Evaluation of an offline, artificial intelligence system for referable glaucoma screening using a smartphone-based fundus camera: a prospective study.

BACKGROUND/OBJECTIVES: An affordable and scalable screening model is critical for undetected glaucoma. The study evaluated the performance of an offline, smartphone-based AI system for the detection of referable glaucoma against two benchmarks: specialist diagnosis following full glaucoma workup and consensus image grading. SUBJECTS/METHODS: This prospective study (tertiary glaucoma centre, India) included 243 subjects with varying severity of glaucoma and control group without glaucoma. Disc-centred images were captured using a validated smartphone-based fundus camera analysed by the AI system and graded by specialists. Diagnostic ability of the AI in detecting referable Glaucoma (Confirmed glaucoma) and no referable Glaucoma (Suspects and No glaucoma) when compared to a final diagnosis (comprehensive glaucoma workup) and majority grading (image grading) by Glaucoma specialists (pre-defined criteria) were evaluated. RESULTS: The AI system demonstrated a sensitivity and specificity of 93.7% (95% CI: 87.6-96.9%) and 85.6% (95% CI:78.6-90.6%), respectively, in the detection of referable glaucoma when compared against final diagnosis following full glaucoma workup. True negative rate in definite non-glaucoma cases was 94.7% (95% CI: 87.2-97.9%). Amongst the false negatives were 4 early and 3 moderate glaucoma. When the same set of images provided to the AI was also provided to the specialists for image grading, specialists detected 60% (67/111) of true glaucoma cases versus a detection rate of 94% (104/111) by the AI. CONCLUSION: The AI tool showed robust performance when compared against a stringent benchmark. It had modest over-referral of normal subjects despite being challenged with fundus images alone. The next step involves a population-level assessment.

Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population.

Purpose: The primary objective of this study was to develop and validate an AI algorithm as a screening tool for the detection of retinopathy of prematurity (ROP). Participants: Images were collected from infants enrolled in the KIDROP tele-ROP screening program. Methods: We developed a deep learning (DL) algorithm with 227,326 wide-field images from multiple camera systems obtained from the KIDROP tele-ROP screening program in India over an 11-year period. 37,477 temporal retina images were utilized with the dataset split into train (n = 25,982, 69.33%), validation (n = 4,006, 10.69%), and an independent test set (n = 7,489, 19.98%). The algorithm consists of a binary classifier that distinguishes between the presence of ROP (Stages 1-3) and the absence of ROP. The image labels were retrieved from the daily registers of the tele-ROP program. They consist of per-eye diagnoses provided by trained ROP graders based on all images captured during the screening session. Infants requiring treatment and a proportion of those not requiring urgent referral had an additional confirmatory diagnosis from an ROP specialist. Results: Of the 7,489 temporal images analyzed in the test set, 2,249 (30.0%) images showed the presence of ROP. The sensitivity and specificity to detect ROP was 91.46% (95% CI: 90.23%-92.59%) and 91.22% (95% CI: 90.42%-91.97%), respectively, while the positive predictive value (PPV) was 81.72% (95% CI: 80.37%-83.00%), negative predictive value (NPV) was 96.14% (95% CI: 95.60%-96.61%) and the AUROC was 0.970. Conclusion: The novel ROP screening algorithm demonstrated high sensitivity and specificity in detecting the presence of ROP. A prospective clinical validation in a real-world tele-ROP platform is under consideration. It has the potential to lower the number of screening sessions required to be conducted by a specialist for a high-risk preterm infant thus significantly improving workflow efficiency.

Diagnostic Accuracy of Automated Diabetic Retinopathy Image Assessment Softwares: IDx-DR and Medios Artificial Intelligence.

INTRODUCTION: Numerous studies have demonstrated the use of artificial intelligence (AI) for early detection of referable diabetic retinopathy (RDR). A direct comparison of these multiple automated diabetic retinopathy (DR) image assessment softwares (ARIAs) is, however, challenging. We retrospectively compared the performance of two modern ARIAs, IDx-DR and Medios AI. METHODS: In this retrospective-comparative study, retinal images with sufficient image quality were run on both ARIAs. They were captured in 811 consecutive patients with diabetes visiting diabetic clinics in Poland. For each patient, four non-mydriatic images, 45° field of view, i.e., two sets of one optic disc and one macula-centered image using Topcon NW400 were captured. Images were manually graded for severity of DR as no DR, any DR (mild non-proliferative diabetic retinopathy [NPDR] or more severe disease), RDR (moderate NPDR or more severe disease and/or clinically significant diabetic macular edema [CSDME]), or sight-threatening DR (severe NPDR or more severe disease and/or CSDME) by certified graders. The ARIA output was compared to manual consensus image grading (reference standard). RESULTS: On 807 patients, based on consensus grading, there was no evidence of DR in 543 patients (67%). Any DR was seen in 264 (33%) patients, of which 174 (22%) were RDR and 41 (5%) were sight-threatening DR. The sensitivity of detecting RDR against reference standard grading was 95% (95% CI: 91, 98%) and the specificity was 80% (95% CI: 77, 83%) for Medios AI. They were 99% (95% CI: 96, 100%) and 68% (95% CI: 64, 72%) for IDx-DR, respectively. CONCLUSION: Both the ARIAs achieved satisfactory accuracy, with few false negatives. Although false-positive results generate additional costs and workload, missed cases raise the most concern whenever automated screening is debated.

