Dular Lara, Pernuš Franjo, Špiclin Žiga
University of Ljubljana, Faculty of Electrical Engineering, Tržaška cesta 25, Ljubljana 1000, Slovenia.
bioRxiv. 2023 Oct 30:2023.05.10.540134. doi: 10.1101/2023.05.10.540134.
Brain age is an estimate of chronological age obtained from T1-weighted magnetic resonance images (T1w MRI) and represents a simple diagnostic biomarker of brain ageing and associated diseases. While the current best accuracy of brain age predictions on T1w MRIs of healthy subjects ranges from two to three years, comparing results from different studies is challenging due to differences in the datasets, T1w preprocessing pipelines, and performance metrics used. This paper investigates the impact of T1w image preprocessing on the performance of four deep learning brain age models presented in recent literature. Four preprocessing pipelines were evaluated, differing in terms of registration, grayscale correction, and software implementation. The results showed that the choice of software or preprocessing steps can significantly affect the prediction error, with a maximum increase of 0.7 years in mean absolute error (MAE) for the same model and dataset. While grayscale correction had no significant impact on MAE, the affine registration, compared to the rigid registration of T1w images to brain atlas was shown to statistically significantly improve MAE. Models trained on 3D images with isotropic 1 resolution exhibited less sensitivity to the T1w preprocessing variations compared to 2D models or those trained on downsampled 3D images. Some proved invariant to the preprocessing pipeline, however only after offset correction. Our findings generally indicate that extensive T1w preprocessing enhances the MAE, especially when applied to a new dataset. This runs counter to prevailing research literature which suggests that models trained on minimally preprocessed T1w scans are better poised for age predictions on MRIs from unseen scanners. Regardless of model or T1w preprocessing used, we show that to enable generalization of model's performance on a new dataset with either the same or different T1w preprocessing than the one applied in model training, some form of offset correction should be applied.
脑龄是根据T1加权磁共振图像（T1w MRI）得出的对实际年龄的估计，是脑老化及相关疾病的一种简单诊断生物标志物。虽然目前对健康受试者T1w MRI进行脑龄预测的最佳准确率在两到三年之间，但由于数据集、T1w预处理流程和所使用的性能指标存在差异，比较不同研究的结果具有挑战性。本文研究了T1w图像预处理对近期文献中提出的四种深度学习脑龄模型性能的影响。评估了四种预处理流程，它们在配准、灰度校正和软件实现方面存在差异。结果表明，软件或预处理步骤的选择会显著影响预测误差，对于相同的模型和数据集，平均绝对误差（MAE）最多可增加0.7岁。虽然灰度校正对MAE没有显著影响，但与将T1w图像刚性配准到脑图谱相比，仿射配准在统计学上显著改善了MAE。与二维模型或在降采样三维图像上训练的模型相比，在各向同性1分辨率的三维图像上训练的模型对T1w预处理变化的敏感性较低。有些模型被证明对预处理流程具有不变性，但这仅在偏移校正之后。我们的研究结果总体表明，广泛的T1w预处理会增加MAE，尤其是应用于新数据集时。这与主流研究文献相反，主流文献表明，在最少预处理的T1w扫描上训练的模型更适合对来自未知扫描仪的MRI进行年龄预测。无论使用何种模型或T1w预处理，我们表明，为了使模型在与模型训练中应用的T1w预处理相同或不同的新数据集上的性能具有通用性，应应用某种形式的偏移校正。
