Assessment of diabetic retinopathy using two‐field 60° fundus photography. A comparison between red‐free, black‐and‐white prints and colour transparencies

Wendt, Gunvor von; Heikkila, Kauko; Summanen, Paula

doi:10.1034/j.1600-0420.1999.770607.x

Cited by 15 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those early changes are more easily detected by red-free black-on-white photography than on color photographs (34). As the RTA operates with a green heliumneon laser and a black-on-white fundus camera, it meets those requirements.…”

Section: Photographymentioning

confidence: 83%

Tele-Screening for Diabetic Retinopathy With the Retinal Thickness Analyzer

et al. 2003

View full text Add to dashboard Cite

OBJECTIVE -To compare the effectiveness of tele-screening using a novel enhanced retinal thickness analyzer (RTA) with onsite routine ophthalmologic examination for diabetic retinopathy. RESEARCH DESIGN AND METHODS-A consecutive series of 31 eyes from diabetic patients were included. All underwent ophthalmologic examination, including stereoscopic dilated funduscopy and scanning with the RTA. The RTA reports consisted of a wide-angle, red-free fundus photograph and a macular-region retinal thickness map. Reports were graded by three independent graders in a masked manner. The diagnoses of proliferative retinopathy, macular edema, and treatment decisions made by the RTA graders and the clinical examiner were compared.RESULTS -On clinical examination 5 of 31 eyes were diagnosed with proliferative diabetic retinopathy (PDR). All five were referred for treatment by two graders and four eyes by one grader. All eyes with PDR and 12 of the 26 eyes with nonproliferative diabetic retinopathy showed severe macular edema. Seven of the 12 eyes with macular edema were clinically eligible for focal laser treatment, and all of them were detected by all RTA graders. Macular thickening was detected in eight eyes by RTA where no treatment was necessary, as judged by clinical examination. Thus, sensitivity was 93% (mean) for detecting PDR and 100% for detecting macular edema, with a specificity of 58 -96% depending on the grader. The RTA did not allow valid assessment due to poor image quality in only one case.CONCLUSIONS -Screening for diabetic retinopathy with a combination of wide-angle fundus photography and macular thickness mapping by an objective method, such as optical coherence tomography or the RTA, offers the prerequisites for establishing a successful telescreening program. Diabetes Care 26:2890 -2897, 2003D iabetic retinopathy is a leading cause of visual impairment and blindness in developed countries. Macular edema is the major cause of vision loss in diabetic patients, while proliferative retinopathy is another common cause (1). An annual clinical examination of dilated pupils by an ophthalmologist is the current gold standard of care for reducing diabetes-related ocular complications in patients with no or mild diabetic retinopathy (2). In the Early Treatment Diabetic Retinopathy Study (ETDRS), this led to a reduction of moderate visual loss by 50% (3).In many countries, an effective population-based screening cannot be offered by ophthalmologists and is performed by optometrists or general practitioners (4). One possible way to increase the number of ophthalmologically monitored diabetic patients is teleophthalmologic examination by a specialist (5-9). The gold standard of photographic documentation consists of seven stereoscopic fundus photographs, as defined by the ETDRS, requiring expensive equipment and a skilled photographer (10). Consequently, a number of alternative photographic methods have been evaluated for this purpose and are potentially able to identify patients requiring laser treatment (11).Recentl...

show abstract

Section: Photographymentioning

confidence: 83%

Tele-Screening for Diabetic Retinopathy With the Retinal Thickness Analyzer

et al. 2003

View full text Add to dashboard Cite

show abstract

“…Although ophthalmoscopy provides an effective means of analysing the retina, there is evidence that fundus photographs are more reliable than ophthalmoscopy, for instance, in the diagnosis of diabetic retinal lesions (Harding et al, 1995;von Wendt et al, 1999). Moreover, retinal fundus photography provides the possibility of analysing the produced images in batch mode.…”

Section: Introductionmentioning

confidence: 99%

Trainable COSFIRE filters for vessel delineation with application to retinal images

Azzopardi

Strisciuglio

Vento

et al. 2015

Medical Image Analysis

642

400

View full text Add to dashboard Cite

a b s t r a c tRetinal imaging provides a non-invasive opportunity for the diagnosis of several medical pathologies. The automatic segmentation of the vessel tree is an important pre-processing step which facilitates subsequent automatic processes that contribute to such diagnosis.We introduce a novel method for the automatic segmentation of vessel trees in retinal fundus images. We propose a filter that selectively responds to vessels and that we call B-COSFIRE with B standing for bar which is an abstraction for a vessel. It is based on the existing COSFIRE (Combination Of Shifted Filter Responses) approach. A B-COSFIRE filter achieves orientation selectivity by computing the weighted geometric mean of the output of a pool of Difference-of-Gaussians filters, whose supports are aligned in a collinear manner. It achieves rotation invariance efficiently by simple shifting operations. The proposed filter is versatile as its selectivity is determined from any given vessel-like prototype pattern in an automatic configuration process. We configure two B-COSFIRE filters, namely symmetric and asymmetric, that are selective for bars and bar-endings, respectively. We achieve vessel segmentation by summing up the responses of the two rotation-invariant B-COSFIRE filters followed by thresholding.The results that we achieve on three publicly available data sets (DRIVE: Se = 0.7655, Sp = 0.9704; STARE: Se = 0.7716, Sp = 0.9701; CHASE_DB1: Se = 0.7585, Sp = 0.9587) are higher than many of the state-of-the-art methods. The proposed segmentation approach is also very efficient with a time complexity that is significantly lower than existing methods.

show abstract

“…Nonmydriatic fundus cameras allow the acquisition of high-quality digital images with no need for medically induced mydriasis. It has been shown that fundus photographs are more reliable than ophthalmoscopy in the diagnosis of diabetic retinal lesions (21)(22)(23)(24). Therefore, the use of these cameras might be considered for screening, diagnosis, and grading of DR (25)(26)(27).…”

mentioning

confidence: 99%

Digital Retinal Images and Teleophthalmology for Detecting and Grading Diabetic Retinopathy

et al. 2002

View full text Add to dashboard Cite

6OBJECTIVE -Detecting and grading of diabetic retinopathy (DR) by means of digital retinal images sent via the Internet.RESEARCH DESIGN AND METHODS -Four nonstereoscopic digital retinal images (45°field each) of 126 eye fundus images from 70 diabetic patients were obtained with a nonmydriatic camera at two peripheral units. The images were sent via the Internet using a web-based system to a reference center, where they were diagnosed and graded by one ophthalmologist. These results were compared with those obtained by two other ophthalmologists, one at each peripheral unit, after direct examination of the patients. A modified severity scale of Airlie House was used for grading DR in all cases. Agreement between observers was assessed using unweighted for categorical data and the intraclass correlation coefficient (ICC) for continuous data. RESULTS -Presence of DR was detected in 69 eyes (55%). All eyes with DR (69 of 69, 100%)were correctly identified ( ϭ 1) by inspecting the digital images. In 118 eyes (118 of 126, 94%), 57 with no DR and 61 with DR, there was an agreement between the gradation made after the direct examination and the gradation made after the inspection of the images (ICC ϭ 0.92). In eight eyes with DR (8 of 126, 6%), there was disagreement in the grading made with both techniques.CONCLUSIONS -Inspection of digital retinal images sent via the Internet allowed diagnosis and grading of DR. The presence or absence of DR was correctly assessed by inspection of the images in all instances. We also found agreement, in most cases, between retinopathy gradation made from the images and the gradation made by direct examination of the eyes. These findings suggest that this technique is suitable for screening procedures.

show abstract

Assessment of diabetic retinopathy using two‐field 60° fundus photography. A comparison between red‐free, black‐and‐white prints and colour transparencies

Cited by 15 publications

References 25 publications

Tele-Screening for Diabetic Retinopathy With the Retinal Thickness Analyzer

Tele-Screening for Diabetic Retinopathy With the Retinal Thickness Analyzer

Trainable COSFIRE filters for vessel delineation with application to retinal images

Digital Retinal Images and Teleophthalmology for Detecting and Grading Diabetic Retinopathy

Contact Info

Product

Resources

About