ArticleScientific reports2026
Portable AI-powered scanning slit-light device for low-cost eye disease screening.
Article in Scientific reports, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
7 authors.
Funding
Abstract
Accurate anterior-segment assessment is essential for detecting conditions such as primary angle-closure glaucoma, cataract, and keratoconus, yet current tools remain limited: slit-lamp biomicroscopy is qualitative and operator-dependent, whereas anterior segment OCT (AS-OCT) is costly and clinic-bound. We introduce an AI-integrated portable scanning slit-light device that delivers quantitative anterior-segment biometry at a material cost below USD 500. The system combines a motorized slit-scanning mechanism with synchronized imaging and an on-device deep-learning model (LWBNA-unet) to segment corneal and iris reflections, pupil boundaries, and corneal surfaces. Geometry-aware corrections—including slit-incidence compensation and per-frame anatomical scaling—enable calibrated estimation of anterior chamber depth (ACD) as the primary quantitative output, with exploratory estimates of central corneal thickness (CCT) derived from the same scan. In a clinical study of 170 participants, ACD showed excellent agreement with AS-OCT (Pearson’s r ≈ 0.92, concordance correlation coefficient ≈ 0.90; mean bias ≈ 0.0–0.04 mm with 95% limits of agreement LoR ~ ± 0.3 mm) indicating near-clinical interchangeability for ACD in a screening context. Representative cases illustrated clear visualization of anterior-segment features associated with narrow angles, cataract, corneal opacity, and keratoconic ectasia from a single scanning-slit video. A typical 51-frame video (captured in ~ 15 s) can be fully processed on a Jetson Orin Nano in 18.5 s (≈ 2.7 fps), supporting compact, battery-powered deployment. These results establish the first ultra–low-cost platform capable of automated, quantitative, and anatomically calibrated anterior-segment imaging, offering a scalable foundation for community screening and teleophthalmology in resource-limited settings.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.