CathAction: A Benchmark for Endovascular Intervention Understanding

Baoru Huang; Tuan Vo; Chayun Kongtongvattana; Giulio Dagnino; Dennis Kundrat; Wenqiang Chi; Mohamed Abdelaziz; Trevor Kwok; Tudor Jianu; Tuong Do; Hieu Le; M. Nguyen; Hoan Nguyen; Erman Tjiputra; Q. Tran; Jianyang Xie; Yanda Meng; Binod Bhattarai; Zhaorui Tan; Hongbin Liu; Hong Seng Gan; W. Wang; Xi Yang; Qiufeng Wang; Jionglong Su; Kaizhu Huang; Angelos Stefanidis; Min Guo; Bo Du; Rong Tao; Minh Vu; Guoyan Zheng; Yalin Zheng; Francisco Vasconcelos; Danail Stoyanov; Daniel Elson; Ferdinando Rodriguez y Baena; Anh Nguyen

doi:10.48550/arXiv.2408.13126

CathAction: A Benchmark for Endovascular Intervention Understanding

Baoru Huang, Tuan Vo, Chayun Kongtongvattana, Giulio Dagnino, Dennis Kundrat, Wenqiang Chi, Mohamed Abdelaziz, Trevor Kwok, Tudor Jianu, Tuong Do, Hieu Le, M. Nguyen, Hoan Nguyen, Erman Tjiputra, Q. Tran, Jianyang Xie, Yanda Meng, Binod Bhattarai, Zhaorui Tan, Hongbin LiuHong Seng Gan, W. Wang, Xi Yang, Qiufeng Wang, Jionglong Su, Kaizhu Huang, Angelos Stefanidis, Min Guo, Bo Du, Rong Tao, Minh Vu, Guoyan Zheng, Yalin Zheng, Francisco Vasconcelos, Danail Stoyanov, Daniel Elson, Ferdinando Rodriguez y Baena, Anh Nguyen

Robotics and Mechatronics

Research output: Working paper › Preprint › Academic

40 Downloads (Pure)

Abstract

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/.

Original language	English
Publisher	ArXiv.org
DOIs	https://doi.org/10.48550/arXiv.2408.13126
Publication status	Published - 23 Aug 2024

Keywords

cs.CV

Access to Document

10.48550/arXiv.2408.13126

2408.13126v2Final published version, 2.13 MB

Cite this

@techreport{ee704704677443ba998647051a258ca4,

title = "CathAction: A Benchmark for Endovascular Intervention Understanding",

abstract = "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/. ",

keywords = "cs.CV",

author = "Baoru Huang and Tuan Vo and Chayun Kongtongvattana and Giulio Dagnino and Dennis Kundrat and Wenqiang Chi and Mohamed Abdelaziz and Trevor Kwok and Tudor Jianu and Tuong Do and Hieu Le and M. Nguyen and Hoan Nguyen and Erman Tjiputra and Q. Tran and Jianyang Xie and Yanda Meng and Binod Bhattarai and Zhaorui Tan and Hongbin Liu and Gan, {Hong Seng} and W. Wang and Xi Yang and Qiufeng Wang and Jionglong Su and Kaizhu Huang and Angelos Stefanidis and Min Guo and Bo Du and Rong Tao and Minh Vu and Guoyan Zheng and Yalin Zheng and Francisco Vasconcelos and Danail Stoyanov and Daniel Elson and {Rodriguez y Baena}, Ferdinando and Anh Nguyen",

note = "10 pages. Webpage: https://airvlab.github.io/cathaction/",

year = "2024",

month = aug,

day = "23",

doi = "10.48550/arXiv.2408.13126",

language = "English",

publisher = "ArXiv.org",

type = "WorkingPaper",

institution = "ArXiv.org",

}

Huang, B, Vo, T, Kongtongvattana, C, Dagnino, G, Kundrat, D, Chi, W, Abdelaziz, M, Kwok, T, Jianu, T, Do, T, Le, H, Nguyen, M, Nguyen, H, Tjiputra, E, Tran, Q, Xie, J, Meng, Y, Bhattarai, B, Tan, Z, Liu, H, Gan, HS, Wang, W, Yang, X, Wang, Q, Su, J, Huang, K, Stefanidis, A, Guo, M, Du, B, Tao, R, Vu, M, Zheng, G, Zheng, Y, Vasconcelos, F, Stoyanov, D, Elson, D, Rodriguez y Baena, F & Nguyen, A 2024 'CathAction: A Benchmark for Endovascular Intervention Understanding' ArXiv.org. https://doi.org/10.48550/arXiv.2408.13126

TY - UNPB

T1 - CathAction

T2 - A Benchmark for Endovascular Intervention Understanding

AU - Huang, Baoru

AU - Vo, Tuan

AU - Kongtongvattana, Chayun

AU - Dagnino, Giulio

AU - Kundrat, Dennis

AU - Chi, Wenqiang

AU - Abdelaziz, Mohamed

AU - Kwok, Trevor

AU - Jianu, Tudor

AU - Do, Tuong

AU - Le, Hieu

AU - Nguyen, M.

AU - Nguyen, Hoan

AU - Tjiputra, Erman

AU - Tran, Q.

AU - Xie, Jianyang

AU - Meng, Yanda

AU - Bhattarai, Binod

AU - Tan, Zhaorui

AU - Liu, Hongbin

AU - Gan, Hong Seng

AU - Wang, W.

AU - Yang, Xi

AU - Wang, Qiufeng

AU - Su, Jionglong

AU - Huang, Kaizhu

AU - Stefanidis, Angelos

AU - Guo, Min

AU - Du, Bo

AU - Tao, Rong

AU - Vu, Minh

AU - Zheng, Guoyan

AU - Zheng, Yalin

AU - Vasconcelos, Francisco

AU - Stoyanov, Danail

AU - Elson, Daniel

AU - Rodriguez y Baena, Ferdinando

AU - Nguyen, Anh

N1 - 10 pages. Webpage: https://airvlab.github.io/cathaction/

PY - 2024/8/23

Y1 - 2024/8/23

N2 - 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/.

AB - 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/.

KW - cs.CV

U2 - 10.48550/arXiv.2408.13126

DO - 10.48550/arXiv.2408.13126

M3 - Preprint

BT - CathAction

PB - ArXiv.org

ER -

CathAction: A Benchmark for Endovascular Intervention Understanding

Abstract

Keywords

Access to Document

Fingerprint

Cite this