Exudate-based diabetic macular edema detection in fundus images using publicly available datasets

[Display omitted] ► Presentation of a new dataset (HEI-MED) for retinal diabetic macular edema (DME). ► New method for the automatic detection of DME with fundus images. ► New image based feature vector approach with colour, wavelets and exudate probability. ► Good computational performance. Automat...

Full description

Saved in:
Bibliographic Details
Published in:Medical image analysis 2012-01, Vol.16 (1), p.216-226
Main Authors: Giancardo, Luca, Meriaudeau, Fabrice, Karnowski, Thomas P., Li, Yaqin, Garg, Seema, Tobin, Kenneth W., Chaum, Edward
Format: Article
Language:English
Subjects:
Algorithms
Automatic diagnosis
Computer Science
Databases, Factual
Diabetic Retinopathy - pathology
Exudates and Transudates - cytology
Exudates segmentation
Feature extraction
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image Processing
Lesion probability
Macular Edema - pathology
Pattern Recognition, Automated - methods
Reproducibility of Results
Retinoscopy - methods
Sensitivity and Specificity
Wavelets
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] ► Presentation of a new dataset (HEI-MED) for retinal diabetic macular edema (DME). ► New method for the automatic detection of DME with fundus images. ► New image based feature vector approach with colour, wavelets and exudate probability. ► Good computational performance. Automatic analysis is completed in ∼4.4s (∼9.3s with the automatic ON localization). ► Automatic diagnosis is comparable to manual diagnosis of two retina experts. Diabetic macular edema (DME) is a common vision threatening complication of diabetic retinopathy. In a large scale screening environment DME can be assessed by detecting exudates (a type of bright lesions) in fundus images. In this work, we introduce a new methodology for diagnosis of DME using a novel set of features based on colour, wavelet decomposition and automatic lesion segmentation. These features are employed to train a classifier able to automatically diagnose DME through the presence of exudation. We present a new publicly available dataset with ground-truth data containing 169 patients from various ethnic groups and levels of DME. This and other two publicly available datasets are employed to evaluate our algorithm. We are able to achieve diagnosis performance comparable to retina experts on the MESSIDOR (an independently labelled dataset with 1200 images) with cross-dataset testing (e.g., the classifier was trained on an independent dataset and tested on MESSIDOR). Our algorithm obtained an AUC between 0.88 and 0.94 depending on the dataset/features used. Additionally, it does not need ground truth at lesion level to reject false positives and is computationally efficient, as it generates a diagnosis on an average of 4.4s (9.3s, considering the optic nerve localisation) per image on an 2.6GHz platform with an unoptimised Matlab implementation.
ISSN:1361-8415
1361-8423
DOI:10.1016/j.media.2011.07.004