Automatic Diabetic Macular Edema Detection in Fundus Images Using Publicly Available Datasets

By Luca Giancardo, Fabrice Mériaudeau, T. Karnowski, Yaqin Li, Seema Garg, Kenneth W. Tobin, Edward Chaum. Medical Image Anal., 2011

351 citations recorded by the source corpus.

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. 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 is robust to segmentation uncertainties, does not need ground truth at lesion level, and is computationally efficient, as it generates a diagnosis on an average of 9.3 seconds per image on an 2.6 GHz platform with an unoptimised Matlab implementation.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/bf180af64f74eb5bd2e813cbcdbdf5cfc108afe1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Applications of Deep Learning in Fundus Images: A Review (2021, methodology): “The HEI-MED dataset12 (Giancardo et al., 2012) consists of 169 images, of”
Machine Learning and Data Mining Methods in Diabetes Research (2017, background): “Finally, Giancardo et al. proposed a methodology for Diabetic macular edema prediction, which is a common vision-threatening complication of DR [107].”
Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research (2018, methodology): “The risk of macular edema can be determined by the presence of exudates [26], severity grading of DME is done based on occurrences of hard exudates near to macula center as per the definitions provided by Messidor database [27].”
Drishti-GS: Retinal image dataset for optic nerve head(ONH) segmentation (2014, background): “It involves a progressive degeneration of the optic nerve fibers.”
A Gaussian Scale Space Approach For Exudates Detection, Classification And Severity Prediction (2015, methodology): “Also the proposed by Giancardo et al.[2], achieved AUC value of 0.87.”
IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge. (2020, background): “As DME is graded based on the location of EXs from the macula, many researchers ( Giancardo et al., 2012; Medhi and Dandapat, 2014; Perdomo et al., 2016; Marin et al., 2018 ) proposed EXs based features to determine the severity of DME.”
FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE (2014, methodology): “Concerning retinal lesions, like microaneurysms and exudates, several databases are available such as DIARETDB0, DIARETDB1 (Kauppi et al. (2007)), HEI-MED (Giancardo et al. (2012)), ROC (Niemeijer et al. (2010)) and e-ophtha (Decencière et al. (2013)).”