Siegel Nys Tjade, Kainmueller Dagmar, Deniz Fatma, Ritter Kerstin, Schulz Marc-Andre
Department of Psychiatry and Neurosciences, Charité - Universitätsmedizin Berlin (Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health), Berlin, Germany.
Max-Delbrueck-Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany.
Hum Brain Mapp. 2025 Jun 1;46(8):e70243. doi: 10.1002/hbm.70243.
"Predicted brain age" refers to a biomarker of structural brain health derived from machine learning analysis of T1-weighted brain magnetic resonance (MR) images. A range of machine learning methods have been used to predict brain age, with convolutional neural networks (CNNs) currently yielding state-of-the-art accuracies. Recent advances in deep learning have introduced transformers, which are conceptually distinct from CNNs, and appear to set new benchmarks in various domains of computer vision. Given that transformers are not yet established in brain age prediction, we present three key contributions to this field: First, we examine whether transformers outperform CNNs in predicting brain age. Second, we identify that different deep learning model architectures potentially capture different (sub-)sets of brain aging effects, reflecting divergent "concepts of brain age". Third, we analyze whether such differences manifest in practice. To investigate these questions, we adapted a Simple Vision Transformer (sViT) and a shifted window transformer (SwinT) to predict brain age, and compared both models with a ResNet50 on 46,381 T1-weighted structural MR images from the UK Biobank. We found that SwinT and ResNet performed on par, though SwinT is likely to surpass ResNet in prediction accuracy with additional training data. Furthermore, to assess whether sViT, SwinT, and ResNet capture different concepts of brain age, we systematically analyzed variations in their predictions and clinical utility for indicating deviations in neurological and psychiatric disorders. Reassuringly, we observed no substantial differences in the structure of brain age predictions across the model architectures. Our findings suggest that the choice of deep learning model architecture does not appear to have a confounding effect on brain age studies.
“预测脑龄”指的是通过对T1加权脑磁共振（MR）图像进行机器学习分析得出的脑结构健康生物标志物。一系列机器学习方法已被用于预测脑龄，其中卷积神经网络（CNN）目前取得了最优精度。深度学习的最新进展引入了Transformer，它在概念上与CNN不同，并且似乎在计算机视觉的各个领域设定了新的基准。鉴于Transformer在脑龄预测中尚未得到应用，我们在此领域做出了三项关键贡献：第一，我们研究了Transformer在预测脑龄方面是否优于CNN。第二，我们发现不同的深度学习模型架构可能捕捉到不同的（亚）组脑老化效应，反映出不同的“脑龄概念”。第三，我们分析了这些差异在实际中是否显现。为了研究这些问题，我们改编了一个简单视觉Transformer（sViT）和一个移位窗口Transformer（SwinT）来预测脑龄，并将这两个模型与ResNet50在来自英国生物银行的46381张T1加权结构MR图像上进行了比较。我们发现SwinT和ResNet表现相当，不过随着更多训练数据的增加，SwinT在预测精度上可能会超过ResNet。此外，为了评估sViT、SwinT和ResNet是否捕捉到不同的脑龄概念，我们系统地分析了它们预测结果的差异以及在指示神经和精神疾病偏差方面的临床效用。令人欣慰的是，我们观察到不同模型架构的脑龄预测结构没有实质性差异。我们的研究结果表明，深度学习模型架构的选择似乎不会对脑龄研究产生混淆效应。
