Papers/2611.17586
🧪 Test?View on arXiv

Where to Predict in Retinal OCT? Anatomy-Guided Target Selection for I-JEPA

Not provided in the abstract

representation learningself-supervised learningmedical imagingglaucoma classification
2611.17586
Builder Relevance
70%
19h ago

Abstract

This paper investigates anatomy-guided target selection in retinal OCT to improve representation learning using the I-JEPA architecture.

Reality Card

Core Claim

Anatomy-guided rectangular targets based on image intensity achieved the highest linear-probe AUC for glaucoma classification.

Method / Result

Rectangular targets guided by image intensity achieved the highest linear-probe AUC in comparisons.

Limitations

Greater anatomical specificity did not consistently improve performance, indicating variability in results.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers