Post

New research · Ophthalmology
Translational vision science & technology · 1d
AI / informaticsTranslational vision science & technology · 2026

Interpretable Deep Learning for OCT-Based Diagnosis of Vitreoretinal Lymphoma Versus Uveitis.

Azaz Khan, Ogul E Uner, Pengxiao Zang … Yali Jia
Read paper
OphthalmologyAI / informatics

Deep learning model distinguishes eye lymphoma from uveitis using retinal scans.

Interpretable Deep Learning for OCT-Based Diagnosis of Vitreoretinal Lymphoma Versus Uveitis.

Azaz Khan … Yali Jia
Translational vision science & technology · 2026
Purpose

To develop and validate an interpretable deep learning model that classifies optical coherence tomography (optical coherence tomography) scans as vitreoretinal lymphoma (vitreoretinal lymphoma) or non-infectious uveitis (non-infectious uveitis)-intermediate, posterior, or panuveitis-and visualizes differentiating pathological optical coherence tomography features.

Methods

This cross-sectional study included 45 patients with vitreoretinal lymphoma and 52 with non-infectious uveitis who underwent SPECTRALIS optical coherence tomography imaging.

n = 45 patients
76.0
Results
76.0
± 8.0
AUROC score - how well scans told lymphoma apart from uveitis
n = 45 patients
More results

Grad-CAM features of vitreoretinal lymphoma included preretinal deposits and changes in the retinal pigment epithelium.

“
Conclusion

A deep learning model with interpretability can reliably differentiate vitreoretinal lymphoma from non-infectious uveitis, highlighting disease-relevant optical coherence tomography features.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
Cross-sectional
44.1%
had too much homocysteine in the blood, a far larger share than in dry AMD or healthy eyes
Cohort Study
92.3%
most laser-treated eyes had a favorable eye-structure outcome
Cohort Study
56%
lost three or more lines on the eye-chart vision test
Cohort Study
50%
older patients were more likely to lose three or more lines of vision
Study
81%
trials where mask air leaks were detected blowing toward the eyes
Cohort Study
13.5%
Central retinal artery peak blood-flow speed was 13.5% lower in diabetic patients.
Study
379 +/- 156 microm
lower thickness in the central retina, checked with an eye scan
Case Report
9 of 10 eyes
eyes had better measured vision after treatment