EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural Radiance Fields for High-Fidelity Soft Tissue Reconstruction in Endoscopy

Jinhua Liu iD, Yongsheng Shi iD, Dongjin Huang, Jiantao Qu

Sensors · 19.01.2025 · 25 (2) · 565

DOI: 10.3390/s25020565 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.01.2025. Verfasst von Jinhua Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Film Academy, Shanghai University, Shanghai 200072, China. Hauptthemen laut MEDLINE: Endoscopy, Imaging, Three-Dimensional, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Science and Technology Projects of National Archives Administration of China, the Shanghai Talent Development Funding of China, National Archives Administration of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advancement of neural radiance fields (NeRFs) has facilitated the high-quality 3D reconstruction of complex scenes. However, for most NeRFs, reconstructing 3D tissues from endoscopy images poses significant challenges due to the occlusion of soft tissue regions by invalid pixels, deformations in soft tissue, and poor image quality, which severely limits their application in endoscopic scenarios. To address the above issues, we propose a novel framework to reconstruct high-fidelity soft tissue scenes from low-quality endoscopic images. We first construct an EndoTissue dataset of soft tissue regions in endoscopic images and fine-tune the Segment Anything Model (SAM) based on EndoTissue to obtain a potent segmentation network. Given a sequence of monocular endoscopic images, this segmentation network can quickly obtain the tissue mask images. Additionally, we incorporate tissue masks into a dynamic scene reconstruction method called Tensor4D to effectively guide the reconstruction of 3D deformable soft tissues. Finally, we propose adopting the image enhancement model EDAU-Net to improve the quality of the rendered views. The experimental results show that our method can effectively focus on the soft tissue regions in the image, achieving higher fidelity in detail and geometric structural integrity in reconstruction compared to state-of-the-art algorithms. Feedback from the user study indicates high participant scores for our method.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EndoscopyImaging, Three-DimensionalImage Processing, Computer-AssistedHumansAlgorithmsNeural Networks, Computer

Stichwörter der Autor:innen

3D reconstructionendoscopic imageimage segmentationneural radiance fieldssoft tissue dynamics

Autor:innen und Institutionen

  • Shanghai Film Academy, Shanghai University, Shanghai 200072, China.
  • Shanghai Engineering Research Center of Motion Picture Special Effects, Shanghai 200072, China.

ORCID-Profile: Jinhua Liu, Yongsheng Shi

Förderung

  • the Science and Technology Projects of National Archives Administration of China
  • the Shanghai Talent Development Funding of China
  • National Archives Administration of China
  • Shanghai Talent Development Funding of China

Zitieren

APA

Liu, J., Shi, Y., Huang, D., & Qu, J. (2025). Neural Radiance Fields for High-Fidelity Soft Tissue Reconstruction in Endoscopy. Sensors, 25(2), 565. https://doi.org/10.3390/s25020565

Vancouver

Liu J, Shi Y, Huang D, Qu J. Neural Radiance Fields for High-Fidelity Soft Tissue Reconstruction in Endoscopy. Sensors. 2025;25(2):565. doi:10.3390/s25020565

BibTeX
@article{Liu2025,
  author = {Liu, Jinhua and Shi, Yongsheng and Huang, Dongjin and Qu, Jiantao},
  title = {Neural Radiance Fields for High-Fidelity Soft Tissue Reconstruction in Endoscopy},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {2},
  pages = {565},
  doi = {10.3390/s25020565}
}
Kostenlos starten →