METHODS: Firstly, color fundus images from the publicly available database DRIVE were converted from RGB to grayscale. To enhance the contrast of the dark objects (blood vessels) against the background, the dot product of the grayscale image with itself was generated. To rectify the variation in contrast, we used a 5 × 5 window filter on each pixel. Based on 5 regional features, 1 intensity feature and 2 Hessian features per scale using 9 scales, we extracted a total of 24 features. A linear minimum squared error (LMSE) classifier was trained to classify each pixel into a vessel or non-vessel pixel.
RESULTS: The DRIVE dataset provided 20 training and 20 test color fundus images. The proposed algorithm achieves a sensitivity of 72.05% with 94.79% accuracy.
CONCLUSIONS: Our proposed algorithm achieved higher accuracy (0.9206) at the peripapillary region, where the ocular manifestations in the microvasculature due to glaucoma, central retinal vein occlusion, etc. are most obvious. This supports the proposed algorithm as a strong candidate for automated vessel segmentation.
METHODS: This retrospective analysis was of handheld SD OCT images obtained under a prospective research protocol in children who had established XLRS diagnosis based on genetic testing or clinical history. Three OCT graders performed standardized qualitative and quantitative assessment of retinal volume scans, which were divided into foveal, parafoveal, and extrafoveal regions. Visual acuity data were obtained when possible.
RESULTS: Spectral domain OCT images were available of both eyes in 8 pediatric patients with ages 7 months to 10 years. The schisis cavities involved inner nuclear layer in over 90% (15/16) of eyes in all 3 regions. Retinal nerve fiber and ganglion cell layer involvement was present only in the extrafoveal region in 63% (10/16) eyes and outer nuclear and plexiform layer in few others. In 7 children followed over 2 months to 15 months, the location of schisis remained consistent. Central foveal thickness decreased from the baseline to final available visit in 4/6 eyes. Ellipsoid zone disruption seemed to accompany lower visual acuity in 1/4 eyes.
CONCLUSION: Early in life, the SD OCT findings in XLRS demonstrate differences in schisis location in fovea-parafoveal versus extrafoveal region, possible association between poor visual acuity and degree of ellipsoid zone disruption and decrease in central foveal thickness over time in this group. Furthermore, they illustrates that the pattern of XLRS in adults is already present in very young children, and unlike in older children and adults, those presenting with earlier disease may have a more aggressive course. Further studies in this early age group may provide more insights into treatment and prevention of progressive visual impairment in children with XLRS.
METHODS: The morphological features of the disc that is characteristic of glaucoma are clearly seen in the fundus images. However, manual inspection of the acquired fundus images may be prone to inter-observer variation. Therefore, a computer-aided detection (CAD) system is proposed to make an accurate, reliable and fast diagnosis of glaucoma based on the optic nerve features of fundus imaging. In this paper, we reviewed existing techniques to automatically diagnose glaucoma.
RESULTS: The use of CAD is very effective in the diagnosis of glaucoma and can assist the clinicians to alleviate their workload significantly. We have also discussed the advantages of employing state-of-art techniques, including deep learning (DL), when developing the automated system. The DL methods are effective in glaucoma diagnosis.
CONCLUSIONS: Novel DL algorithms with big data availability are required to develop a reliable CAD system. Such techniques can be employed to diagnose other eye diseases accurately.