Accuracy Assessment of Intra- and Intervisit Fundus Image Registration for Diabetic Retinopathy Screening

Adal, Kedir M.; Etten, Peter G van; Martínez, Joaquín; Vliet, Lucas J. van; Vermeer, Koenraad A.

doi:10.1167/iovs.14-15949

Cited by 35 publications

(31 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The local graders, including the RS, graded the majority of the photos as R0, however, those were graded as R1 by the CERA grader. In fact, tracking small retinal features, such as micro-aneurysms, requires more experience and skill, high recordkeeping accuracy, and competence in grading [20]. Therefore, misclassification in the R1 category by the local graders was anticipated and their accuracy can be expected to increase in reliability as their years of experience increases.…”

Section: Discussionmentioning

confidence: 99%

Accuracy and reliability of retinal photo grading for diabetic retinopathy: Remote graders from a developing country and standard retinal photo grader in Australia

Islam

2017

PLoS ONE

View full text Add to dashboard Cite

BackgroundTo evaluate the accuracy and reliability of fundus retinal photos graded by local graders in Bangladesh with those graded by an expert at the Centre for Eye Research Australia (CERA) in the context of mass scale diabetic retinopathy (DR) screening in Bangladesh.MethodsA population-based cross-sectional study of 3,104 adults identified 213 (7.2%) eligible patients with diabetes of age ≥ 40 years in 2012–2013. Retinal photographs were collected using a non-mydriatic digital fundus retinal camera and a two-field imaging protocol. The photos were graded by two remote graders (G1 and G2) who were trained by a retinal specialist (RS) in Bangladesh, by the RS himself, and by a Centre for Eye Research Australia (CERA) grader. The local graders up skilled their grading ability by comparing 30% of the photos graded by the CERA grader with their own grades. Learning from that exercise was applied to the remaining 70% of photos, which were re-graded. Reliability and accuracy of grading amongst the graders were reported using cross tabulation, inter- and intra-grader reliability, and with sensitivity and specificity.ResultsOf 122 eyes from 61 patients, the mild (R1) DR was estimated to be 14 to 25%, pre-proliferative (R2) DR 4–8%, and proliferative (R3) DR 0.8 to 1.6%, whereas 25%, 8%, 18%, and 15% were found to be ungradable by CERA, RS, G1, and G2, respectively. Of 8 (6.6%) eyes identified as R2 by the CERA grader, 5 (63%), 3 (38%) and 3 (38%) were correctly classified as R2, whereas the rest were classified either as R1 or R3 but none were classified as no DR (R0) or ungradable by the RS, G1 and G2, respectively. After getting experience reviewing the 30% test set graded by the CERA grader, the local graders graded moderate and severe DR with 100% accuracy. After excluding ungradable photos, the sensitivity (specificity) relative to the CERA grader was 82% (88%) before and 80% (93%) after training for G1 and 56% (87%) before and 77% (90%) after training for G2. In case of maculopathy, the CERA grader reported 11.2% eyes with maculopathy, which included 100% of the 4.9% by RS, 6.6% by G1, and 7.4% by G2.ConclusionsLocal graders in Bangladesh are able to grade retinal photos with high accuracy if the DR is at least of a moderate level. With appropriate training and experience, local graders have the ability to contribute significantly to the grading of millions of retinal photos, which required grading in resource- poor countries.

show abstract

Section: Discussionmentioning

confidence: 99%

Accuracy and reliability of retinal photo grading for diabetic retinopathy: Remote graders from a developing country and standard retinal photo grader in Australia

Islam

2017

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The publicly available retina data sets are mainly prepared for automatic pathology detection (e.g., [48]- [55]), segmentation of anatomical structures such as optic disc, macula, CRBVs (e.g., [56]- [59]), assessing quality of retinal image (e.g., [60], [61]), retinal image registration (e.g., [62], [63]) and so on. Most of these data sets have images from only one side and one session.…”

Section: B Data Setsmentioning

confidence: 99%

A Study of Bilateral Symmetry in Color Fundus Photographs

et al. 2021

View full text Add to dashboard Cite

We have previously shown that there is a high degree of bilateral similarity in the central retinal blood vessels (CRBVs), which are responsible for supplying blood to retinas and can be used as a strong biometric. We have also shown that a side-independent retina verification system can be developed based on the bilateral similarity in CRBVs. In this paper, we perform a similar investigation for color fundus photographs since color fundus photographs are much richer representations of retinas than CRBVs. We investigate whether the color fundus photographs of the left and right retinas possess strong enough bilateral symmetry so that we reliably tell whether a pair of the left and right retinas belong to a single subject. We evaluate and analyse the performance of both human-and deep neural network-based bilateral verification by experimenting on color fundus photographs of two publicly available data sets.

show abstract

“…In longitudinal study application, retinal images captured from different time are utilized in the registration. The longitudinal study application is important to monitor the progression of eye diseases such as glaucoma and age-related macular degeneration that usually undergoes a long degeneration process [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

“…This will restrict their practical utilization for super-resolution, image mosaicking, and longitudinal study applications. These applications are crucial in diagnosis and monitoring retinal diseases, such as diabetic retinopathy, glaucoma, and age-related macular degeneration [ 4 ]. Therefore, feature points should be detected on the low-quality region that consists of high and low contrast vessels of varying sizes to ensure a uniform distribution of feature points on the retinal image.…”

Section: Introductionmentioning

confidence: 99%

Feature-Based Retinal Image Registration Using D-Saddle Feature

Ramli

Idris

Hasikin‬

et al. 2017

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Retinal image registration is important to assist diagnosis and monitor retinal diseases, such as diabetic retinopathy and glaucoma. However, registering retinal images for various registration applications requires the detection and distribution of feature points on the low-quality region that consists of vessels of varying contrast and sizes. A recent feature detector known as Saddle detects feature points on vessels that are poorly distributed and densely positioned on strong contrast vessels. Therefore, we propose a multiresolution difference of Gaussian pyramid with Saddle detector (D-Saddle) to detect feature points on the low-quality region that consists of vessels with varying contrast and sizes. D-Saddle is tested on Fundus Image Registration (FIRE) Dataset that consists of 134 retinal image pairs. Experimental results show that D-Saddle successfully registered 43% of retinal image pairs with average registration accuracy of 2.329 pixels while a lower success rate is observed in other four state-of-the-art retinal image registration methods GDB-ICP (28%), Harris-PIIFD (4%), H-M (16%), and Saddle (16%). Furthermore, the registration accuracy of D-Saddle has the weakest correlation (Spearman) with the intensity uniformity metric among all methods. Finally, the paired t-test shows that D-Saddle significantly improved the overall registration accuracy of the original Saddle.

show abstract

Accuracy Assessment of Intra- and Intervisit Fundus Image Registration for Diabetic Retinopathy Screening

Cited by 35 publications

References 25 publications

Accuracy and reliability of retinal photo grading for diabetic retinopathy: Remote graders from a developing country and standard retinal photo grader in Australia

Accuracy and reliability of retinal photo grading for diabetic retinopathy: Remote graders from a developing country and standard retinal photo grader in Australia

A Study of Bilateral Symmetry in Color Fundus Photographs

Feature-Based Retinal Image Registration Using D-Saddle Feature

Contact Info

Product

Resources

About