Chronological age of healthy brain is able to be predicted using deep neural networks from T1-weighted magnetic resonance images (T1 MRIs), and the predicted brain age could serve as an effective biomarker for detecting aging-related diseases or disorders. In this paper, we propose an end-to-end neural network architecture, referred to as optimal transport based feature pyramid fusion (OTFPF) network, for the brain age estimation with T1 MRIs. The OTFPF consists of three types of modules: Optimal Transport based Feature Pyramid Fusion (OTFPF) module, 3D overlapped ConvNeXt (3D OL-ConvNeXt) module and fusion module. These modules strengthen the OTFPF network's understanding of each brain's semi-multimodal and multi-level feature pyramid information, and significantly improve its estimation performances. Comparing with recent state-of-the-art models, the proposed OTFPF converges faster and performs better. The experiments with 11,728 MRIs aged 3-97 years show that OTFPF network could provide accurate brain age estimation, yielding mean absolute error (MAE) of 2.097, Pearson's correlation coefficient (PCC) of 0.993 and Spearman's rank correlation coefficient (SRCC) of 0.989, between the estimated and chronological ages. Widespread quantitative experiments and ablation experiments demonstrate the superiority and rationality of OTFPF network. The codes and implement details will be released on GitHub: https://github.com/ZJU-Brain/OTFPF after final decision.

中文翻译：

---

OTFPF：基于 3D 重叠 ConvNeXt 的脑年龄估计的基于传输的最优特征金字塔融合网络

可以使用来自 T1 加权磁共振图像 (T1 MRI) 的深度神经网络预测健康大脑的实际年龄，并且预测的大脑年龄可以作为检测与衰老相关的疾病或病症的有效生物标志物。在本文中，我们提出了一种端到端的神经网络架构，称为基于最优传输的特征金字塔融合 (OTFPF) 网络，用于使用 T1 MRI 进行脑年龄估计。OTFPF由三类模块组成：基于最优传输的特征金字塔融合（OTFPF）模块、3D重叠ConvNeXt（3D OL-ConvNeXt）模块和融合模块。这些模块加强了 OTFPF 网络对每个大脑的半多模态和多级特征金字塔信息的理解，并显着提高了其估计性能。与最近的最先进模型相比，所提出的 OTFPF 收敛速度更快，性能更好。对 11,728 个 3-97 岁 MRI 的实验表明，OTPFF 网络可以提供准确的大脑年龄估计，平均绝对误差 (MAE) 为 2.097，皮尔逊相关系数 (PCC) 为 0.993，斯皮尔曼等级相关系数 (SRCC) 为 0.989，在估计年龄和实际年龄之间。广泛的定量实验和消融实验证明了 OTFPF 网络的优越性和合理性。最终决定后，代码和实现细节将在 GitHub 上发布：https://github.com/ZJU-Brain/OTFPF。在估计年龄和实际年龄之间产生 2.097 的平均绝对误差 (MAE)、0.993 的皮尔逊相关系数 (PCC) 和 0.989 的斯皮尔曼等级相关系数 (SRCC)。广泛的定量实验和消融实验证明了 OTFPF 网络的优越性和合理性。最终决定后，代码和实现细节将在 GitHub 上发布：https://github.com/ZJU-Brain/OTFPF。在估计年龄和实际年龄之间产生 2.097 的平均绝对误差 (MAE)、0.993 的皮尔逊相关系数 (PCC) 和 0.989 的斯皮尔曼等级相关系数 (SRCC)。广泛的定量实验和消融实验证明了 OTFPF 网络的优越性和合理性。最终决定后，代码和实现细节将在 GitHub 上发布：https://github.com/ZJU-Brain/OTFPF。