A smartphone-based tool for rapid, portable, and automated wide-field retinal imaging

Abstract

PurposeHigh-quality, wide-field retinal imaging is a valuable method to screen 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. MethodsThe system was designed to improve smartphone retinal imaging by combining automated fixation guidance, photomontage, and multi-colored illumination with optimized optics, user-tested ergonomics, and touch-screen interface. System performance was evaluated from images of ophthalmic patients taken by non-ophthalmic personnel. Two masked ophthalmologists evaluated images for abnormalities and disease severity. ResultsThe system automatically generated 100-degree 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 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%. ConclusionsAutomation-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 RelevanceEnhancement of smartphone-based retinal imaging through automation and software intelligence holds great promise for increasing the accessibility of retinal screening.

Comparison of Telemedicine Screening of Diabetic Retinopathy by Mydriatic Smartphone-Based vs Nonmydriatic Tabletop Camera-Based Fundus Imaging

“…Several other studies support the use of mydriatic smartphone-based fundus photography as a reliable and cost-effective option to expand screening for DR. 11,14 -16,18,29,30 The prospective CAMRA (Comparison Among Methods of Retinopathy Assessment) study of 300 patients compared smartphone fundus photography after dilation and nonmydriatic fundus photography against reference standard 7-field mydriatic fundus photography in their ability to detect and grade DR. 15 Tested in an outreach setting in India, detection of moderate NPDR or worse was comparable between mydriatic smartphone photography and nonmydriatic tabletop photography, with sensitivity of 59% (smartphone; 95% CI, 46%-72%) vs 54% (nonmydriatic; 95% CI, 40%-67%) and specificity of 100% (smartphone; 95% CI, 99%-100%) vs 99% (nonmydriatic; 95% CI, 98%-100%). Russo et al 14 prospectively compared mydriatic smartphone-based direct ophthalmoscopy to dilated slitlamp examination in the detection of DR in 120 patients with type 1 or type 2 diabetes and found exact agreement in 204 of 240 eyes (85%, κ = 0.78; CI, 0.71-0.84).…”

Smartphone-based imaging systems for medical applications: a critical review

“…Some studies have quantified usability improvements by measuring time for task completion, performing surveys, or conducting blinded image reviews. 11 , 129 , 133 Broader use of such assessments to substantiate improved usability of SBI systems should be encouraged. When possible, usability should be assessed in the intended clinical setting, but anatomical models and/or imaging phantoms can be good alternatives when clinical evaluation is infeasible.…”

“…As diagnostics are typically used for triage to treatment interventions, such applications more likely to be performed by medical personnel and in clinical settings rather than by individuals at home. Some of the primary in vivo diagnostic modalities proposed for SBI systems include white light imaging, 52 , 65 , 66 , 91 , 100 – 102 , 126 – 133 autofluorescence imaging, 17 , 65 , 66 , 71 , 100 multispectral/hyperspectral imaging, 52 , 64 , 88 endoscopy, 10 – 13 in vivo spectroscopy, 14 , 51 , 85 and in vivo microscopy. 14 – 16 , 62 , 134 For these modalities, the most frequent imaging sites are external tissues (dermis, facial, and retinal), externally accessible tissues (oral cavity, cervix, and ear), as well as some deeper tissues in the case of endoscopy (bladder, larynx, and esophagus).…”

Imaging the pediatric retina

“…The quick data transfer capability in smartphones can be utilized as an effective telemedicine tool to share and discuss the cases in remote places, e.g., screening for pediatric eye diseases such as ROP and diabetic retinopathy in children and adolescents. [ 29 ] Hazy vitreous, small pupil and vasculosa lentis could hamper good quality image acquisition. [ 26 ] There is a learning curve in using the smartphone camera to capture the images since it is based on inverted virtual images.…”