用深度聚类生成可定制的脑图谱，提升功能一致性与诊断效果
DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases
- 基于预训练自编码器与空间正则化聚类，生成个体化脑区划分
- 在多数据集上功能同质性提升98.8%，轮廓系数提高29%
- 适用于自闭症诊断等下游任务，支持任意脑结构灵活建模
脑图谱对神经影像数据降维和可解释分析至关重要。但现有图谱多为预定义的群体模板，灵活性与分辨率有限。本文提出深度聚类图谱（DCA），一种基于图引导的深度嵌入聚类框架，用于生成个体化、体素级的脑区划分。DCA结合预训练自编码器与空间正则化深度聚类，生成功能一致且空间连续的脑区。该方法支持灵活控制分辨率与解剖范围，并可推广至任意脑结构。我们还构建了标准化基准平台，使用多个大规模fMRI数据集进行评估。在多数据集与多尺度下，DCA显著优于现有最优图谱：功能同质性提升98.8%，轮廓系数提高29%，并在自闭症诊断与认知解码等下游任务中表现更优。此外，微调后的预训练模型在对应任务上表现更佳。代码与模型已开源。
原文摘要 · Abstract (English)
Brain atlases are essential for reducing the dimensionality of neuroimaging data and enabling interpretable analysis. However, most existing atlases are predefined, group-level templates with limited flexibility and resolution. We present Deep Cluster Atlas (DCA), a graph-guided deep embedding clustering framework for generating individualized, voxel-wise brain parcellations. DCA combines a pretrained autoencoder with spatially regularized deep clustering to produce functionally coherent and spatially contiguous regions. Our method supports flexible control over resolution and anatomical scope, and generalizes to arbitrary brain structures. We further introduce a standardized benchmarking platform for atlas evaluation, using multiple large-scale fMRI datasets. Across multiple datasets and scales, DCA outperforms state-of-the-art atlases, improving functional homogeneity by 98.8% and silhouette coefficient by 29%, and achieves superior performance in downstream tasks such as autism diagnosis and cognitive decoding. We also observe that a fine-tuned pretrained model achieves superior results on the corresponding task. Codes and models are available at https://github.com/ncclab-sustech/DCA .
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。