利用残差Beylkin-Coifman-Rokhlin神经网络求解显微成像反问题
Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
AI总结：
本文提出一种基于物理约束的残差Beylkin-Coifman-Rokhlin神经网络，用于显微成像反问题，通过减少冗余参数提升效率和性能。
摘要：
光学显微镜的反演解卷积指的是从图像中恢复物体细节，揭示样本的真实情况。传统显微镜中显式方法依赖于成像过程中点扩散函数（PSF）。然而，这些方法常常因PSF模型不准确和噪声伪影而效果不佳，影响整体恢复质量。本文将光学解卷积视为反问题。受Beylkin、Coifman和Rokhlin（BCR）引入的非标准形式压缩方案启发，我们提出了一种创新的物理约束神经网络Multi-Stage Residual-BCR Net（m-rBCR）来近似光学解卷积。我们验证了m-rBCR模型在四个显微镜数据集上的性能，包括两个来自ImageNet和BioSR的模拟显微镜数据集、真实的dSTORM显微镜图像和真实的宽场显微镜图像。与显式解卷积方法（如Richardson-Lucy）和其他最先进的神经网络模型（U-Net、DDPM、CARE、DnCNN、ESRGAN、RCAN、Noise2Noise、MPRNet和MIMO-U-Net）相比，m-rBCR在两个真实显微镜数据集和模拟BioSR数据集上通过PSNR和SSIM指标表现出色。在模拟ImageNet数据集中，m-rBCR排名第二（仅次于MIMO-U-Net）。基于光学物理的骨干网络，m-rBCR利用可训练参数，性能从约30倍少于基准MIMO-U-Net到约210倍优于ESRGAN。这使m-rBCR能够实现更短的运行时间（从约3倍快于MIMO-U-Net到约300倍快于DDPM）。总之，通过利用物理约束，我们的模型在专业神经网络候选者中显著减少了潜在冗余参数，并实现了高效性能。
英文摘要：
Optic deconvolution in light microscopy (LM) refers to recovering the object details from images, revealing the ground truth of samples. Traditional explicit methods in LM rely on the point spread function (PSF) during image acquisition. Yet, these approaches often fall short due to inaccurate PSF models and noise artifacts, hampering the overall restoration quality. In this paper, we approached the optic deconvolution as an inverse problem. Motivated by the nonstandard-form compression scheme introduced by Beylkin, Coifman, and Rokhlin (BCR), we proposed an innovative physics-informed neural network Multi-Stage Residual-BCR Net (m-rBCR) to approximate the optic deconvolution. We validated the m-rBCR model on four microscopy datasets - two simulated microscopy datasets from ImageNet and BioSR, real dSTORM microscopy images, and real widefield microscopy images. In contrast to the explicit deconvolution methods (e.g. Richardson-Lucy) and other state-of-the-art NN models (U-Net, DDPM, CARE, DnCNN, ESRGAN, RCAN, Noise2Noise, MPRNet, and MIMO-U-Net), the m-rBCR model demonstrates superior performance to other candidates by PSNR and SSIM in two real microscopy datasets and the simulated BioSR dataset. In the simulated ImageNet dataset, m-rBCR ranks the second-best place (right after MIMO-U-Net). With the backbone from the optical physics, m-rBCR exploits the trainable parameters with better performances (from ~30 times fewer than the benchmark MIMO-U-Net to ~210 times than ESRGAN). This enables m-rBCR to achieve a shorter runtime (from ~3 times faster than MIMO-U-Net to ~300 times faster than DDPM). To summarize, by leveraging physics constraints our model reduced potentially redundant parameters significantly in expertise-oriented NN candidates and achieved high efficiency with superior performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
