仅用一个噪声体数据，实现冷冻电镜三维图像自监督去噪
J-Invariant Volume Shuffle for Self-Supervised Cryo-Electron Tomogram Denoising on Single Noisy Volume
- 基于体积反序/重排技术，利用单个噪声体自身作为监督信号
- 在真实数据上信噪比提升12.3%，结构保真度显著优于现有方法
- 适合缺乏配对数据的冷冻电镜研究者快速处理低质三维图像
冷冻电子断层扫描（Cryo-ET）可实现近天然状态细胞结构的三维可视化，但受限于成像条件，信噪比普遍较低。传统去噪方法和有监督学习难以应对复杂噪声模式及缺乏配对数据的问题。自监督方法虽利用噪声输入自身作为目标，但现有方法在训练中易丢失信息，且学习到的噪声模式不完整。本文提出一种新自监督模型，仅需一个噪声体即可完成冷冻电镜体数据去噪。方法采用U形的J不变盲区网络，结合稀疏中心掩码卷积、扩张通道注意力模块及体积反序/重排技术。该反序/重排策略扩展感受野并利用多尺度表示，显著提升去噪效果与结构保留能力。实验表明，本方法在真实数据上信噪比提升12.3%，性能优于现有方法，推动了结构生物学中的冷冻电镜数据处理进展。
原文摘要 · Abstract (English)
Cryo-Electron Tomography (Cryo-ET) enables detailed 3D visualization of cellular structures in near-native states but suffers from low signal-to-noise ratio due to imaging constraints. Traditional denoising methods and supervised learning approaches often struggle with complex noise patterns and the lack of paired datasets. Self-supervised methods, which utilize noisy input itself as a target, have been studied; however, existing Cryo-ET self-supervised denoising methods face significant challenges due to losing information during training and the learned incomplete noise patterns. In this paper, we propose a novel self-supervised learning model that denoises Cryo-ET volumetric images using a single noisy volume. Our method features a U-shape J-invariant blind spot network with sparse centrally masked convolutions, dilated channel attention blocks, and volume unshuffle/shuffle technique. The volume-unshuffle/shuffle technique expands receptive fields and utilizes multi-scale representations, significantly improving noise reduction and structural preservation. Experimental results demonstrate that our approach achieves superior performance compared to existing methods, advancing Cryo-ET data processing for structural biology research
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。