Automatic detection of pathological retinal images using color and shape features

Autores/as

  • Flávio Henrique Duarte de Araújo Universidade Federal do Piauí
  • Rodrigo de Melo Souza Veras Departamento de Computação, Universidade Federal do Piauí, Teresina.
  • Romuere Rodrigues Veloso e Silva Universidade Federal do Piauí, Campus Senador Helvídio Nunes de Barros, Picos. Engenharia de Teleinformática, Universidade Federal do Ceará, Fortaleza
  • André Macedo Santana Departamento de Computação, Universidade Federal do Piauí, Teresina.
  • Fátima Nelsizeuma Sombra de Medeiros Engenharia de Teleinformática, Universidade Federal do Ceará, Fortaleza

Palabras clave:

Machine Learning, Diagnostic Imaging, Exudates and Transudates

Resumen

Objective: We propose an algorithm for exudate detection and pathological retinal images identification. Method: We improved an existing algorithm that detects exudates in a retinal image replacing the k-means clustering by fuzzy k-means and applied an additional step to detect optical disc (OD). Furthermore, our approach added a classification process to eliminate remaining false exudate regions. Finally, we classify the retinal image as pathological or non-pathological by measuring the ratio of candidate exudate regions before classification and the number of regions removed by the classification step. Results: Tests were performed on DIARETDB1 database, and the results obtained were; Fmeasure – 90%, area under the ROC curve – 88% and the Kappa coefficient – 77% (very good). Conclusion: The success of the algorithm is due mostly to the OD detection approach and the classification step. The obtained results confirmed that the proposed algorithm outperformed the others.

Publicado

2017-11-27

Cómo citar

Duarte de Araújo, F. H., Souza Veras, R. de M., Veloso e Silva, R. R., Santana, A. M., & Sombra de Medeiros, F. N. (2017). Automatic detection of pathological retinal images using color and shape features. Journal of Health Informatics, 9(4). Recuperado a partir de https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/519

Número

Sección

Artículo Original

Artículos similares

<< < 4 5 6 7 8 9 10 11 12 13 > >> 

También puede {advancedSearchLink} para este artículo.

Artículos más leídos del mismo autor/a