用纵向MRI自监督训练，提升阿尔茨海默病诊断准确率与可解释性。
Self-Supervised Cross-Encoder for Neurodegenerative Disease Diagnosis
- 利用纵向MRI的时间连续性设计自监督学习框架
- 在ADNI数据集上分类准确率超越现有方法，零样本迁移至OASIS
- 分离静态解剖特征与动态变化特征，适合临床可解释性需求
深度学习在基于MRI数据诊断神经退行性疾病方面展现出巨大潜力。然而，现有方法大多依赖大量标注数据，且学习到的表征缺乏可解释性。为解决这两个问题，我们提出一种新型自监督跨编码器框架，利用纵向MRI扫描中的时间连续性作为监督信号。该框架将学习到的表征解耦为两个部分：通过对比学习约束的静态表征，捕捉稳定的解剖特征；以及通过输入梯度正则化引导的动态表征，反映时间上的变化，并可有效微调用于下游分类任务。在阿尔茨海默病影像计划（ADNI）数据集上的实验结果表明，该方法在分类准确性上表现优异，并显著提升了可解释性。此外，所学表征在开放影像研究系列（OASIS）数据集上表现出强大的零样本泛化能力，在帕金森进展标志物计划（PPMI）数据集上实现跨任务泛化。该方法的代码将公开发布。
原文摘要 · Abstract (English)
Deep learning has shown significant potential in diagnosing neurodegenerative diseases from MRI data. However, most existing methods rely heavily on large volumes of labeled data and often yield representations that lack interpretability. To address both challenges, we propose a novel self-supervised cross-encoder framework that leverages the temporal continuity in longitudinal MRI scans for supervision. This framework disentangles learned representations into two components: a static representation, constrained by contrastive learning, which captures stable anatomical features; and a dynamic representation, guided by input-gradient regularization, which reflects temporal changes and can be effectively fine-tuned for downstream classification tasks. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our method achieves superior classification accuracy and improved interpretability. Furthermore, the learned representations exhibit strong zero-shot generalization on the Open Access Series of Imaging Studies (OASIS) dataset and cross-task generalization on the Parkinson Progression Marker Initiative (PPMI) dataset. The code for the proposed method will be made publicly available.
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。