url = {https://europepmc.org/article/MED/42902327},
note = {CC BY},
}
RIS
TY - JOUR
TI - Accuracy of artificial intelligence-based detection of dental crowding and spacing on cone-beam computed tomography.
AU - Natalia Kazimierczak
AU - Łukasz Wanczura
AU - Tomasz Kulczyk
AU - Tomasz Jankowski
AU - Agnieszka Jankowska
AU - Emilia Zielińska
AU - Emilia Czarnecka
AU - Małgorzata Dittrich
AU - Wiktoria Biegała
AU - Zbigniew Serafin
AU - Wojciech Kazimierczak
PY - 2026
DA - 2026/07/01
JO - BMC oral health
DO - 10.1186/s12903-026-09405-0
UR - https://europepmc.org/article/MED/42902327
AB - Background To evaluate the accuracy of an artificial intelligence (AI) system for detecting anterior dental crowding and spacing on cone-beam computed tomography (CBCT) and to characterise clinically relevant patterns of diagnostic failure.Methods In this retrospective diagnostic accuracy study, CBCT scans from 88 patients were analysed. AI-generated diagnoses at the tooth-pair level were compared with a reference standard based on a modified Little's Irregularity Index (mLII) that incorporates signed contact-point displacement. Diagnostic performance - sensitivity, specificity, positive and negative predictive values, and Cohen's κ - was assessed at the tooth-pair level (n = 875) across five thresholds (± 0.5 to ± 2.5 mm). Arch-level performance was assessed using the conventional Little's Irregularity Index (LII). Statistical significance was set at α = 0.05, and all estimates are reported with 95% confidence intervals.Results At the tooth-pair level, sensitivity for crowding ranged from 28.8% to 42.0%, whereas specificity remained high (81.9-88.9%). Agreement with the reference standard was fair (maximum κ = 0.247). A consistent blind spot was identified at the maxillary central-incisor pair (11-21), where no crowded cases were detected despite confirmed irregularities. Spacing detection was poor (sensitivity 10-25%). At the arch level, detection improved with increasing severity of irregularity (38.8-75.0%) but remained incomplete and was accompanied by a high false-positive rate (41.2% in perfectly aligned arches).Conclusions The AI system showed limited sensitivity and only fair agreement for detecting anterior crowding and spacing on CBCT. Clinically relevant irregularities, including those at the anterior midline, may be missed. Because crowding and spacing are most reliably assessed from clinical examination and intraoral records rather than from CBCT, AI-based CBCT assessments should be interpreted with caution and cannot replace clinician evaluation.
SN - 1472-6831
ER -