Purchase this article with an account.
Andrew Caterfino, Ashley Ooms, Sameer Trikha, Brian Caterfino, Ben Szirth, Albert S Khouri; Integration of Artificial Intelligence and OpacitySuppressionTM Software in Tele-Retinal Screenings. Invest. Ophthalmol. Vis. Sci. 2019;60(9):162. doi: https://doi.org/.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
Images captured through non-mydriatic retinal cameras remain the standard in tele-retinal screening. Aging populations, with media opacity and small pupils, offer challenges in tele-retinal screenings that do not use mydriatic agents. Combining Artificial Intelligence (AI) software with image enhancement software such as OpacitySupressionTM (OS), to assist in interpreting retinal images in diabetic retinopathy screenings, has been evaluated.
45° color retinal images were captured with a resolution of 21 Mp and a minimum pupil size of 2.8mm. 117 individuals with confirmed Type 1 Diabetic Mellitus (age 25 +/- 17.1, 42% male) were imaged having a natural pupillary dilation of >4.0mm. OSTM was applied to images in ImageSpectrum (Canon, Los Angeles, CA), including 6 images (5%) that had been deemed unreadable by human readers due to pupil size bellow 2.8mm. OSTM enhanced and OSTM non-enhanced images were uploaded to a secure cloud and graded through AI software. XLSTAT was used to determine differences between the AI’s readings of enhanced versus non-enhanced images with respect to clinical screening parameters.
AI read 117 images and flagged 49 positive pick-ups (42%); 38 microaneurysms, 6 exudates, and 5 hemorrhages. Paired T-test showed no significant difference between the AI’s detection with and without OSTM for hemorrhages (mean pickup of 0.03 vs 0.04; p = 0.71), microaneurysms (0.32 vs 0.34; p = 0.68), exudates (0.05 vs 0.03; p = 0.26), and a difference in the ability to detect diabetic retinopathy (0. 49 vs 0.35; p = 0.03). All 6 images unreadable by a human reader were readable post OSTM by a human reader, and OSTM increased luminosity by an average of 34.7% in 6 images. While the AI was able to read these unreadable images without OSTM, it did not flag any positive pickups. A human reader found a hemorrhage in one of the 6 previous unreadable images (17%) with the addition of OSTM. The AI was not able to pick up any pathology in these images post-OS TM. AI interpreted images in 6 seconds while human reader’s interpretation time was 43 seconds per image.
Our results shows no significant difference in the ability of AI’s readings of enhanced versus non-enhanced OSTM fundus images. However, OSTM was found to be useful when human readers evaluate retinal images in community-based screenings.
This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.
This PDF is available to Subscribers Only