Vitor Simbalista Teixeira Soares, Anna Luíza Damaceno Araújo, Ivan José Correia-Neto, Cristina Saldivia-Siracusa, Raísa Sales de Sá, Hugo Abritta Reis, Ayrton da Costa Ganem Filho, André Carlos Ponce de Leon Ferreira de Carvalho, Thierry Urruty, Paulo Rogério Ferreti Bonan, Nathalia Rodrigues Gomes, Felipe Paiva Fonseca, Pablo Agustin Vargas, Alan Roger Santos-Silva, Luiz Paulo Kowalski, Matheus Cardoso Moraes, Marcio Ajudarte Lopes
EffiSegNet-B0 demonstrated high accuracy and adaptability in segmenting lip lesions, reinforcing its potential for clinical image analysis applications. The proposed model generalizes well across different institutions and lesion phenotypes, consistently extracting the complete region of interest. This proof-of-concept study supports its promise as a tool for automated lip lesion segmentation in heterogeneous clinical settings.
BACKGROUND: Actinic cheilitis (AC) is a potentially malignant oral disorder linked to lip squamous cell carcinoma (LSCC). Clinical diagnosis is hindered by lesion heterogeneity. While AI tools have shown promise in oral lesion detection and diagnosis, image segmentation remains underexplored. This study developed and externally validated a deep learning segmentation model for digital photographs of lip lesions.
METHODS: A total of 489 clinical photographs from one institution were used for training/internal testing, and 82 external images from two independent institutions (UFPB and UFMG) served as external validation. EffiSegNet‑B0 used Image Net‑pretrained EfficientNet‑B0 encoder, with stage features aggregated via Ghost Modules. Manual segmentation masks comprised the clinically affected lip region and were used as ground truth. Performance was assessed using accuracy, sensitivity (recall), precision, Dice Similarity Coefficient (DSC) and intersection over union (IoU).
RESULTS: The model achieved high accuracy (> 95%) on both internal and external datasets. DSCs were 0.888 (95% CI: 0.871-0.904) for internal test and 0.875 (95% CI: 0.862-0.888) for external validation, while IoU values were 0.802 (95% CI: 0.777-0.828) and 0.782 (95% CI: 0.763-0.801), respectively. No performance decline was observed on external validation data. The model remained robust to lesion variations (ulceration, crusting, and keratinization).
CONCLUSION: EffiSegNet-B0 demonstrated high accuracy and adaptability in segmenting lip lesions, reinforcing its potential for clinical image analysis applications. The proposed model generalizes well across different institutions and lesion phenotypes, consistently extracting the complete region of interest. This proof-of-concept study supports its promise as a tool for automated lip lesion segmentation in heterogeneous clinical settings.