Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

This paper studies how to choose prediction target regions for I-JEPA self-supervised learning on retinal OCT images. It compares anatomy-guided placement based on image intensity and predicted retinal segmentation against I-JEPA's default uniform placement, finding that intensity-guided rectangular targets achieved the highest linear-probe AUC for glaucoma classification on FairVision, while greater anatomical specificity did not consistently improve performance.

SourcearXiv Computer VisionAuthor: Yunchu Feng, Wai Tak Lau, Kaveri A. Thakoor
Where to Predict in Retinal OCT? Anatomy-Guided Target Selection for I-JEPA
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

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

View a PDF of the paper titled Where to Predict in Retinal OCT? Anatomy-Guided Target Selection for I-JEPA, by Yunchu Feng and 2 other authors

View PDF HTML (experimental)

Abstract:Self-supervised learning aims to learn meaningful representations from unlabeled data, potentially allowing models to capture subtle anatomical variations across patients and reduce the amount of labeled data needed. Image-based Joint-Embedding Predictive Architecture (I-JEPA) learns by predicting target-region representations from visible context rather than reconstructing pixels. However, its uniform target placement does not account for the anatomical structure of retinal OCT, where retinal tissue occupies only part of each B-scan. We investigate anatomy-guided target selection using image intensity and predicted retinal segmentation while retaining the I-JEPA architecture and latent prediction objective. We compare anatomy-guided rectangular targets, anatomy-shaped targets and coverage-constrained placement with uniform masking, and evaluate the learned representations using linear probing for glaucoma classification on FairVision. We found that rectangular targets guided by image intensity achieved the highest linear-probe AUC in our comparisons. We show that anatomically meaningful target selection is promising for retinal OCT representation learning, while greater anatomical specificity did not consistently improve performance.

Comments: 18 pages. Accepted as a poster at the GenAI for Health Workshop at NeurIPS 2026 (non-archival)

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.17586 [cs.CV]

(or arXiv:2611.17586v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.17586

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yunchu Feng [view email] [v1] Thu, 12 Nov 2026 23:11:21 UTC (2,269 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Where to Predict in Retinal OCT? Anatomy-Guided Target Selection for I-JEPA, by Yunchu Feng and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • The work keeps the I-JEPA architecture and latent prediction objective, changing only how target regions are selected.
  • Intensity-guided rectangular targets gave the highest linear-probe AUC for glaucoma classification on FairVision.
  • Anatomy-shaped targets and coverage-constrained placement did not consistently outperform simpler options.
  • The 18-page paper was accepted as a non-archival poster at the NeurIPS 2026 GenAI for Health Workshop.

Highlights and analysis are generated automatically and may contain errors. Check the original source.