Validation of a Simple-to-Use, Affordable, Portable Wavefront Aberrometry-Based Auto Refractometer in a Paediatric Population.

Purpose: InstaRef R20 is a handheld, affordable auto refractometer based on Shack Hartmann aberrometry technology. The study's objective was to compare InstaRef R20's performance for identifying refractive error in a paediatric population to that of standard subjective and objective refraction under both pre- and post-cycloplegic conditions. Methods: Refraction was performed using 1) standard clinical procedure consisting of retinoscopy followed by subjective refraction (SR) under pre- and post-cycloplegic conditions and 2) InstaRef R20. Agreement between both methods was evaluated using Bland-Altman analysis. The repeatability of the device based on three measurements in a subgroup of 20 children was assessed. Results: The refractive error was measured in 132 children (mean age 12.31 ± 3 years). The spherical equivalent (M) and cylindrical components (J0 and J45) of the device had clinically acceptable differences (within ±0.50D) and acceptable agreement compared to standard pre- and post-cycloplegic manual retinoscopy and subjective refraction (SR). The device agreed within ± 0.50D of retinoscopy in 67% of eyes for M, 78% for J0 and 80% for J45 and within ± 0.50D of SR in 70% for M and 77% for cylindrical components. Conclusion: InstaRef R20 has an acceptable agreement compared to standard retinoscopy in paediatric population. The measurements from this device can be used as a starting point for subjective acceptance. The device being simple to use, portable, reliable and affordable has the potential for large-scale community-based refractive error detection.

Validation of a simple-to-use, affordable, portable, wavefront aberrometry-based auto refractometer in the adult population: A prospective study.

BACKGROUND: Refraction is one of the key components of a comprehensive eye examination. Auto refractometers that are reliable and affordable can be beneficial, especially in a low-resource community setting. The study aimed to validate the accuracy of a novel wave-front aberrometry-based auto refractometer, Instaref R20 against the open-field system and subjective refraction in an adult population. METHODS: All the participants underwent a comprehensive eye examination including objective refraction, subjective acceptance, anterior and posterior segment evaluation. Refraction was performed without cycloplegia using WAM5500 open-field auto refractometer (OFAR) and Instaref R20, the study device. Agreement between both methods was evaluated using Bland-Altman analysis. The repeatability of the device based on three measurements in a subgroup of 40 adults was assessed. RESULTS: The refractive error was measured in 132 participants (mean age,30.53 ± 9.36 years, 58.3% female). The paired mean difference of the refraction values of the study device against OFAR was - 0.13D for M, - 0.0002D (J0) and - 0.13D (J45) and against subjective refraction (SR) was - 0.09D (M), 0.06 (J0) and 0.03D (J45). The device agreed within +/- 0.50D of OFAR in 78% of eyes for M, 79% for J0 and 78% for J45. The device agreed within +/- 0.5D of SR values for M (84%), J0 (86%) and J45 (89%). CONCLUSION: This study found a good agreement between the measurements obtained with the portable autorefractor against open-field refractometer and SR values. It has a potential application in population-based community vision screening programs for refractive error correction without the need for highly trained personnel.

Towards a Device Agnostic AI for Diabetic Retinopathy Screening: An External Validation Study.

Purpose: To evaluate the performance of a validated Artificial Intelligence (AI) algorithm developed for a smartphone-based camera on images captured using a standard desktop fundus camera to screen for diabetic retinopathy (DR). Participants: Subjects with established diabetes mellitus. Methods: Images captured on a desktop fundus camera (Topcon TRC-50DX, Japan) for a previous study with 135 consecutive patients (233 eyes) with established diabetes mellitus, with or without DR were analysed by the AI algorithm. The performance of the AI algorithm to detect any DR, referable DR (RDR Ie, worse than mild non proliferative diabetic retinopathy (NPDR) and/or diabetic macular edema (DME)) and sight-threatening DR (STDR Ie, severe NPDR or worse and/or DME) were assessed based on comparisons against both image-based consensus grades by two fellowship trained vitreo-retina specialists and clinical examination. Results: The sensitivity was 98.3% (95% CI 96%, 100%) and the specificity 83.7% (95% CI 73%, 94%) for RDR against image grading. The specificity for RDR decreased to 65.2% (95% CI 53.7%, 76.6%) and the sensitivity marginally increased to 100% (95% CI 100%, 100%) when compared against clinical examination. The sensitivity for detection of any DR when compared against image-based consensus grading and clinical exam were both 97.6% (95% CI 95%, 100%). The specificity for any DR detection was 90.9% (95% CI 82.3%, 99.4%) as compared against image grading and 88.9% (95% CI 79.7%, 98.1%) on clinical exam. The sensitivity for STDR was 99.0% (95% CI 96%, 100%) against image grading and 100% (95% CI 100%, 100%) as compared against clinical exam. Conclusion: The AI algorithm could screen for RDR and any DR with robust performance on images captured on a desktop fundus camera when compared to image grading, despite being previously optimized for a smartphone-based camera.

A Novel, Smartphone-Based, Teleophthalmology-Enabled, Widefield Fundus Imaging Device With an Autocapture Algorithm.

Purpose: Widefield imaging can detect signs of retinal pathology extending beyond the posterior pole and is currently moving to the forefront of posterior segment imaging. We report a novel, smartphone-based, telemedicine-enabled, mydriatic, widefield retinal imaging device with autofocus and autocapture capabilities to be used by non-specialist operators. Methods: The Remidio Vistaro uses an annular illumination design without cross-polarizers to eliminate Purkinje reflexes. The measured resolution using the US Air Force target test was 64 line pairs (lp)/mm in the center, 57 lp/mm in the middle, and 45 lp/mm in the periphery of a single-shot retinal image. An autocapture algorithm was developed to capture images automatically upon reaching the correct working distance. The field of view (FOV) was validated using both model and real eyes. A pilot study was conducted to objectively assess image quality. The FOVs of montaged images from the Vistaro were compared with regulatory-approved widefield and ultra-widefield devices. Results: The FOV of the Vistaro was found to be approximately 65° in one shot. Automatic image capture was achieved in 80% of patient examinations within an average of 10 to 15 seconds. Consensus grading of image quality among three graders showed that 91.6% of the images were clinically useful. A two-field montage on the Vistaro was shown to exceed the cumulative FOV of a seven-field Early Treatment Diabetic Retinopathy Study image. Conclusions: A novel, smartphone-based, portable, mydriatic, widefield imaging device can view the retina beyond the posterior pole with a FOV of 65° in one shot. Translational Relevance: Smartphone-based widefield imaging can be widely used to screen for retinal pathologies beyond the posterior pole.

Design and Performance Characterization of a Novel, Smartphone-Based, Portable Digital Slit Lamp for Anterior Segment Screening Using Telemedicine.

Purpose: Telemedicine-enabled, portable digital slit lamps can help to decentralize screening to close-to-patient contexts. We report a novel design for a portable, digital slit lamp using a smartphone. It works on an advanced optical design and has the capability of instantaneous, objective photodocumentation to capture anterior segment images and is telemedicine-enabled. Methods: The device is constructed keeping its usability and the importance of design ergonomics for nonspecialized field personnel in mind. The optical design is described, and the resolution and magnification are compared with traditional desktop-based slit lamps. A Health Insurance Portability and Accountability Act (HIPAA)-compliant, patient management software is integrated to synchronize the captured images with a secure cloud server along with a sharpness algorithm to extract the best focused frames of the cornea, iris, and lens, from videos. We demonstrate its photodocumentation ability and teleophthalmology feasibility by capturing images in a pilot study from nine subjects. Results: Images were obtained in various illumination, magnification, and filter settings. Synchronous and asynchronous teleophthalmology consults were conducted. The performance of the device was shown to be limited by the smartphone sensor resolution and not the optical design, because the Air Force target resolution was found to be the same on smartphone-mounted traditional slit lamps despite a lower magnification. Conclusions: The novel, portable, digital slit lamp with advanced optical design using smartphones has the ability to screen for anterior segment pathologies using telemedicine. Translational Relevance: A portable, telemedicine-friendly, ergonomically designed, slit lamp used by nonspecialist personnel allows for both synchronous and asynchronous modes of consultation at remote locations, facilitating mass screening programs.

A novel approach to anterior segment imaging with smartphones in the COVID-19 era.

PURPOSE: To report a novel, telemedicine-friendly, smartphone-based, wireless anterior segment device with instant photo-documentation ability in the COVID-19 era. METHODS: Anterior Imaging Module (AIM) was constructed based on a 50/50 beam splitter design, to match the magnification drum optics of slit-lamps with a three-step or higher level of magnification. The design fills the smartphone sensor fully at the lowest magnification and matches the fixed focus of the slit-lamp. It comes with a smartphone for instant photo-documentation, an in-built software application for data-management and secure HIPAA compliant cloud storage, and a Bluetooth trigger for a one-tap image capture. The construction of the device is explained, and the optical resolution measured using U.S. air-force resolution test. AIM's performance was characterized with traceability to internationally relevant performance standards for digital slit-lamps after image quality assessment through a pilot study. RESULTS: Clinically useful anterior segment images were obtained with both diffuse and slit illumination at different magnification settings with the highest magnification (40X) resolution of 359 lines per cm and the lowest magnification (16X) resolution of 113 lines per cm. CONCLUSION: AIM is a novel, wireless, telemedicine-enabled design that digitizes existing, analog slit lamps with at least three-step magnification. The settings ensure the focus is determined purely by the position of the slit-lamp. Hence, the image viewed and captured on the smartphone is exactly what the clinician sees through the eyepiece. This helps in maintaining distance from the patient in the ongoing COVID-19 pandemic, as well.