IEEE Trans Med Imaging. 2023 Jun;42(6):1577-1589. doi: 10.1109/TMI.2022.3231730. Epub 2023 Jun 1.
In neuroimaging, the difference between predicted brain age and chronological age, known as brain age delta, has shown its potential as a biomarker related to various pathological phenotypes. There is a frequently observed bias when estimating brain age delta using regression models. This bias manifests as an overestimation of brain age for young participants and an underestimation of brain age for older participants. Therefore, the brain age delta is negatively correlated with chronological age, which can be problematic when evaluating relationships between brain age delta and other age-associated variables. This paper proposes a novel bias correction method for regression models by introducing a skewed loss function to replace the normal symmetric loss function. The regression model then behaves differently depending on whether it makes overestimations or underestimations. Our approach works with any type of MR image and no specific preprocessing is required, as long as the image is sensitive to age-related changes. The proposed approach has been validated using three classic deep learning models, namely ResNet, VGG, and GoogleNet on publicly available neuroimaging aging datasets. It shows flexibility across different model architectures and different choices of hyperparameters. The corrected brain age delta from our approach then has no linear relationship with chronological age and achieves higher predictive accuracy than a commonly-used two-stage approach.
在神经影像学中，预测脑龄与实际年龄之间的差异，即脑龄差值，已显示出作为与各种病理表型相关的生物标志物的潜力。在使用回归模型估计脑龄差值时，经常会出现偏差。这种偏差表现为对年轻参与者的脑龄高估和对年长参与者的脑龄低估。因此，脑龄差值与实际年龄呈负相关，这在评估脑龄差值与其他与年龄相关的变量之间的关系时可能会带来问题。本文提出了一种通过引入偏态损失函数来替代正态对称损失函数的回归模型偏差修正方法。然后，根据回归模型是高估还是低估，其表现会有所不同。我们的方法适用于任何类型的磁共振成像，不需要特定的预处理，只要图像对年龄相关的变化敏感即可。我们的方法已经在三个公开的神经影像老化数据集上的三个经典深度学习模型（ResNet、VGG 和 GoogleNet）上进行了验证。它在不同的模型架构和不同的超参数选择上具有灵活性。我们的方法修正后的脑龄差值与实际年龄没有线性关系，并且比常用的两阶段方法具有更高的预测准确性。
