发表机构
University Hospital Cologne; Center for Molecular Medicine Cologne (CMMC), University of Cologne; Cluster of Excellence Cellular Stress Responses in Aging-Associated Diseases (CECAD), University of Cologne; MedTechLabs, Karolinska University Hospital; Karolinska Institutet; Royal Institute of Technology (KTH)（科隆大学医院; 科隆大学科隆分子医学中心; 科隆大学衰老相关疾病细胞应激反应卓越集群; 卡罗林斯卡大学医院 MedTechLabs; 卡罗林斯卡学院; 皇家理工学院（KTH））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出端到端GPU加速框架，适配3D U-Net与SwinUNETR骨干，以连续性损失抑制伪影，实现无密集标注的各向异性生物结构全自动三维形态计量，在GBM分析中达到专家间分割准确率。
AI 中文摘要
光学透明和溶胀组织的共聚焦显微镜可解析三维复杂生物结构，但这类成像存在高度各向异性：欠采样的轴向方向上结构可能呈现不连续性，阻碍重建与自动定量分析。常规解决方案是在训练分割模型前将轴向维度上采样为各向同性体积，这需要上采样空间中的密集标注，标注负担极高。我们提出一种端到端、GPU加速的框架，无需额外标注即可克服上述问题。模型在原始采集体积上训练，训练块的随机旋转利用已良好解析的横向平面补充缺失的轴向信息，z轴连续性损失则保持相邻切片一致性。我们适配卷积（3D U-Net）和Transformer（SwinUNETR）两种骨干网络，通过高斯共识聚合重叠块，并在GPU上通过射线-表面相交计算经点扩散函数校正的膜厚度。我们将该方法应用于肾小球基底膜（GBM）——肾脏滤过屏障中薄且高度卷曲的部分，疾病状态下其不规则性会增加。分割准确率达到专家间一致性水平。连续性感知训练提升了重建平滑度，以极小的准确率代价抑制了周期性阶梯状伪影。我们在重建的三维表面上量化GBM厚度，捕捉到与疾病相关的增厚现象，实现了无需密集体积标注或图像复原的生物结构全自动各向异性三维形态计量学分析。
英文摘要
Confocal microscopy of optically cleared and swelled tissue resolves complex biological structures in 3D, but such acquisitions are highly anisotropic: along the under-sampled axial direction the structure can appear discontinuous, hampering reconstruction and automated quantitative analysis. The usual remedy upsamples the axial dimension to an isotropic volume before training a segmentation model, which requires dense annotations in the upsampled space, a prohibitive labeling burden. We present an end-to-end, GPU-accelerated framework that overcomes this without additional annotations. The model is trained on the native acquisition volume; random rotation of training patches leverages the well-resolved lateral plane to supply the missing axial information, and a z-axis continuity loss keeps neighboring slices consistent. We adapt both a convolutional (3D U-Net) and a transformer (SwinUNETR) backbone, aggregate overlapping patches by Gaussian consensus, and compute point-spread-function-corrected membrane thickness by ray-surface intersection on the GPU. We apply the method to the glomerular basement membrane (GBM), a thin, highly convoluted part of the kidney's filtration barrier that grows more irregular in disease. Segmentation accuracy matches inter-expert agreement. Continuity-aware training improves reconstruction smoothness and suppresses a periodic terracing artifact at minimal accuracy cost. We quantify GBM thickness across the reconstructed 3D surface and capture disease-related thickening, enabling fully automated anisotropic 3D morphometry of biological structures without dense volumetric labels or image restoration.
