A Novel Multimodal Deep Image Analysis Model for Predicting Extraction/Non-Extraction Decision.

Journal: Orthodontics & craniofacial research
Published Date: Nov 6, 2025

Abstract

OBJECTIVE: This study aimed to develop a deep learning model classifier capable of predicting the extraction/non-extraction binary decision using lateral cephalometric radiographs (LCRs) and intraoral scans (IOS) to serve as an additional decision-support tool for orthodontists. MATERIALS AND METHODS: The dataset was composed of LCRs and IOS from 617 patients (mean age: 18.2, 63.5% female) treated at the Indiana University School of Dentistry. Subjects were categorised into two groups: extraction (192) and non-extraction (425). Two sets of features were extracted from IOS: traditional arch measurements and novel tooth spatial features. For LCRs, features were derived using CephNet-based landmark detection (Land), a convolutional autoencoder (AE), and the dimensionality was reduced using Principal Component Analysis (PCA). Models were evaluated using accuracy, sensitivity, specificity, positive predictive value (PPV or precision), negative predictive value (NPV), positive likelihood ratio (LR+), negative likelihood ratio (LR-), and F1 score. RESULTS: IOS + Land model achieved the highest overall accuracy (77%) and F1 score (0.62), with strong specificity (83%) and PPV (62%). In contrast, the Land model yielded the highest sensitivity (82%), but at the cost of lower specificity (57%). McNemar's test revealed that the AE model was significantly less accurate than IOS + AE (p = 0.048), IOS + Land (p = 0.006), and IOS + AE + Land (p = 0.005). CONCLUSION: Deep learning models can predict the extraction/non-extraction decision using IOS and LCRs with high accuracy and diagnostic performance. Multimodal approaches, particularly those integrating IOS with cephalometric landmarks, demonstrate superior accuracy, sensitivity, and specificity compared to single-modality models.

Authors

  • Sunna Imtiaz Ahmad
    School of Dentistry, Indiana University, Indianapolis, Indiana, USA.
  • Jakub Olczyk
    School of Dentistry, Indiana University, Indianapolis, Indiana, USA.
  • Adriel S Araujo
    Visual Lab, Institute of Computing, Fluminense Federal University, Av. Gal. Milton Tavares de Souza, S/N, Niterói 24210-346, RJ, Brazil.
  • João Pedro de Moura Medeiros
    School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre, Brazil.
  • Vinicius C Teixeira
    School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre, Brazil.
  • Carlos F A Gomes
    School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre, Brazil.
  • Maurício Cecílio Magnaguagno
    School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre, Brazil.
  • Quinn Roederer
    School of Dentistry, Indiana University, Indianapolis, Indiana, USA.
  • Vinicius Dutra
    Department of Oral Pathology, Medicine, and Radiology, Indiana University School of Dentistry, Indianapolis, Indiana, USA.
  • R Scott Conley
    School of Dentistry, Indiana University, Indianapolis, Indiana, USA.
  • Dalvan Griebler
    School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre, Brazil.
  • George Eckert
    Department of Biostatistics and Health Data Science, Indianapolis, Indiana University School of Medicine, IN, US.
  • Márcio Sarroglia Pinho
    School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre, Brazil.
  • Hakan Turkkahraman
    Department of Orthodontics and Oral Facial Genetics, Indiana University School of Dentistry, 1121 West Michigan Street, 46202, Indianapolis, IN, USA. [email protected].

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals