基于稳定扩散基础模型的无监督多尺度 3D 亚细胞世界分割
Unsupervised Multi-Scale Segmentation of 3D Subcellular World with Stable Diffusion Foundation Model
利用在自然图像上预训练的 Stable Diffusion 基础模型提取特征，结合启发式特征聚合与自适应阈值实现无监督分割，为缺乏标注的专业成像域（如 cryo-ET）提供了一种可复用的伪标签生成与监督模型训练流程。
原文依据 leveraging a Stable Diffusion foundation model pretrained on mostly natural images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出一种无监督方法，用于分割三维体积冷冻电子断层扫描（cryo-ET）图像中的多尺度亚细胞对象。为此，我们解决了若干关键挑战，如缺乏标注数据、数据量庞大、亚细胞形状与尺寸高度异质，以及不同实验和背景下细胞 cryo-ET 图像的高域间变异性。我们的方法仅要求用户从数据集中少数代表性断层图中选取少量切片。方法核心是为相应切片提取特征，利用主要基于自然图像预训练的稳定扩散基础模型。特征提取之后，采用一种新颖的基于启发式的特征聚合策略，并通过自适应阈值化对聚合特征进行分割。所得掩码利用预训练的 CellPose 进行细化以拆分复合区域，随后作为伪真值用于训练监督深度学习模型。我们在公开的 cryo-ET 基准数据集上验证了基于基础模型的无监督流程，性能与专家人工标注高度接近。这一全自动、数据驱动的框架能够挖掘多尺度亚细胞模式，为从大规模细胞 cryo-ET 数据集中加速生物发现铺平了道路。
英文原文摘要 1380 字符
We introduce an unsupervised approach for segmenting multiscale subcellular objects in 3D volumetric cryo-electron tomography (cryo-ET) images. To this end, we address key challenges such as lack of annotated data, large data volumes, high heterogeneity of subcellular shapes and sizes, and high inter-domain variability of cellular cryo-ET images across different experiments and contexts. Our method requires users to only select a small number of slabs from a few representative tomograms in the dataset. The core of our method is extracting features for the corresponding slabs, leveraging a Stable Diffusion foundation model pretrained on mostly natural images. The feature extraction is followed by a novel heuristic-based feature aggregation strategy, and adaptive thresholding to segment the aggregated features. The resulting masks are refined with pretrained CellPose to split composite regions, and then utilized as pseudo-ground truth for training supervised deep learning models. We validated our unsupervised foundation-model based pipeline on publicly available cryo-ET benchmark datasets, demonstrating performance that closely approximates expert human annotations. This fully automated, data-driven framework enables the mining of multi-scale subcellular patterns, paving the way for accelerated biological discoveries from large-scale cellular cryo-ET datasets.