The Experts below are selected from a list of 3543 Experts worldwide ranked by ideXlab platform
Reinhard Klette - One of the best experts on this subject based on the ideXlab platform.
-
ICS - A Comparison of Transfer Learning Techniques, Deep Convolutional Neural Network and Multilayer Neural Network Methods for the Diagnosis of Glaucomatous Optic Neuropathy
Communications in Computer and Information Science, 2019Co-Authors: Mohammad Norouzifard, Ali Nemati, Hamid Gholamhosseini, Anmar Abdul-rahman, Reinhard KletteAbstract:Early glaucoma diagnosis prevents permanent structural Optic nerve damage and consequent irreversible vision impairment. Longitudinal studies have described both baseline structural and functional factors that predict the development of Glaucomatous change in ocular hypertensive and glaucoma suspects. Although there is neither a gold standard for disease diagnosis nor progression, photographic assessment of the Optic nerve head remains a mainstay in the diagnosis and management of glaucoma suspects and glaucoma patients. We describe a method aimed at both detecting pathologic changes, characteristic of Glaucomatous Optic Neuropathy in Optic disc images, and classification of images into categories Glaucomatous/suspect or normal Optic discs. Three different deep-learning algorithms used are transfer learning, deep convolutional neural network, and deep multilayer neural network that extract features automatically based on clinically relevant Optic-disc features. Of the total of 455 cases extracted from the RIM-ONE public dataset (version 2), consisting of 348 training, 87 validation and 20 test cases, the proposed approach classified images with a training accuracy of 98.16%. We hypothesise that this approach can support the clinical decision algorithm in the diagnosis of Glaucomatous Optic Neuropathy.
-
a comparison of transfer learning techniques deep convolutional neural network and multilayer neural network methods for the diagnosis of Glaucomatous Optic Neuropathy
International Conference on Supercomputing, 2018Co-Authors: Mohammad Norouzifard, Ali Nemati, Anmar Abdulrahman, Hamid Gholamhosseini, Reinhard KletteAbstract:Early glaucoma diagnosis prevents permanent structural Optic nerve damage and consequent irreversible vision impairment. Longitudinal studies have described both baseline structural and functional factors that predict the development of Glaucomatous change in ocular hypertensive and glaucoma suspects. Although there is neither a gold standard for disease diagnosis nor progression, photographic assessment of the Optic nerve head remains a mainstay in the diagnosis and management of glaucoma suspects and glaucoma patients. We describe a method aimed at both detecting pathologic changes, characteristic of Glaucomatous Optic Neuropathy in Optic disc images, and classification of images into categories Glaucomatous/suspect or normal Optic discs. Three different deep-learning algorithms used are transfer learning, deep convolutional neural network, and deep multilayer neural network that extract features automatically based on clinically relevant Optic-disc features. Of the total of 455 cases extracted from the RIM-ONE public dataset (version 2), consisting of 348 training, 87 validation and 20 test cases, the proposed approach classified images with a training accuracy of 98.16%. We hypothesise that this approach can support the clinical decision algorithm in the diagnosis of Glaucomatous Optic Neuropathy.
-
a comparison of transfer learning techniques deep convolutional neural network and multilayer neural network methods for the diagnosis of Glaucomatous Optic Neuropathy
International Computer Symposium, 2018Co-Authors: Mohammad Norouzifard, Ali Nemati, Anmar Abdulrahman, Hamid Gholamhosseini, Reinhard KletteAbstract:Early glaucoma diagnosis prevents permanent structural Optic nerve damage and consequent irreversible vision impairment. Longitudinal studies have described both baseline structural and functional factors that predict the development of Glaucomatous change in ocular hypertensive and glaucoma suspects. Although there is neither a gold standard for disease diagnosis nor progression, photographic assessment of the Optic nerve head remains a mainstay in the diagnosis and management of glaucoma suspects and glaucoma patients. We describe a method aimed at both detecting pathologic changes, characteristic of Glaucomatous Optic Neuropathy in Optic disc images, and classification of images into categories Glaucomatous/suspect or normal Optic discs. Three different deep-learning algorithms used are transfer learning, deep convolutional neural network, and deep multilayer neural network that extract features automatically based on clinically relevant Optic-disc features. Of the total of 455 cases extracted from the RIM-ONE public dataset (version 2), consisting of 348 training, 87 validation and 20 test cases, the proposed approach classified images with a training accuracy of 98.16%. We hypothesise that this approach can support the clinical decision algorithm in the diagnosis of Glaucomatous Optic Neuropathy.
