mlsanityData to 7 Oct 2026

MURPHY: Relations Matter in Surgical Workflow Analysis

arXiv 2212.12719 ↗First posted 24 Dec 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Autonomous robotic surgery has advanced significantly based on analysis of visual and temporal cues in surgical workflow, but relational cues from domain knowledge remain under investigation. Complex relations in surgical annotations can be divided into intra- and inter-relations, both valuable to autonomous systems to comprehend surgical workflows. Intra- and inter-relations describe the relevance of various categories within a particular annotation type and the relevance of different annotation types, respectively. This paper aims to systematically investigate the importance of relational cues in surgery. First, we contribute the RLLS12M dataset, a large-scale collection of robotic left lateral sectionectomy (RLLS), by curating 50 videos of 50 patients operated by 5 surgeons and annotating a hierarchical workflow, which consists of 3 inter- and 6 intra-relations, 6 steps, 15 tasks, and 38 activities represented as the triplet of 11 instruments, 8 actions, and 16 objects, totaling 2,113,510 video frames and 12,681,060 annotation entities. Correspondingly, we propose a multi-relation purification hybrid network (MURPHY), which aptly incorporates novel relation modules to augment the feature representation by purifying relational features using the intra- and inter-relations embodied in annotations. The intra-relation module leverages a R-GCN to implant visual features in different graph relations, which are aggregated using a targeted relation purification with affinity information measuring label consistency and feature similarity. The inter-relation module is motivated by attention mechanisms to regularize the influence of relational features based on the hierarchy of annotation types from the domain knowledge. Extensive experimental results on the curated RLLS dataset confirm the effectiveness of our approach, demonstrating that relations matter in surgical workflow analysis.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 24 Dec 2022.

Builds on

35 of 56 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2016EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videoscited by 366
  10. 2020TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networkscited by 139
  11. 2021Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videoscited by 139
  12. 2020Surgical Data Science -- from Concepts toward Clinical Translationcited by 105
23 more
  1. 2021Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformercited by 93
  2. 2019Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysiscited by 75
  3. 2020Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Tripletscited by 66
  4. 2021Temporal Memory Relation Network for Workflow Recognition from Surgical Videocited by 66
  5. 2021OperA: Attention-Regularized Transformers for Surgical Phase Recognitioncited by 60
  6. 2020Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Roomcited by 47
  7. 2022CholecTriplet2021: A benchmark challenge for surgical action triplet recognitioncited by 44
  8. 2021Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedurescited by 42
  9. 2016The TUM LapChole dataset for the M2CAI 2016 workflow challengecited by 37
  10. 2022Towards Holistic Surgical Scene Understandingcited by 33
  11. 2022Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentationcited by 27
  12. 2018Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networkscited by 24
  13. 2020Automatic Gesture Recognition in Robot-assisted Surgery with Reinforcement Learning and Tree Searchcited by 23
  14. 2019ImageGCN: Multi-Relational Image Graph Convolutional Networks for Disease Identification with Chest X-rayscited by 22
  15. 2020Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detectioncited by 22
  16. 2016Recognizing Surgical Activities with Recurrent Neural Networkscited by 21
  17. 2020Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgerycited by 17
  18. 2020Multi-Task Recurrent Neural Network for Surgical Gesture Recognition and Progress Predictioncited by 16
  19. 2020Temporal Segmentation of Surgical Sub-tasks through Deep Learning with Multiple Data Sourcescited by 12
  20. 2020Aggregating Long-Term Context for Learning Laparoscopic and Robot-Assisted Surgical Workflowscited by 10
  21. 2018Future-State Predicting LSTM for Early Surgery Type Recognitioncited by 9
  22. 2022Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applicationscited by 7
  23. 2021Surgical Gesture Recognition Based on Bidirectional Multi-Layer Independently RNN with Explainable Spatial Feature Extractioncited by 5

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024Instrument-tissue Interaction Detection Framework for Surgical Video Understandingcited by 8
  2. 2025ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detectioncited by 4
  3. 2024Label-supervised surgical instrument segmentation using temporal equivariance and semantic continuitycited by 0