Post

New research · Ophthalmology
American journal of ophthalmology · 23h
AI / informaticsAmerican journal of ophthalmology · 2026

Multistream Deep Learning Models Using Multimodal Optical Coherence Tomography for Predicting Visual Impairment in Epiretinal Membrane.

Hsu-Hang Yeh, Po-Yung Chou, Cheng-Chang Hsieh … Cheng-Hung Lin
Read paper
OphthalmologyAI / informatics

An eight-image AI model best predicted visual impairment from epiretinal membrane.

Multistream Deep Learning Models Using Multimodal Optical Coherence Tomography for Predicting Visual Impairment in Epiretinal Membrane.

Hsu-Hang Yeh … Cheng-Hung Lin
American journal of ophthalmology · 2026
Purpose

To develop multistream deep learning models that receive multimodal optical coherence tomography (optical coherence tomography) images to predict visual impairment in epiretinal membrane (epiretinal membrane), and to identify possible optical coherence tomography biomarkers for visual impairment.

Methods

Who were diagnosed as idiopathic epiretinal membrane at one medical center were retrospectively enrolled.

n = 351 sets of images
Results
90.90%
The combined eight-image deep learning model correctly predicted vision loss in 90.90% of cases.
n = 351 sets of images
More results

The single-stream models achieved accuracies ranging from 79.48% to 88.89% in model development but decreased to 60.69%-75.11% in external validation.

Increasing the number of input streams to two or three further enhanced predictive performance.

“
Conclusion · 1 of 2

B-scan optical coherence tomography, en face optical coherence tomography angiography and retinal thickness maps of the macula could all be used for predicting visual impairment in epiretinal membrane via deep learning.

Conclusion · 2 of 2

The multistream design can enhance predictive accuracy and may provide localization of vital retinal regions relevant to visual compromise in epiretinal membrane.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
0·962 for OCT
MerMED-FM was very accurate at diagnosing diseases using eye scans
AI / Informatics
0.98
Artificial intelligence's eyelid-height measurements matched doctors' manual measurements almost perfectly
AI / Informatics
92.1%
combining eye scans and photos correctly told benign from cancerous lesions apart nearly every time
Cohort Study
28.6%
recurred locally in more than 1 in 4 patients over years of follow-up
Cohort Study
-0.395
excision group's post-op eyelid fullness score was lower - greater improvement
Cohort Study
86.7%
of infants probed after 12 months still had unresolved tear duct blockage
Observational
16%
eyelid tissue in rosacea patients showed less of this key repair-signaling protein inside cell nuclei
Cohort Study
25%
about 1 in 4 treated cases had symptoms return after improving