Predicting future brain state from a baseline magnetic resonance image (MRI) is a central challenge in neuroimaging and has important implications for studying neurodegenerative diseases such as Alzheimer's disease (AD). Most existing approaches predict future cognitive scores or clinical outcomes, such as conversion from mild cognitive impairment to dementia. Instead, here we investigate longitudinal MRI image-to-image prediction that forecasts a participant's entire brain MRI several years into the future, intrinsically modeling complex, spatially distributed neurodegenerative patterns. We implement and evaluate five deep learning architectures (UNet, U2-Net, UNETR, Time-Embedding UNet, and ODE-UNet) on two longitudinal cohorts (ADNI and AIBL). Predicted follow-up MRIs are directly compared with the actual follow-up scans using metrics that capture global similarity and local differences. The best performing models achieve high-fidelity predictions, and all models generalize well to an independent external dataset, demonstrating robust cross-cohort performance. Our results indicate that deep learning can reliably predict participant-specific brain MRI at the voxel level, offering new opportunities for individualized prognosis.

翻译：基于基线磁共振成像（MRI）预测未来脑状态是神经影像学中的核心挑战，对研究阿尔茨海默病（AD）等神经退行性疾病具有重要意义。现有方法多侧重于预测未来认知评分或临床结局，例如从轻度认知障碍向痴呆的转化。相反，本研究探讨纵向MRI图像至图像预测，旨在预测参与者数年后的完整脑部MRI，从而内在地建模复杂且空间分布的神经退行模式。我们在两个纵向队列（ADNI和AIBL）上实现并评估了五种深度学习架构（UNet、U2-Net、UNETR、时间嵌入UNet和ODE-UNet）。通过捕捉全局相似性和局部差异的指标，将预测的随访MRI与实际随访扫描进行直接比较。性能最佳的模型实现了高保真度预测，且所有模型在独立外部数据集上均表现出良好的泛化能力，证明了稳健的跨队列性能。我们的结果表明，深度学习能够在体素级别可靠地预测参与者特异性脑部MRI，为个体化预后提供了新的机遇。