EUVIMEDEUVIMED entdecken
Systematische Übersicht

Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review

Daniela Giraldo-Roldán iD, Anna Luíza Damaceno Araújo iD, Matheus Cardoso Moraes iD, Viviane Mariano da Silva iD, Erin Crespo Cordeiro Ribeiro iD, Matheus Cerqueira iD, Cristina Saldivia-Siracusa iD, Sebastião Silvério Sousa-Neto iD, Maria Eduarda Pérez-de-Oliveira iD, Marcio Ajudarte Lopes iD, Luiz Paulo Kowalski iD, André Carlos Ponce de Leon Ferreira de Carvalho iD und 2 weitere

Journal of Oral Pathology & Medicine · 2024-08 · 53 (7) · 415-433

DOI: 10.1111/jop.13548 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Journal of Oral Pathology & Medicine, online erschienen am 28.05.2024. Verfasst von Daniela Giraldo-Roldán und 13 weiteren Autor:innen. Beteiligte Einrichtung: Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, Brazil. Hauptthemen laut MEDLINE: Artificial Intelligence, Radiomics. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Fundação de Amparo à Pesquisa do Estado de São Paulo, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Conselho Nacional de Desenvolvimento Científico e Tecnológico.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The purpose of this systematic review (SR) is to gather evidence on the use of machine learning (ML) models in the diagnosis of intraosseous lesions in gnathic bones and to analyze the reliability, impact, and usefulness of such models. This SR was performed in accordance with the PRISMA 2022 guidelines and was registered in the PROSPERO database (CRD42022379298).

Methods

The acronym PICOS was used to structure the inquiry‐focused review question “Is Artificial Intelligence reliable for the diagnosis of intraosseous lesions in gnathic bones?” The literature search was conducted in various electronic databases, including PubMed, Embase, Scopus, Cochrane Library, Web of Science, Lilacs, IEEE Xplore, and Gray Literature (Google Scholar and ProQuest). Risk of bias assessment was performed using PROBAST, and the results were synthesized by considering the task and sampling strategy of the dataset.

Results

Twenty‐six studies were included (21 146 radiographic images). Ameloblastomas, odontogenic keratocysts, dentigerous cysts, and periapical cysts were the most frequently investigated lesions. According to TRIPOD, most studies were classified as type 2 (randomly divided). The F1 score was presented in only 13 studies, which provided the metrics for 20 trials, with a mean of 0.71 (±0.25).

Conclusion

There is no conclusive evidence to support the usefulness of ML‐based models in the detection, segmentation, and classification of intraosseous lesions in gnathic bones for routine clinical application. The lack of detail about data sampling, the lack of a comprehensive set of metrics for training and validation, and the absence of external testing limit experiments and hinder proper evaluation of model performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceRadiomicsHumansAmeloblastomaDentigerous CystJaw DiseasesMachine LearningOdontogenic CystsReproducibility of Results

Stichwörter der Autor:innen

computer tomographyconvolutional neural networkmachine learningpanoramic radiography

Autor:innen und Institutionen

  • Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, Brazil.
  • Head and Neck Surgery Department, University of São Paulo Medical School (FMUSP), São Paulo, Brazil.
  • Department of Science and Technology, Institute of Science and Technology, Federal University of São Paulo (ICT-Unifesp), São José dos Campos, Brazil.
  • Department of Computer Science, Institute of Mathematics and Computer Science (ICMC - USP), University of São Paulo, São Carlos, Brazil.
  • Department of Head and Neck Surgery and Otorhinolaryngology, A.C. Camargo Cancer Center, São Paulo, Brazil.

ORCID-Profile: Daniela Giraldo-Roldán, Anna Luíza Damaceno Araújo, Matheus Cardoso Moraes, Viviane Mariano da Silva, Erin Crespo Cordeiro Ribeiro, Matheus Cerqueira, Cristina Saldivia-Siracusa, Sebastião Silvério Sousa-Neto, Maria Eduarda Pérez-de-Oliveira, Marcio Ajudarte Lopes, Luiz Paulo Kowalski, André Carlos Ponce de Leon Ferreira de Carvalho, Alan Roger Santos-Silva, Pablo Agustin Vargas

Förderung

  • Fundação de Amparo à Pesquisa do Estado de São Paulo
  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico

Zitieren

APA

Giraldo-Roldán, D., Araújo, A. L. D., Moraes, M. C., da Silva, V. M., Ribeiro, E. C. C., Cerqueira, M., Saldivia-Siracusa, C., Sousa-Neto, S. S., Pérez-de-Oliveira, M. E., Lopes, M. A., Kowalski, L. P., de Carvalho, A. C. P. L. F., Santos-Silva, A. R., & Vargas, P. A. (2024). Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review. Journal of Oral Pathology & Medicine, 53(7), 415-433. https://doi.org/10.1111/jop.13548

Vancouver

Giraldo-Roldán D, Araújo ALD, Moraes MC, da Silva VM, Ribeiro ECC, Cerqueira M, et al. Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review. Journal of Oral Pathology & Medicine. 2024;53(7):415-433. doi:10.1111/jop.13548

BibTeX
@article{GiraldoRoldn2024,
  author = {Giraldo-Roldán, Daniela and Araújo, Anna Luíza Damaceno and Moraes, Matheus Cardoso and da Silva, Viviane Mariano and Ribeiro, Erin Crespo Cordeiro and Cerqueira, Matheus and Saldivia-Siracusa, Cristina and Sousa-Neto, Sebastião Silvério and Pérez-de-Oliveira, Maria Eduarda and Lopes, Marcio Ajudarte and Kowalski, Luiz Paulo and de Carvalho, André Carlos Ponce de Leon Ferreira and Santos-Silva, Alan Roger and Vargas, Pablo Agustin},
  title = {Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review},
  journal = {Journal of Oral Pathology & Medicine},
  year = {2024},
  volume = {53},
  number = {7},
  pages = {415--433},
  doi = {10.1111/jop.13548}
}
Kostenlos starten →