A Novel Multimodal Deep Image Analysis Model for Predicting Extraction/Non‐Extraction Decision
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
- Hakan Türkkahraman
- Maurício Cecílio Magnaguagno (ORCID: https://orcid.org/0000-0002-7401-1859)
- George J. Eckert (ORCID: https://orcid.org/0000-0001-7798-7155)
- Adriel Silva de Araújo (ORCID: https://orcid.org/0000-0001-7537-1867)
- R. Scott Conley (ORCID: https://orcid.org/0000-0002-4888-4875)
- Vinícius Dutra
- Márcio Sarroglia Pinho (ORCID: https://orcid.org/0000-0002-8873-1005)
- José Edil Guimarães de Medeiros (ORCID: https://orcid.org/0000-0001-6529-0780)
- Dalvan Griebler (ORCID: https://orcid.org/0000-0002-4690-3964)
- Sunna Ahmad
- Carlos F. A. Gomes
- Quinn Roederer
- Vinicius C. Teixeira
- Jakub Olczyk
Institutions
- Pontifícia Universidade Católica do Rio Grande do Sul (BR)
- Indiana University – Purdue University Indianapolis (US)
Publication Details
- Journal
- Orthodontics and Craniofacial Research
- Published
- 2025-11-06
- DOI
- https://doi.org/10.1111/ocr.70057
- Primary Topic
- Dental Radiography and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul
- Instituto Nacional de Ciência e Tecnologia em Medicina Assistida por Computação Científica