mlsanityData to 14 Oct 2026

CathAction: A Benchmark for Endovascular Intervention Understanding

arXiv 2408.13126 ↗First posted 23 Aug 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Real-time visual feedback from catheterization analysis is crucial for enhancing surgical safety and efficiency during endovascular interventions. However, existing datasets are often limited to specific tasks, small scale, and lack the comprehensive annotations necessary for broader endovascular intervention understanding. To tackle these limitations, we introduce CathAction, a large-scale dataset for catheterization understanding. Our CathAction dataset encompasses approximately 500,000 annotated frames for catheterization action understanding and collision detection, and 25,000 ground truth masks for catheter and guidewire segmentation. For each task, we benchmark recent related works in the field. We further discuss the challenges of endovascular intentions compared to traditional computer vision tasks and point out open research questions. We hope that CathAction will facilitate the development of endovascular intervention understanding methods that can be applied to real-world applications. The dataset is available at https://airvlab.github.io/cathaction/.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 42 of its 89 references that are in the map. First posted on arXiv 23 Aug 2024.

Builds on

42 of 89 references.

References · 42

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  4. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  5. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
  6. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  7. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  8. 2022Vision Transformer with Deformable Attentioncited by 295
  9. 2020A Brief Review of Domain Adaptationcited by 288
  10. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 187
  11. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  12. 2021BEVT: BERT Pretraining of Video Transformerscited by 169
30 more
  1. 2017Domain Adaptation for Visual Applications: A Comprehensive Surveycited by 128
  2. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 123
  3. 2018When will you do what? - Anticipating Temporal Occurrences of Activitiescited by 107
  4. 2022SegViT: Semantic Segmentation with Plain Vision Transformerscited by 106
  5. 2019What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attentioncited by 105
  6. 2023Large AI Models in Health Informatics: Applications, Challenges, and the Futurecited by 61
  7. 2023LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matchingcited by 60
  8. 2019You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localizationcited by 59
  9. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  10. 2019STEP: Spatio-Temporal Progressive Learning for Video Action Detectioncited by 51
  11. 2020Effective Fusion Factor in FPN for Tiny Object Detectioncited by 44
  12. 2022Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipationcited by 41
  13. 2022Holistic Interaction Transformer Network for Action Detectioncited by 28
  14. 2022Source-Free Progressive Graph Learning for Open-Set Domain Adaptationcited by 25
  15. 2020End-to-End Real-time Catheter Segmentation with Optical Flow-Guided Warping during Endovascular Interventioncited by 20
  16. 2022Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistencycited by 19
  17. 2022YOLOV: Making Still Image Object Detectors Great at Video Object Detectioncited by 18
  18. 2023Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performancescited by 16
  19. 2017Fully Automatic and Real-Time Catheter Segmentation in X-Ray Fluoroscopycited by 13
  20. 2023Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detectioncited by 12
  21. 2022CathSim: An Open-source Simulator for Endovascular Interventioncited by 11
  22. 2018Deep Segmentation and Registration in X-Ray Angiography Videocited by 9
  23. 2018Automatic catheter detection in pediatric X-ray images using a scale-recurrent network and synthetic datacited by 7
  24. 2018Medical Technologies and Challenges of Robot Assisted Minimally Invasive Intervention and Diagnosticscited by 6
  25. 2017Model-based Catheter Segmentation in MRI-imagescited by 4
  26. 2023Shape-Sensitive Loss for Catheter and Guidewire Segmentationcited by 4
  27. 2024Autonomous Catheterization with Open-source Simulator and Expert Trajectorycited by 4
  28. 2017HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localizationcited by 3
  29. 2022YOWO-Plus: An Incremental Improvementcited by 2
  30. 2021Inertial Sensor Data To Image Encoding For Human Action Recognitioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

  1. 2024SurgicalGS: Dynamic 3D Gaussian Splatting for Accurate Robotic-Assisted Surgical Scene Reconstructioncited by 14
  2. 2025FedEFM: Federated Endovascular Foundation Model with Unseen Datacited by 2
  3. 2025Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutionscited by 2
  4. 2026Towards Real-Time Autonomous Navigation: Transformer-Based Catheter Tip Tracking in Fluoroscopycited by 1
  5. 2026Dual-Part Multi-Lateral Branched Network for Multi-Class Segmentation in Cardiovascular Catheterization Angiogramscited by 0
  6. 2026Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federated Learning Settingcited by 0