NUMERO: #20220276

Título: Deep Learning for Oral Epithelial Dysplasia Grading

Nome do Apresentador: Anna Luiza Damaceno ARAUJO

Categoria do Trabalho: Trabalhos Aprovados para Disponibilização em Vídeo (ADV)

Área Temática: Patologia Oral

Resumo: Objective: The present study proposes a Deep Learning model based on the binary system for grading oral epithelial dysplasia (OED) at whole slide imaging level to eliminate inter-pathologist variability.
Study Design: A dataset of 99 whole slide images from three institutions were manually annotated, segmented and fragmented into smaller patches of 299x299 pixels. A total of 40,893 images were sampled into 80%:10%:10% for training, validation and independent test sets. An adaptation of ResNet50 with 2 hidden layers and 512 neurons in the fully connected layer (FC) was implemented with a low learning rate of 0.00001 for 200 epochs.
Preliminary Results: The proposed ResNet50 reached 85.30% accuracy during training and 85.11% for validation, showing the potential of learning. The independent test showed an overall accuracy of 60% with 61% sensitivity, 59% specificity, and AUROC was 0.64, showing a lack of generalization ability for the present classification problem.
Conclusion: The proposed DL-based model presented a capacity for learning with the potential of achieving high accuracy but with relatively low generalization ability. Further work will encompass a 2-class problem (premalignant and malignant) to reinforce class separation, and investigate the stability of accuracy and generalization of alternatives DL models.

Autor 1:  Anna Luiza Damaceno ARAUJO

E-mail 1:  [email protected]

Autor 2:   Viviane Mariano da SILVA

E-mail 2:  [email protected]

Autor 3 :  Márcio Ajudarte lOPES

E-mail 3:  [email protected]

Autor 4:  Pablo Agustin VARGAS

E-mail 4:  [email protected]

Autor 5:  Matheus Cardoso MORAES

E-mail 5:  [email protected]

Autor 6:  Alan Roger SANTOS-SILVA

E-mail 6:  [email protected]