Deep Relation Learning for Regression and Its Application to Brain Age Estimation.
Deep Relation Learning for Regression and Its Application to Brain Age Estimation.
复制标题
DOI：
10.1109/tmi.2022.3161739
复制
发表时间：
2022-09
影响因子：
10.6
通讯作者：
中科院分区：
文献类型：
--
作者：
大多数时间回归的深度学习模型直接输出基于单个输入图像的估计，忽略了不同图像之间的关系。在本文中，我们提出了用于回归的深度关系学习，旨在学习一对输入图像之间的不同关系。考虑了四种非线性关系：“累积关系”、“相对关系”、“最大关系”和“最小关系”。这四种关系是从一个深度神经网络中同时学习的，该网络有两个部分：特征提取和关系回归。我们使用高效的卷积神经网络从输入图像对中提取深度特征，并应用Transformer进行关系学习。该方法在一个合并的数据集上进行了评估，该数据集有6,049名年龄在0-97岁之间的受试者，使用5倍交叉验证进行脑年龄估计。实验结果表明，该方法的平均绝对误差（MAE）为2.38年，低于其他8种最先进的算法的MAE，在配对T检验（双侧）中具有统计学意义（p<0.05）。
Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: “cumulative relation”, “relative relation”, “maximal relation” and “minimal relation”. These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0-97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p<0.05) in paired T-test (two-side).