Purpose

High-quality, wide-field retinal imaging is a valuable method for screening preventable, vision-threatening diseases of the retina. Smartphone-based retinal cameras hold promise for increasing access to retinal imaging, but variable image quality and restricted field of view can limit their utility. We developed and clinically tested a smartphone-based system that addresses these challenges with automation-assisted imaging.

Methods

The system was designed to improve smartphone retinal imaging by combining automated fixation guidance, photomontage, and multicolored illumination with optimized optics, user-tested ergonomics, and touch-screen interface. System performance was evaluated from images of ophthalmic patients taken by nonophthalmic personnel. Two masked ophthalmologists evaluated images for abnormalities and disease severity.

Results

The system automatically generated 100° retinal photomontages from five overlapping images in under 1 minute at full resolution (52.3 pixels per retinal degree) fully on-phone, revealing numerous retinal abnormalities. Feasibility of the system for diabetic retinopathy (DR) screening using the retinal photomontages was performed in 71 diabetics by masked graders. DR grade matched perfectly with dilated clinical examination in 55.1% of eyes and within 1 severity level for 85.2% of eyes. For referral-warranted DR, average sensitivity was 93.3% and specificity 56.8%.

Conclusions

Automation-assisted imaging produced high-quality, wide-field retinal images that demonstrate the potential of smartphone-based retinal cameras to be used for retinal disease screening.

Translational relevance

Enhancement of smartphone-based retinal imaging through automation and software intelligence holds great promise for increasing the accessibility of retinal screening.

Conjunctival examination for trachomatous inflammation-follicular (TF) guides public health decisions for trachoma. Smartphone cameras may allow remote conjunctival grading, but previous studies have found low sensitivity. A random sample of 412 children aged 1-9 years received an in-person conjunctival examination and then had conjunctival photographs taken with 1) a single-lens reflex (SLR) camera and 2) a smartphone coupled to a 3D-printed magnifying attachment. Three masked graders assessed the conjunctival photographs for TF. Latent class analysis was used to determine the sensitivity and specificity of each grading method for TF. Single-lens reflex photo-grading was 95.0% sensitive and 93.6% specific, and smartphone photo-grading was 84.1% sensitive and 97.6% specific. The sensitivity of the smartphone-CellScope device was considerably higher than that of a previous study using the native smartphone camera, without attachment. Magnification of smartphone images with a simple attachment improved the grading sensitivity while maintaining high specificity in a region with hyperendemic trachoma.

Background

Corneal ulcers are a common cause of blindness in low-income and middle-income countries, usually resulting from traumatic corneal abrasions during agricultural work. Antimicrobial prophylaxis of corneal abrasions can help prevent corneal ulcers, but delays in the initiation of therapy are frequent. We aimed to assess whether a community-based programme for corneal ulcer prevention would reduce the incidence of corneal ulceration.

Methods

A cluster-randomised trial was performed in village development committees (VDCs) in Nepal. VDCs in the catchment area of Bharatpur Eye Hospital, Nepal with less than 15 000 people were eligible for inclusion. We randomly assigned (1:1) VDCs to either an intervention group or a control group. In the intervention VDCs, existing female community health volunteers (FCHVs) were trained to diagnose corneal abrasions and provide a 3-day course of ophthalmic antimicrobials to their patients. In the control VDCs, FCHVs did not provide this intervention. Participants were not masked given the nature of the intervention. Both groups were followed up for 3 years for photographic evidence of corneal ulceration. The primary outcome was the incidence of corneal ulceration, determined by masked assessment of corneal photographs. The analysis was by intention to treat. This trial is registered with ClinicalTrials.gov, NCT01969786.

Findings

We assessed 112 VDCs, of which 24 were enrolled. The study was performed between Feb 4, 2014, and Oct 20, 2017. 12 VDCs were randomly assigned to the intervention group and 12 to the control group. 252 539 individuals were included in the study (130 579 in the intervention group and 121 960 in the control group). FCHVs diagnosed and provided antimicrobials for 4777 corneal abrasions. The census identified 289 corneal ulcers among 246 893 person-years in the intervention group (incidence 1·21 cases [95% CI 0·85-1·74] per 1000 person-years) and 262 corneal ulcers among 239 170 person-years in the control group (incidence 1·18 cases [0·82-1·70] per 1000 person-years; incidence rate ratio 1·03 [95% CI 0·63-1·67]; p=0·93). Medication allergy was self-reported in 0·2% of participants.

Interpretation

We did not detect a reduction in the incidence of corneal ulceration during the first 3 years of a community-based corneal ulcer prevention programme. Further study might be warranted in more rural areas where basic eye care facilities are not available.

Funding

National Eye Institute.