Mingguang He - One of the best experts on this subject based on the ideXlab platform.
-
efficacy of a deep learning system for detecting Glaucomatous Optic Neuropathy based on color fundus photographs
Ophthalmology, 2018Co-Authors: Zhixi Li, Robert T. Chang, Yifan He, Stuart Keel, Wei Meng, Mingguang HeAbstract:Purpose To assess the performance of a deep learning algorithm for detecting referable Glaucomatous Optic Neuropathy (GON) based on color fundus photographs. Design A deep learning system for the classification of GON was developed for automated classification of GON on color fundus photographs. Participants We retrospectively included 48 116 fundus photographs for the development and validation of a deep learning algorithm. Methods This study recruited 21 trained ophthalmologists to classify the photographs. Referable GON was defined as vertical cup-to-disc ratio of 0.7 or more and other typical changes of GON. The reference standard was made until 3 graders achieved agreement. A separate validation dataset of 8000 fully gradable fundus photographs was used to assess the performance of this algorithm. Main Outcome Measures The area under receiver operator characteristic curve (AUC) with sensitivity and specificity was applied to evaluate the efficacy of the deep learning algorithm detecting referable GON. Results In the validation dataset, this deep learning system achieved an AUC of 0.986 with sensitivity of 95.6% and specificity of 92.0%. The most common reasons for false-negative grading (n = 87) were GON with coexisting eye conditions (n = 44 [50.6%]), including pathologic or high myopia (n = 37 [42.6%]), diabetic retinopathy (n = 4 [4.6%]), and age-related macular degeneration (n = 3 [3.4%]). The leading reason for false-positive results (n = 480) was having other eye conditions (n = 458 [95.4%]), mainly including physiologic cupping (n = 267 [55.6%]). Misclassification as false-positive results amidst a normal-appearing fundus occurred in only 22 eyes (4.6%). Conclusions A deep learning system can detect referable GON with high sensitivity and specificity. Coexistence of high or pathologic myopia is the most common cause resulting in false-negative results. Physiologic cupping and pathologic myopia were the most common reasons for false-positive results.
Mohammad Norouzifard - One of the best experts on this subject based on the ideXlab platform.
-
ICS - A Comparison of Transfer Learning Techniques, Deep Convolutional Neural Network and Multilayer Neural Network Methods for the Diagnosis of Glaucomatous Optic Neuropathy
Communications in Computer and Information Science, 2019Co-Authors: Mohammad Norouzifard, Ali Nemati, Hamid Gholamhosseini, Anmar Abdul-rahman, Reinhard KletteAbstract:Early glaucoma diagnosis prevents permanent structural Optic nerve damage and consequent irreversible vision impairment. Longitudinal studies have described both baseline structural and functional factors that predict the development of Glaucomatous change in ocular hypertensive and glaucoma suspects. Although there is neither a gold standard for disease diagnosis nor progression, photographic assessment of the Optic nerve head remains a mainstay in the diagnosis and management of glaucoma suspects and glaucoma patients. We describe a method aimed at both detecting pathologic changes, characteristic of Glaucomatous Optic Neuropathy in Optic disc images, and classification of images into categories Glaucomatous/suspect or normal Optic discs. Three different deep-learning algorithms used are transfer learning, deep convolutional neural network, and deep multilayer neural network that extract features automatically based on clinically relevant Optic-disc features. Of the total of 455 cases extracted from the RIM-ONE public dataset (version 2), consisting of 348 training, 87 validation and 20 test cases, the proposed approach classified images with a training accuracy of 98.16%. We hypothesise that this approach can support the clinical decision algorithm in the diagnosis of Glaucomatous Optic Neuropathy.
