Neural Radiance Fields for High-Fidelity Soft Tissue Reconstruction in Endoscopy
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.
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)
Stichwörter der Autor:innen
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}
}
EUVIMED