NUMERO: #20230421

Título: DIAGNOSIS OF ORAL POTENTIALLY MALIGNANT DISORDERS: A STUDY BASED ON ARTIFICIAL INTELLIGENCE

Nome do Apresentador: Maria Clara Falcão RIBEIRO DE ASSIS

Categoria do Trabalho: Painel de pesquisa científica (PPC)

Área Temática: Patologia Oral

Resumo: OBJECTIVE: Creation of a database based on artificial intelligence (AI) for the purpose of diagnosing malignant and potentially malignant disorders.
STUDY DESIGN: This is a retrospective and descriptive study conducted in a reference center for oral diagnosis in Espírito Santo. Clinical, sociodemographic, pathological and histopathological images of cases of oral leukoplakia and squamous cell carcinoma (OSCC) diagnosed in this institution in the period 2010-2021 were used. All data were stored in a self-system and used for the training of a computer-aided diagnostic system (CADS).
RESULTS: A total of 69 patients were included, generating 237 images, 146 of leukoplakia and 91 of OSCC. The validation of the results attested to the feasibility of CADS in distinguishing between leukoplakia and OSCC, and presence or absence of dysplasia in the samples through tests of precision, balanced accuracy and area under the ROC curve.
CONCLUSION: The creation of the database allowed the development of CADS. Thus, the use of AI in head and neck pathologies can be translated in the near feature, into more effective strategies to assist in the diagnosis of patients affected by these lesions in addition to assisting in the secondary prevention of OSCC.
Thanks for financial support to the research: UFES and CNPq.

Autor 1:  Maria Clara Falcão RIBEIRO DE ASSIS

E-mail 1:  [email protected]

Autor 2:   Júlia Pessini SOARES

E-mail 2:  [email protected]

Autor 3 :  Leandro Muniz DE LIMA

E-mail 3:  [email protected]

Autor 4:  Liliana Aparecida Pimenta DE BARROS

E-mail 4:  [email protected]

Autor 5:  Tânia Regina GRÃO-VELLOSO

E-mail 5:  [email protected]

Autor 6:  Renato A. KROHLING

E-mail 6:  [email protected]

Autor 7:  Danielle Resende CAMISASCA

E-mail 7:  [email protected]