Early Detection Of Age-related Macular Degeneration Research Articles

ADAM Challenge: Detecting Age-Related Macular Degeneration From Fundus Images.

Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss caused by this disease is irreversible and permanent. Color fundus photography is the most cost-effective imaging modality to screen for retinal disorders. Cutting edge deep learning based algorithms have been recently developed for automatically detecting AMD from fundus images. However, there are still lack of a comprehensive annotated dataset and standard evaluation benchmarks. To deal with this issue, we set up the Automatic Detection challenge on Age-related Macular degeneration (ADAM), which was held as a satellite event of the ISBI 2020 conference. The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions. As part of the ADAM challenge, we have released a comprehensive dataset of 1200 fundus images with AMD diagnostic labels, pixel-wise segmentation masks for both optic disc and AMD-related lesions (drusen, exudates, hemorrhages and scars, among others), as well as the coordinates corresponding to the location of the macular fovea. A uniform evaluation framework has been built to make a fair comparison of different models using this dataset. During the ADAM challenge, 610 results were submitted for online evaluation, with 11 teams finally participating in the onsite challenge. This paper introduces the challenge, the dataset and the evaluation methods, as well as summarizes the participating methods and analyzes their results for each task. In particular, we observed that the ensembling strategy and the incorporation of clinical domain knowledge were the key to improve the performance of the deep learning models.

DeepSeeNet: A Deep Learning Model for Automated Classification of Patient-based Age-related Macular Degeneration Severity from Color Fundus Photographs

In assessing the severity of age-related macular degeneration (AMD), the Age-Related Eye Disease Study (AREDS) Simplified Severity Scale predicts the risk of progression to late AMD. However, its manual use requires the time-consuming participation of expert practitioners. Although several automated deep learning systems have been developed for classifying color fundus photographs (CFP) of individual eyes by AREDS severity score, none to date has used a patient-based scoring system that uses images from both eyes to assign a severity score. DeepSeeNet, a deep learning model, was developed to classify patients automatically by the AREDS Simplified Severity Scale (score 0-5) using bilateral CFP. DeepSeeNet was trained on 58 402 and tested on 900 images from the longitudinal follow-up of 4549 participants from AREDS. Gold standard labels were obtained using reading center grades. DeepSeeNet simulates the human grading process by first detecting individual AMD risk factors (drusen size, pigmentary abnormalities) for each eye and then calculating a patient-based AMD severity score using the AREDS Simplified Severity Scale. Overall accuracy, specificity, sensitivity, Cohen's kappa, and area under the curve (AUC). The performance of DeepSeeNet was compared with that of retinal specialists. DeepSeeNet performed better on patient-based classification (accuracy= 0.671; kappa= 0.558) than retinal specialists (accuracy= 0.599; kappa= 0.467) with high AUC in the detection of large drusen (0.94), pigmentary abnormalities (0.93), and late AMD (0.97). DeepSeeNetalso outperformed retinal specialists in the detection of large drusen (accuracy 0.742 vs. 0.696; kappa 0.601 vs. 0.517) and pigmentary abnormalities (accuracy 0.890 vs. 0.813; kappa 0.723 vs. 0.535) but showed lower performance in the detection of late AMD (accuracy 0.967 vs. 0.973; kappa 0.663 vs. 0.754). By simulating the human grading process, DeepSeeNet demonstrated high accuracy with increased transparency in the automated assignment of individual patients to AMD risk categories based on the AREDS Simplified Severity Scale. These results highlight the potential of deep learning to assist and enhance clinical decision-making in patients with AMD, such as early AMD detection and risk prediction for developing late AMD. DeepSeeNet is publicly available on https://github.com/ncbi-nlp/DeepSeeNet.

Identification of vinculin as a potential plasma marker for age-related macular degeneration.

To identify plasma protein biomarkers for age-related macular degeneration (AMD) using a large-scale quantitative proteomic discovery procedure. Plasma proteomes from 20 exudative AMD patients and 20 healthy control patients were comparatively profiled by four-dimensional liquid chromatography-tandem mass spectrometry (LC-MS/MS). Proteins existing at statistically different levels were validated by enzyme-linked immunosorbent assay (ELISA) and Western blotting in 233 case-controlled samples. Newly discovered plasma biomarkers were further confirmed using in vivo and in vitro experiments. Out of 320 proteins identified, vinculin, protein S100A9, triosephosphate isomerase, protein S100A8, protein Z-dependent protease inhibitor, C-X-C motif chemokine 7, and tenascin X showed significantly differential expression in AMD patient plasma compared to control plasma. Among these, the area under the curve (AUC) for vinculin was 0.871 for discriminating between exudative AMD and controls (n = 201) and 0.879 for discriminating between AMD and controls (n = 233). A proteogenomic combination model using vinculin and two known risk genotypes in ARMS2 and CFH genes additionally provided excellent discrimination of AMD from controls (AUC = 0.916). The plasma level of vinculin was not associated with any confounding clinical variables, such as age, smoking, and other comorbidities. Additionally, vinculin was strongly expressed in retinal pigment epithelial cells of human eyes, and its expression was elevated when exposed to oxidative stress in vitro. Vinculin was identified as a potential plasma biomarker for AMD. The early detection of AMD using novel plasma biomarkers with genetic modeling may enable timely treatment and vision preservation in the elderly.

