In order to recognize the brain network topology deviated from the normal pattern of aging, a model of healthy brain aging is needed. In this paper, a framework for automatically and efficiently estimating the age of healthy subjects from their DTI MRI scans was introduced, by using connectome analysis. The age estimation procedures included automatic preprocessing of the DTI, anatomical network construction, connectome analysis and finally estimation of the age of the subjects based on Scaled Subprofile Model ( SSM ) . The prediction model was proved to be accurate and reliable in healthy subjects, yielding brain age gap estimate ( BrainAGE ) + 0. 09 years for the healthy aging group. Applying the framework to subjects with hypertension resulted in a mean score BrainAGE of +5. 55 years. This model may serve as a clinically relevant biomarker for the detection of abnormal brain aging associated with disease.%为了识别大脑的网络拓扑结构相对于正常老化模式的偏离,需要建立健康大脑的老化模型.提出了一个自动、高效地通过对健康老年受试者DTI图像的大脑连接组分析所建立的大脑年龄预测系统.脑年龄预测的处理流程包括自动DTI图像预处理、结构网络构建、大脑连接组分析,最后基于尺度子配置模型估计受试者的脑年龄.结果证明该预测模型可以精确可靠地估计老年健康受试者的脑年龄.健康老年人组脑平均年龄差距为0.09 a,而应用该模型对高血压患者的脑年龄估计可以发现高血压患者脑平均年龄差距为5.55 a.该模型可作为一种重要的生物影像标志物来检测与疾病相关的异常脑老化.
展开▼
