A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina

By Thomas Walter, Jean-Claude Klein, Pascale Massin, Ali Erginay. IEEE Transactions on Medical Imaging, 2002

934 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/f1451864009d278d3b930037e12ee28f22978975

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Retinal Imaging and Image Analysis (2010, neutral): “The two major forms are dry and wet AMD, of which dry AMD typically leads to gradual loss of visual acuity.”
A Computational-Intelligence-Based Approach for Detection of Exudates in Diabetic Retinopathy Images (2009, methodology): “It is assumed in [10] and [11] that the retinal images do not contain cotton wool spots as both methods have been implemented for the gray-level images.”
Detection of optic disc in retinal images by means of a geometrical model of vessel structure (2004, background): “Many techniques have been proposed to detect the OD, mainly based on its specific round shape and relatively high brightness, as compared to the rest of the fundus image (see, e.g., [2]–[7]).”
DREAM: Diabetic Retinopathy Analysis Using Machine Learning (2014, methodology): “Another ARVO 2008 version of the method in [30] tested on 400 images from this dataset achieved an AUC of 0.”
Retinal Vessel Centerline Extraction Using Multiscale Matched Filters, Confidence and Edge Measures (2006, background): “[7], image registration [8]–[14], change detection [15]–[21], pathology detection and quantification [22], tracking in video sequences [23]–[25], and computer-aided screening systems [26]– [29] depend on vessel extraction.”
DIARETDB 1 diabetic retinopathy database and evaluation protocol (2007, background): “Sensitivity and specificity can be computed as [22]: sensitivity (SN) = TP TP + FN , specificity (SP) = TN TN + FP (1)”
The DIARETDB1 Diabetic Retinopathy Database and Evaluation Protocol (2007, background): “Sensitivity and specificity are computed as [16] : sensitivity (SN) = T P T P + F N , specificity (SP) = T N T N + F P (1) where T P is the number of abnormal fundus images found as abnormal, T N is the number of normal fundus images found as normal, F P is the number of normal fundus images found…”
Automatic Diabetic Macular Edema Detection in Fundus Images Using Publicly Available Datasets (2011, methodology): “In the literature, there are exudate segmentation algorithms that are evaluated on an image based fashion in order to diagnose DME (Osareh et al., 2003; Walter et al., 2002; Li and Chutatape, 2004; Niemeijer et al., 2007; Sanchez et al., 2009; Garcia et al., 2009).”
Automated Diagnosis of Glaucoma Using Digital Fundus Images (2009, background): “The open operation would remove any small stray bright spots that are present in the image [21].”
Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research (2018, background): “Due to the large number of people that require a continuous follow-up and shortage of ophthalmologists, management of DR needs attention to develop computer-aided diagnosis tool [14,15].”
A Gaussian Scale Space Approach For Exudates Detection, Classification And Severity Prediction (2015, background): “[4] 96.0 89.0 0.95 Niemeijer et al. [3] 95.0 86.0 0.95 Sinthanayothin et al. [16] 88.5 99.6 NA Osareh et al. [5] 93 94.1 NA Walter et al. [17] 92.74 100 NA with other pathological features etc.”
A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images (2017, methodology): “Though [5] and [6] performs better in sensitivity than ours, our method performs better when the images do not contain exudates.”
IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge. (2020, methodology): “In initial effort s, Walter et al. (2002) devised a technique for OD and EXs segmentation, afterward removed OD to obtain EX candidates.”