Color Fundus Photography, Optical Coherence Tomography, and Fluorescein Angiography in Diagnosing Polypoidal Choroidal Vasculopathy

Diagnosing Polypoidal Choroidal Vasculopathy Using Color Fundus Photography, Optical Coherence Tomography, and Optical Coherence Tomography Angiography

PURPOSE

To compare the diagnostic accuracy of differentiating polypoidal choroidal vasculopathy (PCV) from exudative age-related macular degeneration (AMD), using color fundus photography (CFP), optical coherence tomography (OCT), and swept-source OCT angiography (SS-OCTA) without using indocyanine green angiography (ICGA).

METHODS

Treatment-naive eyes with exudative AMD that underwent CFP, OCT, SS-OCTA, and ICGA imaging before treatment were identified. Images of each patient were categorized into two sets (set A, CFP + OCT; set B, CFP + SS-OCTA). In set B, both the en face and cross-sectional B scans were analyzed. Each set was reviewed by two graders, and it was determined whether the presumed diagnosis was PCV. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) for the diagnosis of PCV were assessed for each set by comparing diagnoses that included ICGA. The number of polypoidal lesions in each set was calculated and compared to ICGA.

RESULTS

A total of 94 eyes from 94 patients with AMD were included in the study, of which 66.0% were male, and the mean age was 71.8 ± 9.0 years. The PCV diagnosis rate using ICGA was 45.7%. The sensitivity was 0.88 for set A and 0.93 for set B, while the specificity was 0.94 for set A and 0.96 for set B. The AUC was 0.90 (95% confidence interval [CI], 0.83-0.97) for set A and 0.96 (95% CI, 0.90-1.00) for set B. Set A detected 1.28 ± 0.91 polypoidal lesions, while set B detected 1.47 ± 1.01; ICGA showed 1.51 ± 0.86.

CONCLUSIONS

This study highlights that, without using ICGA, both CFP combined with OCT and CFP combined with SS-OCTA demonstrate high sensitivity, specificity, and AUC in diagnosing PCV. It is evident that SS-OCTA contributes to enhancing sensitivity, specificity, and AUC for PCV diagnosis.

Automatic interpretation and clinical evaluation for fundus fluorescein angiography images of diabetic retinopathy patients by deep learning

BACKGROUND/AIMS

Fundus fluorescein angiography (FFA) is an important technique to evaluate diabetic retinopathy (DR) and other retinal diseases. The interpretation of FFA images is complex and time-consuming, and the ability of diagnosis is uneven among different ophthalmologists. The aim of the study is to develop a clinically usable multilevel classification deep learning model for FFA images, including prediagnosis assessment and lesion classification.

METHODS

A total of 15 599 FFA images of 1558 eyes from 845 patients diagnosed with DR were collected and annotated. Three convolutional neural network (CNN) models were trained to generate the label of image quality, location, laterality of eye, phase and five lesions. Performance of the models was evaluated by accuracy, F-1 score, the area under the curve and human-machine comparison. The images with false positive and false negative results were analysed in detail.

RESULTS

Compared with LeNet-5 and VGG16, ResNet18 got the best result, achieving an accuracy of 80.79%-93.34% for prediagnosis assessment and an accuracy of 63.67%-88.88% for lesion detection. The human-machine comparison showed that the CNN had similar accuracy with junior ophthalmologists. The false positive and false negative analysis indicated a direction of improvement.

CONCLUSION

This is the first study to do automated standardised labelling on FFA images. Our model is able to be applied in clinical practice, and will make great contributions to the development of intelligent diagnosis of FFA images.

Advances in multi-modal non-invasive imaging techniques in the diagnosis and treatment of polypoidal choroidal vasculopathy

Polypoidal choroidal vasculopathy (PCV) is a disease characterized by subretinal pigment epithelium (RPE) orange-red polypoidal lesions and abnormal branching neovascular networks (BNNs). In recent years, various non-invasive imaging technologies have rapidly developed, especially the emergence of optical coherence tomography angiography (OCTA), multi-spectral imaging, and other technologies, which enable the observation of more features of PCV. In addition, these technologies are faster and less invasive compared to indocyanine green angiography (ICGA). Multi-modal imaging, which combined multiple imaging techniques, provides important references for the diagnosis and treatment of PCV with the assistance of regression models, deep learning, and other algorithms. In this study, we reviewed the non-invasive imaging techniques, multi-modal imaging diagnosis, and multi-scene therapeutic applications of PCV, with the aim of providing a reference for non-invasive multi-modal diagnosis and treatment of PCV.

New Concepts for the Diagnosis of Polypoidal Choroidal Vasculopathy

Polypoidal choroidal vasculopathy (PCV) is a subtype of neovascular age-related macular degeneration (nAMD) that is characterized by a branching neovascular network and polypoidal lesions. It is important to differentiate PCV from typical nAMD as there are differences in treatment response between subtypes. Indocyanine green angiography (ICGA) is the gold standard for diagnosing PCV; however, ICGA is an invasive detection method and impractical for extensive use for regular long-term monitoring. In addition, access to ICGA may be limited in some settings. The purpose of this review is to summarize the utilization of multimodal imaging modalities (color fundus photography, optical coherence tomography (OCT), OCT angiography (OCTA), and fundus autofluorescence (FAF)) in differentiating PCV from typical nAMD and predicting disease activity and prognosis. In particular, OCT shows tremendous potential in diagnosing PCV. Characteristics such as subretinal pigment epithelium (RPE) ring-like lesion, en face OCT-complex RPE elevation, and sharp-peaked pigment epithelial detachment provide high sensitivity and specificity for differentiating PCV from nAMD. With the use of more practical, non-ICGA imaging modalities, the diagnosis of PCV can be more easily made and treatment tailored as necessary for optimal outcomes.

Application effect of an artificial intelligence-based fundus screening system: evaluation in a clinical setting and population screening

BACKGROUND

To investigate the application effect of artificial intelligence (AI)-based fundus screening system in real-world clinical environment.

METHODS

A total of 637 color fundus images were included in the analysis of the application of the AI-based fundus screening system in the clinical environment and 20,355 images were analyzed in the population screening.

RESULTS

The AI-based fundus screening system demonstrated superior diagnostic effectiveness for diabetic retinopathy (DR), retinal vein occlusion (RVO) and pathological myopia (PM) according to gold standard referral. The sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of three fundus abnormalities were greater (all > 80%) than those for age-related macular degeneration (ARMD), referable glaucoma and other abnormalities. The percentages of different diagnostic conditions were similar in both the clinical environment and the population screening.

CONCLUSIONS

In a real-world setting, our AI-based fundus screening system could detect 7 conditions, with better performance for DR, RVO and PM. Testing in the clinical environment and through population screening demonstrated the clinical utility of our AI-based fundus screening system in the early detection of ocular fundus abnormalities and the prevention of blindness.

Polypoidal Choroidal Vasculopathy: An Update on Diagnosis and Treatment

Polypoidal choroidal vasculopathy (PCV) is a vascular disease of the choroid that leads to hemorrhagic and exudative macular degeneration. It may cause significant vision loss and thus affect the quality-of-life and psychological well-being. Non-invasive, non-ICGA-based OCT criteria have shown reliable results to plan adjunct photodynamic therapy (PDT) treatment, with the complete and consistent coverage of polypoidal lesions (PL) and branching neovascular network (BNN). The safety and efficacy of anti-vascular endothelial growth factor (anti-VEGF) monotherapy and its combination with verteporfin PDT have been established. However, treatment is still challenging due to frequent follow-ups, non-availability of PDT, and need for multiple anti-VEGF injection visits that increase the treatment burden and lead to patients being lost to follow-up. Effective treatments that prolong intervals between injections while maintaining vision and anatomical gains remain a critical unmet need. Longer acting molecules, like brolucizumab, have shown non-inferiority in BCVA gains and superior anatomical outcomes compared to other anti-VEGF agents. Newer therapies in the pipeline to enhance the efficacy and longevity of treatment include Faricimab and a port delivery system (PDS). This review summarizes the most recent diagnostic and treatment approaches in PCV to offer better treatment avenues.

Polypoidal Choroidal Vasculopathy Based on Non-ICGA Criteria in White Patients With Neovascular Age-Related Macular Degeneration

PURPOSE

To determine prevalence of probable polypoidal choroidal vasculopathy (PCV) among White patients with neovascular age-related macular degeneration (nAMD) using non-indocyanine green angiography (ICGA) criteria DESIGN: Multicenter, multinational, retrospective, cross-sectional study.

METHODS

A total of 208 treatment-naive eyes from Hispanic and non-Hispanic White individuals diagnosed with nAMD were included. All underwent color fundus photography (CFP), optical coherence tomography (OCT), and fluorescein angiography (FFA). De-identified images of study eyes were sent to 2 groups of graders. Group 1 reviewed CFP, OCT, and FFA to confirm nAMD diagnosis. Group 2 reviewed CFP and OCT to determine highly suggestive features for PCV. Probable PCV diagnosis defined as the presence of ≥2 of 4 highly suggestive features for PCV: notched or fibrovascular pigment epithelial detachment (PED) on CFP, sharply-peaked PED, notched PED, and hyperreflective ring on OCT.

RESULTS

Eleven eyes were excluded because of poor image quality (6) or non-nAMD diagnosis (5). Of 197 eligible eyes (197 patients), the mean age (SD) was 78.8 years (8.9), 44.2% were men, 26.4% were Hispanic, and 73.6% were non-Hispanic White individuals; 41.1%, 23.4%, 9.1%, and 2.5% had ≥1, ≥2, ≥3, and 4 highly suggestive features. Results showed that 23.4% (95% CI, 17.6%-29.9%) had probable PCV diagnosis. Predominantly occult CNV was more frequently found in probable PCV than nAMD subgroup (84.8% vs 64.9%, P = .01). Hispanic White individuals had a lower prevalence of probable PCV than non-Hispanic White individuals (9.6% vs 28.2%, P = .006) CONCLUSIONS: These findings suggest that probable PCV occurs between 17.6% and 29.9% in White individuals with nAMD, and more commonly in non-Hispanic than in Hispanic White individuals.

Current Trends in Clinical Characteristics, Diagnosis, and Treatment of Polypoidal Choroidal Vasculopathy: A Perspective from Vietnam

Polypoidal choroidal vasculopathy (PCV) is a common choroidal disease in the Asian population including Vietnam and is characterized by subretinal red-orange nodules, pigmented epithelium detachment, and massive subretinal hemorrhage. The recent focus on PCV in Vietnam can be attributed to advancements in PCV diagnosis and treatment. However, there is a scarcity of published literature and clinical data on PCV in the Vietnamese population, highlighting a key knowledge gap in this region. In order to address this gap, we gathered the opinions of experienced clinicians and retinal experts in Vietnam and reviewed available medical literature with the aim of: (i) providing an overview of PCV in the Vietnamese population—in terms of epidemiology, clinical characteristics, and management; (ii) tailoring international/national guidelines for the diagnosis and management of PCV, in line with available resources and medical equipment in Vietnam; and (iii) identifying gaps in clinical data in order to guide future PCV research in Vietnam and other countries with similar clinical conditions. The present review will enable healthcare providers and researchers to gain insight into current clinical practices and the limitations of PCV management in Vietnam and provide optimal and effective solutions.

Diagnostic Value of Spectral-Domain Optical Coherence Tomography for Polypoidal Choroidal Vasculopathy: A Systematic Review and Meta-Analysis

Purpose

To evaluate the diagnostic value of spectral-domain optical coherence tomography (SD-OCT) for polypoidal choroidal vasculopathy (PCV).

Methods

A search of electronic databases was conducted from 2010 to 2021 to review the relevant literature on SD-OCT to identify PCV and other lesions causing serious or serosanguinous retinal pigment epithelial detachment (PED), specifically neovascular age-related macular degeneration (nvAMD). The QUADAS-2 scale was used to evaluate the quality of the literature. We performed a meta-analysis, including heterogeneity tests, analyze and synthesize the study data, meta-regression analysis, subgroup analysis, Fagan's plot, sensitivity analysis and publication bias tests.

Results

A total of 12 related studies involving 1,348 eyes were included in this study, and the random-effects model was used for meta-analysis. The results showed that the pooled sensitivity of SD-OCT in the diagnosis of PCV was 0.87 (95% CI: 0.84–0.89), the pooled specificity was 0.83 (95% CI: 0.80–0.86), and the pooled positive/negative likelihood ratios were 5.38 (95% CI: 3.28–8.80) and 0.16 (95% CI: 0.10–0.25), respectively. The diagnostic odds ratio (DOR) was 36.07 (95% CI: 15.98–81.40), and the area under the sROC curve (AUC) was 0.9429. When the pre–test probability was set at 20%, the post-test positive and negative probabilities were 58% and 4%, respectively. Meta-regression indicated that race was the primary source of heterogeneity (P <0.05). The Deeks' funnel plot showed no significant publication bias in this study (P>0.05).

Conclusion

SD-OCT has high sensitivity and specificity for the diagnosis of PCV, as well as significant clinical applicability. Since color fundus photography (CFP) is more clinically available and can improve the diagnostic efficacy, we recommend SD-OCT combined with CFP to diagnose PCV, especially without indocyanine green angiography (ICGA).

Systematic Review Registration

https://inplasy.com/inplasy-2021-12-0048/, identifier: INPLASY2021120048.

Small dome-shaped pigment epithelium detachment in polypoidal choroidal vasculopathy: an under-recognized sign of polypoidal lesions on optical coherence tomography?

PURPOSE

To evaluate the diagnostic accuracy of spectral-domain optical coherence tomography (SD-OCT) and swept-source optical coherence tomographic angiography (SS-OCTA) to identify polypoidal lesions in serous or serosanguinous maculopathy.

MATERIALS AND METHODS

A retrospective review of patients presenting pigment epithelial detachments (PEDs) with the diagnosis of polypoidal choroidal vasculopathy (PCV), neovascular age-related macular degeneration (nAMD), and central serous chorioretinopathy (CSC), all of which underwent SD-OCT, SS-OCTA, and indocyanine green angiography (ICGA). Typical features of polypoidal lesions on SD-OCT included sharply peaked PED, notched PED, and hyperreflective ring underneath PED. SS-OCTA feature was vascularized PEDs on cross-sectional images corresponding to cluster-like structures on en face images. The parameters of PEDs were measured for analysis.

RESULTS

Of 72 eyes, 30 had PCV, 22 had nAMD, and 20 had CSC. A total of 128 localized PEDs were detected on SD-OCT. Typical features on SD-OCT had a high specificity (94.0%) but a limited sensitivity (73.8%). SS-OCTA features provided a higher sensitivity (96.7%). PEDs of the polypoidal lesions unrecognized by SD-OCT were dome-shaped, with smaller ratio of height to base diameter and less area, and almost had heterogeneous internal reflectivity and a connected double-layer sign. Some lesions misidentified by SS-OCTA developed into ICGA-proven polypoidal lesions at follow-up visits.

CONCLUSION

A small dome-shaped PED with heterogeneous internal reflectivity and a connected double-layer sign on SD-OCT may suggest a polypoidal lesion of PCV. SS-OCTA may be a helpful tool to investigate preclinical PCV and observe the formation of polypoidal lesions.

Optical coherence tomography in diagnosing polypoidal choroidal vasculopathy. Looking into the future: a systematic review and meta-analysis

Background

Polypoidal choroidal vasculopathy (PCV) is an exudative maculopathy with features similar to wet age macular degeneration. The incidence of PCV is known to be higher in the Asian population compared to Caucasians. Imaging modality is needed to make the diagnosis of PCV. Although Indocyanine green angiography (ICGA) is still the gold standard, it is not routinely performed in vitreoretinal practice. Thus another imaging modality is currently a popular research area. Spectral domain optical coherence tomography (SD-OCT) has emerged as a new imaging modality mostly available in clinics. Some studies have reported the sensitivity and specificity of SD-OCT in diagnosing PCV with different results and thresholds.

Methods

Relevant studies from PubMed, Science Direct and Google Scholar databases were systematically searched. In random effect models using STATA 14 software, a meta-analysis was performed to determine the pooled diagnostic accuracy. QUADAS 2 was used to evaluate the risk of bias of each study by Revman 5.4 software.

Results

Seven eligible studies which met the inclusion and exclusion criteria were enrolled in this study. A total of 911 eyes were included to investigate the diagnostic accuracy of SD-OCT. As a result, the pooled sensitivity was 0.91 (95% CI 0.87–0.93), specificity 0.88 (95% 0.83–0.92), positive likelihood ratio 8, negative likelihood ratio 11, the area under the summary receiver operating characteristic curve 0.95 (95% CI 0.93–0.97), and diagnostic odds ratio 71.81 (95% CI 38.89–132.74).

Conclusion

SD-OCT provided a high diagnostic value for detecting PCV. Sharply peaked pigment epithelial detachment (PED), notched PED, bubble sign, multiple PED, and double-layer sign were the most common features found in PCV.

Diagnosis of Polypoidal Choroidal Vasculopathy From Fluorescein Angiography Using Deep Learning

Purpose

To differentiate polypoidal choroidal vasculopathy (PCV) from choroidal neovascularization (CNV) and to determine the extent of PCV from fluorescein angiography (FA) using attention-based deep learning networks.

Methods

We build two deep learning networks for diagnosis of PCV using FA, one for detection and one for segmentation. Attention-gated convolutional neural network (AG-CNN) differentiates PCV from other types of wet age-related macular degeneration. Gradient-weighted class activation map (Grad-CAM) is generated to highlight important regions in the image for making the prediction, which offers explainability of the network. Attention-gated recurrent neural network (AG-PCVNet) for spatiotemporal prediction is applied for segmentation of PCV.

Results

AG-CNN is validated with a dataset containing 167 FA sequences of PCV and 70 FA sequences of CNV. AG-CNN achieves a classification accuracy of 82.80% at image-level, and 86.21% at patient-level for PCV. Grad-CAM shows that regions contributing to decision-making have on average 21.91% agreement with pathological regions identified by experts. AG-PCVNet is validated with 56 PCV sequences from the EVEREST-I study and achieves a balanced accuracy of 81.132% and dice score of 0.54.

Conclusions

The developed software provides a means of performing detection and segmentation of PCV on FA images for the first time. This study is a promising step in changing the diagnostic procedure of PCV and therefore improving the detection rate of PCV using FA alone.

Translational Relevance

The developed deep learning system enables early diagnosis of PCV using FA to assist the physician in choosing the best treatment for optimal visual prognosis.

Artificial intelligence applied to ophthalmology and optometry: A citation network analysis

PURPOSE

The objective of this study is to analyse co-authorship and co-citation networks of publications in the field of artificial intelligence in ophthalmology and optometry. As well as, identify the different areas of research and the most cited publication.

METHOD

A search of publications was performed in the Web of Science database for the period from 1977 to December 2021, using the term "Artificial Intelligence AND (Ophthalmol* OR optometry)". The analysis of the publication was carried out using the Citation Network Explorer, VOSviewer and CiteSpace software.

RESULTS

1086 publications and 2348 citation networks were found. 2020 was the year with the highest number of publications, a total of 351 publications and 115 citation networks. The most cited publication was "Clinically applicable deep learning for diagnosis and referral in retinal disease" published by De Fauw et al. in 2018, with a citation index of 723. Through the clustering function, three groups were found that cover the main research areas in this field: retinal pathology, anterior segment and glaucoma.

CONCLUSIONS

The citation network analysis offers an in-depth analysis of scientific publications and the adoption of new topics and fields of research. The results of an exhaustive analysis of citation networks in artificial intelligence in the field of ophthalmology and optometry are presented since the publication of the first article in 1977.

SENSITIVITY AND SPECIFICITY OF MULTISPECTRAL IMAGING FOR POLYPOIDAL CHOROIDAL VASCULOPATHY

PURPOSE

To evaluate the sensitivity and specificity of multispectral imaging (MSI), a noninvasive imaging technique composed of a series of monochromatic scanning light, for polypoidal choroidal vasculopathy (PCV).

METHODS

This was a prospective observational study. Polypoidal lesions on MSI are defined by oval or lobular hyperreflective oval lesion with dark hyporeflective center. Branching vascular networks on MSI is featured by hyperreflective interlacing signal. Detection sensitivity and specificity of polypoidal lesions was compared with indocyanine green angiography, whereas sensitivity and specificity of branching vascular networks, subretinal fluid, and pigment epithelium detachment were compared with optical coherence tomography.

RESULTS

Among 67 eyes, 38 eyes (56.7%) were diagnosed with PCV, 7 eyes (10.4%) with neovascular age-related macular degeneration, 13 eyes (19.4%) with central serous chorioretinopathy, 6 eyes (9.0%) with pathological myopia, and 3 eyes (4.5%) with idiopathic choroidal neovascularization. Compared with indocyanine green angiography, the sensitivity and specificity for diagnosing PCV by MSI alone was 84.21% and 93.10%, respectively, and the positive predictive value and the negative predictive value for PCV by MSI was 94.12% and 81.82%, respectively. The sensitivity and specificity for detecting polypoidal lesions were 84.21% and 93.10% compared with indocyanine green angiography. Compared with optical coherence tomography, the sensitivity and specificity for detecting branching vascular networks were 95.83% and 88.37%, for the subretinal fluid were 76.92% and 86.67%, and for the pigment epithelium detachment were 91.11% and 90.91%, respectively.

CONCLUSION

Multispectral imaging allowed noninvasive visualization of polypoidal lesions and branching vascular networks and may serve as a new diagnostic option for PCV.

Therapeutic Effect of Abelmoschus manihot on Type 2 Diabetic Nonproliferative Retinopathy and the Involvement of VEGF

Objective

To evaluate the efficacy of Abelmoschus manihot in treating type 2 diabetic nonproliferative retinopathy.

Methods

It was a randomized controlled clinical trial. The recruited eighty subjects with type 2 diabetic nonproliferative retinopathy were randomly divided into treatment group and control group. The two groups received basic treatments including control of blood glucose, blood pressure and blood lipid, management of diet, exercise and health education, and monitoring of relevant indicators. Additionally, the treatment group was given oral administration of Abelmoschus manihot. All subjects were followed up on monthly basis for consecutive six months. The related parameters including diabetic retinopathy (DR) incidence rates, “Early Treatment Diabetic Retinopathy Study” (ETDRS) vision scores, retinal thicknesses in macular region, serum vascular endothelial growth factor (VEGF) levels, and biochemical indicators of both groups before and after treatment were accurately collected and statistically analyzed.

Results

There were no significant differences of DR severity levels, ETDRS vision scores, macular retinal thicknesses such as cube average thickness (CAT), central subfield thickness (CST), and cube volume (CV), and serum VEGF levels between two groups before treatment. Meanwhile, there were no significant differences of demographic characteristics, case terminations, blood glucose, blood lipid, blood pressure, biochemical indicators of hepatorenal function, hypoglycemic drugs, hypotensive drugs, and other basic treatments between two groups during six months treatment. The present study suggested that the remission rate of DR and the ETDRS vision score in the treatment group were significantly higher than those of the control group (remission rate: 25.4% vs 9.3%, P=0.01; ETDRS score: 78 (72, 82) vs 72 (67, 80), P=0.0002) while the progression rate of DR in the treatment group was significantly lower than that of the control group (progression rate: 4.2% vs 18.7%, P=0.007) after six months treatment. In addition, the CAT, CST, CV, and serum VEGF levels of the treatment group were significantly improved after the treatment (CAT: 286 (278, 302) vs 282 (270, 295) μm, P < 0.0001; CST: 251 (239, 274) vs 248 (235, 265) μm, P < 0.0001; CV: 10.3 (10.0, 10.9) vs 10.1 (9.7, 10.6) mm³, P < 0.0001; VEGF: 0.21 (0.14, 0.58) vs 0.16 (0.10, 0.23) ng/ml, P=0.0026), while there were no significant differences of the control group before and after treatment (CAT: 287 (279, 294) vs 287 (279, 295) μm, P=0.27; CST: 250 (240, 266) vs 252 (238, 266) μm, P=0.72; CV: 10.4 (10.1, 10.6) vs 10.4 (10.1, 10.7) mm³, P=0.53; VEGF: 0.21 (0.13, 0.66) vs 0.23 (0.12, 0.64) ng/ml, P=0.85).

Conclusion

The study offered the novel evidence for the therapeutic effect of Abelmoschus manihot on type 2 diabetic nonproliferative retinopathy, which was associated with improved VEGF. This trial is registered with ChiCTR1800019292.

Latest Developments in Polypoidal Choroidal Vasculopathy: Epidemiology, Etiology, Diagnosis, and Treatment

Polypoidal choroidal vasculopathy (PCV) is a condition characterized by multiple, recurrent, serosanguineous pigment epithelial detachments, and neurosensory retinal detachments due to abnormal aneurysmal neovascular lesions. It is generally considered as a variant of neovascular age-related macular degeneration, but there are some differences between the clinical presentation, natural history, and treatment response between patients with PCV and typical neovascular age-related macular degeneration patients. Over the past decade, new research and technological advancements have greatly improved our understanding of the PCV disease process and the management of PCV. This review aims to summarize the recent research findings to highlight the epidemiology, pathogenesis, genetics, the application of various diagnostic tools for PCV, and the available treatment options for PCV.

Application of machine learning in ophthalmic imaging modalities

In clinical ophthalmology, a variety of image-related diagnostic techniques have begun to offer unprecedented insights into eye diseases based on morphological datasets with millions of data points. Artificial intelligence (AI), inspired by the human multilayered neuronal system, has shown astonishing success within some visual and auditory recognition tasks. In these tasks, AI can analyze digital data in a comprehensive, rapid and non-invasive manner. Bioinformatics has become a focus particularly in the field of medical imaging, where it is driven by enhanced computing power and cloud storage, as well as utilization of novel algorithms and generation of data in massive quantities. Machine learning (ML) is an important branch in the field of AI. The overall potential of ML to automatically pinpoint, identify and grade pathological features in ocular diseases will empower ophthalmologists to provide high-quality diagnosis and facilitate personalized health care in the near future. This review offers perspectives on the origin, development, and applications of ML technology, particularly regarding its applications in ophthalmic imaging modalities.

Sensitivity and Specificity of Potential Diagnostic Features Detected Using Fundus Photography, Optical Coherence Tomography, and Fluorescein Angiography for Polypoidal Choroidal Vasculopathy

Importance

The use of indocyanine green angiography (ICGA) is a criterion standard for diagnosing polypoidal choroidal vasculopathy (PCV), an endemic and common cause of vision loss in Asian and African individuals that also presents in white individuals. However, the use of ICGA is expensive, invasive, and not always available at clinical centers. Therefore, knowing the value of certain features detected using fundus photography (FP), optical coherence tomography (OCT), and fluorescein angiography (FA) to diagnose PCV without ICGA could assist ophthalmologists to identify PCV when ICGA is not readily available.

Objective

To explore the sensitivity, specificity, and predictive accuracy of potential diagnostic features detected using FP, OCT, and FA in diagnosing PCV without ICGA.

Design, Setting, and Participants

Deidentified images of FP alone, OCT alone, and FA alone were graded by 3 retina specialists masked to ICGA findings for potentially diagnostic features of PCV prespecified before grading compared with the criterion standard grading of 2 other retina specialists with access simultaneously to FP, OCT, FA and ICGA. Specialists graded images of 124 eyes of 120 patients presenting between January 1, 2013, and December 31, 2016, with newly identified serous or serosanguinous maculopathy who had undergone FP, OCT, FA, and ICGA before treatment at a large referral eye center in Thailand.

Main Outcomes and Measures

Sensitivity, specificity, positive predictive value, negative predictive value, and predictive accuracy from the area under the receiver operating characteristic curve (AUC).

Results

The mean (SD) age of the patients was 57.7 (12.6) years, 52 were women, 68 were men, and the diagnosis (from ICGA) was PCV for 65 eyes (52.4%), central serous chorioretinopathy for 45 eyes (36.3%), and typical neovascular age-related macular degeneration for 12 eyes (9.7%). With the use of FP, a potential diagnostic feature for PCV was notched or hemorrhagic pigment epithelial detachment (AUC, 0.77; 95% CI, 0.70-0.85). With the use of OCT, potential diagnostic features for PCV were pigment epithelial detachment notch (AUC, 0.90; 95% CI, 0.85-0.96), sharply peaked pigment epithelial detachment (AUC, 0.86; 95% CI, 0.80-0.92), and a hyperreflective ring (AUC, 0.86; 95% CI, 0.80-0.92). When at least 2 of these 4 signs were present, the AUC was 0.93 (95% CI, 0.89-0.98), with a sensitivity of 0.95 (95% CI, 0.87-0.99), a specificity of 0.95 (95% CI, 0.82-0.97), a positive predictive value of 0.92 (95% CI, 0.83-0.97), and a negative predictive value of 0.95 (95% CI, 0.86-0.99).

Conclusions and Relevance

These data suggest that the potential diagnostic features detected using FP and OCT provide high sensitivity and specificity for a diagnosis of PCV, especially when at least 2 of 4 highly suggestive signs are present.

Polypoidal Choroidal Vasculopathy in Congolese Patients

Purpose

Polypoidal choroidal vasculopathy (PCV) is a visually debilitating disease that mostly affects people of African and Asian heritage. Indocyanine green angiography (ICGA) is the recommended exploratory method for definitive diagnosis. The disease has been extensively described in Asians and Caucasians, but not in Africans. This study was conducted to document the clinical presentation and optical coherence tomography features of polypoidal choroidal vasculopathy (PCV) in Congolese patients.

Methods

A prospective case series of patients with PCV was performed between January 2017 and June 2019. Routine ocular examination was performed including best corrected visual acuity measurement, slit-lamp examination, dilated direct fundoscopy, and spectral domain optical coherence tomography (OCT). The diagnosis was based on a combination of clinical and OCT signs.

Results

Fourteen patients were diagnosed with PCV during this period. The average age was 64.7 ± 6.9 years. There were 8 females. Ten (71.4%) patients had systemic hypertension. Most patients (n = 9, 64.3%) had bilateral involvement. Blurred vision was the most common complaint (71.4%). The main clinical presentation was subretinal exudates, seen in 19 (82.6%) eyes of 11 (78.6%) patients and subretinal hemorrhage in 10 (43.5%) eyes. Macular localization was found in 16 eyes (69.5%) of 12 (85.7%) patients. Drusen were observed in 35.7% of the patients. On OCT imaging, thumb-like pigment epithelial detachment and subretinal exudation were the most frequent features, observed in 92.9% and 71.4% of the patients, respectively.

Conclusions

PCV in Congolese patients showed features that are more similar to those observed in Caucasians. In this setting where indocyanine green angiography is not available, OCT facilitates the diagnosis of PCV.

Noninvasive multimodal imaging in diagnosing polypoidal choroidal vasculopathy

PURPOSE

To investigate the diagnostic accuracy of noninvasive multimodal imaging methods in diagnosing polypoidal choroidal vasculopathy (PCV) and distinguishing PCV from typical neovascular age-related macular degeneration (nvAMD).

METHODS

Retrospective study. Imaging features of noninvasive multimodal imaging methods, including fundus photography (FP), B-scan optical coherence tomography (OCT), en face OCT, OCT angiography, and autofluorescence, of 103 eyes with PCV or typical nvAMD were reviewed. Diagnostic strategy was established based on imaging features and was validated in other 105 eyes with PCV or typical nvAMD.

RESULTS

Features of subretinal orange nodule on FP, thumb-like PED on OCT, notched PED on OCT, bubble sign on OCT, and Bruch's membrane depression under serosanguinous PED on OCT were more common. When the diagnostic strategy of using at least 2 of 5 features was performed, there is 0.88 sensitivity and 0.92 specificity for diagnosing PCV. The results of the validation test further confirmed the diagnostic strategy with 0.94 sensitivity and 0.93 specificity.

CONCLUSIONS

Noninvasive multimodal imaging, especially FP and B-scan OCT, provide high sensitivity and specificity for diagnosing PCV and distinguishing PCV from typical nvAMD, when at least 2 of 5 suggestive imaging features are present.