-
a comparison of transfer learning techniques deep convolutional neural network and multilayer neural network methods for the diagnosis of Glaucomatous Optic Neuropathy
International Conference on Supercomputing, 2018Co-Authors: Mohammad Norouzifard, Ali Nemati, Anmar Abdulrahman, Hamid Gholamhosseini, Reinhard KletteAbstract:Early glaucoma diagnosis prevents permanent structural Optic nerve damage and consequent irreversible vision impairment. Longitudinal studies have described both baseline structural and functional factors that predict the development of Glaucomatous change in ocular hypertensive and glaucoma suspects. Although there is neither a gold standard for disease diagnosis nor progression, photographic assessment of the Optic nerve head remains a mainstay in the diagnosis and management of glaucoma suspects and glaucoma patients. We describe a method aimed at both detecting pathologic changes, characteristic of Glaucomatous Optic Neuropathy in Optic disc images, and classification of images into categories Glaucomatous/suspect or normal Optic discs. Three different deep-learning algorithms used are transfer learning, deep convolutional neural network, and deep multilayer neural network that extract features automatically based on clinically relevant Optic-disc features. Of the total of 455 cases extracted from the RIM-ONE public dataset (version 2), consisting of 348 training, 87 validation and 20 test cases, the proposed approach classified images with a training accuracy of 98.16%. We hypothesise that this approach can support the clinical decision algorithm in the diagnosis of Glaucomatous Optic Neuropathy.
-
a comparison of transfer learning techniques deep convolutional neural network and multilayer neural network methods for the diagnosis of Glaucomatous Optic Neuropathy
International Computer Symposium, 2018Co-Authors: Mohammad Norouzifard, Ali Nemati, Anmar Abdulrahman, Hamid Gholamhosseini, Reinhard KletteAbstract:Early glaucoma diagnosis prevents permanent structural Optic nerve damage and consequent irreversible vision impairment. Longitudinal studies have described both baseline structural and functional factors that predict the development of Glaucomatous change in ocular hypertensive and glaucoma suspects. Although there is neither a gold standard for disease diagnosis nor progression, photographic assessment of the Optic nerve head remains a mainstay in the diagnosis and management of glaucoma suspects and glaucoma patients. We describe a method aimed at both detecting pathologic changes, characteristic of Glaucomatous Optic Neuropathy in Optic disc images, and classification of images into categories Glaucomatous/suspect or normal Optic discs. Three different deep-learning algorithms used are transfer learning, deep convolutional neural network, and deep multilayer neural network that extract features automatically based on clinically relevant Optic-disc features. Of the total of 455 cases extracted from the RIM-ONE public dataset (version 2), consisting of 348 training, 87 validation and 20 test cases, the proposed approach classified images with a training accuracy of 98.16%. We hypothesise that this approach can support the clinical decision algorithm in the diagnosis of Glaucomatous Optic Neuropathy.
Robert N Weinreb - One of the best experts on this subject based on the ideXlab platform.
-
Performance of Deep Learning Architectures and Transfer Learning for Detecting Glaucomatous Optic Neuropathy in Fundus Photographs
Scientific Reports, 2018Co-Authors: Mark Christopher, Akram Belghith, James Proudfoot, Christopher A. Girkin, Michael H Goldbaum, Christopher Bowd, Jeffrey M. Liebmann, Robert N Weinreb, Linda M ZangwillAbstract:The ability of deep learning architectures to identify Glaucomatous Optic Neuropathy (GON) in fundus photographs was evaluated. A large database of fundus photographs (n = 14,822) from a racially and ethnically diverse group of individuals (over 33% of African descent) was evaluated by expert reviewers and classified as GON or healthy. Several deep learning architectures and the impact of transfer learning were evaluated. The best performing model achieved an overall area under receiver operating characteristic (AUC) of 0.91 in distinguishing GON eyes from healthy eyes. It also achieved an AUC of 0.97 for identifying GON eyes with moderate-to-severe functional loss and 0.89 for GON eyes with mild functional loss. A sensitivity of 88% at a set 95% specificity was achieved in detecting moderate-to-severe GON. In all cases, transfer improved performance and reduced training time. Model visualizations indicate that these deep learning models relied on, in part, anatomical features in the inferior and superior regions of the Optic disc, areas commonly used by clinicians to diagnose GON. The results suggest that deep learning-based assessment of fundus images could be useful in clinical decision support systems and in the automation of large-scale glaucoma detection and screening programs.
-
Inter-Eye Comparison of Patterns of Visual Field Loss in Patients With Glaucomatous Optic Neuropathy
American Journal of Ophthalmology, 2006Co-Authors: Esther M. Hoffmann, Linda M Zangwill, Robert N Weinreb, Catherine Boden, Rupert R A Bourne, Pamela A. SampleAbstract:Purpose To compare inter-eye patterns of visual field (VF) loss on standard automated perimetry (SAP) in patients with Glaucomatous Optic Neuropathy. Design Observational cross-sectional study. Methods Four-hundred-and-ninety eyes of 245 patients with Glaucomatous Optic Neuropathy in at least one eye defined by masked stereophoto review were included. Patients had two reliable SAP visual fields within fifteen months for each eye. Patterns of visual field loss were classified independently by two graders masked to all other patient information. Patterns were described as altitudinal, arcuate, partial arcuate, paracentral, nasal step, temporal wedge, or normal based on the classification system of Keltner and associates. Superior and inferior hemifields were graded separately. Results Inter-grader agreement in visual field patterns before adjudication was 97% and 94% for the worse eye (superior and inferior hemifield) and 97% and 95% for the better eye (superior and inferior hemifield). The percentage of correspondence by hemifield location was: 53% (superior-superior), 62% (inferior-inferior), 45% (superior-inferior), and 55% (inferior-superior). The highest correspondence of individual Glaucomatous VF pattern between eyes was for arcuate (superior-superior) and inferior partial arcuate (inferior-inferior) defects (24% and 26%, respectively). Smaller hemifield patterns showed lower correspondence between the eyes (nasal step, paracentral, temporal wedge, 0% to 13% correspondence). Conclusions Patterns of visual field loss between eyes often corresponded within the same VF hemifield (superior-superior, inferior-inferior) as well as between opposite hemifields (inferior-superior), although opposite hemifield correspondence was less common. More advanced visual field defects (for example, partial arcuate) showed higher correspondence rates between the eyes than less advanced defects.
-
corneal thickness as a risk factor for visual field loss in patients with preperimetric Glaucomatous Optic Neuropathy
American Journal of Ophthalmology, 2003Co-Authors: Felipe A Medeiros, Christopher Bowd, Linda M Zangwill, Pamela A. Sample, Makoto Aihara, Robert N WeinrebAbstract:Abstract Purpose To determine whether central corneal thickness (CCT) is a risk factor for visual field loss development among patients diagnosed with preperimetric Glaucomatous Optic Neuropathy (GON). Design Observational cohort study. Methods The study included 98 eyes of 98 patients with GON, with a mean follow-up time of 4.3 ± 2.7 years. Diagnosis of GON was based on masked assessment of Optic disk stereophotographs. All patients had normal standard automated perimetry visual fields at baseline. Criteria for visual field abnormality were derived from a prior study. Several clinical factors (CCT, intraocular pressure, vertical cup-to-disk ratio, refraction, age, gender, family history of glaucoma, high blood pressure, cardiovascular disease, and migraine) were investigated to ascertain whether there is an association with development of repeatable visual field loss. Cox proportional hazards models were used to obtain hazard ratios (HR) and identify factors that predicted which individuals developed Glaucomatous visual field loss during the follow-up period. Results Thirty-four patients (35%) developed repeatable visual field abnormality during follow-up. In multivariate analysis, risk factors that predicted the development of visual field loss were a thinner CCT (adjusted HR = 1.62/40 μm thinner; P = .023; 95% confidence interval [CI]: 1.07–2.45), higher baseline intraocular pressure (adjusted HR = 1.07/mm Hg; P = .022; 95% CI: 1.01–1.14), and larger baseline vertical cup-to-disk ratio (adjusted HR = 1.63/0.1 larger; P = .009; 95% CI: 1.13–2.35). The mean ± standard deviation CCT of GON patients who developed visual field loss was 543 ± 36 μm compared with 565 ± 35 μm of those who did not develop visual field abnormalities (P = .005, Student t test). Conclusion Central corneal thickness is a risk factor for development of visual field loss among patients diagnosed with preperimetric GON. It is important to consider CCT when establishing target intraocular pressure of patients with GON.
-
New technologies for diagnosing and monitoring Glaucomatous Optic Neuropathy.
Optometry and Vision Science, 1999Co-Authors: Linda M Zangwill, Ching-fei Chang, Julia M. Williams, Robert N WeinrebAbstract:Background. Recently, instruments have been developed to provide real-time, quantitative measurements of the Optic disc and retinal nerve fiber layer (RNFL) for use in glaucoma management. Our objective is to (1) provide an overview of two of these instruments, the confocal scanning laser ophthalmoscope (Heidelberg Retina Tomograph, HRT) and scanning laser polarimeter (Nerve Fiber Analyzer, NFA) and (2) compare measurements obtained with these instruments to clinical features used in the diagnosis of glaucoma. Methods. Twenty glaucoma patients, 4 normal subjects and 20 glaucoma subjects were included. All subjects had images obtained with the HRT and NFA, and RNFL and Optic disc photography completed within 5 weeks of each other. The HRT results were compared with qualitative evaluation of stereophotographs of the Optic disc, and NFA results were compared against a semi-quantitative RNFL photograph severity score. Results. Twenty-five (57%) subjects had thinning of the neuroretinal rim identified by evaluation of stereoscopic Optic disc photographs. Despite overlap, HRT measurements of rim volume, rim area, and rim/disc ratio were significantly smaller in eyes with evidence of rim thinning than in eyes with no evidence of rim thinning. Moderate to severe RNFL damage was detected by evaluation of photographs in 25 (57%) of subjects. NFA RNFL thickness measures were smaller in eyes with moderate to severe RNFL damage than in relatively healthy eyes. Conclusions. Previous studies have documented the reproducibility of these instruments and suggested analytic techniques for improving their ability to differentiate between normal and glaucoma eyes. Our results indicate that despite overlap in values, these instruments provide measurements that reflect clinically relevant features of the Optic disc and RNFL. Whether these technologies can improve our ability to detect Glaucomatous progression over time needs to be determined with well-designed longitudinal studies and comparison with established diagnostic techniques for evaluating Glaucomatous Optic Neuropathy. (Optom Vis Sci 1999;76:526-536)
-
Imaging technologies for assessing neuroprotection in Glaucomatous Optic Neuropathy.
European journal of ophthalmology, 1999Co-Authors: Robert N Weinreb, Linda M ZangwillAbstract:The confocal scanning laser ophthalmoscope and the scanning laser polarimeter are two new imaging devices that may be beneficial in the diagnosis and monitoring of glaucoma patients. For each of these instruments, the authors describe benefits and limitations with regard to imaging mechanisms, sensitivity, and clinical applications. In comparison with currently used tests for glaucoma, these instruments provide quantitative assessment of the Optic disc and RNFL at the clinic visit, with reduced need for pupil dilation and clear media. They also show promise for improving the ability to monitor progression of Glaucomatous Optic Neuropathy and might allow better assessment of the efficacy of a neuroprotective agent.
Linda M Zangwill - One of the best experts on this subject based on the ideXlab platform.
-
Performance of Deep Learning Architectures and Transfer Learning for Detecting Glaucomatous Optic Neuropathy in Fundus Photographs
Scientific Reports, 2018Co-Authors: Mark Christopher, Akram Belghith, James Proudfoot, Christopher A. Girkin, Michael H Goldbaum, Christopher Bowd, Jeffrey M. Liebmann, Robert N Weinreb, Linda M ZangwillAbstract:The ability of deep learning architectures to identify Glaucomatous Optic Neuropathy (GON) in fundus photographs was evaluated. A large database of fundus photographs (n = 14,822) from a racially and ethnically diverse group of individuals (over 33% of African descent) was evaluated by expert reviewers and classified as GON or healthy. Several deep learning architectures and the impact of transfer learning were evaluated. The best performing model achieved an overall area under receiver operating characteristic (AUC) of 0.91 in distinguishing GON eyes from healthy eyes. It also achieved an AUC of 0.97 for identifying GON eyes with moderate-to-severe functional loss and 0.89 for GON eyes with mild functional loss. A sensitivity of 88% at a set 95% specificity was achieved in detecting moderate-to-severe GON. In all cases, transfer improved performance and reduced training time. Model visualizations indicate that these deep learning models relied on, in part, anatomical features in the inferior and superior regions of the Optic disc, areas commonly used by clinicians to diagnose GON. The results suggest that deep learning-based assessment of fundus images could be useful in clinical decision support systems and in the automation of large-scale glaucoma detection and screening programs.
-
Inter-Eye Comparison of Patterns of Visual Field Loss in Patients With Glaucomatous Optic Neuropathy
American Journal of Ophthalmology, 2006Co-Authors: Esther M. Hoffmann, Linda M Zangwill, Robert N Weinreb, Catherine Boden, Rupert R A Bourne, Pamela A. SampleAbstract:Purpose To compare inter-eye patterns of visual field (VF) loss on standard automated perimetry (SAP) in patients with Glaucomatous Optic Neuropathy. Design Observational cross-sectional study. Methods Four-hundred-and-ninety eyes of 245 patients with Glaucomatous Optic Neuropathy in at least one eye defined by masked stereophoto review were included. Patients had two reliable SAP visual fields within fifteen months for each eye. Patterns of visual field loss were classified independently by two graders masked to all other patient information. Patterns were described as altitudinal, arcuate, partial arcuate, paracentral, nasal step, temporal wedge, or normal based on the classification system of Keltner and associates. Superior and inferior hemifields were graded separately. Results Inter-grader agreement in visual field patterns before adjudication was 97% and 94% for the worse eye (superior and inferior hemifield) and 97% and 95% for the better eye (superior and inferior hemifield). The percentage of correspondence by hemifield location was: 53% (superior-superior), 62% (inferior-inferior), 45% (superior-inferior), and 55% (inferior-superior). The highest correspondence of individual Glaucomatous VF pattern between eyes was for arcuate (superior-superior) and inferior partial arcuate (inferior-inferior) defects (24% and 26%, respectively). Smaller hemifield patterns showed lower correspondence between the eyes (nasal step, paracentral, temporal wedge, 0% to 13% correspondence). Conclusions Patterns of visual field loss between eyes often corresponded within the same VF hemifield (superior-superior, inferior-inferior) as well as between opposite hemifields (inferior-superior), although opposite hemifield correspondence was less common. More advanced visual field defects (for example, partial arcuate) showed higher correspondence rates between the eyes than less advanced defects.
-
corneal thickness as a risk factor for visual field loss in patients with preperimetric Glaucomatous Optic Neuropathy
American Journal of Ophthalmology, 2003Co-Authors: Felipe A Medeiros, Christopher Bowd, Linda M Zangwill, Pamela A. Sample, Makoto Aihara, Robert N WeinrebAbstract:Abstract Purpose To determine whether central corneal thickness (CCT) is a risk factor for visual field loss development among patients diagnosed with preperimetric Glaucomatous Optic Neuropathy (GON). Design Observational cohort study. Methods The study included 98 eyes of 98 patients with GON, with a mean follow-up time of 4.3 ± 2.7 years. Diagnosis of GON was based on masked assessment of Optic disk stereophotographs. All patients had normal standard automated perimetry visual fields at baseline. Criteria for visual field abnormality were derived from a prior study. Several clinical factors (CCT, intraocular pressure, vertical cup-to-disk ratio, refraction, age, gender, family history of glaucoma, high blood pressure, cardiovascular disease, and migraine) were investigated to ascertain whether there is an association with development of repeatable visual field loss. Cox proportional hazards models were used to obtain hazard ratios (HR) and identify factors that predicted which individuals developed Glaucomatous visual field loss during the follow-up period. Results Thirty-four patients (35%) developed repeatable visual field abnormality during follow-up. In multivariate analysis, risk factors that predicted the development of visual field loss were a thinner CCT (adjusted HR = 1.62/40 μm thinner; P = .023; 95% confidence interval [CI]: 1.07–2.45), higher baseline intraocular pressure (adjusted HR = 1.07/mm Hg; P = .022; 95% CI: 1.01–1.14), and larger baseline vertical cup-to-disk ratio (adjusted HR = 1.63/0.1 larger; P = .009; 95% CI: 1.13–2.35). The mean ± standard deviation CCT of GON patients who developed visual field loss was 543 ± 36 μm compared with 565 ± 35 μm of those who did not develop visual field abnormalities (P = .005, Student t test). Conclusion Central corneal thickness is a risk factor for development of visual field loss among patients diagnosed with preperimetric GON. It is important to consider CCT when establishing target intraocular pressure of patients with GON.
-
New technologies for diagnosing and monitoring Glaucomatous Optic Neuropathy.
Optometry and Vision Science, 1999Co-Authors: Linda M Zangwill, Ching-fei Chang, Julia M. Williams, Robert N WeinrebAbstract:Background. Recently, instruments have been developed to provide real-time, quantitative measurements of the Optic disc and retinal nerve fiber layer (RNFL) for use in glaucoma management. Our objective is to (1) provide an overview of two of these instruments, the confocal scanning laser ophthalmoscope (Heidelberg Retina Tomograph, HRT) and scanning laser polarimeter (Nerve Fiber Analyzer, NFA) and (2) compare measurements obtained with these instruments to clinical features used in the diagnosis of glaucoma. Methods. Twenty glaucoma patients, 4 normal subjects and 20 glaucoma subjects were included. All subjects had images obtained with the HRT and NFA, and RNFL and Optic disc photography completed within 5 weeks of each other. The HRT results were compared with qualitative evaluation of stereophotographs of the Optic disc, and NFA results were compared against a semi-quantitative RNFL photograph severity score. Results. Twenty-five (57%) subjects had thinning of the neuroretinal rim identified by evaluation of stereoscopic Optic disc photographs. Despite overlap, HRT measurements of rim volume, rim area, and rim/disc ratio were significantly smaller in eyes with evidence of rim thinning than in eyes with no evidence of rim thinning. Moderate to severe RNFL damage was detected by evaluation of photographs in 25 (57%) of subjects. NFA RNFL thickness measures were smaller in eyes with moderate to severe RNFL damage than in relatively healthy eyes. Conclusions. Previous studies have documented the reproducibility of these instruments and suggested analytic techniques for improving their ability to differentiate between normal and glaucoma eyes. Our results indicate that despite overlap in values, these instruments provide measurements that reflect clinically relevant features of the Optic disc and RNFL. Whether these technologies can improve our ability to detect Glaucomatous progression over time needs to be determined with well-designed longitudinal studies and comparison with established diagnostic techniques for evaluating Glaucomatous Optic Neuropathy. (Optom Vis Sci 1999;76:526-536)
-
Imaging technologies for assessing neuroprotection in Glaucomatous Optic Neuropathy.
European journal of ophthalmology, 1999Co-Authors: Robert N Weinreb, Linda M ZangwillAbstract:The confocal scanning laser ophthalmoscope and the scanning laser polarimeter are two new imaging devices that may be beneficial in the diagnosis and monitoring of glaucoma patients. For each of these instruments, the authors describe benefits and limitations with regard to imaging mechanisms, sensitivity, and clinical applications. In comparison with currently used tests for glaucoma, these instruments provide quantitative assessment of the Optic disc and RNFL at the clinic visit, with reduced need for pupil dilation and clear media. They also show promise for improving the ability to monitor progression of Glaucomatous Optic Neuropathy and might allow better assessment of the efficacy of a neuroprotective agent.