Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Mamba-based modulated fusion model for video moment retrieval.

Scientific reports·2026
Same author

Commentary: The association between uric acid to high-density cholesterol ratio and depression: A population-based cross-sectional study.

Journal of affective disorders·2025
Same author

Diffusion-driven multi-modality medical image fusion.

Medical & biological engineering & computing·2025
Same author

Universal Image Restoration with Text Prompt Diffusion.

Sensors (Basel, Switzerland)·2024
Same author

Deep polyp image enhancement using region of interest with paired supervision.

Computers in biology and medicine·2023
Same author

Deep unsupervised endoscopic image enhancement based on multi-image fusion.

Computer methods and programs in biomedicine·2022

Related Experiment Video

Updated: May 31, 2025

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

9.7K

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

Jinhua Liu1, Yongsheng Shi1, Dongjin Huang1,2

  • 1Shanghai Film Academy, Shanghai University, Shanghai 200072, China.

Sensors (Basel, Switzerland)
|January 25, 2025
PubMed
Summary

This study introduces a new framework for high-fidelity 3D reconstruction of soft tissues from endoscopic images. The method uses advanced segmentation and dynamic scene reconstruction to overcome challenges like poor image quality and tissue deformation.

Keywords:
3D reconstructionendoscopic imageimage segmentationneural radiance fieldssoft tissue dynamics

More Related Videos

Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery
11:05

Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery

Published on: September 19, 2014

12.1K
Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.0K

Related Experiment Videos

Last Updated: May 31, 2025

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

9.7K
Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery
11:05

Tissue-simulating Phantoms for Assessing Potential Near-infrared Fluorescence Imaging Applications in Breast Cancer Surgery

Published on: September 19, 2014

12.1K
Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.0K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • 3D Reconstruction

Background:

  • Neural Radiance Fields (NeRFs) enable high-quality 3D scene reconstruction.
  • Reconstructing 3D soft tissues from endoscopic images is challenging due to occlusions, deformations, and low image quality.
  • Existing NeRF methods struggle with the specific constraints of endoscopic soft tissue imaging.

Purpose of the Study:

  • To develop a novel framework for high-fidelity 3D reconstruction of soft tissue scenes from low-quality endoscopic images.
  • To address limitations of current NeRFs in endoscopic applications.
  • To improve the accuracy and detail of 3D soft tissue models derived from endoscopic data.

Main Methods:

  • Constructed the EndoTissue dataset for soft tissue segmentation.
  • Fine-tuned the Segment Anything Model (SAM) for potent tissue segmentation, generating tissue masks.
  • Integrated tissue masks into the Tensor4D dynamic scene reconstruction method.
  • Employed the EDAU-Net image enhancement model to improve rendered view quality.

Main Results:

  • The proposed framework effectively focuses on soft tissue regions in endoscopic images.
  • Achieved higher fidelity in detail and geometric structural integrity compared to state-of-the-art algorithms.
  • User study feedback indicated high participant satisfaction with the reconstruction quality.

Conclusions:

  • The novel framework significantly enhances 3D soft tissue reconstruction from challenging endoscopic imagery.
  • The integration of SAM-based segmentation and Tensor4D reconstruction overcomes key limitations.
  • The method shows promise for improved applications in endoscopic scenarios requiring accurate 3D tissue modeling.