SOURCE-LINKED INTELLIGENCE

Multimodal Shared Latent Representation of Narration, Microscope and iOCT Images for Phase Recognition in Vitreoretinal Surgery

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Surgical phase recognition is key to context-aware computer-assisted feedback in vitreoretinal procedures, yet the scarcity of synchronized multimodal intraoperative data, particularly microscope views and intraoperative OCT, limits approaches that aim to replicate the multimodal integration surgeons perform naturally. Surgical narration, by contrast, is abundantly available online and offers rich semantic supervision. Prior work has mainly explored pairwise contrastive learning (e.g., intraoperative OCT-microscope or microscope-narration), leaving the joint modeling of all three modalities la

Read original source ↗ Open in workspace

recordType

paper

region

Global