ANALYSIS OF TRANSFER LEARNING FOR SELECT RETINAL DISEASE CLASSIFICATION.

PURPOSE: To analyze the effect of transfer learning for classification of diabetic retinopathy (DR) by fundus photography and select retinal diseases by spectral domain optical coherence tomography (SD-OCT). METHODS: Five widely used open-source deep neural networks and four customized simpler and smaller networks, termed the CBR family, were trained and evaluated on two tasks: 1) classification of DR using fundus photography and 2) classification of drusen, choroidal neovascularization, and diabetic macular edema using SD-OCT. For DR classification, the quadratic weighted Kappa coefficient was used to measure the level of agreement between each network and ground truth-labeled test cases. For SD-OCT-based classification, accuracy was calculated for each network. Kappa and accuracy were compared between iterations with and without use of transfer learning for each network to assess for its effect. RESULTS: For DR classification, Kappa increased with transfer learning for all networks (range of increase 0.152-0.556). For SD-OCT-based classification, accuracy increased for four of five open-source deep neural networks (range of increase 1.8%-3.5%), slightly decreased for the remaining deep neural network (-0.6%), decreased slightly for three of four CBR networks (range of decrease 0.9%-1.8%), and decreased by 9.6% for the remaining CBR network. CONCLUSION: Transfer learning improved performance, as measured by Kappa, for DR classification for all networks, although the effect ranged from small to substantial. Transfer learning had minimal effect on accuracy for SD-OCT-based classification for eight of the nine networks analyzed. These results imply that transfer learning may substantially increase performance for DR classification but may have minimal effect for SD-OCT-based classification.

Vitreous Metastasis in a Case of Metastatic Breast Cancer.

A 35-year-old female with a history of metastatic breast cancer (BC) presented with unilateral blurred vision and floaters over 6 weeks. Examination findings showed vitreous opacities and a vasculitis concerning for an infectious process. Diagnostic vitrectomy revealed no infectious cause, but rather metastatic cells in the vitreous, with no obvious retinal or choroidal metastatic focus. In this report we illustrate a case of vitreous metastasis in a patient with metastatic BC, highlighting the importance of recognizing this rare entity which can mimic an inflammatory or infectious process. Novel to this report is the use of modern wide-field retinal imaging, spectral-domain optical coherence tomography, and a surgical video to document the findings of this disease entity.

Risperidone-related bilateral cystoid macular edema: a case report.

BACKGROUND: A report of the second known case of bilateral cystoid macular edema in a patient taking risperidone. CASE PRESENTATION: We report a case of a 69-year-old African American woman using risperidone who presented with worsening visual acuity and was found to have bilateral cystoid macular edema. Upon decreasing the dosage of risperidone, the cystoid macular edema resolved and visual acuity markedly improved. Fluorescein angiography and optical coherence tomography were used to document the severity of cystoid macular edema and subsequent resolution after decreased dosage of risperidone. CONCLUSION: The documentation of a patient who developed cystoid macular edema associated with risperidone usage indicates that it may be beneficial to monitor patients taking risperidone for the development of maculopathy.

DIAGNOSTIC ACCURACY EVALUATION OF VISUAL ACUITY AND FUNDUS AUTOFLUORESCENCE MACULAR GEOGRAPHIC ATROPHY AREA FOR THE DISCRIMINATION OF STARGARDT GROUPS.

PURPOSE: To evaluate diagnostic accuracy of visual acuity and fundus autofluorescence (FAF) macular geographic atrophy (GA) area for the discrimination of autosomal recessive Stargardt groups. METHODS: Subjects aged <50 years old with confirmed molecular diagnoses were classified to Groups 1, 2, or 3 according to a full-field electroretinogram reference standard. Diagnostic accuracy of visual acuity and the FAF macular GA area was assessed with generalized estimating equations, receiver operating characteristic curve area under the curve, and support vector machines. RESULTS: Ten eyes were classified as Group 1 and 7 as Group 2. The mean log minimum angle resolution (Snellen equivalent) was 0.64 (20/87) for group 1 and 0.96 (20/182) for group 2. Mean FAF macular GA area was 0.96 mm for Group 1 and 3.23 mm for Group 2. The generalized estimating equation analysis showed an 8.3% increase in odds of Group 2 classification with each 0.1-unit increase in log minimum angle resolution and a 24% increase with each 1-mm increase in FAF macular GA area. Multivariate generalized estimating equation analysis showed that only the FAF macular GA area was significant. Area under the curve was 0.79 for log minimum angle resolution and 0.89 for FAF macular GA area. The support vector machine classification accuracy was 71% for log minimum angle resolution and 82% for FAF macular GA area. CONCLUSION: Visual acuity and FAF macular GA area had good independent accuracy for the discrimination of groups 1 and 2, indicating that they may serve as useful diagnostic parameters.

SEQUENTIAL CENTRAL RETINAL VEIN AND OPHTHALMIC ARTERY OCCLUSIONS IN A PEDIATRIC CASE OF PRIMARY ANTIPHOSPHOLIPID SYNDROME.

PURPOSE: To report a case of sequential central retinal vein occlusion and ophthalmic artery occlusion in a patient with primary antiphospholipid syndrome. METHODS: Observational case report. Color fundus photography, fluorescein angiography, and optical coherence tomography were used to document the progression of a central retinal vein occlusion and sequential development of an ophthalmic artery occlusion within a 1-week period in a patient with primary antiphospholipid syndrome. RESULTS: A 15-year-old boy presented with unilateral blurry vision due to a central retinal vein occlusion along with other systemic symptoms. Within a 1-week period, he developed an ophthalmic artery occlusion in the same eye, with resulting bare light perception vision. Extensive evaluation by the pediatrics and rheumatology services led to a diagnosis of primary antiphospholipid syndrome as the etiology for the occlusions. CONCLUSION: This case report illustrates the rapid sequential venous and arterial ocular thrombosis in a patient with primary antiphospholipid syndrome.

Retinal vasculature remodeling in a case of systemic lupus erythematosus vaso-occlusive retinopathy.

PURPOSE: To report a case of systemic lupus erythematosus vaso-occlusive retinopathy illustrating vascular remodeling over 4 years of follow-up. METHODS: Observational case report of one patient. RESULTS: A 12-year-old previously healthy girl presented with profound vision loss to 20/800 in both eyes. Her medical workup, neuro-imaging, and ophthalmic examination were consistent with coexistent central nervous system systemic lupus erythematosus and vaso-occlusive systemic lupus erythematosus retinopathy. At 15 months after presentation, retinal vasculature remodeling was evident along with severe macular atrophy. By 4 years after presentation, retinal neovascularization developed that was successfully treated with photocoagulation. CONCLUSION: We describe a case of systemic lupus erythematosus vaso-occlusive retinopathy illustrating vascular remodeling over 4 years of follow-up.

Multimodal imaging in a case of deferoxamine-induced maculopathy.

PURPOSE: To report a case of deferoxamine-induced maculopathy and present the use of multimodal retinal imaging to study this disease entity. METHODS: This is an observational case report of one patient. Multimodal imaging with fundus autofluorescence, infrared imaging, and spectral domain optical coherence tomography was used to investigate the macular changes induced by deferoxamine toxicity. RESULTS: A 53-year-old man with history of ß-thalassemia presented with decreased vision in both eyes 1 month after initiating deferoxamine therapy. Infrared imaging showed areas of increased stippled infrared intensity through the macula. Fundus autofluorescence revealed diffuse areas of stippled hyperautofluorescence and hypoautofluorescence. Spectral domain optical coherence tomography changes included disruption of the ellipsoid zone, attenuation of the photoreceptors, and deposits within the retinal pigment epithelium. CONCLUSION: A case of deferoxamine-induced maculopathy was described and the use of multimodal retinal imaging to study this disease entity was presented.

Hyperautofluorescent macular ring in a series of patients with enhanced S-cone syndrome.

The authors describe fundus autofluorescence (AF) and spectral-domain optical coherence tomography (SD-OCT) findings in three patients with enhanced S-cone syndrome and their correlation around the hyperautofluorescent ring border. Patients had AF imaging in combination with SD-OCT line-scans through the fovea, at the posterior pole, and at a temporal locus centered on the ring border. All eyes demonstrated a macular ring of high-intensity AF. The inner segment ellipsoid band showed thinning and disorganization toward the ring border, where it was lost.

Juvenile-onset macular degeneration and allied disorders.

While age-related macular degeneration (AMD) is a leading cause of central vision loss among the elderly, many inherited diseases that present earlier in life share features of AMD. These diseases of juvenile-onset macular degeneration include Stargardt disease, Best disease, retinitis pigmentosa, X-linked retinoschisis, and other allied disorders. In particular, they can be accompanied by the appearance of drusen, geographic atrophy, macular hyperpigmentation, choroidal neovascularization, and disciform scarring just as in AMD, and often may be confused for the adult form of the disease. Diagnosis based on funduscopic findings alone can be challenging. However, the use of diagnostic studies such as electroretinography, electrooculography, optical coherence tomography, and fundus autofluorescence in conjunction with genetic testing can lead to an accurate diagnosis.

Clinical predictors of sustained intraocular pressure elevation due to intravitreal anti-vascular endothelial growth factor therapy.

PURPOSE: We assess for frequency and predictive factors related to sustained intraocular pressure (IOP) elevation in eyes with neovascular age-related macular degeneration receiving intravitreal injections of ranibizumab and/or bevacizumab. METHODS: A total of 328 patients with neovascular age-related macular degeneration (449 eyes) who presented to a single physician over a 6-month period were retrospectively assessed for baseline demographic/clinical information, total number of bevacizumab and/or ranibizumab injections, and sustained IOP elevation on 2 or more consecutive visits (absolute IOP >25 mmHg, increase above baseline >10 mmHg, or IOP of >21 mmHg and increase of >5 mmHg). Cox regression survival analysis and multivariate logistic regression were performed to assess the influence of intravitreal injections on experiencing sustained IOP elevation. RESULTS: Overall, 32 eyes (7.1%) experienced sustained IOP elevation. Survival analysis showed a significant effect of the number of anti-vascular endothelial growth factor injections on sustained IOP elevation (hazard ratio, 1.085; 95% confidence interval: 1.06-1.11, P < 0.001). Also, there was an increased odds ratio (16.1, P = 0.008) of sustained IOP elevation in eyes receiving ≥29 injections compared with ≤12 injections. After controlling for the confounder (prior intravitreal steroid injection), total number of injections still showed a statistically significant association (P = 0.002). CONCLUSION: A greater number of intravitreal anti-vascular endothelial growth factor injections is associated with an increased risk for sustained IOP elevation in eyes with neovascular age-related macular degeneration receiving intravitreal ranbizumab and/or bevacizumab.

Sequential bilateral central retinal vein occlusions in a cystic fibrosis patient with hyperhomocysteinemia and hypergamma-globulinemia.

PURPOSE: To report a case of sequential bilateral central retinal vein occlusions in a cystic fibrosis patient with hyperhomocysteinemia and hypergamma-globulinemia over 6 years of follow up. METHODS: Observational case report of one patient. RESULTS: A 31 year-old male with a history of cystic fibrosis presented with a central retinal vein occlusion (CRVO) in his left eye, followed by a CRVO in his right eye 4 years later. His medical workup was significant for elevated levels of homocysteine and gamma-globulins, which coincided with initiation of intravenous immunoglobulin (IVIG) proceeding his second CRVO. CONCLUSIONS: We describe a case of sequential bilateral central retinal vein occlusions in a cystic fibrosis patient with hyperhomocysteinemia and hypergamma-globulinemia over 6 years of follow up and discuss the important role of these risk factors in retinal venous occlusive disease.

Plus disease in retinopathy of prematurity: diagnostic impact of field of view.

PURPOSE: To examine the impact of retinal field of view and magnification on interexpert reliability of plus disease diagnosis in retinopathy of prematurity. METHODS: Fifteen wide-angle images from infants with retinopathy of prematurity were cropped and adjusted in magnification to create 2 additional image categories: medium angle (40°-50°) and narrow angle (20°-30°). These 45 images were uploaded to a Web-based system and interpreted independently by 13 experts of retinopathy of prematurity using a 3-level (plus, preplus, neither) and 2-level (plus, not plus) classification. Absolute agreement and kappa statistics were calculated to compare interexpert reliability. RESULTS: In the 3-level classification, ≥ 70% experts agreed on the same diagnosis in 8 of the 15 wide-angle images (53%), but only in 3 of the 15 medium-angle (20%) and 3 of the 15 narrow-angle (20%) images. In the 2-level classification, ≥ 80% experts agreed on the same diagnosis in 11 of the 15 wide-angle images (73%), but only in 9 of the 15 medium-angle (60%) and 3 of the 15 narrow-angle (20%) images. Mean kappa of each expert compared with all other experts was 0.40 to 0.59 in 8 of 13 experts (62%) using wide-angle images, was 0 to 0.19 in 7 of 13 experts (54%) using medium-angle images, and was 0.20 to 0.39 in 9 of 13 experts (69%) using narrow-angle images. CONCLUSION: Interexpert agreement in plus disease diagnosis in wide-angle images is higher than from medium-angle and narrow-angle images. Plus disease is defined using a narrow-angle standard published photograph, yet this study suggests that peripheral findings also contribute to diagnosis.

Fundus autofluorescence imaging in a patient with rapidly developing scotoma.

PURPOSE: To evaluate the findings in a case of acute macular neuroretinopathy involving sudden development of scotomas accompanied by rapid focal increases in fundus autofluorescence. METHODS: The clinical presentation of the patient was documented by color fundus photographs, fundus autofluorescence, infrared imaging, and high-resolution spectral domain optical coherence tomography. The scotomas were assessed by Humphrey visual field 10-2 and MP-1 microperimetry. RESULTS: Visual field defects exhibited spatial correspondence with wedge-shaped lesions demonstrable in color fundus photographs and infrared imaging. It was notable that the lesions exhibited increased intensity on autofluorescence images obtained within 3 weeks of presentation. Optical coherence tomography revealed focal loss of photoreceptor inner segment/outer segment junctions in both eyes. CONCLUSION: This case was distinguished by the relative rapidity with which the lesions became hyperautofluorescent in fundus autofluorescence images. Given that the bisretinoids that are the source of autofluorescence form in photoreceptor cells and are transferred to retinal pigment epithelium secondarily, the rapid increase in autofluorescence is unlikely to only reflect retinal pigment epithelium status and is more likely to be indicative of photoreceptor cell dysfunctioning and loss of structural integrity.

Evaluation of vascular disease progression in retinopathy of prematurity using static and dynamic retinal images.

PURPOSE: To measure accuracy and speed for detection of vascular progression in retinopathy of prematurity (ROP) from serial images. Two strategies are compared: static side-by-side presentation and dynamic flickering of superimposed image pairs. DESIGN: Prospective comparative study. METHODS: Fifteen de-identified, wide-angle retinal image pairs were taken from infants who eventually developed plus disease. Image pairs representing vascular disease progression were taken ≥1 week apart, and control images without progression were taken on the same day. Dynamic flickering pairs were created by digital image registration. Ten experts independently reviewed each image pair on a secure website using both strategies, and were asked to identify progression or state that images were identical. Accuracy and speed were measured, using examination date and ophthalmoscopic findings as a reference standard. RESULTS: Using static images, experts were accurate in a mean (%) ± standard deviation (SD) of 11.4 of 15 (76%) ± 1.7 image pairs. Using dynamic flickering images, experts were accurate in a mean (%) ± SD of 11.3 of 15 (75%) ± 1.7 image pairs. There was no significant difference in accuracy between these strategies (P = .420). Diagnostic speed was faster using dynamic flickering (24.7 ± 8.3 seconds) vs static side-by-side images (40.3 ± 18.3 seconds) (P = .002). Experts reported higher confidence when interpreting dynamic flickering images (P = .001). CONCLUSIONS: Retinal imaging provides objective documentation of vascular appearance, with potentially improved ability to recognize ROP progression compared to standard ophthalmoscopy. Speed of identifying vascular progression was faster by review of dynamic flickering image pairs than by static side-by-side images, although there was no difference in accuracy.

Image analysis for retinopathy of prematurity diagnosis.

PURPOSE: To review findings from the authors' published studies involving telemedicine and image analysis for retinopathy of prematurity (ROP) diagnosis. METHODS: Twenty-two ROP experts interpreted a set of 34 wide-angle retinal images for presence of plus disease. For each image, a reference standard diagnosis was defined from expert consensus. A computer-based system was used to measure individual and linear combinations of image parameters for arteries and veins: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis were determined for each expert. Sensitivity and specificity curves were calculated for the computer-based system by varying the diagnostic cutoffs for arterial IC and venous diameter. Individual vessels from the original 34 images were identified with particular diagnostic cutoffs, and combined into composite wide-angle images using graphics editing software. RESULTS: For plus disease diagnosis, expert sensitivity ranged from 0.308-1.000, specificity from 0.571-1.000, and AUC from 0.784 to 1.000. Among computer system parameters, one linear combination had AUC 0.967, which was greater than that of 18 of 22 (81.8%) experts. Composite computer-generated images were produced using the arterial IC and venous diameter values associated with 75% under-diagnosis of plus disease (ie, 25% sensitivity cutoff), 50% under-diagnosis of plus disease (ie, 50% sensitivity cutoff), and 25% under-diagnosis of plus disease (ie, 75% sensitivity cutoff). CONCLUSIONS: Computer-based image analysis has the potential to diagnose severe ROP with comparable or better accuracy than experts, and could provide added value to telemedicine systems. Future quantitative definitions of plus disease might improve diagnostic objectivity.

Plus disease in retinopathy of prematurity: development of composite images by quantification of expert opinion.

PURPOSE: To demonstrate a methodology for generating composite wide-angle images of plus disease in retinopathy of prematurity (ROP), using quantitative analysis of expert opinions. METHODS: Thirty-four wide-angle retinal images were independently interpreted by 22 ROP experts as "plus" or "not plus." All images were processed by the computer-based Retinal Image multiScale Analysis (RISA) system to calculate two parameters: arterial integrated curvature (AIC) and venous diameter (VD). Using a reference standard defined by expert consensus, sensitivity and specificity curves were calculated by varying the diagnostic cutoffs for AIC and VD. From these curves, individual vessels from multiple images were identified with particular diagnostic cutoffs, and were combined into composite wide-angle images using graphics-editing software. RESULTS: The values associated with 75% underdiagnosis of true plus disease (i.e., 25% sensitivity cutoff) were AIC 0.061 and VD 4.272, the values associated with 50% underdiagnosis of true plus disease (i.e., a 50% sensitivity cutoff) were AIC 0.049 and VD 4.088, and the values associated with 25% underdiagnosis of true plus disease (i.e., 75% sensitivity cutoff) were AIC 0.042 and VD 3.795. Composite wide-angle images were generated by identifying and combining individual vessels with these characteristics. CONCLUSIONS: Computer-based image analysis permits quantification of retinal vascular features, and a spectrum of abnormalities is seen in ROP. Selection of appropriate vessels from multiple images can produce composite plus disease images corresponding to expert opinions. This method may be useful for educational purposes, and for development of future disease definitions based on objective, quantitative principles.

Evaluation of a computer-based system for plus disease diagnosis in retinopathy of prematurity.

OBJECTIVE: To measure accuracy and reliability of the computer-based Retinal Image Multiscale Analysis (RISA) system compared with those of recognized retinopathy of prematurity (ROP) experts, for plus disease diagnosis. DESIGN: Evaluation of diagnostic test or technology. PARTICIPANTS: Eleven recognized ROP experts and the RISA image analysis system interpreted a set of 20 wide-angle retinal photographs for presence of plus disease. METHODS: All experts used a secure Web site to review independently 20 images for presence of plus disease. Images were also analyzed by measuring individual computer-based system parameters (integrated curvature [IC], diameter, and tortuosity index) for arterioles and venules and by computing linear combinations and logical combinations of those parameters. Performance was compared with a reference standard, defined as the majority vote of experts. MAIN OUTCOME MEASURES: Diagnostic accuracy was measured by calculating sensitivity, specificity, and receiver operating characteristic area under the curve (AUC) for plus disease diagnosis by each expert, and by each computer-based system parameter, compared with the reference standard. Diagnostic agreement was measured by calculating the mean kappa value of each expert compared with all other experts and the mean kappa value of each computer-based system parameter compared with all experts. RESULTS: Among the 11 experts, sensitivity ranged from 0.167 to 1.000, specificity ranged from 0.714 to 1.000, AUC ranged from 0.798 to 1.000, and mean kappa compared with all other experts ranged from 0.288 to 0.689. Among individual computer system parameters, arteriolar IC had the highest diagnostic accuracy, with sensitivity of 1.000; specificity, 0.846; and AUC, 0.962. Arteriolar IC had the highest diagnostic agreement with experts, with a mean kappa value of 0.578. CONCLUSIONS: A computer-based image analysis system has the potential to perform comparably to recognized ROP experts for plus disease diagnosis.

Plus disease in retinopathy of prematurity: pilot study of computer-based and expert diagnosis.

PURPOSE: To measure accuracy of plus disease diagnosis by recognized experts in retinopathy of prematurity (ROP), and to conduct a pilot study examining performance of a computer-based image analysis system, Retinal Image multiScale Analysis (RISA). METHODS: Twenty-two ROP experts independently interpreted a set of 34 wide-angle retinal images for presence of plus disease. A reference standard diagnosis based on expert consensus was defined for each image. Images were analyzed by the computer-based system using individual and linear combinations of system parameters for arterioles and venules: integrated curvature (IC), diameter, and tortuosity index (TI). Sensitivity, specificity, and receiver operating characteristic areas under the curve (AUC) for plus disease diagnosis compared with the reference standard were determined for each expert, as well as for the computer-based system. RESULTS: Expert sensitivity ranged from 0.308 to 1.000, specificity ranged from 0.571 to 1.000, and AUC ranged from 0.784 to 1.000. Among individual computer system parameters, venular IC had highest AUC (0.853). Among all computer system parameters, the linear combination of arteriolar IC, arteriolar TI, venular IC, venular diameter, and venular TI had highest AUC (0.967), which was greater than that of 18 (81.8%) of 22 experts. CONCLUSIONS: Accuracy of ROP experts for plus disease diagnosis is imperfect. A computer-based image analysis system has potential to diagnose plus disease with high accuracy. Further research involving RISA system parameter cut-off values from this study are required to fully validate performance of this computer-based system compared with that of human experts.

Interexpert agreement of plus disease diagnosis in retinopathy of prematurity.

OBJECTIVE: To measure agreement of plus disease diagnosis among retinopathy of prematurity (ROP) experts. METHODS: A set of 34 wide-angle retinal photographs from infants with ROP was compiled on a secure Web site and was interpreted independently by 22 recognized ROP experts. Diagnostic agreement was analyzed using 3-level (plus, pre-plus, or neither) and 2-level (plus or not plus) categorizations. RESULTS: In the 3-level categorization, all experts agreed on the same diagnosis in 4 of 34 images (12%), and the mean weighted kappa statistic for each expert compared with all others was between 0.21 and 0.40 (fair agreement) for 7 experts (32%) and between 0.41 and 0.60 (moderate agreement) for 15 experts (68%). In the 2-level categorization, all experts who provided a diagnosis agreed in 7 of 34 images (21%), and the mean kappa statistic for each expert compared with all others was between 0 and 0.20 (slight agreement) for 1 expert (5%), between 0.21 and 0.40 (fair agreement) for 3 experts (14%), between 0.41 and 0.60 (moderate agreement) for 12 experts (55%), and between 0.61 and 0.80 (substantial agreement) for 6 experts (27%). CONCLUSIONS: Interexpert agreement of plus disease diagnosis is imperfect. This may have important implications for clinical ROP management, continued refinement of the international ROP classification system, development of computer-based diagnostic algorithms, and implementation of ROP telemedicine systems.