The determination of biological brain age is a crucial biomarker in the assessment of neurological disorders and understanding of the morphological changes that occur during aging. Various machine learning models have been proposed for estimating brain age through Magnetic Resonance Imaging (MRI) of healthy controls. However, developing a robust brain age estimation (BAE) framework has been challenging due to the selection of appropriate MRI-derived features and the high cost of MRI acquisition. In this study, we present a novel BAE framework using the Open Big Healthy Brain (OpenBHB) dataset, which is a new multi-site and publicly available benchmark dataset that includes region-wise feature metrics derived from T1-weighted (T1-w) brain MRI scans of 3965 healthy controls aged between 6 to 86 years. Our approach integrates three different MRI-derived region-wise features and different regression models, resulting in a highly accurate brain age estimation with a Mean Absolute Error (MAE) of 3.25 years, demonstrating the framework's robustness. We also analyze our model's regression-based performance on gender-wise (male and female) healthy test groups. The proposed BAE framework provides a new approach for estimating brain age, which has important implications for the understanding of neurological disorders and age-related brain changes.

翻译：生物脑年龄的测定是评估神经系统疾病和理解衰老过程中形态变化的关键生物标志物。目前已有多种机器学习模型通过健康对照组的磁共振成像来估计脑年龄。然而，由于需要选择合适的MRI衍生特征以及MRI采集成本较高，开发稳健的脑年龄估计框架仍面临挑战。本研究提出了一种新的脑年龄估计框架，采用开放大型健康脑数据集（OpenBHB），这是一个多中心、公开可用的基准数据集，包含3965名年龄在6至86岁之间的健康对照者的T1加权脑MRI扫描的区域特征指标。我们的方法整合了三种不同的MRI衍生区域特征和多种回归模型，实现了高度精准的脑年龄估计，平均绝对误差为3.25年，验证了该框架的稳健性。我们还分析了模型在性别分组（男性和女性）健康测试组上的回归性能。所提出的脑年龄估计框架为估算脑年龄提供了新方法，对理解神经系统疾病和年龄相关的脑部变化具有重要意义。