NUMERO: #20250152

Título: TOWARDS EARLY ORAL CANCER DETECTION: FAST, ACCURATE, AND REAL-TIME DIAGNOSIS WITH YOLO AND MOBILENET

Nome do Apresentador: Anna Luiza Damaceno ARAUJO

Categoria do Trabalho: Painel de pesquisa científica (PPC)

Área Temática: Estomatologia

Resumo: Objective: This study aims to develop detection and classification algorithms to support the early identification of oral squamous cell carcinoma (OSCC). Methods: A retrospective dataset of 773 clinical images-380 of oral potentially malignant disorders and 393 of OSCC.-was divided into training, validation, and testing subsets, preserving class proportions and preventing data leakage. Ten object detection models based on the YOLO11 architecture were trained with varying data augmentation strategies, using COCO-pretrained weights for 200 epochs (640×640 px). Additionally, three MobileNetv2 classification models were trained with different learning rates and augmentation, initialized with ImageNet weights and trained for 200 epochs (224×224 px). Results: The best detection model (YOLO11n) achieved a mAP50 of 0.813, with 0.860 precision and 0.789 recall. The top MobileNetv2classification model reached 0.846 accuracy, 0.871 precision, 0.846 recall, and 0.844 F1-score.
Conclusion: The proposed models demonstrated robust performance and potential to assist in early OSCC detection.

Autor 1:  Anna Luiza Damaceno ARAUJO

E-mail 1:  [email protected]

Autor 2:   Arnaldo Vitor Barros da SILVA

E-mail 2:  [email protected]

Autor 3 :  Ana Rita MAREGA GONÇALVES

E-mail 3:  [email protected]

Autor 4:  Cristina SALDIVIA-SIRACUSA

E-mail 4:  [email protected]

Autor 5:  Márcio Ajudarte LOPES

E-mail 5:  [email protected]

Autor 6:  Luiz Paulo KOWALSKI

E-mail 6:  [email protected]

Autor 7:  Alan Roger SANTOS-SILVA

E-mail 7:  [email protected]