Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Deep Learning and Image Augmentation - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Deep Learning and Image Augmentation

(1, 2) , (1) , (1) , (3)
1
2
3

Abstract

Diabetic retinopathy is a significant complication of diabetes, produced by high blood sugar level, which causes damage to the retina. Effective diabetic retinopathy screening is required because diabetic retinopathy does not show any symptoms in the initial stages, and can cause blindness if it is not diagnosed and treated promptly. This paper presents a novel diabetic retinopathy automatic detection in retinal images by implementing efficient image processing and deep learning techniques. Besides diabetic retinopathy detection, the developed system integrates a novel detection of maculopathy into one detection system. Maculopathy is the damage to the macula, the eye part that is responsible for central vision. Therefore, the combined detection of diabetic retinopathy and maculopathy is essential for an effective screening of diabetic retinopathy. The paper investigates the capability of image pre-processing techniques based on data augmentation as well as deep learning for diabetic retinopathy and maculopathy detection. Computer-assisted clinical decision-making is inevitably transforming the diabetic retinopathy detection and management today, which is crucial for clinicians and patients alike. Therefore, a high degree of accuracy, with which computer algorithms can detect the diabetic retinopathy and maculopathy, is absolutely necessary.
Fichier principal
Vignette du fichier
485369_1_En_8_Chapter.pdf (752.48 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02520049 , version 1 (26-03-2020)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Sarni Suhaila Rahim, Vasile Palade, Ibrahim Almakky, Andreas Holzinger. Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Deep Learning and Image Augmentation. 3rd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2019, Canterbury, United Kingdom. pp.114-127, ⟨10.1007/978-3-030-29726-8_8⟩. ⟨hal-02520049⟩
63 View
32 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More