Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

SurgiSR4K: A High-Resolution Endoscopic Video Dataset for Robotic-Assisted Minimally Invasive Procedures

Created by
  • Haebom

Author

Fengyi Jiang, Xiaorui Zhang, Lingbo Jin, Ruixing Liang, Yuxin Chen, Adi Chola Venkatesh, Jason Culman, Tiantian Wu, Lirong Shao, Wenqing Sun, Cong Gao, Hallie McNamara, Jingpei Lu, Omid Mohareri

Outline

SurgiSR4K is the first publicly available native 4K resolution surgical image and video dataset specifically designed for robotic-assisted minimally invasive surgery (MIS). It reflects a realistic robotic surgical environment, including various visual scenarios such as reflection, instrument occlusion, bleeding, and soft tissue deformation. The super-resolution data can be used for various computer vision tasks such as super-resolution (SR), smoke removal, surgical instrument detection, 3D tissue reconstruction, monocular depth estimation, instance segmentation, novel view synthesis, and vision-language model (VLM) development. It can contribute to the advancement of high-resolution surgical imaging research and the development of intelligent imaging technologies to improve the performance, safety, and usability of image-based robotic surgery.

Takeaways, Limitations

•
Takeaways:
◦
Contributing to enabling research by providing the first publicly available native 4K robotic surgical assistance MIS dataset.
◦
Provides a realistic study environment including various surgical scenarios.
◦
It can be used in various computer vision studies such as super-resolution and surgical instrument detection.
◦
Contributing to the development of high-resolution surgical imaging technology and creating a safe surgical environment.
•
Limitations:
◦
Lack of specific information about the size and diversity of the dataset.
◦
Further validation of the quality and accuracy of the dataset is needed.
◦
Possible bias toward certain surgical types or instruments.
◦
Lack of detailed description of the dataset collection process and ethical considerations.
👍
Made with Slashpage