Search

In this paper, we propose a novel classification model for automatically identifying individuals with age-related macular degeneration (AMD) or Diabetic Macular Edema (DME) using retinal features from Spectral Domain Optical Coherence Tomography (SD-OCT) images. Our classification method uses retinal features such as the thickness of the retina and the thickness of the individual retinal layers, and the volume of the pathologies such as drusen and hyper-reflective intra-retinal spots. We extract automatically, ten clinically important retinal features by segmenting individual SD-OCT images for classification purposes. The effectiveness of the extracted features is evaluated using several classification methods such as Random Forrest on 251 (59 normal, 177 AMD and 15 DME) subjects. We have performed 15-fold cross-validation tests for three phenotypes; DME, AMD and normal cases using these data sets and achieved accuracy of more than 95% on each data set with the classification method using Random Forrest. When we trained the system as a two-class problem of normal and eye with pathology, using the Random Forrest classifier, we obtained an accuracy of more than 96%. The area under the receiver operating characteristic curve (AUC) finds a value of 0.99 for each dataset. We have also shown the performance of four state-of-the-methods for classification the eye participants and found that our proposed method showed the best accuracy., Competing Interests: The authors have declared that no competing interests exist.

Age-related macular degeneration (AMD) is a leading cause of vision loss, characterized by drusen deposits and thickened Bruch's membrane (BM). This study details the capacity of nanosecond laser treatment to reduce drusen and thin BM while maintaining retinal structure. Fifty patients with AMD had a single nanosecond laser treatment session and after 2 yr, change in drusen area was compared with an untreated cohort of patients. The retinal effect of the laser was determined in human and mouse eyes using immunohistochemistry and compared with untreated eyes. In a mouse with thickened BM (ApoEnull), the effect of laser treatment was quantified using electron microscopy and quantitative PCR. In patients with AMD, nanosecond laser treatment reduced drusen load at 2 yr. Retinal structure was not compromised in human and mouse retina after laser treatment, with only a discrete retinal pigment epithelium (RPE) injury, and limited mononuclear cell response observed. BM was thinned in the ApoEnull mouse 3 mo after treatment (ApoEnull treated 683 ± 38 nm, ApoEnull untreated 890 ± 60 nm, C57Bl6J 606 ± 43 nm), with the expression of matrix metalloproteinase-2 and -3 increased (>260%). Nanosecond laser resolved drusen independent of retinal damage and improved BM structure, suggesting this treatment has the potential to reduce AMD progression., (© FASEB.)

Diseases of the retina are the leading causes of blindness in the industrialized world. The recognition that animals develop retinal diseases with similar traits to humans has led to not only a dramatic improvement in our understanding of the pathogenesis of retinal disease but also provided a means for testing possible treatment regimes and successful gene therapy trials. With the advent of genetic and molecular biological tools, the association between specific gene mutations and retinal signs has been made. Animals carrying natural mutations usually in one gene now provide well-established models for a host of inherited retinal diseases, including retinitis pigmentosa, Leber congenital amaurosis, inherited macular degeneration, and optic nerve diseases. In addition, the development of transgenic technologies has provided a means by which to study the effects of these and novel induced mutations on retinal structure and function. Despite these advances, there is a paucity of suitable animal models for complex diseases, including age-related macular degeneration (AMD) and diabetic retinopathy, largely because these diseases are not caused by single gene defects, but involve complex genetics and/or exacerbation through environmental factors, epigenetic, or other modes of genetic influence. In this review, we outline in detail the available animal models for inherited retinal diseases and how this information has furthered our understanding of retinal diseases. We also examine how transgenic technologies have helped to develop our understanding of the role of isolated genes or pathways in complex diseases like AMD, diabetes, and glaucoma., (Copyright © 2011 Elsevier Inc. All rights reserved.)

Purpose: To examine the baseline retina and optic disk characteristics in children., Design: Cross-sectional study., Methods: Subjects included 679 subjects with myopia and 100 with emmetropia, aged 8 to 13 years. Digital retina imaging and cycloplegic autorefraction were conducted to look for signs of retinal degeneration. Other outcome measures were vertical and horizontal cup-to-disk (CD) ratios, CD area ratio, parapapillary atrophy (PPA)-to-disk area ratio, and disk rotational angle., Results: The prevalence of lattice degeneration was 0.15% (95% confidence interval: 0.008-1.00). No other retinal abnormalities were detected. Increased PPA-to-disk area ratio was associated with increased axial length, increased myopia severity, and increasing age. Cup-to-disk ratios were smaller in subjects with myopia compared with those with emmetropia, but this did not correlate with severity of myopia. In subjects with severe myopia, the upper pole of the disk was rotated away from the fovea but to lesser extent than in those with emmetropia or milder myopia., Conclusions: Apart from PPA, degenerative features were not commonly found in this study.

A 35-year-old woman who reported persistent significant vision loss for 3 years after taking the antidepressant nefazodone was referred for electrophysiological assessment of vision. The vision changes included reduced acuities, reduced colour vision and visual field constriction in both eyes and were thought to be associated with the use of nefazodone for 6 - 8 weeks, 3 years earlier. Multifocal electroretinograms and visual evoked potentials were recorded using the Visual Evoked Response Imaging System (VERIS) to investigate the nature and site of the neural deficit. The summed retinal response showed a normal a- and b-wave latency and amplitude, however, the retinal topographic mfERGs showed a severe depression of the macular response in both eyes. The cortical topographic multifocal VEP mapping also showed a central depression in the right eye compared with the left. Two-frame motion and pattern custom mfVEP were also measured to assess different forms of cortical processing and especially of motion as nefazodone has previously been associated with image persistence with moving stimuli. The responses to two frame-motion showed signs of abnormality. Thus these results suggest that the primary locus of neural damage is retinal and is likely to have resulted from neurotoxicity. Other competing hypotheses such as hysterical blindness must be ruled out.