Hemostasis Today

Andrew Morgenstern: Where Is Eye Care Going With AI?
Jun 30, 2026, 20:16

Andrew Morgenstern: Where Is Eye Care Going With AI?

Andrew Morgenstern, Optometrist at Defense Health Agency, Member Board of Trustees at New England College of Optometry, shared a post on LinkedIn about a recent article by Tamir Denis et al., published in npj Digital Medicine, adding:

Where is eye care going with AI?

This is pretty incredible. Able to identify anemia from non-invasive predictive images of conjunctival blood vessels in over 80% of 224 patients via Hb levels and RBC counts through bulbar conjunctiva videos taken with an RGB camera.

Video-to-Vessels, a computer-vision pipeline that converts high-magnification videos of bulbar conjunctiva capillaries into low-dimensional spatiotemporal vessel representations, reducing video dimensionality by approximately 200-fold while preserving hemodynamic information.

These representations feed VesselNet, a multi-instance regression network that encodes each vessel with a modified ConvNeXt backbone, fuses vessel-specific thickness via cross-attention, and predicts blood biomarkers from concatenated embeddings.

On a cohort of 224 participants with paired laboratory counts, VesselNet achieves a hemoglobin-based anemia ROC-AUC of 82.8% and a Spearman’s ρ of 0.47, while attaining a ρ of 0.46 for red-blood-cell (RBC) count regression.”

Title: Towards noninvasive blood count using a deep learning pipeline from bulbar conjunctiva videos

Authors: Tamir Denis, Ifat Sher, Emily Praisman, Marian Haiadry, Amir Zag, Ohad Benjamini, Abraham Avigdor, Keren Asraf, Ram Doolman, Lior Wolf, Haim Suchowski, Ygal Rotenstreich

Andrew Morgenstern

Stay updated on all scientific advances with Hemostasis Today.