• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

使用神经符号距离函数实现具有帧间形状一致性的增量形状整合，用于三维内窥镜系统。

Incremental shape integration with inter-frame shape consistency using neural SDF for a 3D endoscopic system.

作者信息

Furukawa Ryo, Kawasaki Hiroshi, Sagawa Ryusuke

机构信息

Department of Informatics/Graduate School of System Engineering Kindai University Higashihiroshima Japan.

Faculty of Information Science and Electrical Engineering Department of Advanced Information Technology Kyushu University Fukuoka Japan.

出版信息

Healthc Technol Lett. 2025 Jan 30;12(1):e70001. doi: 10.1049/htl2.70001. eCollection 2025 Jan-Dec.

DOI:10.1049/htl2.70001
PMID:39885982
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11780497/
Abstract

3D measurement for endoscopic systems has been largely demanded. One promising approach is to utilize active-stereo systems using a micro-sized pattern-projector attached to the head of an endoscope. Furthermore, a multi-frame integration is also desired to enlarge the reconstructed area. This paper proposes an incremental optimization technique of both the shape-field parameters and the positional parameters of the cameras and projectors. The method assumes that the input data is temporarily sequential images, that is, endoscopic videos, and the relative positions between the camera and the projector may vary continuously. As solution, a differential volume rendering algorithm in conjunction with neural signed distance field (NeuralSDF) representation is proposed to simultaneously optimize the 3D scene and the camera/projector poses. Also, an incremental optimization strategy where the optimized frames are gradually increased is proposed. In the experiment, the proposed method is evaluated by performing 3D reconstruction using both synthetic and real images, proving the effectiveness of our method.

摘要

内窥镜系统的三维测量需求一直很大。一种很有前景的方法是利用有源立体系统，该系统使用附着在内窥镜头部的微型图案投影仪。此外，还需要进行多帧整合以扩大重建区域。本文提出了一种形状场参数以及相机和投影仪位置参数的增量优化技术。该方法假设输入数据是临时的序列图像，即内窥镜视频，并且相机和投影仪之间的相对位置可能会连续变化。作为解决方案，提出了一种结合神经符号距离场（NeuralSDF）表示的差分体绘制算法，以同时优化三维场景和相机/投影仪姿态。此外，还提出了一种增量优化策略，即逐渐增加优化的帧数。在实验中，通过使用合成图像和真实图像进行三维重建来评估所提出的方法，证明了我们方法的有效性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/27eef51955cd/HTL2-12-e70001-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/3f8d3de0d0db/HTL2-12-e70001-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/2680a08e7df1/HTL2-12-e70001-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/b27b53f765da/HTL2-12-e70001-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/a555d996a079/HTL2-12-e70001-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/bebf7c6a29d1/HTL2-12-e70001-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/330dce421472/HTL2-12-e70001-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/e6884d88dc1a/HTL2-12-e70001-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/47f005be11f5/HTL2-12-e70001-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/7ba81a03305a/HTL2-12-e70001-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/05a5afcb64a9/HTL2-12-e70001-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/7c7d21c2da88/HTL2-12-e70001-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/89a7dd05652f/HTL2-12-e70001-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/27eef51955cd/HTL2-12-e70001-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/3f8d3de0d0db/HTL2-12-e70001-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/2680a08e7df1/HTL2-12-e70001-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/b27b53f765da/HTL2-12-e70001-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/a555d996a079/HTL2-12-e70001-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/bebf7c6a29d1/HTL2-12-e70001-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/330dce421472/HTL2-12-e70001-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/e6884d88dc1a/HTL2-12-e70001-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/47f005be11f5/HTL2-12-e70001-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/7ba81a03305a/HTL2-12-e70001-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/05a5afcb64a9/HTL2-12-e70001-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/7c7d21c2da88/HTL2-12-e70001-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/89a7dd05652f/HTL2-12-e70001-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7be3/11780497/27eef51955cd/HTL2-12-e70001-g003.jpg

