EUVIMEDEUVIMED entdecken
Crossref

Feasibility study of ResNet ‐50 in the distinction of intraoral neural tumors using histopathological images

Giovanna Calabrese Dos Santos iD, Anna Luíza Damaceno Araújo iD, Henrique Alves de Amorim iD, Daniela Giraldo-Roldán iD, Sebastião Silvério de Sousa-Neto iD, Pablo Agustin Vargas iD, Luiz Paulo Kowalski iD, Alan Roger Santos-Silva iD, Marcio Ajudarte Lopes iD, Matheus Cardoso Moraes iD

Journal of Oral Pathology & Medicine · 2024

DOI: 10.1111/jop.13560 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Oral Pathology & Medicine, 2024. Verfasst von Giovanna Calabrese Dos Santos und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Science and Technology, Federal University of São Paulo (ICT-UNIFESP), São Paulo, Brazil. Hauptthemen laut MEDLINE: Neurofibroma, Feasibility Studies, Neurilemmoma, Nerve Sheath Neoplasms. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: The Federal Agency for Support and Evaluation of Graduate Education (CAPES), São Paulo Research Foundation, Brazilian National Council for Research and Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Neural tumors are difficult to distinguish based solely on cellularity and often require immunohistochemical staining to aid in identifying the cell lineage. This article investigates the potential of a Convolutional Neural Network for the histopathological classification of the three most prevalent benign neural tumor types: neurofibroma, perineurioma, and schwannoma.

Methods

A model was developed, trained, and evaluated for classification using the ResNet‐50 architecture, with a database of 30 whole‐slide images stained in hematoxylin and eosin (106, 782 patches were generated from and divided among the training, validation, and testing subsets, with strategies to avoid data leakage).

Results

The model achieved an accuracy of 70% (64% normalized), and showed satisfactory results for differentiating two of the three classes, reaching approximately 97% and 77% as true positives for neurofibroma and schwannoma classes, respectively, and only 7% for perineurioma class. The AUROC curves for neurofibroma and schwannoma classes was 0.83%, and 0.74% for perineurioma. However, the specificity rate for the perineurioma class was greater (83%) than in the other two classes (neurofibroma with 61%, and schwannoma with 60%).

Conclusion

This investigation demonstrated significant potential for proficient performance with a limitation regarding the perineurioma class (the limited feature variability observed contributed to a lower performance).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeurofibromaFeasibility StudiesNeurilemmomaNerve Sheath NeoplasmsNeural Networks, ComputerMouth NeoplasmsHumansDiagnosis, Differential

Stichwörter der Autor:innen

classificationdeep learningdiagnosishead and neckoral biopsy

Autor:innen und Institutionen

  • Institute of Science and Technology, Federal University of São Paulo (ICT-UNIFESP), São Paulo, Brazil.
  • Head and Neck Surgery Department, University of São Paulo Medical School, São Paulo, Brazil.
  • Departamento de Diagnóstico Oral, Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, São Paulo, Brazil.
  • Department of Head and Neck Surgery and Otorhinolaryngology, A.C. Camargo Cancer Center, São Paulo, Brazil.

ORCID-Profile: Giovanna Calabrese Dos Santos, Anna Luíza Damaceno Araújo, Henrique Alves de Amorim, Daniela Giraldo-Roldán, Sebastião Silvério de Sousa-Neto, Pablo Agustin Vargas, Luiz Paulo Kowalski, Alan Roger Santos-Silva, Marcio Ajudarte Lopes, Matheus Cardoso Moraes

Förderung

  • The Federal Agency for Support and Evaluation of Graduate Education (CAPES)
  • São Paulo Research Foundation
  • Brazilian National Council for Research and Development
  • Unicamp Development Foundation
  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
  • Fundação de Amparo à Pesquisa do Estado de São Paulo
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico

Zitieren

APA

Dos Santos, G. C., Araújo, A. L. D., de Amorim, H. A., Giraldo-Roldán, D., de Sousa-Neto, S. S., Vargas, P. A., Kowalski, L. P., Santos-Silva, A. R., Lopes, M. A., & Moraes, M. C. (2024). Feasibility study of ResNet ‐50 in the distinction of intraoral neural tumors using histopathological images. Journal of Oral Pathology & Medicine. https://doi.org/10.1111/jop.13560

Vancouver

Dos Santos GC, Araújo ALD, de Amorim HA, Giraldo-Roldán D, de Sousa-Neto SS, Vargas PA, et al. Feasibility study of ResNet ‐50 in the distinction of intraoral neural tumors using histopathological images. Journal of Oral Pathology & Medicine. 2024. doi:10.1111/jop.13560

BibTeX
@article{DosSantos2024,
  author = {Dos Santos, Giovanna Calabrese and Araújo, Anna Luíza Damaceno and de Amorim, Henrique Alves and Giraldo-Roldán, Daniela and de Sousa-Neto, Sebastião Silvério and Vargas, Pablo Agustin and Kowalski, Luiz Paulo and Santos-Silva, Alan Roger and Lopes, Marcio Ajudarte and Moraes, Matheus Cardoso},
  title = {Feasibility study of ResNet ‐50 in the distinction of intraoral neural tumors using histopathological images},
  journal = {Journal of Oral Pathology & Medicine},
  year = {2024},
  doi = {10.1111/jop.13560}
}
Kostenlos starten →