Advanced search
Start date
Betweenand
Related content

ARTIFICIAL INTELLIGENCE FOR CLINICAL AND HISTOPATHOLOGICAL DIAGNOSIS OF INCIPIENT ORAL SQUAMOUS CELL CARCINOMA: A MULTICENTRIC INTERNATIONAL STUDY

Grant number: 22/13069-8
Support Opportunities:Scholarships in Brazil - Doctorate
Effective date (Start): October 01, 2023
Effective date (End): February 28, 2027
Field of knowledge:Health Sciences - Dentistry
Principal Investigator:Alan Roger dos Santos Silva
Grantee:Cristina Saldivia Siracusa
Host Institution: Faculdade de Odontologia de Piracicaba (FOP). Universidade Estadual de Campinas (UNICAMP). Piracicaba , SP, Brazil

Abstract

Early diagnosis of oral squamous cell carcinoma is a desired goal to reduce mortality rates due to this prevalent pathology. To achieve this purpose, identification of lesions in incipient stages (OSCCi), such as carcinoma in situ and microinvasive squamous cell carcinoma is essential since they are the two most initial presentations of OSSC, and their clinical and histopathological features can be subtle, sometimes even being mistaken as oral potentially malignant disorders opposed to conventional OSCC. Nevertheless, their evaluation is extremely challenging, with characteristics difficult to elucidate in suitable specimens even by well trained professionals. Also, factors like professional experience, subjectivity and inter and intra observator discrepancies can often make this diagnosis inaccurate. The ability of artificial models to learn and process dense information in a short time makes the use of artificial intelligence (AI) for diagnosis is very innovative and resourceful. Additionally, AI expands the understanding of this manifestation, and opens the possibility to obtain new clinical-pathological correlations that are not fully understood yet generating a range of interpretive possibilities in the context of the study of these lesions, guaranteeing greater objectivity and reproducibility, and guiding this research line to possibly discover diagnostic and prognostic factors in the treatment of incipient malignant lesions. This study aims to develop AI models through a Deep Learning (DL) approach by analyzing clinical images and digitalized histological slides to identify clinical and microscopic characteristics to diagnose in situ and microinvasive oral squamous cell carcinoma. As a secondary objective, we hope to identify prognostic imaging parameters that are not yet correlated in current clinical and histopathological practice. The research will be carried out at the Piracicaba School of Dentistry, State University of Campinas, (Piracicaba). The development and application of the algorithms, as well as the analysis of the sample will be developed with the support of engineers and programmers from the Federal University of São Paulo (ICT-UNIFESP). All glass slides of the selected cases for this sample will be scanned with the CS Aperio ScanScope® CS system and obtained from the FOP-UNICAMP archive as the proposing institution and from the Stomatology and Oral Pathology services of the collaborating institutions A.C. Camargo Cancer Center (ACCC), Universidade Federal de Rio de Janeiro (UFRJ), Universidade de São Paulo (USP), Universidad de Valparaíso (UV - Chile), Universidad Andrés Bello (UNAB - Chile), Universidad de Los Andes (ULA - Chile), Hospital El Carmen Luis Valentín Ferrada (HCLV - Chile), Universidad Central de Venezuela (UCV - Venezuela) e Universidad Nacional de Córdoba (UNC - Argentina).

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Please report errors in scientific publications list using this form.