Abstract

Scene graph generation from surgical video enables a holistic and structured understanding of surgical scenes by modeling objects and their semantic relationships. Despite recent advances, state-of-the-art approaches rely on large, parameter-heavy deep learning models that are impractical for deployment in the operating room (OR) due to hard-ware footprint, hygiene constraints, latency, and data privacy concerns. To the best of our knowledge, this is the first scene graph generationmethod built on NCAs and the first NCA framework capable of learningstructured representations. We introduce SG-NCA, a lightweight scene graph generation framework based on Neural Cellular Automata (NCA),designed for inference in fanless devices critical for OR hygiene protocols. SG-NCA is the first scene graph generation combining NCA-based multi-class segmentation for efficient object detection and feature extraction with a lightweight relation predictor. We evaluate SG-NCA on videos of cataract surgery and cholecystectomy, demonstrating performance comparable to established baselines while requiring 55× fewer parameters. We showcase deployment on fanless edge devices better suited for the OR and demonstrate downstream applications such as surgical video captioning, highlighting SG-NCA’s potential for affordable, privacy-preserving, and OR-ready intraoperative scene understanding. Our code is publicly available at:https://github.com/MECLabTUDA/SG-NCA

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SafeSurg_001.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to Open Review

Open Review Page: https://openreview.net/forum?id=rkvFU9smmo

BibTex

@InProceedings{LemNic_Sterilizable_MICCAISAT2026,
        author = { Lemke, Nick AND Sivakumar, Ssharvien Kumar AND Sanner, Antoine P. AND Kalkhof, John AND Krumb, Henry John AND Ghazaei, Ghazal AND Mukhopadhyay, Anirban},
        title = { { Sterilizable Scene Graph Generation for Operating Rooms } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS pending},
        month = {pending},
        page = {pending}
}


back to top