Improving patient outcomes: role of the primary care optometrist in the early diagnosis and management of age-related macular degeneration

Not long ago, the management of age-related macular degeneration (AMD) was confined to rehabilitating whatever vision had not been damaged by the disease. The recent suc - cesses of the anti-vascular endothelial growth factor agents and the antioxidant clinical trials have revolutionized AMD treatment. For the first time, there is realistic hope that the progression of AMD can be slowed down or stopped and near normal vision can be preserved. Developments in new vision tests, imaging modalities, and genetic testing have greatly improved the chance of detecting the onset of AMD and choroidal neovascularization. However, because the current treatments still cannot revive degenerated retinal cells, the best patient outcome that can be achieved is early detection of the disease and application of the appropriate treatment before too much retinal damage has occurred. The opportunities and challenges offered by the new treat- ment options and disease detection methods have redefined the role of primary care optometrists in AMD management. This review of literature and practice guidelines demonstrates that, in addition to the traditional roles of refraction and visual rehabilitation, the unique position of optometrists as the first-line eye-care providers has allowed them to play an important role in the early detection of AMD, patient education, lifestyle-change counseling, disease monitor- ing and referral, and nutrition supplement counseling. The active participation of primary care optometrists in the shared care of AMD management is likely to result in great improvement in patient outcomes. Optometrists also need to improve their competence in these areas to meet the new challenges. Although primary care optometrists have always managed patients with AMD, their role in managing this sight-threatening disease has not been adequately documented. In light of the recent game-changing developments in AMD treatment, it is important to review what primary care optometrists are doing, what they can do, and what they should do to improve patient outcomes in the new era of AMD management.

Vergleich des Preferential-Hyperacuity-Perimeter (PHP)-Tests mit dem Amsler-Netz-Test bei der Diagnose verschiedener Stadien der altersbezogenen Makuladegeneration

Age-related macular degeneration (ARMD) is the leading cause of blindness in people over 65 years of age. A rapid loss of vision occurs especially in cases with choroidal neovascularisation. Early detection of ARMD and timely treatment are mandatory. We have prospectively studied the results of two diagnostic self tests for the early detection of metamorphopsia and scotoma, the PHP test and the Amsler grid test, in different stages of ARMD. Patients with ARMD and best corrected visual acuity of 6/30 or better (Snellen charts) were examined with a standardised protocol, including supervised Amsler grid examination and PHP, a new device for metamorphopsia or scotoma measurement, based on the hyperacuity phenomenon in the central 14 degrees of the visual field. The stages of ARMD were independently graded in a masked fashion by stereoscopic ophthalmoscopy, stereoscopic fundus colour photographs, fluorescein angiography, and OCT. The patients were subdivided into 3 non-neovascular groups [early, late (RPE atrophy > 175 microm) and geographic atrophy], a neovascular group (classic and occult CNV) and an age-matched control group (healthy volunteers). 140 patients, with ages ranging from 50 to 90 years (median 68 years), were included in the study. Best corrected visual acuity ranged from 6/30 to 6/6 with a median of 6/12. 95 patients were diagnosed as non-neovascular ARMD. Thirty eyes had early ARMD (9 were tested positive by the PHP test and 9 by the Amsler grid test), and 50 late ARMD (positive: PHP test 23, Amsler grid test 26). The group with geographic atrophy consisted of 15 eyes (positive: PHP test 13, Amsler grid test 10). Forty-five patients presented with neovascular ARMD (positive: PHP test 38, Amsler grid test 36), 34 volunteers served as control group (positive: PHP test 1, Amsler grid test 5). The PHP and Amsler grid tests revealed comparable results detecting metamorphopsia and scotoma in early ARMD (30 vs. 30 %) and late ARMD (46 vs. 52 %). However, the PHP test more often revealed disease-related functional changes in the groups of geographic atrophy (87 vs. 67 %) and neovascular ARMD (84 vs. 80 %). This implies that the PHP and Amsler grid self tests are useful tools for detection of ARMD and that the PHP test has a greater sensitivity in the groups of geographic atrophy and neovascular AMD.