相似文献

1
Incremental shape integration with inter-frame shape consistency using neural SDF for a 3D endoscopic system.使用神经符号距离函数实现具有帧间形状一致性的增量形状整合，用于三维内窥镜系统。
Healthc Technol Lett. 2025 Jan 30;12(1):e70001. doi: 10.1049/htl2.70001. eCollection 2025 Jan-Dec.
2
NeRF-based multi-frame 3D integration for 3D endoscopy using active stereo.基于神经辐射场的主动立体多帧3D集成用于3D内窥镜检查
Annu Int Conf IEEE Eng Med Biol Soc. 2024 Jul;2024:1-5. doi: 10.1109/EMBC53108.2024.10782699.
3
Single and multi-frame auto-calibration for 3D endoscopy with differential rendering.用于具有差分渲染的3D内窥镜检查的单帧和多帧自动校准
Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul;2023:1-5. doi: 10.1109/EMBC40787.2023.10340381.
4
Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan.基于卷积神经网络的网格一次性扫描的三维内窥镜系统形状与相机-投影仪参数同步估计
Healthc Technol Lett. 2019 Nov 26;6(6):249-254. doi: 10.1049/htl.2019.0070. eCollection 2019 Dec.
5
Calibration-free structured-light-based 3D scanning system in laparoscope for robotic surgery.用于机器人手术的腹腔镜中基于免校准结构光的3D扫描系统。
Healthc Technol Lett. 2024 Mar 8;11(2-3):196-205. doi: 10.1049/htl2.12083. eCollection 2024 Apr-Jun.
6
Fully Auto-calibrated Active-stereo-based 3D Endoscopic System using Correspondence Estimation with Graph Convolutional Network.基于图卷积网络对应估计的全自动校准主动立体3D内镜系统
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:4357-4360. doi: 10.1109/EMBC44109.2020.9176417.
7
Calibration of a 3D endoscopic system based on active stereo method for shape measurement of biological tissues and specimen.基于主动立体视觉方法的三维内镜系统校准，用于生物组织和标本的形状测量。
Annu Int Conf IEEE Eng Med Biol Soc. 2014;2014:4991-4. doi: 10.1109/EMBC.2014.6944745.
8
3D endoscope system with AR display superimposing dense and wide-angle-of-view 3D points obtained by using micro pattern projector.采用微图案投影仪获得密集且宽视角的 3D 点，并将其与 AR 显示器叠加的 3D 内窥镜系统。
Annu Int Conf IEEE Eng Med Biol Soc. 2022 Jul;2022:881-885. doi: 10.1109/EMBC48229.2022.9871060.
9
2-DOF auto-calibration for a 3D endoscope system based on active stereo.基于主动立体视觉的三维内窥镜系统的二自由度自动校准
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:7937-41. doi: 10.1109/EMBC.2015.7320233.
10
Real-Time Seamless Multi-Projector Displays on Deformable Surfaces.可变形表面上的实时无缝多投影仪显示
IEEE Trans Vis Comput Graph. 2024 May;30(5):2527-2537. doi: 10.1109/TVCG.2024.3372097. Epub 2024 Apr 19.

本文引用的文献

1
Single and multi-frame auto-calibration for 3D endoscopy with differential rendering.用于具有差分渲染的3D内窥镜检查的单帧和多帧自动校准
Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul;2023:1-5. doi: 10.1109/EMBC40787.2023.10340381.
2
EMDQ-SLAM: Real-time High-resolution Reconstruction of Soft Tissue Surface from Stereo Laparoscopy Videos.EMDQ-SLAM：基于立体腹腔镜视频的软组织表面实时高分辨率重建
Med Image Comput Comput Assist Interv. 2021 Sep-Oct;12904:331-340. doi: 10.1007/978-3-030-87202-1_32. Epub 2021 Sep 21.
3
Fully Auto-calibrated Active-stereo-based 3D Endoscopic System using Correspondence Estimation with Graph Convolutional Network.
基于图卷积网络对应估计的全自动校准主动立体3D内镜系统
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:4357-4360. doi: 10.1109/EMBC44109.2020.9176417.
4
Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan.基于卷积神经网络的网格一次性扫描的三维内窥镜系统形状与相机-投影仪参数同步估计
Healthc Technol Lett. 2019 Nov 26;6(6):249-254. doi: 10.1049/htl.2019.0070. eCollection 2019 Dec.
5
Live Tracking and Dense Reconstruction for Handheld Monocular Endoscopy.手持单目内窥镜的实时跟踪和密集重建。
IEEE Trans Med Imaging. 2019 Jan;38(1):79-89. doi: 10.1109/TMI.2018.2856109. Epub 2018 Jul 13.
6
Evaluation and Stability Analysis of Video-Based Navigation System for Functional Endoscopic Sinus Surgery on In Vivo Clinical Data.基于活体临床数据的功能性内窥镜鼻窦手术视频导航系统的评估与稳定性分析。
IEEE Trans Med Imaging. 2018 Oct;37(10):2185-2195. doi: 10.1109/TMI.2018.2833868. Epub 2018 May 7.
7
SLAM-based dense surface reconstruction in monocular Minimally Invasive Surgery and its application to Augmented Reality.基于 SLAM 的单目微创手术中密集表面重建及其在增强现实中的应用。
Comput Methods Programs Biomed. 2018 May;158:135-146. doi: 10.1016/j.cmpb.2018.02.006. Epub 2018 Feb 8.
8
An efficient EM-ICP algorithm for symmetric consistent non-linear registration of point sets.一种用于点集对称一致非线性配准的高效期望最大化-迭代最近点（EM-ICP）算法。
Med Image Comput Comput Assist Interv. 2010;13(Pt 2):594-601. doi: 10.1007/978-3-642-15745-5_73.