Katz Jonathan E, Finegan Jamie, Beutelspacher Pablo F, Lu Jingpei, Lin Shan, Yip Michael, Sur Roger L
Urology, University of California San Diego, San Diego, USA.
Electrical and Computer Engineering, University of California San Diego, San Diego, USA.
Cureus. 2025 Aug 11;17(8):e89825. doi: 10.7759/cureus.89825. eCollection 2025 Aug.
Recent developments in neural radiance field (NeRF) processing have leveraged the power of neural networks to quickly reconstruct 3D spaces from 2D images. Our objective was to utilize this technology to 3D render video recordings of diagnostic cystoscopies and test their fidelity. With institutional review board (IRB) approval, we recorded two diagnostic cystoscopies, one with an Ambu single-use flexible cystoscope and the other with a Richard Wolf digital cystoscope. We converted the videos to images and manually curated approximately 100 representative images, which minimized blur and spanned a large segment of the bladder. We then utilized the NVIDIA Instant Neural Graphics Primitives (iNGP), a NeRF algorithm that uses multiresolution hash encoding with a compact neural network for significantly faster convergence, to reconstruct the bladder and render novel, unseen views within seconds. We computed the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) to assess the quality and fidelity of the 3D rendering. Both videos were able to be utilized for 3D rendering using iNGP. The rendering derived from the Richard Wolf cystoscopy had a PSNR = 29.8 (min = 27.2, max = 32.6) and SSIM = 0.89. Similarly, the rendering derived from the Ambu cystoscopy had a PSNR = 31.3 (min = 27.1, max = 35.1) and SSIM = 0.90. Independent of cystoscopy equipment, both 3D renderings achieved reasonable fidelity. Major limitations to widespread adoption of this technology include the need for a curator to select representative and high-quality images from the initial cystoscopy video recording and the relatively small segments of bladder successfully rendered. Nonetheless, we feel that with further refinement, this technology can be scaled to create 3D renderings of cystoscopies that will enable evaluation of both completeness and quality of the cystoscopy. Furthermore, this technology would be able to facilitate the comparison of cystoscopies performed in the same patient over time.
神经辐射场（NeRF）处理技术的最新进展借助神经网络的强大功能，能够从二维图像快速重建三维空间。我们的目标是利用这项技术对诊断性膀胱镜检查的视频进行三维渲染，并测试其逼真度。在获得机构审查委员会（IRB）批准后，我们录制了两次诊断性膀胱镜检查视频，一次使用的是阿姆布一次性软性膀胱镜，另一次使用的是理查德·沃尔夫数字膀胱镜。我们将视频转换为图像，并手动挑选了大约100张具有代表性的图像，这些图像尽量减少了模糊，并且涵盖了膀胱的大部分区域。然后，我们使用NVIDIA即时神经图形原语（iNGP），这是一种NeRF算法，它使用多分辨率哈希编码和紧凑神经网络，以实现更快的收敛，从而在几秒钟内重建膀胱并渲染出全新的、未见的视角。我们计算了结构相似性指数（SSIM）和峰值信噪比（PSNR），以评估三维渲染的质量和逼真度。两个视频都能够使用iNGP进行三维渲染。来自理查德·沃尔夫膀胱镜检查的渲染结果的PSNR = 29.8（最小值 = 27.2，最大值 = 32.6），SSIM = 0.89。同样，来自阿姆布膀胱镜检查的渲染结果的PSNR = 31.3（最小值 = 27.1，最大值 = 35.1），SSIM = 0.90。与膀胱镜检查设备无关，两种三维渲染都达到了合理的逼真度。这项技术广泛应用的主要限制包括需要一名编辑人员从最初的膀胱镜检查视频记录中选择具有代表性的高质量图像，以及成功渲染的膀胱区域相对较小。尽管如此，我们认为通过进一步改进，这项技术可以扩大规模，以创建膀胱镜检查的三维渲染，从而能够评估膀胱镜检查的完整性和质量。此外，这项技术将能够促进对同一患者不同时间进行的膀胱镜检查的比较。
