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

Autor: Dos Santos GC; Institute of Science and Technology, Federal University of São Paulo (ICT-UNIFESP), São Paulo, Brazil., Araújo ALD; Head and Neck Surgery Department, University of São Paulo Medical School, São Paulo, Brazil., de Amorim HA; Institute of Science and Technology, Federal University of São Paulo (ICT-UNIFESP), São Paulo, Brazil., Giraldo-Roldán D; Departamento de Diagnóstico Oral, Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, São Paulo, Brazil., de Sousa-Neto SS; Departamento de Diagnóstico Oral, Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, São Paulo, Brazil., Vargas PA; Departamento de Diagnóstico Oral, Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, São Paulo, Brazil., Kowalski LP; Head and Neck Surgery Department, University of São Paulo Medical School, São Paulo, Brazil.; Department of Head and Neck Surgery and Otorhinolaryngology, A.C. Camargo Cancer Center, São Paulo, Brazil., Santos-Silva AR; Departamento de Diagnóstico Oral, Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, São Paulo, Brazil., Lopes MA; Departamento de Diagnóstico Oral, Faculdade de Odontologia de Piracicaba, Universidade Estadual de Campinas (FOP-UNICAMP), Piracicaba, São Paulo, Brazil., Moraes MC; Institute of Science and Technology, Federal University of São Paulo (ICT-UNIFESP), São Paulo, Brazil.
Jazyk: angličtina
Zdroj: Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology [J Oral Pathol Med] 2024 Aug; Vol. 53 (7), pp. 444-450. Date of Electronic Publication: 2024 Jun 04.
DOI: 10.1111/jop.13560
Abstrakt: 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).
(© 2024 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)
Databáze: MEDLINE
Externí odkaz: