Integrated image-based deep learning and language models for primary diabetes care.

Primary diabetes care and diabetic retinopathy (DR) screening persist as major public health challenges due to a shortage of trained primary care physicians (PCPs), particularly in low-resource settings. Here, to bridge the gaps, we developed an integrated image-language system (DeepDR-LLM), combining a large language model (LLM module) and image-based deep learning (DeepDR-Transformer), to provide individualized diabetes management recommendations to PCPs. In a retrospective evaluation, the LLM module demonstrated comparable performance to PCPs and endocrinology residents when tested in English and outperformed PCPs and had comparable performance to endocrinology residents in Chinese. For identifying referable DR, the average PCP's accuracy was 81.0% unassisted and 92.3% assisted by DeepDR-Transformer. Furthermore, we performed a single-center real-world prospective study, deploying DeepDR-LLM. We compared diabetes management adherence of patients under the unassisted PCP arm (n = 397) with those under the PCP+DeepDR-LLM arm (n = 372). Patients with newly diagnosed diabetes in the PCP+DeepDR-LLM arm showed better self-management behaviors throughout follow-up (P < 0.05). For patients with referral DR, those in the PCP+DeepDR-LLM arm were more likely to adhere to DR referrals (P < 0.01). Additionally, DeepDR-LLM deployment improved the quality and empathy level of management recommendations. Given its multifaceted performance, DeepDR-LLM holds promise as a digital solution for enhancing primary diabetes care and DR screening.

Deep learning-based image quality assessment for optical coherence tomography macular scans: a multicentre study.

AIMS: To develop and externally test deep learning (DL) models for assessing the image quality of three-dimensional (3D) macular scans from Cirrus and Spectralis optical coherence tomography devices. METHODS: We retrospectively collected two data sets including 2277 Cirrus 3D scans and 1557 Spectralis 3D scans, respectively, for training (70%), fine-tuning (10%) and internal validation (20%) from electronic medical and research records at The Chinese University of Hong Kong Eye Centre and the Hong Kong Eye Hospital. Scans with various eye diseases (eg, diabetic macular oedema, age-related macular degeneration, polypoidal choroidal vasculopathy and pathological myopia), and scans of normal eyes from adults and children were included. Two graders labelled each 3D scan as gradable or ungradable, according to standardised criteria. We used a 3D version of the residual network (ResNet)-18 for Cirrus 3D scans and a multiple-instance learning pipline with ResNet-18 for Spectralis 3D scans. Two deep learning (DL) models were further tested via three unseen Cirrus data sets from Singapore and five unseen Spectralis data sets from India, Australia and Hong Kong, respectively. RESULTS: In the internal validation, the models achieved the area under curves (AUCs) of 0.930 (0.885-0.976) and 0.906 (0.863-0.948) for assessing the Cirrus 3D scans and Spectralis 3D scans, respectively. In the external testing, the models showed robust performance with AUCs ranging from 0.832 (0.730-0.934) to 0.930 (0.906-0.953) and 0.891 (0.836-0.945) to 0.962 (0.918-1.000), respectively. CONCLUSIONS: Our models could be used for filtering out ungradable 3D scans and further incorporated with a disease-detection DL model, allowing a fully automated eye disease detection workflow.

Displacement of Submacular Hemorrhage Using Subretinal Cocktail Injection versus Pneumatic Displacement: A Real-World Comparative Study.

INTRODUCTION: The objective of this study was to compare the outcome of submacular hemorrhage (SMH) displacement using pneumatic displacement with intravitreal expansile gas versus pars plana vitrectomy (PPV) with subretinal injection of tissue plasminogen activator (tPA), anti-vascular endothelial growth factor (VEGF) agent, and air as primary surgery. METHODS: Retrospective interventional case series of 63 patients who underwent surgical displacement of SMH secondary to neovascular age-related macular degeneration (nAMD) or polypoidal choroidal vasculopathy (PCV) from May 1, 2015, to October 31, 2022. Medical records were reviewed for diagnosis, logMAR visual acuity (VA), central subfield thickness (CST), and postoperative displacement rates and complications up to 12 months after operation. RESULTS: The diagnosis was nAMD in 24 (38.1%) and PCV in 39 (61.9%) eyes. There were 40 (63.5%) eyes in the pneumatic displacement group (38 received C3F8, 2 received SF6) and 23 (36.5%) eyes in the subretinal cocktail injection. Mean baseline VA was 1.46 and 1.62, respectively (p = 0.404). The subretinal injection group had more extensive SMH (p = 0.005), thicker CST (1,006.6 µm vs. 780.2 µm, p = 0.012), and longer interval between symptom and operation (10.65 vs. 5.53 days, p < 0.001). The mean postoperative VA at 6 months was 0.67 and 0.91 (p = 0.180) for pneumatic displacement and subretinal injection groups, respectively, though VA was significantly better in the pneumatic group at 12-month visit (0.64 vs. 1.03, p = 0.040). At least 10 mean change in VA were >10 letters gain in both groups up to 12 months. Postoperative CST reduction was greater (625.1 µm vs. 326.5 µm, p = 0.008) and complete foveal displacement (87.0% vs. 37.5%), p < 0.001, odds ratio [OR] = 11.1) and displacement to arcade or beyond (52.5% vs. 17.5%, p = 0.009, OR = 5.15) were more frequent in the subretinal injection group. Two patients with failed pneumatic displacement were successfully treated with subretinal cocktail injection as a second operation. CONCLUSION: Surgical displacement of SMH leads to clinically meaningful improvement in VA. PPV with subretinal cocktail injection is more effective than pneumatic displacement in displacing SMH with similar safety profile despite longer interval before operation, higher CST, and more extensive SMH at baseline. Retinal surgeons could consider this novel technique in cases with thick and extensive SMH or as a rescue secondary operation in selected cases.

Performance of Artificial Intelligence in Detecting Diabetic Macular Edema From Fundus Photography and Optical Coherence Tomography Images: A Systematic Review and Meta-analysis.

BACKGROUND: Diabetic macular edema (DME) is the leading cause of vision loss in people with diabetes. Application of artificial intelligence (AI) in interpreting fundus photography (FP) and optical coherence tomography (OCT) images allows prompt detection and intervention. PURPOSE: To evaluate the performance of AI in detecting DME from FP or OCT images and identify potential factors affecting model performances. DATA SOURCES: We searched seven electronic libraries up to 12 February 2023. STUDY SELECTION: We included studies using AI to detect DME from FP or OCT images. DATA EXTRACTION: We extracted study characteristics and performance parameters. DATA SYNTHESIS: Fifty-three studies were included in the meta-analysis. FP-based algorithms of 25 studies yielded pooled area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of 0.964, 92.6%, and 91.1%, respectively. OCT-based algorithms of 28 studies yielded pooled AUROC, sensitivity, and specificity of 0.985, 95.9%, and 97.9%, respectively. Potential factors improving model performance included deep learning techniques, larger size, and more diversity in training data sets. Models demonstrated better performance when validated internally than externally, and those trained with multiple data sets showed better results upon external validation. LIMITATIONS: Analyses were limited by unstandardized algorithm outcomes and insufficient data in patient demographics, OCT volumetric scans, and external validation. CONCLUSIONS: This meta-analysis demonstrates satisfactory performance of AI in detecting DME from FP or OCT images. External validation is warranted for future studies to evaluate model generalizability. Further investigations may estimate optimal sample size, effect of class balance, patient demographics, and additional benefits of OCT volumetric scans.

Optical coherence tomography in the management of diabetic macular oedema.

Diabetic macular oedema (DMO) is the major cause of visual impairment in people with diabetes. Optical coherence tomography (OCT) is now the most widely used modality to assess presence and severity of DMO. DMO is currently broadly classified based on the involvement to the central 1 mm of the macula into non-centre or centre involved DMO (CI-DMO) and DMO can occur with or without visual acuity (VA) loss. This classification forms the basis of management strategies of DMO. Despite years of research on quantitative and qualitative DMO related features assessed by OCT, these do not fully inform physicians of the prognosis and severity of DMO relative to visual function. Having said that, recent research on novel OCT biomarkers development and re-defined classification of DMO show better correlation with visual function and treatment response. This review summarises the current evidence of the association of OCT biomarkers in DMO management and its potential clinical importance in predicting VA and anatomical treatment response. The review also discusses some future directions in this field, such as the use of artificial intelligence to quantify and monitor OCT biomarkers and retinal fluid and identify phenotypes of DMO, and the need for standardisation and classification of OCT biomarkers to use in future clinical trials and clinical practice settings as prognostic markers and secondary treatment outcome measures in the management of DMO.

What can GPT-4 do for Diagnosing Rare Eye Diseases? A Pilot Study.

INTRODUCTION: Generative pretrained transformer-4 (GPT-4) has gained widespread attention from society, and its potential has been extensively evaluated in many areas. However, investigation of GPT-4's use in medicine, especially in the ophthalmology field, is still limited. This study aims to evaluate GPT-4's capability to identify rare ophthalmic diseases in three simulated scenarios for different end-users, including patients, family physicians, and junior ophthalmologists. METHODS: We selected ten treatable rare ophthalmic disease cases from the publicly available EyeRounds service. We gradually increased the amount of information fed into GPT-4 to simulate the scenarios of patient, family physician, and junior ophthalmologist using GPT-4. GPT-4's responses were evaluated from two aspects: suitability (appropriate or inappropriate) and accuracy (right or wrong) by senior ophthalmologists (> 10 years' experiences). RESULTS: Among the 30 responses, 83.3% were considered "appropriate" by senior ophthalmologists. In the scenarios of simulated patient, family physician, and junior ophthalmologist, seven (70%), ten (100%), and eight (80%) responses were graded as "appropriate" by senior ophthalmologists. However, compared to the ground truth, GPT-4 could only output several possible diseases generally without "right" responses in the simulated patient scenarios. In contrast, in the simulated family physician scenario, 50% of GPT-4's responses were "right," and in the simulated junior ophthalmologist scenario, the model achieved a higher "right" rate of 90%. CONCLUSION: To our knowledge, this is the first proof-of-concept study that evaluates GPT-4's capacity to identify rare eye diseases in simulated scenarios involving patients, family physicians, and junior ophthalmologists. The results indicate that GPT-4 has the potential to serve as a consultation assisting tool for patients and family physicians to receive referral suggestions and an assisting tool for junior ophthalmologists to diagnose rare eye diseases. However, it is important to approach GPT-4 with caution and acknowledge the need for verification and careful referrals in clinical settings.

Pathogenesis of myopic choroidal neovascularization: A systematic review and meta-analysis.

Myopic choroidal neovascularization (CNV) is a vision-threatening complication of high myopia. Here, we systematically review cohort, case-control, and cross-sectional studies in PubMed, Embase, and Web of Science, and summarize the associated factors of myopic CNV using meta-analysis where applicable. Among 1,333 records assessed, 50 were found eligible, all having a low-to-moderate risk of bias. Highly myopic eyes with CNV had a higher risk of lacquer cracks (odds ratio = 2.88) and patchy chorioretinal atrophy (odds ratio = 3.43) than those without. The mean posterior staphyloma height (µm) was greater in myopic CNV eyes than in highly myopic eyes without CNV (mean difference = 82.03). The thinning of choroidal thickness (µm) between myopic eyes with and without CNV differed significantly (mean difference = -47.76). The level of vascular endothelial growth factor (pg/ml) in the aqueous humor of myopic CNV eyes was significantly higher than in highly myopic eyes without CNV (mean difference = 24.98), the same as interleukin-8 (IL-8) (pg/ml, mean difference = 7.73). Single-nucleotide polymorphisms in the vascular endothelial growth factor, complement factor I, and collagen type VIII alpha 1 genes were associated with myopic CNV. We found that myopic CNV eyes have a higher ratio of lacquer cracks and patchy chorioretinal atrophy, thinner choroid, greater posterior staphyloma height, and a higher level of vascular endothelial growth factor and IL-8 in aqueous. Structural predisposing lesions, hemodynamic, genetic, and systemic factors are also associated with myopic CNV.

Assessment of Parafoveal Diabetic Macular Ischemia on Optical Coherence Tomography Angiography Images to Predict Diabetic Retinal Disease Progression and Visual Acuity Deterioration.

Importance: The presence of diabetic macular ischemia (DMI) on optical coherence tomography angiography (OCTA) images predicts diabetic retinal disease progression and visual acuity (VA) deterioration, suggesting an OCTA-based DMI evaluation can further enhance diabetic retinopathy (DR) management. Objective: To investigate whether an automated binary DMI algorithm using OCTA images provides prognostic value on DR progression, diabetic macular edema (DME) development, and VA deterioration in a cohort of patients with diabetes. Design, Setting, and Participants: In this cohort study, DMI assessment of superficial capillary plexus and deep capillary plexus OCTA images was performed by a previously developed deep learning algorithm. The presence of DMI was defined as images exhibiting disruption of fovea avascular zone with or without additional areas of capillary loss, while absence of DMI was defined as images presented with intact fovea avascular zone outline and normal distribution of vasculature. Patients with diabetes were recruited starting in July 2015 and were followed up for at least 4 years. Cox proportional hazards models were used to evaluate the association of the presence of DMI with DR progression, DME development, and VA deterioration. Analysis took place between June and December 2022. Main Outcomes and Measures: DR progression, DME development, and VA deterioration. Results: A total of 321 eyes from 178 patients were included for analysis (85 [47.75%] female; mean [SD] age, 63.39 [11.04] years). Over a median (IQR) follow-up of 50.41 (48.16-56.48) months, 105 eyes (32.71%) had DR progression, 33 eyes (10.28%) developed DME, and 68 eyes (21.18%) had VA deterioration. Presence of superficial capillary plexus-DMI (hazard ratio [HR], 2.69; 95% CI, 1.64-4.43; P < .001) and deep capillary plexus-DMI (HR, 3.21; 95% CI, 1.94-5.30; P < .001) at baseline were significantly associated with DR progression, whereas presence of deep capillary plexus-DMI was also associated with DME development (HR, 4.60; 95% CI, 1.15-8.20; P = .003) and VA deterioration (HR, 2.12; 95% CI, 1.01-5.22; P = .04) after adjusting for age, duration of diabetes, fasting glucose, glycated hemoglobin, mean arterial blood pressure, DR severity, ganglion cell-inner plexiform layer thickness, axial length, and smoking at baseline. Conclusions and Relevance: In this study, the presence of DMI on OCTA images demonstrates prognostic value for DR progression, DME development, and VA deterioration.

Recent Advances in Clinical Applications of Imaging in Retinal Diseases.

Many diseases that cause visual impairment, as well as systemic conditions, manifest in the posterior segment of the eye. With the advent of high-speed, high-resolution, reliable, and noninvasive imaging techniques, ophthalmologists are becoming more dependent on ocular imaging for disease diagnosis, classification, and management in clinical practice. There are rapid advances on the indications of multimodal retinal imaging techniques, including the application of ultra-widefield fundus angiography, fundus autofluorescence, optical coherence tomography, as well as optical coherence tomography angiography. This review summarizes and highlights the clinical applications, latest indications, and interpretations of multimodal imaging in age-related macular degeneration, polypoidal choroidal vasculopathy, diabetic macular edema, central serous chorioretinopathy, diabetic retinopathy, retinal vein occlusion, and uveitis.

OCT-based biomarkers for predicting treatment response in eyes with centre-involved diabetic macular oedema treated with anti-VEGF injections: a real-life retina clinic-based study.

BACKGROUND/AIMS: To determine whether a combination of baseline and change in spectral domain-optical coherence tomography (SD-OCT)-based biomarkers can predict visual outcomes in eyes with diabetic macular oedema (DMO) treated with antivascular endothelial growth factors (VEGF) injections. METHODS: This is a retrospective cohort study conducted in Hong Kong, China. 196 eyes with centre-involving DMO, who received anti-VEGF injections between 1 January 2011 and 30 June 2018 were recruited. Medical records of the participants were retrieved retrospectively, visual acuity (VA) at baseline, 6, 12 and 24 months and SD-OCT before initiation and after completion of anti-VEGF treatment were obtained. The SD-OCT images were evaluated for the morphology of DMO, vitreomacular status, presence of disorganisation of retinal inner layers (DRIL), sizes of intraretinal cysts, visibility of external limiting membrane (ELM), ellipsoid zone (EZ) and cone outer segment tip (COST) and the presence of hyper-reflective foci in retina or the choroid. RESULTS: The presence of baseline DRIL, hyper-reflective foci in retina and disruption of ELM/EZ and COST were associated with worse baseline and subsequent VA up to 24 months after treatment. Improvement in DRIL (p=0.048), ELM/EZ (p=0.001) and COST (p=0.002) disruption after treatment was associated with greater improvement in VA at 12 months. Eyes with cystoid macular oedema (p=0.003, OR=8.18) and serous retinal detachment (p=0.011, OR=4.84) morphology were more likely to achieve at least 20% reduction in central subfield thickness. CONCLUSION AND RELEVANCE: Baseline SD-OCT biomarkers and their subsequent change predict VA and improvement in vision in eyes with DMO treated with anti-VEGF injections. We proposed an SD-OCT-based system that can be readily used in real-life eye clinics to improve decision making in the management of DMO.

Massive retinal infiltrates as the presenting sign of chronic myeloid leukemia: Clinical and imaging features of leukemic retinopathy.

PURPOSE: To describe the clinical and optical coherence tomography (OCT) features of two cases with bilateral diffuse retinal infiltrates as the only presenting feature of chronic myeloid leukemia (CML) on initial diagnosis and upon relapse. METHODS: We reported two patients with CML, one at initial diagnosis and one in remission who presented with bilateral subacute visual impairment. Fundal examination revealed bilateral symmetrical leukostatic appearance with increased vascular tortuosity, diffuse retinal infiltrates with size up to 6 disk diameters, retinal hemorrhages, and Roth's spots. OCT showed multiple intra-retinal hyper-reflective foci corresponding to intra-retinal hemorrhages, and outer retinal hyper-reflective foci in area corresponding to retinal infiltrate. The different retinal layers were relatively preserved and distinguishable. RESULTS: White cell count (WCC) were elevated in both patients ranging from 544 to 810 × 109/L. Bone marrow biopsy confirmed the diagnosis of CML in the patient without prior diagnosis and relapse of CML in another patient. Cytogenetic test detected Abelson murine leukemia (ABL) - breakpoint cluster region (BCR) fusion transcript in both cases. Both patients were started on oral imatinib, subsequently WCC returned to within normal values in both cases. Vision and OCT abnormalities improved and reduction in retinal hemorrhages and infiltrates were observed in follow up. CONCLUSION: This report highlights the important role of ophthalmologists and detailed fundus examination in making a prompt diagnosis of leukemia in patients with visual complaints. Appropriate systemic investigation and hematologist referrals for prompt treatment of CML may improve survival rate and preserve vision.

Clinically relevant factors associated with a binary outcome of diabetic macular ischaemia: an OCTA study.

AIMS: We investigated the demographic, ocular, diabetes-related and systemic factors associated with a binary outcome of diabetic macular ischaemia (DMI) as assessed by optical coherence tomography angiography (OCTA) evaluation of non-perfusion at the level of the superficial capillary plexus (SCP) and deep capillary plexus (DCP) in a cohort of patients with diabetes mellitus (DM). MATERIALS AND METHODS: 617 patients with DM were recruited from July 2015 to December 2020 at the Chinese University of Hong Kong Eye Centre. Image quality assessment (gradable or ungradable for assessing DMI) and DMI evaluation (presence or absence of DMI) were assessed at the level of the SCP and DCP by OCTA. RESULTS: 1107 eyes from 593 subjects were included in the final analysis. 560 (50.59%) eyes had DMI at the level of SCP, and 647 (58.45%) eyes had DMI at the level of DCP. Among eyes without diabetic retinopathy (DR), DMI was observed in 19.40% and 24.13% of eyes at SCP and DCP, respectively. In the multivariable logistic regression models, older age, poorer visual acuity, thinner ganglion cell-inner plexiform layer thickness, worsened DR severity, higher haemoglobin A1c level, lower estimated glomerular filtration rate and higher low-density lipoprotein cholesterol level were associated with SCP-DMI. In addition to the aforementioned factors, presence of diabetic macular oedema and shorter axial length were associated with DCP-DMI. CONCLUSION: We reported a series of associated factors of SCP-DMI and DCP-DMI. The binary outcome of DMI might promote a simplified OCTA-based DMI evaluation before subsequent quantitative analysis for assessing DMI extent and fulfil the urge for an updating diabetic retinal disease staging to be implemented with OCTA.

Case Report: Retinal Vasculitis in Two Adolescents After COVID-19 Vaccination.

PURPOSE: To report two cases of bilateral retinal vasculitis in adolescents following COVID-19 vaccination. STUDY DESIGN: Case report. RESULTS:  We report the first two cases of retinal vasculitis in adolescents following COVID-19 vaccinations. Both patients received recent second-dose COVID-19 vaccinations (7 weeks and 4 weeks respectively), and presented with bilateral retinal vasculitis and vitritis. Investigations did not reveal other causes of retinal vasculitis. Both patients' retinal vasculitis settled with a short course of oral prednisolone. CONCLUSION: Although rare, the temporal association between vaccination, bilateral eye involvement, and the absence of alternative infective or inflammatory causes, makes this a plausible etiology. mRNA vaccinations may cause an autoimmune reaction via host antigenic mimicry, and systemic vasculitis has previously been described. We believe that a short interval between COVID-19 vaccination doses might be a risk factor for the development of retinal vasculitis in adolescents, and clinicians should be aware to elicit vaccination history.

Light exposure therapy for myopia control: a systematic review and Bayesian network meta-analysis.

AIMS: To compare and rank the myopia control effects of different light wavelengths in children using a systematic review and Bayesian network meta-analysis (Bayesian NMA). METHODS: The review protocol was registered with PROSPERO. We searched PubMed, EMBASE and MEDLINE for relevant clinical and animal studies published as of 2 February 2023. We included studies comparing red, violet or full-spectrum light with controls. Data extracted included descriptive statistics and study outcomes (axial length (AL) elongation and progression of spherical equivalent (SE) refraction). After quality assessment, estimates of treatment effect outcomes (mean differences (MDs) and 95% CIs) were first pooled for the animal and clinical studies in a traditional meta-analysis. To compare and rank the different light wavelengths, the Bayesian NMA was then conducted for all the included clinical studies (12 studies) and separately for only randomised controlled trials (8 studies). MDs, 95% credible intervals (CrIs) and ranks of the various light wavelengths were estimated in the Bayesian NMA. RESULTS: When all clinical studies were included in the Bayesian NMA (12 studies), only red-light significantly slowed AL elongation, MD (95% CrI), -0.38 mm (-0.59 mm to -0.16 mm)/year and SE refraction progression, 0.72D (0.35D to 1.10D)/year compared with controls. It remained the only significant intervention when effect sizes from only RCTs (eight studies) were separately combined, (-0.28 mm (-0.40 mm to -0.15 mm)/year and 0.57D (0.22D to 0.92D)/year, for AL and SE refraction, respectively). CONCLUSION: Myopia control efficacy varied among different wavelengths of light, with red light ranked as the most effective. PROSPERO REGISTRATION NUMBER: Clinical studies: CRD42022368998; animal studies: CRD42022368671.

Association of Fundus Autofluorescence Abnormalities and Pachydrusen in Central Serous Chorioretinopathy and Polypoidal Choroidal Vasculopathy.

A specific form of drusen, known as pachydrusen, has been demonstrated to be associated with pachychoroid eye diseases, such as central serous chorioretinopathy (CSC) and polypoidal choroidal vasculopathy (PCV). These pachydrusen have been found in up to 50% of eyes with CSC and PCV and may affect the disease progression and treatment response. This study aims to investigate the association between pachydrusen and changes in fundus autofluorescence (FAF) in eyes with CSC and PCV. A total of 65 CSC patients and 32 PCV patients were evaluated. Pachydrusen were detected using both color fundus photography and spectral-domain optical coherence tomography. The relationships between pachydrusen and FAF changes were then investigated. The prevalence of pachydrusen in CSC and PCV eyes was 16.7% and 61.8%, respectively. The mean age of patients with pachydrusen was significantly older than those without pachydrusen (CSC: 56.3 vs. 45.0 years, p < 0.001; PCV: 68.8 vs. 59.5 years, p < 0.001). No significant difference was found in the mean subfoveal choroidal thickness between eyes with or without pachydrusen. Eyes with pachydrusen were significantly associated with more extensive FAF changes in both CSC and PCV (p < 0.001 and p = 0.037, respectively). The study demonstrated that pachydrusen are more prevalent in PCV than CSC. Increasing age and more extensive abnormalities in FAF are associated with the presence of pachydrusen, suggesting that dysfunction of retinal pigment epithelial cells is associated with pachydrusen.

Giant Fornix Syndrome: How Much Conjunctiva Should Be Resected?

PURPOSE: To characterize clinical profiles of Chinese patients with giant fornix syndrome (GFS), compare surgical outcomes with amount of Müller's muscle-conjunctival resection (MMCR), and elicit risk factors for those who have prolonged recovery after MMCR. METHODS: Retrospective, observational, interventional cohort study on GFS eyes. Two treatment groups were established: limited MMCR-as defined by 8 mm or less resection; maximal MMCR-as defined by 10-12 mm resection. Good responders were defined as eyes exhibiting disease resolution within 3 months after surgery. Primary outcome was disease resolution, secondary outcome was ptosis improvement. RESULTS: Mean age was 81.9 years old (range, 76-89), with 6 (75%) females and 2 (25%) males. All 10 eyes presented with discharge, partial ptosis, and conjunctival injection. In the limited MMCR group, time to symptom resolution was longer at 5.56 months, while maximal MMCR group was 2.02 months (p = 0.004). Limited MMCR group also had lower primary surgical success and required additional surgery compared with maximal MMCR group (p = 0.008). At mean follow up of 34.4 months (range, 11-65 months), all eyes achieved disease resolution, no recurrence, and ptosis improvement. CONCLUSIONS: In the largest series on Chinese eyes with GFS to date, GFS is mainly a disease in elderly females. Maximal MMCR has a higher rate of surgical success with no additional complications. For those who underwent MMCR, additional treatment such as topical steroids and fortified antibiotics do not affect time to recovery. These findings may help ophthalmologists consider maximal MMCR as a definitive surgical treatment in GFS eyes.

A MULTITASK DEEP-LEARNING SYSTEM FOR ASSESSMENT OF DIABETIC MACULAR ISCHEMIA ON OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY IMAGES.

PURPOSE: We aimed to develop and test a deep-learning system to perform image quality and diabetic macular ischemia (DMI) assessment on optical coherence tomography angiography (OCTA) images. METHODS: This study included 7,194 OCTA images with diabetes mellitus for training and primary validation and 960 images from three independent data sets for external testing. A trinary classification for image quality assessment and the presence or absence of DMI for DMI assessment were labeled on all OCTA images. Two DenseNet-161 models were built for both tasks for OCTA images of superficial and deep capillary plexuses, respectively. External testing was performed on three unseen data sets in which one data set using the same model of OCTA device as of the primary data set and two data sets using another brand of OCTA device. We assessed the performance by using the area under the receiver operating characteristic curves with sensitivities, specificities, and accuracies and the area under the precision-recall curves with precision. RESULTS: For the image quality assessment, analyses for gradability and measurability assessment were performed. Our deep-learning system achieved the area under the receiver operating characteristic curves >0.948 and area under the precision-recall curves >0.866 for the gradability assessment, area under the receiver operating characteristic curves >0.960 and area under the precision-recall curves >0.822 for the measurability assessment, and area under the receiver operating characteristic curves >0.939 and area under the precision-recall curves >0.899 for the DMI assessment across three external validation data sets. Grad-CAM demonstrated the capability of our deep-learning system paying attention to regions related to DMI identification. CONCLUSION: Our proposed multitask deep-learning system might facilitate the development of a simplified assessment of DMI on OCTA images among individuals with diabetes mellitus at high risk for visual loss.

Optical Coherence Tomography Classification Systems for Diabetic Macular Edema and Their Associations With Visual Outcome and Treatment Responses - An Updated Review.

ABSTRACT: Optical coherence tomography (OCT) is an invaluable imaging tool in detecting and assessing diabetic macular edema (DME). Over the past decade, there have been different proposed OCT-based classification systems for DME. In this review, we present an update of spectral-domain OCT (SDOCT)-based DME classifications over the past 5 years. In addition, we attempt to summarize the proposed OCT qualitative and quantitative parameters from different classification systems in relation to disease severity, risk of progression, and treatment outcome. Although some OCT-based measurements were found to have prognostic value on visual outcome, there has been a lack of consensus or guidelines on which parameters can be reliably used to predict treatment outcomes. We also summarize recent literatures on the prognostic value of these parameters including quantitative measures such as macular thickness or volume, central subfield thickness or foveal thickness, and qualitative features such as the morphology of the vitreoretinal interface, disorganization of retinal inner layers, ellipsoid zone disruption integrity, and hyperreflec-tive foci. In addition, we discuss that a framework to assess the validity of biomarkers for treatment outcome is essentially important in assessing the prognosis before deciding on treatment in DME. Finally, we echo with other experts on the demand for updating the current diabetic retinal disease classification.

A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis.

OBJECTIVE: Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. RESEARCH DESIGN AND METHODS: We trained and validated two versions of a multitask convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume scans and 2D B-scans, respectively. For both 3D and 2D CNNs, we used the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent data sets from Singapore, Hong Kong, the U.S., China, and Australia. RESULTS: In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920-0.954), 0.958 (0.930-0.977), and 0.965 (0.948-0.977) for the primary data set obtained from CIRRUS, SPECTRALIS, and Triton OCTs, respectively, in addition to AUROCs >0.906 for the external data sets. For further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940-0.995), 0.951 (0.898-0.982), and 0.975 (0.947-0.991) for the primary data set and >0.894 for the external data sets. CONCLUSIONS: We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics.

Detection of Diabetic Retinopathy from Ultra-Widefield Scanning Laser Ophthalmoscope Images: A Multicenter Deep Learning Analysis.

PURPOSE: To develop a deep learning (DL) system that can detect referable diabetic retinopathy (RDR) and vision-threatening diabetic retinopathy (VTDR) from images obtained on ultra-widefield scanning laser ophthalmoscope (UWF-SLO). DESIGN: Observational, cross-sectional study. PARTICIPANTS: A total of 9392 UWF-SLO images of 1903 eyes from 1022 subjects with diabetes from Hong Kong, the United Kingdom, India, and Argentina. METHODS: All images were labeled according to the presence or absence of RDR and the presence or absence of VTDR. Labeling was performed by retina specialists from fundus examination, according to the International Clinical Diabetic Retinopathy Disease Severity Scale. Three convolutional neural networks (ResNet50) were trained with a transfer-learning procedure for assessing gradability and identifying VTDR and RDR. External validation was performed on 4 datasets spanning different geographical regions. MAIN OUTCOME MEASURES: Area under the receiver operating characteristic curve (AUROC); area under the precision-recall curve (AUPRC); sensitivity, specificity, and accuracy of the DL system in gradability assessment; and detection of RDR and VTDR. RESULTS: For gradability assessment, the system achieved an AUROC of 0.923 (95% confidence interval [CI], 0.892-0.947), sensitivity of 86.5% (95% CI, 77.6-92.8), and specificity of 82.1% (95% CI, 77.3-86.2) for the primary validation dataset, and >0.82 AUROCs, >79.6% sensitivity, and >70.4% specificity for the geographical external validation datasets. For detecting RDR and VTDR, the AUROCs were 0.981 (95% CI, 0.977-0.984) and 0.966 (95% CI, 0.961-0.971), with sensitivities of 94.9% (95% CI, 92.3-97.9) and 87.2% (95% CI, 81.5-91.6), specificities of 95.1% (95% CI, 90.6-97.9) and 95.8% (95% CI, 93.3-97.6), and positive predictive values (PPVs) of 98.0% (95% CI, 96.1-99.0) and 91.1% (95% CI, 86.3-94.3) for the primary validation dataset, respectively. The AUROCs and accuracies for detecting both RDR and VTDR were >0.9% and >80%, respectively, for the geographical external validation datasets. The AUPRCs were >0.9, and sensitivities, specificities, and PPVs were >80% for the geographical external validation datasets for RDR and VTDR detection. CONCLUSIONS: The excellent performance achieved with this DL system for image quality assessment and detection of RDR and VTDR in UWF-SLO images highlights its potential as an efficient and effective diabetic retinopathy screening tool.