基于NeRF的关节镜图像三维重建：一项初步的计算机模拟研究
3D Reconstruction from Arthroscopic Images using NeRF: a preliminary in-silico study
浏览论文内容
中文总结 AI 辅助
本研究探索MIS-NeRF在关节镜图像三维重建中的应用，在模拟数据上取得高PSNR、SSIM和低LPIPS，初步验证了可行性，为术前到术中配准奠定基础。
中文摘要 AI 辅助
在膝关节镜手术中，术前与术中解剖结构的精确配准是患者特异性导航的关键步骤。实现精确配准需要在手术过程中对关节进行可靠的三维重建。术前三维模型可通过患者影像的分割与重建获得，但生成术中三维表示仍极具挑战性。关节镜成像存在视野有限、表面纹理低以及强镜面反射等问题，这使得传统的基于特征的三维重建方法不可靠。在本研究中，我们探讨了MIS-NeRF（微创手术神经辐射场）在从单目关节镜图像重建术中膝关节三维模型中的应用。该方法在六个模拟关节镜采集数据上进行了评估，这些数据代表了六个患者特异性的膝关节三维模型。我们给出了定性和定量结果以评估重建质量。重建的膝关节三维模型通过其渲染图像进行评估，达到了PSNR（峰值信噪比）31.88 ± 2.82，SSIM（结构相似性指数）0.98 ± 0.004，以及LPIPS（学习感知图像块相似性）0.017 ± 0.006。这些初步结果表明，在关节镜这一具有挑战性的背景下，基于NeRF的重建具有可行性，并可能成为迈向计算机辅助骨科手术中精确的计算机模拟术前到术中三维配准的有前景的一步。此外，需要在真实关节镜数据上进行验证以评估临床适用性。
英文摘要
In knee arthroscopy surgery, accurate registration between preoperative and intraoperative anatomy is a critical step for patient-specific navigation. Achieving an accurate registration requires a reliable 3D reconstruction of the joint during surgery. Preoperative 3D models can be obtained from patient imaging through segmentation and reconstruction, but generating an intraoperative 3D representation remains particularly challenging. Arthroscopic imaging suffers from a limited field of view, low surface texture, and strong specular reflections, which make conventional feature-based 3D reconstruction methods unreliable. In this work, we investigate the application of MIS-NeRF (Minimally-Invasive Surgery Neural Radiance Fields) for reconstructing intraoperative knee 3D models from monocular arthroscopic images. The approach is evaluated on six simulated arthroscopic acquisitions representing six patient-specific knee 3D models. Both qualitative and quantitative results are presented to assess the reconstruction quality. The reconstructed knee 3D models were evaluated through their rendered images, achieving PSNR (Peak Signal-to-Noise Ratio) of 31.88 $\pm$ 2.82, SSIM (Structural Similarity Index) of 0.98 $\pm$ 0.004 and LPIPS (Learned Perceptual Image Patch Similarity) of 0.017 $\pm$ 0.006. These preliminary results suggest the feasibility of NeRF-based reconstruction in the challenging context of arthroscopy and may represent a promising step toward accurate in-silico preoperative-to-intraoperative 3D registration for computer-assisted orthopedic surgery. Further, validation on real arthroscopic data will be necessary to assess clinical applicability.
发表机构
- LaTIM - UMR 1101 INSERM（INSERM LaTIM联合研究单位）
- University of Western Brittany（布列塔尼大学）
- IMT Atlantique（大西洋理工大学）
- Brest University Hospital（布雷斯特大学医院）
- Universidad de Alcala（阿尔卡拉大学）
- INSA Centre Val de Loire（卢瓦尔河谷国立应用科学学院）
- Rennes University Hospital（雷恩大学医院）
机构由 AI 辅助整理，请以论文原文为准。
