“…The vessels inside this region were segmented with the method presented by Bankhead et al 28 The width of the vessels was also estimated as in Bankhead et al 28 Vessel classification was performed by using the algorithm by Ivanov et al 29 For the necessary optic disk detection and segmentation of the optic disk border, the method of Dietter et al was used. 30 Figure 1 Example of an analyzed fundus photo. …”
Purpose
To compare changes in central retinal arterial equivalent (CRAE), central retinal vein equivalent (CRVE), arteriovenous ratio (AVR), tortuosity and fractal dimension in primary open-angle glaucoma (POAG), normal-tension glaucoma (NTG) and in a control group (CG) on fundus photographs. Further, to provide further evidence of vascular change in glaucoma patients using a novel method of tortuosity.
Patients and Methods
The primary endpoint was the change in CRAE, CRVE, AVR, fractal dimension and tortuosity of the retinal vasculature from baseline, retrospectively analyzed from 2011 to 2017 at the University Eye Hospital Tuebingen. Fundus photos of POAG (N = 49), NTG (N = 38) and CG (N = 18) were computer evaluated and analyzed in the quantities mentioned above.
Results
CRAE in NTG and POAG and CRVE in NTG significantly decreased (P = 0.02, P = 0.01; P = 0.03) whereas CRVE in POAG increased insignificantly (P = 0.72). In NTG, AVR decreased significantly (P = 0.05), but to a lesser extent than in POAG (P < 0.001). In CG, CRAE decreased insignificantly (P = 0.10), CRVE decreased significantly (P = 0.03) and AVR increased insignificantly (P = 0.77). In POAG tortuosity calculated using standard methods as well as our novel method, increased significantly (P = 0.015–0.04), whereas it did not occur in NTG (P = 0.18–0.57) and CG (P = 0.11–0.21). Fractal dimensions in POAG decreased significantly (P = 0.001–0.002), whereas in NTG and CG changes were insignificant (P = 0.33–0.92).
Conclusion
Based on a retrospective analysis of fundus photographs, specific retinal vasculature features of the retinal vasculature display significant alterations associated with NTG and POAG. The assessment of tortuosity using our novel method was consistent with previously established methods for analyzing tortuosity.
“…The vessels inside this region were segmented with the method presented by Bankhead et al 28 The width of the vessels was also estimated as in Bankhead et al 28 Vessel classification was performed by using the algorithm by Ivanov et al 29 For the necessary optic disk detection and segmentation of the optic disk border, the method of Dietter et al was used. 30 Figure 1 Example of an analyzed fundus photo. …”
Purpose
To compare changes in central retinal arterial equivalent (CRAE), central retinal vein equivalent (CRVE), arteriovenous ratio (AVR), tortuosity and fractal dimension in primary open-angle glaucoma (POAG), normal-tension glaucoma (NTG) and in a control group (CG) on fundus photographs. Further, to provide further evidence of vascular change in glaucoma patients using a novel method of tortuosity.
Patients and Methods
The primary endpoint was the change in CRAE, CRVE, AVR, fractal dimension and tortuosity of the retinal vasculature from baseline, retrospectively analyzed from 2011 to 2017 at the University Eye Hospital Tuebingen. Fundus photos of POAG (N = 49), NTG (N = 38) and CG (N = 18) were computer evaluated and analyzed in the quantities mentioned above.
Results
CRAE in NTG and POAG and CRVE in NTG significantly decreased (P = 0.02, P = 0.01; P = 0.03) whereas CRVE in POAG increased insignificantly (P = 0.72). In NTG, AVR decreased significantly (P = 0.05), but to a lesser extent than in POAG (P < 0.001). In CG, CRAE decreased insignificantly (P = 0.10), CRVE decreased significantly (P = 0.03) and AVR increased insignificantly (P = 0.77). In POAG tortuosity calculated using standard methods as well as our novel method, increased significantly (P = 0.015–0.04), whereas it did not occur in NTG (P = 0.18–0.57) and CG (P = 0.11–0.21). Fractal dimensions in POAG decreased significantly (P = 0.001–0.002), whereas in NTG and CG changes were insignificant (P = 0.33–0.92).
Conclusion
Based on a retrospective analysis of fundus photographs, specific retinal vasculature features of the retinal vasculature display significant alterations associated with NTG and POAG. The assessment of tortuosity using our novel method was consistent with previously established methods for analyzing tortuosity.
“…In DRIVE, DiaretDB0 and DiaretDB1, this method had an average ACC of 100%, 96.92% and 98.88% respectively. Diettera et al [21] proposed an OD detection based on strong technical artifacts with a two-stage method. The OD was initially detected using vessel orientation and brightness to segment the region of the OD.…”
In recent days, detecting Optic Disc (OD) in retinal images has been challenging and very important to the early diagnosis of eye diseases. The process of detecting the OD is challenging due to the diversity of color, intensity, brightness and shape of the OD. Moreover, the color similarities of the neighboring organs of the OD create difficulties during OD detection. In the proposed Fuzzy K-Means Threshold (FKMT) and Morphological Operation with Pixel Density Feature (MOPDF), the input retinal images are coarsely segmented by fuzzy K-means clustering and thresholding, in which the OD is classified from its neighboring organs with intensity similarities. Then, the segmented images are given as the input to morphological operation with pixel density feature calculations, which reduce the false detection in the small pixel of the OD. Finally, the OD area is detected by applying the Sobel edge detection method, which accurately detects the OD from the retinal images. After detection optimization, the proposed method achieved Sensitivity (SEN), Specificity (SPEC) and Accuracy (ACC), with 96.74%, 96.78% and 96.92% in DiaretDB0 (Standard Diabetic Retinopathy Database Calibration level 0), 97.12%, 97.10% and 97.75% in Dia-retDB1 (Standard Diabetic Retinopathy Database Calibration level 1) and 97.19%, 97.47% and 97.43% in STARE (Structured Analysis of the Retina) dataset respectively. The experimental results demonstrated the proposed method's efficiency for segmenting and detecting OD areas.
“…The OD region has a higher contrast against the retinal background, making it easy to spot. Past techniques utilized thresholding [31], [32], contrast-based [33], [34], vessel inpainting [35], Hough transform [36]- [38] and morphological algorithm [39] methods to segment or localize OD. DL methods have also been studied for automatic OD segmentation.…”
Section: B Optic Disc Localization and Segmentationmentioning
Smartphone-based mobile fundus photography is gaining popularity due to the rise of handheld fundus lenses, allowing a portable solution for a mobile-based computer-assisted diagnostic system (CADS). With such a system, professionals can monitor and diagnose numerous retinal diseases, including diabetic retinopathy (DR), glaucoma, age-related macular degeneration, etc. on their smartphone devices. In this study, we proposed a unified CADS tool for smartphone devices that can detect and identify six crucial retinal features utilizing both a filtering approach and a deep learning (DL) approach. These features are retinal blood vessels (RBV), optic discs (OD), hemorrhages (HM), microaneurysm (MA), hard exudates (HE), and soft exudates (SE). Traditional filtering is applied for RBV segmentation using B-COSFIRE and Frangi filter, whereas vessel inpainting and automatic canny edge-based Hough transform are used to localize OD center and radius. The DR lesions (HM, MA, HE, OD segmentation, and SE) are detected using a transfer learning-based Resnet50 backbone and multiclass DL U-net architecture. RBV segmentation achieved 94.94% and 94.44% accuracy in the DRIVE and STARE datasets. OD localization achieved an accuracy of 99.60% in the MESSIDOR dataset. Lastly, the IDRiD dataset is used to train and validate the DR lesions with an overall accuracy of 99.7%, F1-score of 77.4, and mean IoU of 59.2. The smartphone application can perform all the segmentation tasks at once in an average of 30 seconds. Given the availability, it is possible to improve the accuracy of the DL method further by training with more mobile fundus datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
