Multi-channel attention-fusion neural network for brain age estimation: Accuracy, generality, and interpretation with 16,705 healthy MRIs across lifespan.
Multi-channel attention-fusion neural network for brain age estimation: Accuracy, generality, and interpretation with 16,705 healthy MRIs across lifespan.
复制标题
DOI：
10.1016/j.media.2021.102091
复制
发表时间：
2021-08
影响因子：
10.9
通讯作者：
Ou Y
中科院分区：
文献类型：
--
作者：
He S;Pereira D;David Perez J;Gollub RL;Murphy SN;Prabhu S;Pienaar R;Robertson RL;Ellen Grant P;Ou Y
通过机器学习从 T1 加权磁共振图像 (T1w MRI) 估计大脑年龄，可以揭示大脑疾病如何改变大脑衰老，并有助于早期发现此类疾病。一个基本步骤是根据健康的大脑 MRI 建立准确的年龄估计器。我们专注于这一步，并提出了一个框架来提高健康脑部 MRI 年龄估计的准确性、通用性和解释性。为了准确性，我们使用最大的样本量之一（N=16,705 个样本）。对于每个受试者，我们提出的算法首先将 T1w 图像（在其他研究中通常被视为单通道 3D 图像）显式分割为两个表示对比度和形态测量信息的 3D 图像通道。我们进一步提出了一种“注意力融合”深度学习卷积神经网络（FiA-Net）来学习如何最好地融合对比度和形态测量图像通道。 FiA-Net 可以识别不同大脑解剖结构和不同特征层的图像通道的不同贡献。相比之下，多通道融合对于脑年龄估计来说并不存在，并且在其他医学图像分析任务（例如图像合成或分割）中大多是无需注意的，在这些任务中平等对待通道可能不是最佳的。出于一般性考虑，我们使用 0-97 岁的真实寿命数据来实现现实世界的实用性；与仅进行一阶段交叉验证的大多数其他研究相比，我们通过发现和复制数据的两阶段交叉验证彻底测试了 FiA-Net 的多站点和多扫描仪通用性。为了进行解释，我们直接测量了每个人工神经元与实际年龄的相关性，与其他着眼于特征显着性的研究相比，其中显着特征可能会或可能不会预测年龄。总体而言，FiA-Net 在 0-97 岁的健康大脑 MRI 中实现了 3.00 年的平均绝对误差 (MAE)，皮尔逊相关性 r = 0.9840，与最先进的算法和跨站点和数据集的准确性和通用性研究相媲美。我们还解释了不同的人工神经元和真实的神经解剖学如何有助于年龄估计。
Brain age estimated by machine learning from T1-weighted magnetic resonance images (T1w MRIs) can reveal how brain disorders alter brain aging and can help in the early detection of such disorders. A fundamental step is to build an accurate age estimator from healthy brain MRIs. We focus on this step, and propose a framework to improve the accuracy, generality, and interpretation of age estimation in healthy brain MRIs. For accuracy, we used one of the largest sample sizes (N=16,705 samples). For each subject, our proposed algorithm first explicitly splits the T1w image, which has been commonly treated as a single-channel 3D image in other studies, into two 3D image channels representing contrast and morphometry information. We further proposed a “fusion-with-attention” deep learning convolutional neural network (FiA-Net) to learn how to best fuse the contrast and morphometry image channels. FiA-Net recognizes varying contributions across image channels at different brain anatomy and different feature layers. In contrast, multi-channel fusion does not exist for brain age estimation, and is mostly attention-free in other medical image analysis tasks (e.g., image synthesis, or segmentation), where treating channels equally may not be optimal. For generality, we used truly lifespan data 0–97 years of age for real-world utility; and we thoroughly tested FiA-Net for multi-site and multi-scanner generality by two phases of cross-validations in discovery and replication data, compared to most other studies with only one phase of cross-validation. For interpretation, we directly measured each artificial neuron’s correlation with the chronological age, compared to other studies looking at the saliency of features where salient features may or may not predict age. Overall, FiA-Net achieved a mean absolute error (MAE) of 3.00 years and Pearson correlation r=0.9840 with known chronological ages in healthy brain MRIs 0–97 years of age, comparing favorably with state-of-the-art algorithms and studies for accuracy and generality across sites and datasets. We also provide interpretations on how different artificial neurons and real neuroanatomy contribute to the age estimation.
登录
查看更多内容
影响因子：
11.2
作者：
Cole, James H.;Leech, Robert;Sharp, David J.
通讯作者：
Sharp, David J.
影响因子：
4.2
作者：
Da, Xiao;Toledo, Jon B.;Zee, Jarcy;Wolk, David A.;Xie, Sharon X.;Ou, Yangming;Shacklett, Amanda;Parmpi, Paraskevi;Shaw, Leslie;Trojanowski, John Q.;Davatzikos, Christos
通讯作者：
Davatzikos, Christos
影响因子：
11
作者：
Di Martino, A.;Yan, C-G;Li, Q.;Denio, E.;Castellanos, F. X.;Alaerts, K.;Anderson, J. S.;Assaf, M.;Bookheimer, S. Y.;Dapretto, M.;Deen, B.;Delmonte, S.;Dinstein, I.;Ertl-Wagner, B.;Fair, D. A.;Gallagher, L.;Kennedy, D. P.;Keown, C. L.;Keysers, C.;Lainhart, J. E.;Lord, C.;Luna, B.;Menon, V.;Minshew, N. J.;Monk, C. S.;Mueller, S.;Mueller, R. A.;Nebel, M. B.;Nigg, J. T.;O'Hearn, K.;Pelphrey, K. A.;Peltier, S. J.;Rudie, J. D.;Sunaert, S.;Thioux, M.;Tyszka, J. M.;Uddin, L. Q.;Verhoeven, J. S.;Wenderoth, N.;Wiggins, J. L.;Mostofsky, S. H.;Milham, M. P.
通讯作者：
Milham, M. P.
DOI：
10.1038/nrn.2018.1
发表时间：
2018-02-16
期刊：
Nature reviews. Neuroscience
影响因子：
--
作者：
Gilmore JH;Knickmeyer RC;Gao W
通讯作者：
Gao W
影响因子：
5.7
作者：
Becker, Benjamin Gutierrez;Klein, Tassilo;Wachinger, Christian
通讯作者：
Wachinger, Christian