统一框架端到端处理脑影像，减少标注依赖并提升分析效率。
End-to-End Deep Learning for Structural Brain Imaging: A Unified Framework
- 将提取、配准、分割等全流程整合为单一优化任务
- 仅需少量标签和一个标注图谱即可训练，显著降低标注成本
- 在多任务上优于传统方法，适合大规模脑影像研究
脑影像分析在神经科学中至关重要，传统流程采用分步处理：脑组织提取、配准、分割、分区、网络构建与分类，各环节独立且依赖特定标注数据与人工干预，尤其对高维影像而言，标注与质控代价高昂。本文提出UniBrain，一种统一的端到端框架，将所有处理步骤整合至单一优化过程，使各任务相互协同优化。相比传统方法，UniBrain仅需低代价标签（如分类结果和提取信息）及一个标注图谱即可运行，大幅减少标注需求。通过联合优化提取、配准、分割、分区、网络生成与分类，UniBrain在准确性与计算效率上均优于现有方法，为神经影像分析提供了更可扩展、更可靠的解决方案。代码与数据见 https://github.com/Anonymous7852/UniBrain。
原文摘要 · Abstract (English)
Brain imaging analysis is fundamental in neuroscience, providing valuable insights into brain structure and function. Traditional workflows follow a sequential pipeline-brain extraction, registration, segmentation, parcellation, network generation, and classification-treating each step as an independent task. These methods rely heavily on task-specific training data and expert intervention to correct intermediate errors, making them particularly burdensome for high-dimensional neuroimaging data, where annotations and quality control are costly and time-consuming. We introduce UniBrain, a unified end-to-end framework that integrates all processing steps into a single optimization process, allowing tasks to interact and refine each other. Unlike traditional approaches that require extensive task-specific annotations, UniBrain operates with minimal supervision, leveraging only low-cost labels (i.e., classification and extraction) and a single labeled atlas. By jointly optimizing extraction, registration, segmentation, parcellation, network generation, and classification, UniBrain enhances both accuracy and computational efficiency while significantly reducing annotation effort. Experimental results demonstrate its superiority over existing methods across multiple tasks, offering a more scalable and reliable solution for neuroimaging analysis. Our code and data can be found at https://github.com/Anonymous7852/UniBrain
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。