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

arXiv: https://arxiv.org/abs/2608.31065 · HTML: https://mlsanity.com/paper/2608.31065/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks](https://mlsanity.com/paper/2003.10751/) (2020)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures](https://mlsanity.com/paper/2102.12218/) (2021)
- [HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition](https://mlsanity.com/paper/2405.10075/) (2024)
- [Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation](https://mlsanity.com/paper/2410.00263/) (2024)
- [OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding](https://mlsanity.com/paper/2406.07471/) (2024)
- [Neural Finite-State Machines for Surgical Phase Recognition](https://mlsanity.com/paper/2411.18018/) (2024)
- [Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding](https://mlsanity.com/paper/2503.11392/) (2025)
- [MoSFormer: Augmenting Temporal Context with Memory of Surgery for Surgical Phase Recognition](https://mlsanity.com/paper/2503.00695/) (2025)

## Abstract (arXiv)

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 largely unexplored. We introduce a framework that uses microscope views as a shared anchor to bridge surgical narrations and intraoperative OCT (iOCT) without requiring a fully synchronized tri-modal dataset, leveraging real microscope-narration videos and a synthetic dataset of synchronized microscope video and tool-aligned iOCT pairs. Contrastive alignment transfers structural priors from the synthetic domain to real videos lacking iOCT, and a dual-head MS-TCN++ integrates the resulting embeddings for joint macro- and micro-phase prediction. Evaluated on real vitreoretinal surgeries, our framework improves macro-phase recognition over a zero-shot baseline (mean F1 0.38 to 0.53) and provides an exploratory route to estimating fine-grained instrument-tissue measurements that are not directly observable in real microscope video alone; these micro-phase estimates are validated quantitatively on synthetic data and shown only qualitatively on real surgery. To our knowledge, this is the first work to unify microscope view, iOCT B-scans, and surgical narrations in a shared latent space for surgical phase recognition.