Segmentation of Eye Fundus Images by Density Clustering in Diabetic Retinopathy

Pedro Furtado1, Carolina Travassos2, Raquel Monteiro2, Sara Pires Oliveira2, Carla Baptista3, Francisco Carrilho4

  • 1Universidade de Coimbra, NIF: 501 617 582
  • 2U. Coimbra
  • 3Serviço Endocrinologia, Diabetes e Metabolismo. Centro Hospitala
  • 41Serviço Endocrinologia, Diabetes e Metabolismo. Centro Hospital

Details

Category

Contributed Paper (Poster)

Theme

5. Imaging Informatics

Sessions

09:05 - 09:55 | Thu 16 Feb | Ballroom D | ThRAF

Rapid Fire Session 01: Imaging Informatics

Abstract

Early diagnosis is crucial in Diabetic Retinopathy (DR), to avoid further complications. The disease can be classified into one of two stages (an early stage of non-proliferative and a later stage of proliferative diabetic retinopathy), diagnosed based on existence and quantity of a characteristic set of lesions, such as micro-aneurysms, hemorrhages or exhudates, in Eye Fundus Images (EFI). It is therefore important to segment adequately regions of potential lesions, to highlight and classify the lesions and the degree of DR. Density clustering methods are promising candidates to isolate individual lesions, and should be used together with effective techniques for vascular tree removal, feature extraction and classification. In this work we report on our approach, results, tradeoffs and conclusions for segmenting and detecting individual lesions.

Additional Information

No information added

Video

No videos found