Advanced search
1 file | 11.70 MB Add to list

Towards abdominal 3-D scene rendering from laparoscopy surgical videos using NeRFs

Khoa Tuan Nguyen (UGent) , Francesca Tozzi (UGent) , Nikdokht Rashidian (UGent) , Wouter Willaert (UGent) , Joris Vankerschaver (UGent) and Wesley De Neve (UGent)
Author
Organization
Abstract
Given that a conventional laparoscope only provides a two-dimensional (2-D) view, the detection and diagnosis of medical ailments can be challenging. To overcome the visual constraints associated with laparoscopy, the use of laparoscopic images and videos to reconstruct the three-dimensional (3-D) anatomical structure of the abdomen has proven to be a promising approach. Neural Radiance Fields (NeRFs) have recently gained attention thanks to their ability to generate photo-realistic images from a 3-D static scene, thus facilitating a more comprehensive exploration of the abdomen through the synthesis of new views. This distinguishes NeRFs from alternative methods such as Simultaneous Localization and Mapping (SLAM) and depth estimation. In this paper, we present a comprehensive examination of NeRFs in the context of laparoscopy surgical videos, with the goal of rendering abdominal scenes in 3-D. Although our experimental results are promising, the proposed approach encounters substantial challenges, which require further exploration in future research.
Keywords
RECONSTRUCTION, 3-D reconstruction, Laparoscopy, Neural Rendering, View Synthesis

Downloads

  • (...).pdf
    • full text (Accepted manuscript)
    • |
    • UGent only (changes to open access on 2024-10-16)
    • |
    • PDF
    • |
    • 11.70 MB

Citation

Please use this url to cite or link to this publication:

MLA
Nguyen, Khoa Tuan, et al. “Towards Abdominal 3-D Scene Rendering from Laparoscopy Surgical Videos Using NeRFs.” MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I, vol. 14348, Springer, 2024, pp. 83–93, doi:10.1007/978-3-031-45673-2_9.
APA
Nguyen, K. T., Tozzi, F., Rashidian, N., Willaert, W., Vankerschaver, J., & De Neve, W. (2024). Towards abdominal 3-D scene rendering from laparoscopy surgical videos using NeRFs. MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I, 14348, 83–93. https://doi.org/10.1007/978-3-031-45673-2_9
Chicago author-date
Nguyen, Khoa Tuan, Francesca Tozzi, Nikdokht Rashidian, Wouter Willaert, Joris Vankerschaver, and Wesley De Neve. 2024. “Towards Abdominal 3-D Scene Rendering from Laparoscopy Surgical Videos Using NeRFs.” In MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I, 14348:83–93. Springer. https://doi.org/10.1007/978-3-031-45673-2_9.
Chicago author-date (all authors)
Nguyen, Khoa Tuan, Francesca Tozzi, Nikdokht Rashidian, Wouter Willaert, Joris Vankerschaver, and Wesley De Neve. 2024. “Towards Abdominal 3-D Scene Rendering from Laparoscopy Surgical Videos Using NeRFs.” In MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I, 14348:83–93. Springer. doi:10.1007/978-3-031-45673-2_9.
Vancouver
1.
Nguyen KT, Tozzi F, Rashidian N, Willaert W, Vankerschaver J, De Neve W. Towards abdominal 3-D scene rendering from laparoscopy surgical videos using NeRFs. In: MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I. Springer; 2024. p. 83–93.
IEEE
[1]
K. T. Nguyen, F. Tozzi, N. Rashidian, W. Willaert, J. Vankerschaver, and W. De Neve, “Towards abdominal 3-D scene rendering from laparoscopy surgical videos using NeRFs,” in MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I, Vancouver, CANADA, 2024, vol. 14348, pp. 83–93.
@inproceedings{01HKYHYMJJGX2MGJV02D666BP5,
  abstract     = {{Given that a conventional laparoscope only provides a two-dimensional (2-D) view, the detection and diagnosis of medical ailments can be challenging. To overcome the visual constraints associated with laparoscopy, the use of laparoscopic images and videos to reconstruct the three-dimensional (3-D) anatomical structure of the abdomen has proven to be a promising approach. Neural Radiance Fields (NeRFs) have recently gained attention thanks to their ability to generate photo-realistic images from a 3-D static scene, thus facilitating a more comprehensive exploration of the abdomen through the synthesis of new views. This distinguishes NeRFs from alternative methods such as Simultaneous Localization and Mapping (SLAM) and depth estimation. In this paper, we present a comprehensive examination of NeRFs in the context of laparoscopy surgical videos, with the goal of rendering abdominal scenes in 3-D. Although our experimental results are promising, the proposed approach encounters substantial challenges, which require further exploration in future research.}},
  author       = {{Nguyen, Khoa Tuan and Tozzi, Francesca and Rashidian, Nikdokht and Willaert, Wouter and Vankerschaver, Joris and De Neve, Wesley}},
  booktitle    = {{MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I}},
  isbn         = {{9783031456725}},
  issn         = {{0302-9743}},
  keywords     = {{RECONSTRUCTION,3-D reconstruction,Laparoscopy,Neural Rendering,View Synthesis}},
  language     = {{eng}},
  location     = {{Vancouver, CANADA}},
  pages        = {{83--93}},
  publisher    = {{Springer}},
  title        = {{Towards abdominal 3-D scene rendering from laparoscopy surgical videos using NeRFs}},
  url          = {{http://doi.org/10.1007/978-3-031-45673-2_9}},
  volume       = {{14348}},
  year         = {{2024}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: