A Coarse to Fine Corneal Ulcer Segmentation Approach Using U-net and DexiNed in Chain

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2021-05

Autores

Helano M.B.F. Portela (Autor) Outra; Rodrigo de M. S. Veras (Autor) Outra; Luis H.S. Vogado (Autor) Outra; Daniel Leite (Autor) Outra; Jefferson A. de Sousa (Autor) Outra; Anselmo C. de Paiva (Autor) Outra; João Manuel R. S. Tavares (Autor) FEUP

Ata de Conferência Internacional

Título: CIARP

Páginas: 13-23

Indexação

ISI Proceedings

Scopus - 0 Citações

Classificação Científica

CORDIS: Ciências Tecnológicas

FOS: Ciências médicas e da saúde

Outras Informações

ID Authenticus: P-00W-4WX

DOI: 10.1007/978-3-030-93420-0_2

Abstract (EN): A corneal ulcer is one of the most frequently appearing diseases that may affect eye health. The proper measurement of corneal ulcer lesions enables the physician to evaluate the treatment effectiveness and assist in decision-making. This article presents the solution for ulcer segmentation as a pixel-wise classification task, and proposes a novel coarse-to-fine method to extract corneal ulcers from ocular staining images. This study combines two classical convolutional neural networks (CNNs), known as U-net and DexiNed, following Morphological Geodesic Active Contour as a post-processing operation. We trained the CNNs using 358 point-flaky corneal ulcer images and evaluated its performance in 91 flaky corneal ulcer images. Our approach achieved 70.50% of Dice Coefficient on average, 87.4% of Recall, and 99.0% of Specificity, and True Dice Coefficient of 63.7%. These results corroborate our approach¿s efficacy and efficiency.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 10